fix: streaming timeout

fix testAllChannels nil pointer panic

LICENSE

@@ -1,21 +1,201 @@
-MIT License
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
 
-Copyright (c) 2024 Calcium-Ion
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
 
-Permission is hereby granted, free of charge, to any person obtaining a copy
-of this software and associated documentation files (the "Software"), to deal
-in the Software without restriction, including without limitation the rights
-to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-copies of the Software, and to permit persons to whom the Software is
-furnished to do so, subject to the following conditions:
+   1. Definitions.
 
-The above copyright notice and this permission notice shall be included in all
-copies or substantial portions of the Software.
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
 
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-SOFTWARE.
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

Midjourney.md

@@ -2,6 +2,21 @@
 
 **简介**:Midjourney Proxy API文档
 
+## 接口列表
+支持的接口如下：
++ [x] /mj/submit/imagine
++ [x] /mj/submit/change
++ [x] /mj/submit/blend
++ [x] /mj/submit/describe
++ [x] /mj/image/{id} （通过此接口获取图片，**请必须在系统设置中填写服务器地址！！**）
++ [x] /mj/task/{id}/fetch （此接口返回的图片地址为经过One API转发的地址）
++ [x] /task/list-by-condition
++ [x] /mj/submit/action （仅midjourney-proxy-plus支持，下同）
++ [x] /mj/submit/modal
++ [x] /mj/submit/shorten
++ [x] /mj/task/{id}/image-seed
++ [x] /mj/insight-face/swap （InsightFace）
+
 ## 模型列表
 
 ### midjourney-proxy支持
@@ -57,11 +72,11 @@
 
 2. 在渠道管理中添加渠道，渠道类型选择**Midjourney Proxy**，如果是plus版本选择**Midjourney Proxy Plus**
    ，模型请参考上方模型列表
-3. 地址填写midjourney-proxy部署的地址，例如：http://localhost:8080
+3. **代理**填写midjourney-proxy部署的地址，例如：http://localhost:8080
 4. 密钥填写midjourney-proxy的密钥，如果没有设置密钥，可以随便填
 
 ### 对接上游new api
 
 1. 在渠道管理中添加渠道，渠道类型选择**Midjourney Proxy Plus**，模型请参考上方模型列表
-2. 地址填写上游new api的地址，例如：http://localhost:3000
+2. **代理**填写上游new api的地址，例如：http://localhost:3000
 3. 密钥填写上游new api的密钥

README.md

@@ -5,8 +5,6 @@
 > 本项目为开源项目，在[One API](https://github.com/songquanpeng/one-api)的基础上进行二次开发，感谢原作者的无私奉献。 
 > 使用者必须在遵循 OpenAI 的[使用条款](https://openai.com/policies/terms-of-use)以及**法律法规**的情况下使用，不得用于非法用途。
 
-
-> [!WARNING]
 > 本项目为个人学习使用，不保证稳定性，且不提供任何技术支持，使用者必须在遵循 OpenAI 的使用条款以及法律法规的情况下使用，不得用于非法用途。  
 > 根据[《生成式人工智能服务管理暂行办法》](http://www.cac.gov.cn/2023-07/13/c_1690898327029107.htm)的要求，请勿对中国地区公众提供一切未经备案的生成式人工智能服务。
 
@@ -18,19 +16,7 @@
 此分叉版本的主要变更如下：
 
 1. 全新的UI界面（部分界面还待更新）
-2. 添加[Midjourney-Proxy(Plus)](https://github.com/novicezk/midjourney-proxy)接口的支持，[对接文档](Midjourney.md)，支持的接口如下：
-   + [x] /mj/submit/imagine
-   + [x] /mj/submit/change
-   + [x] /mj/submit/blend
-   + [x] /mj/submit/describe
-   + [x] /mj/image/{id} （通过此接口获取图片，**请必须在系统设置中填写服务器地址！！**）
-   + [x] /mj/task/{id}/fetch （此接口返回的图片地址为经过One API转发的地址）
-   + [x] /task/list-by-condition
-   + [x] /mj/submit/action （仅midjourney-proxy-plus支持，下同）
-   + [x] /mj/submit/modal
-   + [x] /mj/submit/shorten
-   + [x] /mj/task/{id}/image-seed
-   + [x] /mj/insight-face/swap （InsightFace）
+2. 添加[Midjourney-Proxy(Plus)](https://github.com/novicezk/midjourney-proxy)接口的支持，[对接文档](Midjourney.md)
 3. 支持在线充值功能，可在系统设置中设置，当前支持的支付接口：
    + [x] 易支付
 4. 支持用key查询使用额度:
@@ -47,29 +33,50 @@
     2. 对[@Botfather](https://t.me/botfather)输入指令/setdomain
     3. 选择你的bot，然后输入http(s)://你的网站地址/login
     4. Telegram Bot 名称是bot username 去掉@后的字符串
+13. 添加 [Suno API](https://github.com/Suno-API/Suno-API)接口的支持，[对接文档](Suno.md)
+14. 支持Rerank模型，目前仅兼容Cohere和Jina，可接入Dify，[对接文档](Rerank.md)
 
 ## 模型支持
 此版本额外支持以下模型：
 1. 第三方模型 **gps** （gpt-4-gizmo-*）
 2. 智谱glm-4v，glm-4v识图
-3. Anthropic Claude 3 (claude-3-opus-20240229, claude-3-sonnet-20240229)
+3. Anthropic Claude 3
 4. [Ollama](https://github.com/ollama/ollama?tab=readme-ov-file)，添加渠道时，密钥可以随便填写，默认的请求地址是[http://localhost:11434](http://localhost:11434)，如果需要修改请在渠道中修改
 5. [Midjourney-Proxy(Plus)](https://github.com/novicezk/midjourney-proxy)接口，[对接文档](Midjourney.md)
 6. [零一万物](https://platform.lingyiwanwu.com/)
+7. 自定义渠道，支持填入完整调用地址
+8. [Suno API](https://github.com/Suno-API/Suno-API) 接口，[对接文档](Suno.md)
+9. Rerank模型，目前支持[Cohere](https://cohere.ai/)和[Jina](https://jina.ai/)，[对接文档](Rerank.md)
+10. Dify
 
 您可以在渠道中添加自定义模型gpt-4-gizmo-*，此模型并非OpenAI官方模型，而是第三方模型，使用官方key无法调用。
 
 ## 渠道重试
-渠道重试功能已经实现，可以在渠道管理中设置重试次数，需要开启缓存功能，否则只会使用同优先级重试。  
-如果开启了缓存功能，第一次重试使用同优先级，第二次重试使用下一个优先级，以此类推。  
+渠道重试功能已经实现，可以在`设置->运营设置->通用设置`设置重试次数，**建议开启缓存**功能。  
+如果开启了重试功能，第一次重试使用同优先级，第二次重试使用下一个优先级，以此类推。  
 ### 缓存设置方法
 1. `REDIS_CONN_STRING`：设置之后将使用 Redis 作为缓存使用。
     + 例子：`REDIS_CONN_STRING=redis://default:redispw@localhost:49153`
 2. `MEMORY_CACHE_ENABLED`：启用内存缓存（如果设置了`REDIS_CONN_STRING`，则无需手动设置），会导致用户额度的更新存在一定的延迟，可选值为 `true` 和 `false`，未设置则默认为 `false`。
     + 例子：`MEMORY_CACHE_ENABLED=true`
+### 为什么有的时候没有重试
+这些错误码不会重试：400，504，524
+### 我想让400也重试
+在`渠道->编辑`中，将`状态码复写`改为
+```json
+{
+  "400": "500"
+}
+```
+可以实现400错误转为500错误，从而重试
 
+## 比原版One API多出的配置
+- `STREAMING_TIMEOUT`：设置流式一次回复的超时时间，默认为 30 秒
 
 ## 部署
+### 部署要求
+- 本地数据库（默认）：SQLite（Docker 部署默认使用 SQLite，必须挂载 `/data` 目录到宿主机）
+- 远程数据库：MySQL 版本 >= 5.7.8，PgSQL 版本 >= 9.6
 ### 基于 Docker 进行部署
 ```shell
 # 使用 SQLite 的部署命令：
@@ -88,9 +95,15 @@ docker run --name new-api -d --restart always -p 3000:3000 -e TZ=Asia/Shanghai -
 docker run --name new-api -d --restart always -p 3000:3000 -e SQL_DSN="root:123456@tcp(宝塔的服务器地址:宝塔数据库端口)/宝塔数据库名称" -e TZ=Asia/Shanghai -v /www/wwwroot/new-api:/data calciumion/new-api:latest
 # 注意：数据库要开启远程访问，并且只允许服务器IP访问
 ```
+### 默认账号密码
+默认账号root 密码123456
+
 ## Midjourney接口设置文档
 [对接文档](Midjourney.md)
 
+## Suno接口设置文档
+[对接文档](Suno.md)
+
 ## 交流群
 <img src="https://github.com/Calcium-Ion/new-api/assets/61247483/de536a8a-0161-47a7-a0a2-66ef6de81266" width="300">
 

Rerank.md

@@ -0,0 +1,62 @@
+# Rerank API文档
+
+**简介**:Rerank API文档
+
+## 接入Dify
+模型供应商选择Jina，按要求填写模型信息即可接入Dify。
+
+## 请求方式
+
+Post: /v1/rerank
+
+Request:
+
+```json
+{
+  "model": "rerank-multilingual-v3.0",
+  "query": "What is the capital of the United States?",
+  "top_n": 3,
+  "documents": [
+    "Carson City is the capital city of the American state of Nevada.",
+    "The Commonwealth of the Northern Mariana Islands is a group of islands in the Pacific Ocean. Its capital is Saipan.",
+    "Washington, D.C. (also known as simply Washington or D.C., and officially as the District of Columbia) is the capital of the United States. It is a federal district.",
+    "Capitalization or capitalisation in English grammar is the use of a capital letter at the start of a word. English usage varies from capitalization in other languages.",
+    "Capital punishment (the death penalty) has existed in the United States since beforethe United States was a country. As of 2017, capital punishment is legal in 30 of the 50 states."
+  ]
+}
+```
+
+Response:
+
+```json
+{
+  "results": [
+    {
+      "document": {
+        "text": "Washington, D.C. (also known as simply Washington or D.C., and officially as the District of Columbia) is the capital of the United States. It is a federal district."
+      },
+      "index": 2,
+      "relevance_score": 0.9999702
+    },
+    {
+      "document": {
+        "text": "Carson City is the capital city of the American state of Nevada."
+      },
+      "index": 0,
+      "relevance_score": 0.67800725
+    },
+    {
+      "document": {
+        "text": "Capitalization or capitalisation in English grammar is the use of a capital letter at the start of a word. English usage varies from capitalization in other languages."
+      },
+      "index": 3,
+      "relevance_score": 0.02800752
+    }
+  ],
+  "usage": {
+    "prompt_tokens": 158,
+    "completion_tokens": 0,
+    "total_tokens": 158
+  }
+}
+```

Suno.md

@@ -0,0 +1,44 @@
+# Suno API文档
+
+**简介**:Suno API文档
+
+## 接口列表
+支持的接口如下：
++ [x] /suno/submit/music
++ [x] /suno/submit/lyrics
++ [x] /suno/fetch
++ [x] /suno/fetch/:id
+
+## 模型列表
+
+### Suno API支持
+
+- suno_music (自定义模式、灵感模式、续写)
+- suno_lyrics (生成歌词)
+
+
+## 模型价格设置（在设置-运营设置-模型固定价格设置中设置）
+```json
+{
+  "suno_music": 0.3,
+  "suno_lyrics": 0.01
+}
+```
+
+## 渠道设置
+
+### 对接 Suno API
+
+1.
+部署 Suno API，并配置好suno账号等（强烈建议设置密钥），[项目地址](https://github.com/Suno-API/Suno-API)
+
+2. 在渠道管理中添加渠道，渠道类型选择**Suno API**
+   ，模型请参考上方模型列表
+3. **代理**填写 Suno API 部署的地址，例如：http://localhost:8080
+4. 密钥填写 Suno API 的密钥，如果没有设置密钥，可以随便填
+
+### 对接上游new api
+
+1. 在渠道管理中添加渠道，渠道类型选择**Suno API**，或任意类型，只需模型包含上方模型列表的模型
+2. **代理**填写上游new api的地址，例如：http://localhost:3000
+3. 密钥填写上游new api的密钥

common/constants.go

@@ -9,19 +9,9 @@ import (
 	"github.com/google/uuid"
 )
 
-// Pay Settings
-
-var PayAddress = ""
-var CustomCallbackAddress = ""
-var EpayId = ""
-var EpayKey = ""
-var Price = 7.3
-var MinTopUp = 1
-
 var StartTime = time.Now().Unix() // unit: second
 var Version = "v0.0.0"            // this hard coding will be replaced automatically when building, no need to manually change
 var SystemName = "New API"
-var ServerAddress = "http://localhost:3000"
 var Footer = ""
 var Logo = ""
 var TopUpLink = ""
@@ -31,6 +21,7 @@ var QuotaPerUnit = 500 * 1000.0 // $0.002 / 1K tokens
 var DisplayInCurrencyEnabled = true
 var DisplayTokenStatEnabled = true
 var DrawingEnabled = true
+var TaskEnabled = true
 var DataExportEnabled = true
 var DataExportInterval = 5         // unit: minute
 var DataExportDefaultTime = "hour" // unit: minute
@@ -55,7 +46,8 @@ var TelegramOAuthEnabled = false
 var TurnstileCheckEnabled = false
 var RegisterEnabled = true
 
-var EmailDomainRestrictionEnabled = false
+var EmailDomainRestrictionEnabled = false // 是否启用邮箱域名限制
+var EmailAliasRestrictionEnabled = false  // 是否启用邮箱别名限制
 var EmailDomainWhitelist = []string{
 	"gmail.com",
 	"163.com",
@@ -111,14 +103,14 @@ var IsMasterNode = os.Getenv("NODE_TYPE") != "slave"
 var requestInterval, _ = strconv.Atoi(os.Getenv("POLLING_INTERVAL"))
 var RequestInterval = time.Duration(requestInterval) * time.Second
 
-var SyncFrequency = GetOrDefault("SYNC_FREQUENCY", 60) // unit is second
+var SyncFrequency = GetEnvOrDefault("SYNC_FREQUENCY", 60) // unit is second
 
 var BatchUpdateEnabled = false
-var BatchUpdateInterval = GetOrDefault("BATCH_UPDATE_INTERVAL", 5)
+var BatchUpdateInterval = GetEnvOrDefault("BATCH_UPDATE_INTERVAL", 5)
 
-var RelayTimeout = GetOrDefault("RELAY_TIMEOUT", 0) // unit is second
+var RelayTimeout = GetEnvOrDefault("RELAY_TIMEOUT", 0) // unit is second
 
-var GeminiSafetySetting = GetOrDefaultString("GEMINI_SAFETY_SETTING", "BLOCK_NONE")
+var GeminiSafetySetting = GetEnvOrDefaultString("GEMINI_SAFETY_SETTING", "BLOCK_NONE")
 
 const (
 	RequestIdKey = "X-Oneapi-Request-Id"
@@ -141,10 +133,10 @@ var (
 // All duration's unit is seconds
 // Shouldn't larger then RateLimitKeyExpirationDuration
 var (
-	GlobalApiRateLimitNum            = GetOrDefault("GLOBAL_API_RATE_LIMIT", 180)
+	GlobalApiRateLimitNum            = GetEnvOrDefault("GLOBAL_API_RATE_LIMIT", 180)
 	GlobalApiRateLimitDuration int64 = 3 * 60
 
-	GlobalWebRateLimitNum            = GetOrDefault("GLOBAL_WEB_RATE_LIMIT", 60)
+	GlobalWebRateLimitNum            = GetEnvOrDefault("GLOBAL_WEB_RATE_LIMIT", 60)
 	GlobalWebRateLimitDuration int64 = 3 * 60
 
 	UploadRateLimitNum            = 10
@@ -214,6 +206,15 @@ const (
 	ChannelTypeZhipu_v4       = 26
 	ChannelTypePerplexity     = 27
 	ChannelTypeLingYiWanWu    = 31
+	ChannelTypeAws            = 33
+	ChannelTypeCohere         = 34
+	ChannelTypeMiniMax        = 35
+	ChannelTypeSunoAPI        = 36
+	ChannelTypeDify           = 37
+	ChannelTypeJina           = 38
+
+	ChannelTypeDummy // this one is only for count, do not add any channel after this
+
 )
 
 var ChannelBaseURLs = []string{
@@ -249,4 +250,11 @@ var ChannelBaseURLs = []string{
 	"",                                          //29
 	"",                                          //30
 	"https://api.lingyiwanwu.com",               //31
+	"",                                          //32
+	"",                                          //33
+	"https://api.cohere.ai",                     //34
+	"https://api.minimax.chat",                  //35
+	"",                                          //36
+	"",                                          //37
+	"https://api.jina.ai",                       //38
 }

common/env.go

@@ -0,0 +1,26 @@
+package common
+
+import (
+	"fmt"
+	"os"
+	"strconv"
+)
+
+func GetEnvOrDefault(env string, defaultValue int) int {
+	if env == "" || os.Getenv(env) == "" {
+		return defaultValue
+	}
+	num, err := strconv.Atoi(os.Getenv(env))
+	if err != nil {
+		SysError(fmt.Sprintf("failed to parse %s: %s, using default value: %d", env, err.Error(), defaultValue))
+		return defaultValue
+	}
+	return num
+}
+
+func GetEnvOrDefaultString(env string, defaultValue string) string {
+	if env == "" || os.Getenv(env) == "" {
+		return defaultValue
+	}
+	return os.Getenv(env)
+}

common/go-channel.go

@@ -3,6 +3,7 @@ package common
 import (
 	"fmt"
 	"runtime/debug"
+	"time"
 )
 
 func SafeGoroutine(f func()) {
@@ -16,7 +17,7 @@ func SafeGoroutine(f func()) {
 	}()
 }
 
-func SafeSend(ch chan bool, value bool) (closed bool) {
+func SafeSendBool(ch chan bool, value bool) (closed bool) {
 	defer func() {
 		// Recover from panic if one occured. A panic would mean the channel was closed.
 		if recover() != nil {
@@ -30,3 +31,36 @@ func SafeSend(ch chan bool, value bool) (closed bool) {
 	// If the code reaches here, then the channel was not closed.
 	return false
 }
+
+func SafeSendString(ch chan string, value string) (closed bool) {
+	defer func() {
+		// Recover from panic if one occured. A panic would mean the channel was closed.
+		if recover() != nil {
+			closed = true
+		}
+	}()
+
+	// This will panic if the channel is closed.
+	ch <- value
+
+	// If the code reaches here, then the channel was not closed.
+	return false
+}
+
+// SafeSendStringTimeout send, return true, else return false
+func SafeSendStringTimeout(ch chan string, value string, timeout int) (closed bool) {
+	defer func() {
+		// Recover from panic if one occured. A panic would mean the channel was closed.
+		if recover() != nil {
+			closed = false
+		}
+	}()
+
+	// This will panic if the channel is closed.
+	select {
+	case ch <- value:
+		return true
+	case <-time.After(time.Duration(timeout) * time.Second):
+		return false
+	}
+}

common/group-ratio.go

@@ -1,6 +1,8 @@
 package common
 
-import "encoding/json"
+import (
+	"encoding/json"
+)
 
 var GroupRatio = map[string]float64{
 	"default": 1,

common/logger.go

@@ -2,6 +2,7 @@ package common
 
 import (
 	"context"
+	"encoding/json"
 	"fmt"
 	"github.com/gin-gonic/gin"
 	"io"
@@ -98,3 +99,13 @@ func LogQuota(quota int) string {
 		return fmt.Sprintf("%d 点额度", quota)
 	}
 }
+
+// LogJson 仅供测试使用 only for test
+func LogJson(ctx context.Context, msg string, obj any) {
+	jsonStr, err := json.Marshal(obj)
+	if err != nil {
+		LogError(ctx, fmt.Sprintf("json marshal failed: %s", err.Error()))
+		return
+	}
+	LogInfo(ctx, fmt.Sprintf("%s | %s", msg, string(jsonStr)))
+}

common/model-ratio.go

@@ -5,6 +5,13 @@ import (
 	"strings"
 )
 
+// from songquanpeng/one-api
+const (
+	USD2RMB = 7.3 // 暂定 1 USD = 7.3 RMB
+	USD     = 500 // $0.002 = 1 -> $1 = 500
+	RMB     = USD / USD2RMB
+)
+
 // modelRatio
 // https://platform.openai.com/docs/models/model-endpoint-compatibility
 // https://cloud.baidu.com/doc/WENXINWORKSHOP/s/Blfmc9dlf
@@ -12,97 +19,146 @@ import (
 // TODO: when a new api is enabled, check the pricing here
 // 1 === $0.002 / 1K tokens
 // 1 === ￥0.014 / 1k tokens
-var DefaultModelRatio = map[string]float64{
+
+var defaultModelRatio = map[string]float64{
 	//"midjourney":                50,
-	"gpt-4-gizmo-*":             15,
-	"gpt-4":                     15,
-	"gpt-4-0314":                15,
-	"gpt-4-0613":                15,
-	"gpt-4-32k":                 30,
-	"gpt-4-32k-0314":            30,
+	"gpt-4-gizmo-*": 15,
+	"gpt-4-all":     15,
+	"gpt-4o-all":    15,
+	"gpt-4":         15,
+	//"gpt-4-0314":                   15, //deprecated
+	"gpt-4-0613": 15,
+	"gpt-4-32k":  30,
+	//"gpt-4-32k-0314":               30, //deprecated
 	"gpt-4-32k-0613":            30,
 	"gpt-4-1106-preview":        5,    // $0.01 / 1K tokens
 	"gpt-4-0125-preview":        5,    // $0.01 / 1K tokens
 	"gpt-4-turbo-preview":       5,    // $0.01 / 1K tokens
 	"gpt-4-vision-preview":      5,    // $0.01 / 1K tokens
 	"gpt-4-1106-vision-preview": 5,    // $0.01 / 1K tokens
+	"gpt-4o":                    2.5,  // $0.01 / 1K tokens
+	"gpt-4o-2024-05-13":         2.5,  // $0.01 / 1K tokens
+	"gpt-4-turbo":               5,    // $0.01 / 1K tokens
+	"gpt-4-turbo-2024-04-09":    5,    // $0.01 / 1K tokens
 	"gpt-3.5-turbo":             0.25, // $0.0015 / 1K tokens
-	"gpt-3.5-turbo-0301":        0.75,
-	"gpt-3.5-turbo-0613":        0.75,
-	"gpt-3.5-turbo-16k":         1.5, // $0.003 / 1K tokens
-	"gpt-3.5-turbo-16k-0613":    1.5,
-	"gpt-3.5-turbo-instruct":    0.75, // $0.0015 / 1K tokens
-	"gpt-3.5-turbo-1106":        0.5,  // $0.001 / 1K tokens
-	"gpt-3.5-turbo-0125":        0.25,
-	"babbage-002":               0.2, // $0.0004 / 1K tokens
-	"davinci-002":               1,   // $0.002 / 1K tokens
-	"text-ada-001":              0.2,
-	"text-babbage-001":          0.25,
-	"text-curie-001":            1,
-	"text-davinci-002":          10,
-	"text-davinci-003":          10,
-	"text-davinci-edit-001":     10,
-	"code-davinci-edit-001":     10,
-	"whisper-1":                 15,  // $0.006 / minute -> $0.006 / 150 words -> $0.006 / 200 tokens -> $0.03 / 1k tokens
-	"tts-1":                     7.5, // 1k characters -> $0.015
-	"tts-1-1106":                7.5, // 1k characters -> $0.015
-	"tts-1-hd":                  15,  // 1k characters -> $0.03
-	"tts-1-hd-1106":             15,  // 1k characters -> $0.03
-	"davinci":                   10,
-	"curie":                     10,
-	"babbage":                   10,
-	"ada":                       10,
-	"text-embedding-3-small":    0.01,
-	"text-embedding-3-large":    0.065,
-	"text-embedding-ada-002":    0.05,
-	"text-search-ada-doc-001":   10,
-	"text-moderation-stable":    0.1,
-	"text-moderation-latest":    0.1,
-	"dall-e-2":                  8,
-	"dall-e-3":                  16,
-	"claude-instant-1":          0.4,    // $0.8 / 1M tokens
-	"claude-2.0":                4,      // $8 / 1M tokens
-	"claude-2.1":                4,      // $8 / 1M tokens
-	"claude-3-haiku-20240307":   0.125,  // $0.25 / 1M tokens
-	"claude-3-sonnet-20240229":  1.5,    // $3 / 1M tokens
-	"claude-3-opus-20240229":    7.5,    // $15 / 1M tokens
-	"ERNIE-Bot":                 0.8572, // ￥0.012 / 1k tokens
-	"ERNIE-Bot-turbo":           0.5715, // ￥0.008 / 1k tokens
-	"ERNIE-Bot-4":               8.572,  // ￥0.12 / 1k tokens
-	"Embedding-V1":              0.1429, // ￥0.002 / 1k tokens
-	"PaLM-2":                    1,
-	"gemini-pro":                1, // $0.00025 / 1k characters -> $0.001 / 1k tokens
-	"gemini-pro-vision":         1, // $0.00025 / 1k characters -> $0.001 / 1k tokens
-	"gemini-1.0-pro-vision-001": 1,
-	"gemini-1.0-pro-001":        1,
-	"gemini-1.5-pro":            1,
-	"chatglm_turbo":             0.3572, // ￥0.005 / 1k tokens
-	"chatglm_pro":               0.7143, // ￥0.01 / 1k tokens
-	"chatglm_std":               0.3572, // ￥0.005 / 1k tokens
-	"chatglm_lite":              0.1429, // ￥0.002 / 1k tokens
-	"glm-4":                     7.143,  // ￥0.1 / 1k tokens
-	"glm-4v":                    7.143,  // ￥0.1 / 1k tokens
-	"glm-3-turbo":               0.3572,
-	"qwen-turbo":                0.8572, // ￥0.012 / 1k tokens
-	"qwen-plus":                 10,     // ￥0.14 / 1k tokens
-	"text-embedding-v1":         0.05,   // ￥0.0007 / 1k tokens
-	"SparkDesk-v1.1":            1.2858, // ￥0.018 / 1k tokens
-	"SparkDesk-v2.1":            1.2858, // ￥0.018 / 1k tokens
-	"SparkDesk-v3.1":            1.2858, // ￥0.018 / 1k tokens
-	"SparkDesk-v3.5":            1.2858, // ￥0.018 / 1k tokens
-	"360GPT_S2_V9":              0.8572, // ¥0.012 / 1k tokens
-	"embedding-bert-512-v1":     0.0715, // ¥0.001 / 1k tokens
-	"embedding_s1_v1":           0.0715, // ¥0.001 / 1k tokens
-	"semantic_similarity_s1_v1": 0.0715, // ¥0.001 / 1k tokens
-	"hunyuan":                   7.143,  // ¥0.1 / 1k tokens  // https://cloud.tencent.com/document/product/1729/97731#e0e6be58-60c8-469f-bdeb-6c264ce3b4d0
+	//"gpt-3.5-turbo-0301":           0.75, //deprecated
+	"gpt-3.5-turbo-0613":     0.75,
+	"gpt-3.5-turbo-16k":      1.5, // $0.003 / 1K tokens
+	"gpt-3.5-turbo-16k-0613": 1.5,
+	"gpt-3.5-turbo-instruct": 0.75, // $0.0015 / 1K tokens
+	"gpt-3.5-turbo-1106":     0.5,  // $0.001 / 1K tokens
+	"gpt-3.5-turbo-0125":     0.25,
+	"babbage-002":            0.2, // $0.0004 / 1K tokens
+	"davinci-002":            1,   // $0.002 / 1K tokens
+	"text-ada-001":           0.2,
+	"text-babbage-001":       0.25,
+	"text-curie-001":         1,
+	//"text-davinci-002":               10,
+	//"text-davinci-003":               10,
+	"text-davinci-edit-001":          10,
+	"code-davinci-edit-001":          10,
+	"whisper-1":                      15,  // $0.006 / minute -> $0.006 / 150 words -> $0.006 / 200 tokens -> $0.03 / 1k tokens
+	"tts-1":                          7.5, // 1k characters -> $0.015
+	"tts-1-1106":                     7.5, // 1k characters -> $0.015
+	"tts-1-hd":                       15,  // 1k characters -> $0.03
+	"tts-1-hd-1106":                  15,  // 1k characters -> $0.03
+	"davinci":                        10,
+	"curie":                          10,
+	"babbage":                        10,
+	"ada":                            10,
+	"text-embedding-3-small":         0.01,
+	"text-embedding-3-large":         0.065,
+	"text-embedding-ada-002":         0.05,
+	"text-search-ada-doc-001":        10,
+	"text-moderation-stable":         0.1,
+	"text-moderation-latest":         0.1,
+	"claude-instant-1":               0.4,   // $0.8 / 1M tokens
+	"claude-2.0":                     4,     // $8 / 1M tokens
+	"claude-2.1":                     4,     // $8 / 1M tokens
+	"claude-3-haiku-20240307":        0.125, // $0.25 / 1M tokens
+	"claude-3-sonnet-20240229":       1.5,   // $3 / 1M tokens
+	"claude-3-5-sonnet-20240620":     1.5,
+	"claude-3-opus-20240229":         7.5, // $15 / 1M tokens
+	"ERNIE-4.0-8K":                   0.120 * RMB,
+	"ERNIE-3.5-8K":                   0.012 * RMB,
+	"ERNIE-3.5-8K-0205":              0.024 * RMB,
+	"ERNIE-3.5-8K-1222":              0.012 * RMB,
+	"ERNIE-Bot-8K":                   0.024 * RMB,
+	"ERNIE-3.5-4K-0205":              0.012 * RMB,
+	"ERNIE-Speed-8K":                 0.004 * RMB,
+	"ERNIE-Speed-128K":               0.004 * RMB,
+	"ERNIE-Lite-8K-0922":             0.008 * RMB,
+	"ERNIE-Lite-8K-0308":             0.003 * RMB,
+	"ERNIE-Tiny-8K":                  0.001 * RMB,
+	"BLOOMZ-7B":                      0.004 * RMB,
+	"Embedding-V1":                   0.002 * RMB,
+	"bge-large-zh":                   0.002 * RMB,
+	"bge-large-en":                   0.002 * RMB,
+	"tao-8k":                         0.002 * RMB,
+	"PaLM-2":                         1,
+	"gemini-pro":                     1, // $0.00025 / 1k characters -> $0.001 / 1k tokens
+	"gemini-pro-vision":              1, // $0.00025 / 1k characters -> $0.001 / 1k tokens
+	"gemini-1.0-pro-vision-001":      1,
+	"gemini-1.0-pro-001":             1,
+	"gemini-1.5-pro-latest":          1,
+	"gemini-1.5-flash-latest":        1,
+	"gemini-1.0-pro-latest":          1,
+	"gemini-1.0-pro-vision-latest":   1,
+	"gemini-ultra":                   1,
+	"chatglm_turbo":                  0.3572, // ￥0.005 / 1k tokens
+	"chatglm_pro":                    0.7143, // ￥0.01 / 1k tokens
+	"chatglm_std":                    0.3572, // ￥0.005 / 1k tokens
+	"chatglm_lite":                   0.1429, // ￥0.002 / 1k tokens
+	"glm-4":                          7.143,  // ￥0.1 / 1k tokens
+	"glm-4v":                         7.143,  // ￥0.1 / 1k tokens
+	"glm-3-turbo":                    0.3572,
+	"qwen-turbo":                     0.8572, // ￥0.012 / 1k tokens
+	"qwen-plus":                      10,     // ￥0.14 / 1k tokens
+	"text-embedding-v1":              0.05,   // ￥0.0007 / 1k tokens
+	"SparkDesk-v1.1":                 1.2858, // ￥0.018 / 1k tokens
+	"SparkDesk-v2.1":                 1.2858, // ￥0.018 / 1k tokens
+	"SparkDesk-v3.1":                 1.2858, // ￥0.018 / 1k tokens
+	"SparkDesk-v3.5":                 1.2858, // ￥0.018 / 1k tokens
+	"SparkDesk-v4.0":                 1.2858,
+	"360GPT_S2_V9":                   0.8572, // ¥0.012 / 1k tokens
+	"360gpt-turbo":                   0.0858, // ¥0.0012 / 1k tokens
+	"360gpt-turbo-responsibility-8k": 0.8572, // ¥0.012 / 1k tokens
+	"360gpt-pro":                     0.8572, // ¥0.012 / 1k tokens
+	"embedding-bert-512-v1":          0.0715, // ¥0.001 / 1k tokens
+	"embedding_s1_v1":                0.0715, // ¥0.001 / 1k tokens
+	"semantic_similarity_s1_v1":      0.0715, // ¥0.001 / 1k tokens
+	"hunyuan":                        7.143,  // ¥0.1 / 1k tokens  // https://cloud.tencent.com/document/product/1729/97731#e0e6be58-60c8-469f-bdeb-6c264ce3b4d0
 	// https://platform.lingyiwanwu.com/docs#-计费单元
 	// 已经按照 7.2 来换算美元价格
-	"yi-34b-chat-0205": 0.018,
-	"yi-34b-chat-200k": 0.0864,
-	"yi-vl-plus":       0.0432,
+	"yi-34b-chat-0205":      0.18,
+	"yi-34b-chat-200k":      0.864,
+	"yi-vl-plus":            0.432,
+	"yi-large":              20.0 / 1000 * RMB,
+	"yi-medium":             2.5 / 1000 * RMB,
+	"yi-vision":             6.0 / 1000 * RMB,
+	"yi-medium-200k":        12.0 / 1000 * RMB,
+	"yi-spark":              1.0 / 1000 * RMB,
+	"yi-large-rag":          25.0 / 1000 * RMB,
+	"yi-large-turbo":        12.0 / 1000 * RMB,
+	"yi-large-preview":      20.0 / 1000 * RMB,
+	"yi-large-rag-preview":  25.0 / 1000 * RMB,
+	"command":               0.5,
+	"command-nightly":       0.5,
+	"command-light":         0.5,
+	"command-light-nightly": 0.5,
+	"command-r":             0.25,
+	"command-r-plus	":       1.5,
+	"deepseek-chat":         0.07,
+	"deepseek-coder":        0.07,
+	// Perplexity online 模型对搜索额外收费，有需要应自行调整，此处不计入搜索费用
+	"llama-3-sonar-small-32k-chat":   0.2 / 1000 * USD,
+	"llama-3-sonar-small-32k-online": 0.2 / 1000 * USD,
+	"llama-3-sonar-large-32k-chat":   1 / 1000 * USD,
+	"llama-3-sonar-large-32k-online": 1 / 1000 * USD,
 }
 
-var DefaultModelPrice = map[string]float64{
+var defaultModelPrice = map[string]float64{
+	"dall-e-3":          0.04,
 	"gpt-4-gizmo-*":     0.1,
 	"mj_imagine":        0.1,
 	"mj_variation":      0.1,
@@ -124,9 +180,15 @@ var DefaultModelPrice = map[string]float64{
 var modelPrice map[string]float64 = nil
 var modelRatio map[string]float64 = nil
 
+var CompletionRatio map[string]float64 = nil
+var defaultCompletionRatio = map[string]float64{
+	"gpt-4-gizmo-*": 2,
+	"gpt-4-all":     2,
+}
+
 func ModelPrice2JSONString() string {
 	if modelPrice == nil {
-		modelPrice = DefaultModelPrice
+		modelPrice = defaultModelPrice
 	}
 	jsonBytes, err := json.Marshal(modelPrice)
 	if err != nil {
@@ -140,9 +202,10 @@ func UpdateModelPriceByJSONString(jsonStr string) error {
 	return json.Unmarshal([]byte(jsonStr), &modelPrice)
 }
 
-func GetModelPrice(name string, printErr bool) float64 {
+// GetModelPrice 返回模型的价格，如果模型不存在则返回-1，false
+func GetModelPrice(name string, printErr bool) (float64, bool) {
 	if modelPrice == nil {
-		modelPrice = DefaultModelPrice
+		modelPrice = defaultModelPrice
 	}
 	if strings.HasPrefix(name, "gpt-4-gizmo") {
 		name = "gpt-4-gizmo-*"
@@ -152,14 +215,21 @@ func GetModelPrice(name string, printErr bool) float64 {
 		if printErr {
 			SysError("model price not found: " + name)
 		}
-		return -1
+		return -1, false
 	}
-	return price
+	return price, true
+}
+
+func GetModelPriceMap() map[string]float64 {
+	if modelPrice == nil {
+		modelPrice = defaultModelPrice
+	}
+	return modelPrice
 }
 
 func ModelRatio2JSONString() string {
 	if modelRatio == nil {
-		modelRatio = DefaultModelRatio
+		modelRatio = defaultModelRatio
 	}
 	jsonBytes, err := json.Marshal(modelRatio)
 	if err != nil {
@@ -175,7 +245,7 @@ func UpdateModelRatioByJSONString(jsonStr string) error {
 
 func GetModelRatio(name string) float64 {
 	if modelRatio == nil {
-		modelRatio = DefaultModelRatio
+		modelRatio = defaultModelRatio
 	}
 	if strings.HasPrefix(name, "gpt-4-gizmo") {
 		name = "gpt-4-gizmo-*"
@@ -188,7 +258,38 @@ func GetModelRatio(name string) float64 {
 	return ratio
 }
 
+func DefaultModelRatio2JSONString() string {
+	jsonBytes, err := json.Marshal(defaultModelRatio)
+	if err != nil {
+		SysError("error marshalling model ratio: " + err.Error())
+	}
+	return string(jsonBytes)
+}
+
+func GetDefaultModelRatioMap() map[string]float64 {
+	return defaultModelRatio
+}
+
+func CompletionRatio2JSONString() string {
+	if CompletionRatio == nil {
+		CompletionRatio = defaultCompletionRatio
+	}
+	jsonBytes, err := json.Marshal(CompletionRatio)
+	if err != nil {
+		SysError("error marshalling completion ratio: " + err.Error())
+	}
+	return string(jsonBytes)
+}
+
+func UpdateCompletionRatioByJSONString(jsonStr string) error {
+	CompletionRatio = make(map[string]float64)
+	return json.Unmarshal([]byte(jsonStr), &CompletionRatio)
+}
+
 func GetCompletionRatio(name string) float64 {
+	if strings.HasPrefix(name, "gpt-4-gizmo") {
+		name = "gpt-4-gizmo-*"
+	}
 	if strings.HasPrefix(name, "gpt-3.5") {
 		if name == "gpt-3.5-turbo" || strings.HasSuffix(name, "0125") {
 			// https://openai.com/blog/new-embedding-models-and-api-updates
@@ -200,17 +301,17 @@ func GetCompletionRatio(name string) float64 {
 		}
 		return 4.0 / 3.0
 	}
-	if strings.HasPrefix(name, "gpt-4") {
-		if strings.HasSuffix(name, "preview") {
+	if strings.HasPrefix(name, "gpt-4") && !strings.HasSuffix(name, "-all") && !strings.HasSuffix(name, "-gizmo-*") {
+		if strings.HasPrefix(name, "gpt-4-turbo") || strings.HasSuffix(name, "preview") || strings.HasPrefix(name, "gpt-4o") {
 			return 3
 		}
 		return 2
 	}
-	if strings.HasPrefix(name, "claude-instant-1") {
+	if strings.Contains(name, "claude-instant-1") {
 		return 3
-	} else if strings.HasPrefix(name, "claude-2") {
+	} else if strings.Contains(name, "claude-2") {
 		return 3
-	} else if strings.HasPrefix(name, "claude-3") {
+	} else if strings.Contains(name, "claude-3") {
 		return 5
 	}
 	if strings.HasPrefix(name, "mistral-") {
@@ -219,9 +320,45 @@ func GetCompletionRatio(name string) float64 {
 	if strings.HasPrefix(name, "gemini-") {
 		return 3
 	}
+	if strings.HasPrefix(name, "command") {
+		switch name {
+		case "command-r":
+			return 3
+		case "command-r-plus":
+			return 5
+		default:
+			return 2
+		}
+	}
+	if strings.HasPrefix(name, "deepseek") {
+		return 2
+	}
+	if strings.HasPrefix(name, "ERNIE-Speed-") {
+		return 2
+	} else if strings.HasPrefix(name, "ERNIE-Lite-") {
+		return 2
+	} else if strings.HasPrefix(name, "ERNIE-Character") {
+		return 2
+	} else if strings.HasPrefix(name, "ERNIE-Functions") {
+		return 2
+	}
 	switch name {
 	case "llama2-70b-4096":
-		return 0.8 / 0.7
+		return 0.8 / 0.64
+	case "llama3-8b-8192":
+		return 2
+	case "llama3-70b-8192":
+		return 0.79 / 0.59
+	}
+	if ratio, ok := CompletionRatio[name]; ok {
+		return ratio
 	}
 	return 1
 }
+
+func GetCompletionRatioMap() map[string]float64 {
+	if CompletionRatio == nil {
+		CompletionRatio = defaultCompletionRatio
+	}
+	return CompletionRatio
+}

common/topup-ratio.go

@@ -1,6 +1,8 @@
 package common
 
-import "encoding/json"
+import (
+	"encoding/json"
+)
 
 var TopupGroupRatio = map[string]float64{
 	"default": 1,

common/utils.go

@@ -1,13 +1,13 @@
 package common
 
 import (
+	"encoding/json"
 	"fmt"
 	"github.com/google/uuid"
 	"html/template"
 	"log"
 	"math/rand"
 	"net"
-	"os"
 	"os/exec"
 	"runtime"
 	"strconv"
@@ -190,25 +190,6 @@ func Max(a int, b int) int {
 	}
 }
 
-func GetOrDefault(env string, defaultValue int) int {
-	if env == "" || os.Getenv(env) == "" {
-		return defaultValue
-	}
-	num, err := strconv.Atoi(os.Getenv(env))
-	if err != nil {
-		SysError(fmt.Sprintf("failed to parse %s: %s, using default value: %d", env, err.Error(), defaultValue))
-		return defaultValue
-	}
-	return num
-}
-
-func GetOrDefaultString(env string, defaultValue string) string {
-	if env == "" || os.Getenv(env) == "" {
-		return defaultValue
-	}
-	return os.Getenv(env)
-}
-
 func MessageWithRequestId(message string, id string) string {
 	return fmt.Sprintf("%s (request id: %s)", message, id)
 }
@@ -241,3 +222,28 @@ func RandomSleep() {
 	// Sleep for 0-3000 ms
 	time.Sleep(time.Duration(rand.Intn(3000)) * time.Millisecond)
 }
+
+func MapToJsonStr(m map[string]interface{}) string {
+	bytes, err := json.Marshal(m)
+	if err != nil {
+		return ""
+	}
+	return string(bytes)
+}
+
+func MapToJsonStrFloat(m map[string]float64) string {
+	bytes, err := json.Marshal(m)
+	if err != nil {
+		return ""
+	}
+	return string(bytes)
+}
+
+func StrToMap(str string) map[string]interface{} {
+	m := make(map[string]interface{})
+	err := json.Unmarshal([]byte(str), &m)
+	if err != nil {
+		return nil
+	}
+	return m
+}

constant/env.go

@@ -0,0 +1,7 @@
+package constant
+
+import (
+	"one-api/common"
+)
+
+var StreamingTimeout = common.GetEnvOrDefault("STREAMING_TIMEOUT", 30)

constant/midjourney.go

@@ -1,6 +1,9 @@
 package constant
 
 var MjNotifyEnabled = false
+var MjAccountFilterEnabled = false
+var MjModeClearEnabled = false
+var MjForwardUrlEnabled = true
 
 const (
 	MjErrorUnknown = 5

constant/payment.go

@@ -0,0 +1,8 @@
+package constant
+
+var PayAddress = ""
+var CustomCallbackAddress = ""
+var EpayId = ""
+var EpayKey = ""
+var Price = 7.3
+var MinTopUp = 1

constant/sensitive.go

@@ -16,7 +16,7 @@ var StreamCacheQueueLength = 0
 // SensitiveWords 敏感词
 // var SensitiveWords []string
 var SensitiveWords = []string{
-	"test",
+	"test_sensitive",
 }
 
 func SensitiveWordsToString() string {

constant/system-setting.go

@@ -0,0 +1,9 @@
+package constant
+
+var ServerAddress = "http://localhost:3000"
+var WorkerUrl = ""
+var WorkerValidKey = ""
+
+func EnableWorker() bool {
+	return WorkerUrl != ""
+}

constant/task.go

@@ -0,0 +1,18 @@
+package constant
+
+type TaskPlatform string
+
+const (
+	TaskPlatformSuno       TaskPlatform = "suno"
+	TaskPlatformMidjourney              = "mj"
+)
+
+const (
+	SunoActionMusic  = "MUSIC"
+	SunoActionLyrics = "LYRICS"
+)
+
+var SunoModel2Action = map[string]string{
+	"suno_music":  SunoActionMusic,
+	"suno_lyrics": SunoActionLyrics,
+}

controller/channel-test.go

@@ -6,6 +6,7 @@ import (
 	"errors"
 	"fmt"
 	"io"
+	"math"
 	"net/http"
 	"net/http/httptest"
 	"net/url"
@@ -24,9 +25,13 @@ import (
 )
 
 func testChannel(channel *model.Channel, testModel string) (err error, openaiErr *dto.OpenAIError) {
+	tik := time.Now()
 	if channel.Type == common.ChannelTypeMidjourney {
 		return errors.New("midjourney channel test is not supported"), nil
 	}
+	if channel.Type == common.ChannelTypeSunoAPI {
+		return errors.New("suno channel test is not supported"), nil
+	}
 	w := httptest.NewRecorder()
 	c, _ := gin.CreateTestContext(w)
 	c.Request = &http.Request{
@@ -53,7 +58,7 @@ func testChannel(channel *model.Channel, testModel string) (err error, openaiErr
 	}
 
 	meta := relaycommon.GenRelayInfo(c)
-	apiType := constant.ChannelType2APIType(channel.Type)
+	apiType, _ := constant.ChannelType2APIType(channel.Type)
 	adaptor := relay.GetAdaptor(apiType)
 	if adaptor == nil {
 		return fmt.Errorf("invalid api type: %d, adaptor is nil", apiType), nil
@@ -62,9 +67,27 @@ func testChannel(channel *model.Channel, testModel string) (err error, openaiErr
 		if channel.TestModel != nil && *channel.TestModel != "" {
 			testModel = *channel.TestModel
 		} else {
-			testModel = adaptor.GetModelList()[0]
+			if len(adaptor.GetModelList()) > 0 {
+				testModel = adaptor.GetModelList()[0]
+			} else {
+				testModel = "gpt-3.5-turbo"
+			}
+		}
+	} else {
+		modelMapping := *channel.ModelMapping
+		if modelMapping != "" && modelMapping != "{}" {
+			modelMap := make(map[string]string)
+			err := json.Unmarshal([]byte(modelMapping), &modelMap)
+			if err != nil {
+				openaiErr := service.OpenAIErrorWrapperLocal(err, "unmarshal_model_mapping_failed", http.StatusInternalServerError).Error
+				return err, &openaiErr
+			}
+			if modelMap[testModel] != "" {
+				testModel = modelMap[testModel]
+			}
 		}
 	}
+
 	request := buildTestRequest()
 	request.Model = testModel
 	meta.UpstreamModelName = testModel
@@ -86,7 +109,7 @@ func testChannel(channel *model.Channel, testModel string) (err error, openaiErr
 	if err != nil {
 		return err, nil
 	}
-	if resp.StatusCode != http.StatusOK {
+	if resp != nil && resp.StatusCode != http.StatusOK {
 		err := relaycommon.RelayErrorHandler(resp)
 		return fmt.Errorf("status code %d: %s", resp.StatusCode, err.Error.Message), &err.Error
 	}
@@ -103,6 +126,25 @@ func testChannel(channel *model.Channel, testModel string) (err error, openaiErr
 	if err != nil {
 		return err, nil
 	}
+	modelPrice, usePrice := common.GetModelPrice(testModel, false)
+	modelRatio := common.GetModelRatio(testModel)
+	completionRatio := common.GetCompletionRatio(testModel)
+	ratio := modelRatio
+	quota := 0
+	if !usePrice {
+		quota = usage.PromptTokens + int(math.Round(float64(usage.CompletionTokens)*completionRatio))
+		quota = int(math.Round(float64(quota) * ratio))
+		if ratio != 0 && quota <= 0 {
+			quota = 1
+		}
+	} else {
+		quota = int(modelPrice * common.QuotaPerUnit)
+	}
+	tok := time.Now()
+	milliseconds := tok.Sub(tik).Milliseconds()
+	consumedTime := float64(milliseconds) / 1000.0
+	other := service.GenerateTextOtherInfo(c, meta, modelRatio, 1, completionRatio, modelPrice)
+	model.RecordConsumeLog(c, 1, channel.Id, usage.PromptTokens, usage.CompletionTokens, testModel, "模型测试", quota, "模型测试", 0, quota, int(consumedTime), false, other)
 	common.SysLog(fmt.Sprintf("testing channel #%d, response: \n%s", channel.Id, string(respBody)))
 	return nil, nil
 }
@@ -123,7 +165,7 @@ func buildTestRequest() *dto.GeneralOpenAIRequest {
 }
 
 func TestChannel(c *gin.Context) {
-	id, err := strconv.Atoi(c.Param("id"))
+	channelId, err := strconv.Atoi(c.Param("id"))
 	if err != nil {
 		c.JSON(http.StatusOK, gin.H{
 			"success": false,
@@ -131,7 +173,7 @@ func TestChannel(c *gin.Context) {
 		})
 		return
 	}
-	channel, err := model.GetChannelById(id, true)
+	channel, err := model.GetChannelById(channelId, true)
 	if err != nil {
 		c.JSON(http.StatusOK, gin.H{
 			"success": false,
@@ -205,11 +247,18 @@ func testAllChannels(notify bool) error {
 			if channel.AutoBan != nil && *channel.AutoBan == 0 {
 				ban = false
 			}
-			if isChannelEnabled && service.ShouldDisableChannel(openaiErr, -1) && ban {
-				service.DisableChannel(channel.Id, channel.Name, err.Error())
-			}
-			if !isChannelEnabled && service.ShouldEnableChannel(err, openaiErr) {
-				service.EnableChannel(channel.Id, channel.Name)
+			if openaiErr != nil {
+				openAiErrWithStatus := dto.OpenAIErrorWithStatusCode{
+					StatusCode: -1,
+					Error:      *openaiErr,
+					LocalError: false,
+				}
+				if isChannelEnabled && service.ShouldDisableChannel(channel.Type, &openAiErrWithStatus) && ban {
+					service.DisableChannel(channel.Id, channel.Name, err.Error())
+				}
+				if !isChannelEnabled && service.ShouldEnableChannel(err, openaiErr, channel.Status) {
+					service.EnableChannel(channel.Id, channel.Name)
+				}
 			}
 			channel.UpdateResponseTime(milliseconds)
 			time.Sleep(common.RequestInterval)

controller/channel.go

@@ -1,6 +1,8 @@
 package controller
 
 import (
+	"encoding/json"
+	"fmt"
 	"github.com/gin-gonic/gin"
 	"net/http"
 	"one-api/common"
@@ -9,6 +11,34 @@ import (
 	"strings"
 )
 
+type OpenAIModel struct {
+	ID         string `json:"id"`
+	Object     string `json:"object"`
+	Created    int64  `json:"created"`
+	OwnedBy    string `json:"owned_by"`
+	Permission []struct {
+		ID                 string `json:"id"`
+		Object             string `json:"object"`
+		Created            int64  `json:"created"`
+		AllowCreateEngine  bool   `json:"allow_create_engine"`
+		AllowSampling      bool   `json:"allow_sampling"`
+		AllowLogprobs      bool   `json:"allow_logprobs"`
+		AllowSearchIndices bool   `json:"allow_search_indices"`
+		AllowView          bool   `json:"allow_view"`
+		AllowFineTuning    bool   `json:"allow_fine_tuning"`
+		Organization       string `json:"organization"`
+		Group              string `json:"group"`
+		IsBlocking         bool   `json:"is_blocking"`
+	} `json:"permission"`
+	Root   string `json:"root"`
+	Parent string `json:"parent"`
+}
+
+type OpenAIModelsResponse struct {
+	Data    []OpenAIModel `json:"data"`
+	Success bool          `json:"success"`
+}
+
 func GetAllChannels(c *gin.Context) {
 	p, _ := strconv.Atoi(c.Query("p"))
 	pageSize, _ := strconv.Atoi(c.Query("page_size"))
@@ -35,6 +65,65 @@ func GetAllChannels(c *gin.Context) {
 	return
 }
 
+func FetchUpstreamModels(c *gin.Context) {
+	id, err := strconv.Atoi(c.Param("id"))
+	if err != nil {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": err.Error(),
+		})
+		return
+	}
+	channel, err := model.GetChannelById(id, true)
+	if err != nil {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": err.Error(),
+		})
+		return
+	}
+	if channel.Type != common.ChannelTypeOpenAI {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": "仅支持 OpenAI 类型渠道",
+		})
+		return
+	}
+	url := fmt.Sprintf("%s/v1/models", *channel.BaseURL)
+	body, err := GetResponseBody("GET", url, channel, GetAuthHeader(channel.Key))
+	if err != nil {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": err.Error(),
+		})
+	}
+	result := OpenAIModelsResponse{}
+	err = json.Unmarshal(body, &result)
+	if err != nil {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": err.Error(),
+		})
+	}
+	if !result.Success {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": "上游返回错误",
+		})
+	}
+
+	var ids []string
+	for _, model := range result.Data {
+		ids = append(ids, model.ID)
+	}
+
+	c.JSON(http.StatusOK, gin.H{
+		"success": true,
+		"message": "",
+		"data":    ids,
+	})
+}
+
 func FixChannelsAbilities(c *gin.Context) {
 	count, err := model.FixAbility()
 	if err != nil {

controller/midjourney.go

@@ -10,11 +10,11 @@ import (
 	"log"
 	"net/http"
 	"one-api/common"
+	"one-api/constant"
 	"one-api/dto"
 	"one-api/model"
 	"one-api/service"
 	"strconv"
-	"strings"
 	"time"
 )
 
@@ -86,7 +86,7 @@ func UpdateMidjourneyTaskBulk() {
 				continue
 			}
 			// 设置超时时间
-			timeout := time.Second * 5
+			timeout := time.Second * 15
 			ctx, cancel := context.WithTimeout(context.Background(), timeout)
 			// 使用带有超时的 context 创建新的请求
 			req = req.WithContext(ctx)
@@ -233,6 +233,12 @@ func GetAllMidjourney(c *gin.Context) {
 	if logs == nil {
 		logs = make([]*model.Midjourney, 0)
 	}
+	if constant.MjForwardUrlEnabled {
+		for i, midjourney := range logs {
+			midjourney.ImageUrl = constant.ServerAddress + "/mj/image/" + midjourney.MjId
+			logs[i] = midjourney
+		}
+	}
 	c.JSON(200, gin.H{
 		"success": true,
 		"message": "",
@@ -259,9 +265,9 @@ func GetUserMidjourney(c *gin.Context) {
 	if logs == nil {
 		logs = make([]*model.Midjourney, 0)
 	}
-	if !strings.Contains(common.ServerAddress, "localhost") {
+	if constant.MjForwardUrlEnabled {
 		for i, midjourney := range logs {
-			midjourney.ImageUrl = common.ServerAddress + "/mj/image/" + midjourney.MjId
+			midjourney.ImageUrl = constant.ServerAddress + "/mj/image/" + midjourney.MjId
 			logs[i] = midjourney
 		}
 	}

controller/misc.go

@@ -45,9 +45,9 @@ func GetStatus(c *gin.Context) {
 			"footer_html":              common.Footer,
 			"wechat_qrcode":            common.WeChatAccountQRCodeImageURL,
 			"wechat_login":             common.WeChatAuthEnabled,
-			"server_address":           common.ServerAddress,
-			"price":                    common.Price,
-			"min_topup":                common.MinTopUp,
+			"server_address":           constant.ServerAddress,
+			"price":                    constant.Price,
+			"min_topup":                constant.MinTopUp,
 			"turnstile_check":          common.TurnstileCheckEnabled,
 			"turnstile_site_key":       common.TurnstileSiteKey,
 			"top_up_link":              common.TopUpLink,
@@ -57,10 +57,11 @@ func GetStatus(c *gin.Context) {
 			"display_in_currency":      common.DisplayInCurrencyEnabled,
 			"enable_batch_update":      common.BatchUpdateEnabled,
 			"enable_drawing":           common.DrawingEnabled,
+			"enable_task":              common.TaskEnabled,
 			"enable_data_export":       common.DataExportEnabled,
 			"data_export_default_time": common.DataExportDefaultTime,
 			"default_collapse_sidebar": common.DefaultCollapseSidebar,
-			"enable_online_topup":      common.PayAddress != "" && common.EpayId != "" && common.EpayKey != "",
+			"enable_online_topup":      constant.PayAddress != "" && constant.EpayId != "" && constant.EpayKey != "",
 			"mj_notify_enabled":        constant.MjNotifyEnabled,
 		},
 	})
@@ -120,12 +121,17 @@ func SendEmailVerification(c *gin.Context) {
 		})
 		return
 	}
+	parts := strings.Split(email, "@")
+	if len(parts) != 2 {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": "无效的邮箱地址",
+		})
+		return
+	}
+	localPart := parts[0]
+	domainPart := parts[1]
 	if common.EmailDomainRestrictionEnabled {
-		parts := strings.Split(email, "@")
-		localPart := parts[0]
-		domainPart := parts[1]
-
-		containsSpecialSymbols := strings.Contains(localPart, "+") || strings.Count(localPart, ".") > 1
 		allowed := false
 		for _, domain := range common.EmailDomainWhitelist {
 			if domainPart == domain {
@@ -133,13 +139,7 @@ func SendEmailVerification(c *gin.Context) {
 				break
 			}
 		}
-		if allowed && !containsSpecialSymbols {
-			c.JSON(http.StatusOK, gin.H{
-				"success": false,
-				"message": "Your email address is allowed.",
-			})
-			return
-		} else {
+		if !allowed {
 			c.JSON(http.StatusOK, gin.H{
 				"success": false,
 				"message": "The administrator has enabled the email domain name whitelist, and your email address is not allowed due to special symbols or it's not in the whitelist.",
@@ -147,6 +147,17 @@ func SendEmailVerification(c *gin.Context) {
 			return
 		}
 	}
+	if common.EmailAliasRestrictionEnabled {
+		containsSpecialSymbols := strings.Contains(localPart, "+") || strings.Contains(localPart, ".")
+		if containsSpecialSymbols {
+			c.JSON(http.StatusOK, gin.H{
+				"success": false,
+				"message": "管理员已启用邮箱地址别名限制，您的邮箱地址由于包含特殊符号而被拒绝。",
+			})
+			return
+		}
+	}
+
 	if model.IsEmailAlreadyTaken(email) {
 		c.JSON(http.StatusOK, gin.H{
 			"success": false,
@@ -193,7 +204,7 @@ func SendPasswordResetEmail(c *gin.Context) {
 	}
 	code := common.GenerateVerificationCode(0)
 	common.RegisterVerificationCodeWithKey(email, code, common.PasswordResetPurpose)
-	link := fmt.Sprintf("%s/user/reset?email=%s&token=%s", common.ServerAddress, email, code)
+	link := fmt.Sprintf("%s/user/reset?email=%s&token=%s", constant.ServerAddress, email, code)
 	subject := fmt.Sprintf("%s密码重置", common.SystemName)
 	content := fmt.Sprintf("<p>您好，你正在进行%s密码重置。</p>"+
 		"<p>点击 <a href='%s'>此处</a> 进行密码重置。</p>"+

controller/model.go

@@ -4,49 +4,28 @@ import (
 	"fmt"
 	"github.com/gin-gonic/gin"
 	"net/http"
+	"one-api/common"
 	"one-api/constant"
 	"one-api/dto"
 	"one-api/model"
 	"one-api/relay"
 	"one-api/relay/channel/ai360"
-	"one-api/relay/channel/moonshot"
 	"one-api/relay/channel/lingyiwanwu"
+	"one-api/relay/channel/minimax"
+	"one-api/relay/channel/moonshot"
+	relaycommon "one-api/relay/common"
 	relayconstant "one-api/relay/constant"
 )
 
 // https://platform.openai.com/docs/api-reference/models/list
 
-type OpenAIModelPermission struct {
-	Id                 string  `json:"id"`
-	Object             string  `json:"object"`
-	Created            int     `json:"created"`
-	AllowCreateEngine  bool    `json:"allow_create_engine"`
-	AllowSampling      bool    `json:"allow_sampling"`
-	AllowLogprobs      bool    `json:"allow_logprobs"`
-	AllowSearchIndices bool    `json:"allow_search_indices"`
-	AllowView          bool    `json:"allow_view"`
-	AllowFineTuning    bool    `json:"allow_fine_tuning"`
-	Organization       string  `json:"organization"`
-	Group              *string `json:"group"`
-	IsBlocking         bool    `json:"is_blocking"`
-}
+var openAIModels []dto.OpenAIModels
+var openAIModelsMap map[string]dto.OpenAIModels
+var channelId2Models map[int][]string
 
-type OpenAIModels struct {
-	Id         string                  `json:"id"`
-	Object     string                  `json:"object"`
-	Created    int                     `json:"created"`
-	OwnedBy    string                  `json:"owned_by"`
-	Permission []OpenAIModelPermission `json:"permission"`
-	Root       string                  `json:"root"`
-	Parent     *string                 `json:"parent"`
-}
-
-var openAIModels []OpenAIModels
-var openAIModelsMap map[string]OpenAIModels
-
-func init() {
-	var permission []OpenAIModelPermission
-	permission = append(permission, OpenAIModelPermission{
+func getPermission() []dto.OpenAIModelPermission {
+	var permission []dto.OpenAIModelPermission
+	permission = append(permission, dto.OpenAIModelPermission{
 		Id:                 "modelperm-LwHkVFn8AcMItP432fKKDIKJ",
 		Object:             "model_permission",
 		Created:            1626777600,
@@ -60,7 +39,12 @@ func init() {
 		Group:              nil,
 		IsBlocking:         false,
 	})
+	return permission
+}
+
+func init() {
 	// https://platform.openai.com/docs/models/model-endpoint-compatibility
+	permission := getPermission()
 	for i := 0; i < relayconstant.APITypeDummy; i++ {
 		if i == relayconstant.APITypeAIProxyLibrary {
 			continue
@@ -69,7 +53,7 @@ func init() {
 		channelName := adaptor.GetChannelName()
 		modelNames := adaptor.GetModelList()
 		for _, modelName := range modelNames {
-			openAIModels = append(openAIModels, OpenAIModels{
+			openAIModels = append(openAIModels, dto.OpenAIModels{
 				Id:         modelName,
 				Object:     "model",
 				Created:    1626777600,
@@ -81,40 +65,51 @@ func init() {
 		}
 	}
 	for _, modelName := range ai360.ModelList {
-		openAIModels = append(openAIModels, OpenAIModels{
+		openAIModels = append(openAIModels, dto.OpenAIModels{
 			Id:         modelName,
 			Object:     "model",
 			Created:    1626777600,
-			OwnedBy:    "360",
+			OwnedBy:    ai360.ChannelName,
 			Permission: permission,
 			Root:       modelName,
 			Parent:     nil,
 		})
 	}
 	for _, modelName := range moonshot.ModelList {
-		openAIModels = append(openAIModels, OpenAIModels{
+		openAIModels = append(openAIModels, dto.OpenAIModels{
 			Id:         modelName,
 			Object:     "model",
 			Created:    1626777600,
-			OwnedBy:    "moonshot",
+			OwnedBy:    moonshot.ChannelName,
 			Permission: permission,
 			Root:       modelName,
 			Parent:     nil,
 		})
 	}
 	for _, modelName := range lingyiwanwu.ModelList {
-		openAIModels = append(openAIModels, OpenAIModels{
+		openAIModels = append(openAIModels, dto.OpenAIModels{
 			Id:         modelName,
 			Object:     "model",
 			Created:    1626777600,
-			OwnedBy:    "lingyiwanwu",
+			OwnedBy:    lingyiwanwu.ChannelName,
+			Permission: permission,
+			Root:       modelName,
+			Parent:     nil,
+		})
+	}
+	for _, modelName := range minimax.ModelList {
+		openAIModels = append(openAIModels, dto.OpenAIModels{
+			Id:         modelName,
+			Object:     "model",
+			Created:    1626777600,
+			OwnedBy:    minimax.ChannelName,
 			Permission: permission,
 			Root:       modelName,
 			Parent:     nil,
 		})
 	}
 	for modelName, _ := range constant.MidjourneyModel2Action {
-		openAIModels = append(openAIModels, OpenAIModels{
+		openAIModels = append(openAIModels, dto.OpenAIModels{
 			Id:         modelName,
 			Object:     "model",
 			Created:    1626777600,
@@ -124,9 +119,20 @@ func init() {
 			Parent:     nil,
 		})
 	}
-	openAIModelsMap = make(map[string]OpenAIModels)
-	for _, model := range openAIModels {
-		openAIModelsMap[model.Id] = model
+	openAIModelsMap = make(map[string]dto.OpenAIModels)
+	for _, aiModel := range openAIModels {
+		openAIModelsMap[aiModel.Id] = aiModel
+	}
+	channelId2Models = make(map[int][]string)
+	for i := 1; i <= common.ChannelTypeDummy; i++ {
+		apiType, success := relayconstant.ChannelType2APIType(i)
+		if !success || apiType == relayconstant.APITypeAIProxyLibrary {
+			continue
+		}
+		meta := &relaycommon.RelayInfo{ChannelType: i}
+		adaptor := relay.GetAdaptor(apiType)
+		adaptor.Init(meta, dto.GeneralOpenAIRequest{})
+		channelId2Models[i] = adaptor.GetModelList()
 	}
 }
 
@@ -141,29 +147,47 @@ func ListModels(c *gin.Context) {
 		return
 	}
 	models := model.GetGroupModels(user.Group)
-	userOpenAiModels := make([]OpenAIModels, 0)
+	userOpenAiModels := make([]dto.OpenAIModels, 0)
+	permission := getPermission()
 	for _, s := range models {
 		if _, ok := openAIModelsMap[s]; ok {
 			userOpenAiModels = append(userOpenAiModels, openAIModelsMap[s])
+		} else {
+			userOpenAiModels = append(userOpenAiModels, dto.OpenAIModels{
+				Id:         s,
+				Object:     "model",
+				Created:    1626777600,
+				OwnedBy:    "custom",
+				Permission: permission,
+				Root:       s,
+				Parent:     nil,
+			})
 		}
 	}
 	c.JSON(200, gin.H{
-		"object": "list",
-		"data":   userOpenAiModels,
+		"success": true,
+		"data":    userOpenAiModels,
 	})
 }
 
 func ChannelListModels(c *gin.Context) {
 	c.JSON(200, gin.H{
-		"object": "list",
-		"data":   openAIModels,
+		"success": true,
+		"data":    openAIModels,
+	})
+}
+
+func DashboardListModels(c *gin.Context) {
+	c.JSON(200, gin.H{
+		"success": true,
+		"data":    channelId2Models,
 	})
 }
 
 func RetrieveModel(c *gin.Context) {
 	modelId := c.Param("model")
-	if model, ok := openAIModelsMap[modelId]; ok {
-		c.JSON(200, model)
+	if aiModel, ok := openAIModelsMap[modelId]; ok {
+		c.JSON(200, aiModel)
 	} else {
 		openAIError := dto.OpenAIError{
 			Message: fmt.Sprintf("The model '%s' does not exist", modelId),

controller/option.go

@@ -14,7 +14,7 @@ func GetOptions(c *gin.Context) {
 	var options []*model.Option
 	common.OptionMapRWMutex.Lock()
 	for k, v := range common.OptionMap {
-		if strings.HasSuffix(k, "Token") || strings.HasSuffix(k, "Secret") {
+		if strings.HasSuffix(k, "Token") || strings.HasSuffix(k, "Secret") || strings.HasSuffix(k, "Key") {
 			continue
 		}
 		options = append(options, &model.Option{

controller/pricing.go

@@ -0,0 +1,47 @@
+package controller
+
+import (
+	"github.com/gin-gonic/gin"
+	"one-api/common"
+	"one-api/model"
+)
+
+func GetPricing(c *gin.Context) {
+	userId := c.GetInt("id")
+	// if no login, get default group ratio
+	groupRatio := common.GetGroupRatio("default")
+	group, err := model.CacheGetUserGroup(userId)
+	if err == nil {
+		groupRatio = common.GetGroupRatio(group)
+	}
+	pricing := model.GetPricing(group)
+	c.JSON(200, gin.H{
+		"success":     true,
+		"data":        pricing,
+		"group_ratio": groupRatio,
+	})
+}
+
+func ResetModelRatio(c *gin.Context) {
+	defaultStr := common.DefaultModelRatio2JSONString()
+	err := model.UpdateOption("ModelRatio", defaultStr)
+	if err != nil {
+		c.JSON(200, gin.H{
+			"success": false,
+			"message": err.Error(),
+		})
+		return
+	}
+	err = common.UpdateModelRatioByJSONString(defaultStr)
+	if err != nil {
+		c.JSON(200, gin.H{
+			"success": false,
+			"message": err.Error(),
+		})
+		return
+	}
+	c.JSON(200, gin.H{
+		"success": true,
+		"message": "重置模型倍率成功",
+	})
+}

controller/relay.go

@@ -15,6 +15,7 @@ import (
 	"one-api/relay/constant"
 	relayconstant "one-api/relay/constant"
 	"one-api/service"
+	"strings"
 )
 
 func relayHandler(c *gin.Context, relayMode int) *dto.OpenAIErrorWithStatusCode {
@@ -28,6 +29,8 @@ func relayHandler(c *gin.Context, relayMode int) *dto.OpenAIErrorWithStatusCode
 		fallthrough
 	case relayconstant.RelayModeAudioTranscription:
 		err = relay.AudioHelper(c, relayMode)
+	case relayconstant.RelayModeRerank:
+		err = relay.RerankHelper(c, relayMode)
 	default:
 		err = relay.TextHelper(c)
 	}
@@ -39,12 +42,13 @@ func Relay(c *gin.Context) {
 	retryTimes := common.RetryTimes
 	requestId := c.GetString(common.RequestIdKey)
 	channelId := c.GetInt("channel_id")
+	channelType := c.GetInt("channel_type")
 	group := c.GetString("group")
 	originalModel := c.GetString("original_model")
 	openaiErr := relayHandler(c, relayMode)
-	retryLogStr := fmt.Sprintf("重试：%d", channelId)
+	c.Set("use_channel", []string{fmt.Sprintf("%d", channelId)})
 	if openaiErr != nil {
-		go processChannelError(c, channelId, openaiErr)
+		go processChannelError(c, channelId, channelType, openaiErr)
 	} else {
 		retryTimes = 0
 	}
@@ -55,7 +59,9 @@ func Relay(c *gin.Context) {
 			break
 		}
 		channelId = channel.Id
-		retryLogStr += fmt.Sprintf("->%d", channel.Id)
+		useChannel := c.GetStringSlice("use_channel")
+		useChannel = append(useChannel, fmt.Sprintf("%d", channelId))
+		c.Set("use_channel", useChannel)
 		common.LogInfo(c.Request.Context(), fmt.Sprintf("using channel #%d to retry (remain times %d)", channel.Id, i))
 		middleware.SetupContextForSelectedChannel(c, channel, originalModel)
 
@@ -63,10 +69,14 @@ func Relay(c *gin.Context) {
 		c.Request.Body = io.NopCloser(bytes.NewBuffer(requestBody))
 		openaiErr = relayHandler(c, relayMode)
 		if openaiErr != nil {
-			go processChannelError(c, channelId, openaiErr)
+			go processChannelError(c, channelId, channel.Type, openaiErr)
 		}
 	}
-	common.LogInfo(c.Request.Context(), retryLogStr)
+	useChannel := c.GetStringSlice("use_channel")
+	if len(useChannel) > 1 {
+		retryLogStr := fmt.Sprintf("重试：%s", strings.Trim(strings.Join(strings.Fields(fmt.Sprint(useChannel)), "->"), "[]"))
+		common.LogInfo(c.Request.Context(), retryLogStr)
+	}
 
 	if openaiErr != nil {
 		if openaiErr.StatusCode == http.StatusTooManyRequests {
@@ -92,12 +102,23 @@ func shouldRetry(c *gin.Context, channelId int, openaiErr *dto.OpenAIErrorWithSt
 	if openaiErr.StatusCode == http.StatusTooManyRequests {
 		return true
 	}
+	if openaiErr.StatusCode == 307 {
+		return true
+	}
 	if openaiErr.StatusCode/100 == 5 {
+		// 超时不重试
+		if openaiErr.StatusCode == 504 || openaiErr.StatusCode == 524 {
+			return false
+		}
 		return true
 	}
 	if openaiErr.StatusCode == http.StatusBadRequest {
 		return false
 	}
+	if openaiErr.StatusCode == 408 {
+		// azure处理超时不重试
+		return false
+	}
 	if openaiErr.LocalError {
 		return false
 	}
@@ -107,10 +128,10 @@ func shouldRetry(c *gin.Context, channelId int, openaiErr *dto.OpenAIErrorWithSt
 	return true
 }
 
-func processChannelError(c *gin.Context, channelId int, err *dto.OpenAIErrorWithStatusCode) {
+func processChannelError(c *gin.Context, channelId int, channelType int, err *dto.OpenAIErrorWithStatusCode) {
 	autoBan := c.GetBool("auto_ban")
-	common.LogError(c.Request.Context(), fmt.Sprintf("relay error (channel #%d): %s", channelId, err.Error.Message))
-	if service.ShouldDisableChannel(&err.Error, err.StatusCode) && autoBan {
+	common.LogError(c.Request.Context(), fmt.Sprintf("relay error (channel #%d, status code: %d): %s", channelId, err.StatusCode, err.Error.Message))
+	if service.ShouldDisableChannel(channelType, err) && autoBan {
 		channelName := c.GetString("channel_name")
 		service.DisableChannel(channelId, channelName, err.Error.Message)
 	}
@@ -145,7 +166,7 @@ func RelayMidjourney(c *gin.Context) {
 			"code":        err.Code,
 		})
 		channelId := c.GetInt("channel_id")
-		common.SysError(fmt.Sprintf("relay error (channel #%d): %s", channelId, fmt.Sprintf("%s %s", err.Description, err.Result)))
+		common.LogError(c, fmt.Sprintf("relay error (channel #%d, status code %d): %s", channelId, statusCode, fmt.Sprintf("%s %s", err.Description, err.Result)))
 	}
 }
 
@@ -172,3 +193,94 @@ func RelayNotFound(c *gin.Context) {
 		"error": err,
 	})
 }
+
+func RelayTask(c *gin.Context) {
+	retryTimes := common.RetryTimes
+	channelId := c.GetInt("channel_id")
+	relayMode := c.GetInt("relay_mode")
+	group := c.GetString("group")
+	originalModel := c.GetString("original_model")
+	c.Set("use_channel", []string{fmt.Sprintf("%d", channelId)})
+	taskErr := taskRelayHandler(c, relayMode)
+	if taskErr == nil {
+		retryTimes = 0
+	}
+	for i := 0; shouldRetryTaskRelay(c, channelId, taskErr, retryTimes) && i < retryTimes; i++ {
+		channel, err := model.CacheGetRandomSatisfiedChannel(group, originalModel, i)
+		if err != nil {
+			common.LogError(c.Request.Context(), fmt.Sprintf("CacheGetRandomSatisfiedChannel failed: %s", err.Error()))
+			break
+		}
+		channelId = channel.Id
+		useChannel := c.GetStringSlice("use_channel")
+		useChannel = append(useChannel, fmt.Sprintf("%d", channelId))
+		c.Set("use_channel", useChannel)
+		common.LogInfo(c.Request.Context(), fmt.Sprintf("using channel #%d to retry (remain times %d)", channel.Id, i))
+		middleware.SetupContextForSelectedChannel(c, channel, originalModel)
+
+		requestBody, err := common.GetRequestBody(c)
+		c.Request.Body = io.NopCloser(bytes.NewBuffer(requestBody))
+		taskErr = taskRelayHandler(c, relayMode)
+	}
+	useChannel := c.GetStringSlice("use_channel")
+	if len(useChannel) > 1 {
+		retryLogStr := fmt.Sprintf("重试：%s", strings.Trim(strings.Join(strings.Fields(fmt.Sprint(useChannel)), "->"), "[]"))
+		common.LogInfo(c.Request.Context(), retryLogStr)
+	}
+	if taskErr != nil {
+		if taskErr.StatusCode == http.StatusTooManyRequests {
+			taskErr.Message = "当前分组上游负载已饱和，请稍后再试"
+		}
+		c.JSON(taskErr.StatusCode, taskErr)
+	}
+}
+
+func taskRelayHandler(c *gin.Context, relayMode int) *dto.TaskError {
+	var err *dto.TaskError
+	switch relayMode {
+	case relayconstant.RelayModeSunoFetch, relayconstant.RelayModeSunoFetchByID:
+		err = relay.RelayTaskFetch(c, relayMode)
+	default:
+		err = relay.RelayTaskSubmit(c, relayMode)
+	}
+	return err
+}
+
+func shouldRetryTaskRelay(c *gin.Context, channelId int, taskErr *dto.TaskError, retryTimes int) bool {
+	if taskErr == nil {
+		return false
+	}
+	if retryTimes <= 0 {
+		return false
+	}
+	if _, ok := c.Get("specific_channel_id"); ok {
+		return false
+	}
+	if taskErr.StatusCode == http.StatusTooManyRequests {
+		return true
+	}
+	if taskErr.StatusCode == 307 {
+		return true
+	}
+	if taskErr.StatusCode/100 == 5 {
+		// 超时不重试
+		if taskErr.StatusCode == 504 || taskErr.StatusCode == 524 {
+			return false
+		}
+		return true
+	}
+	if taskErr.StatusCode == http.StatusBadRequest {
+		return false
+	}
+	if taskErr.StatusCode == 408 {
+		// azure处理超时不重试
+		return false
+	}
+	if taskErr.LocalError {
+		return false
+	}
+	if taskErr.StatusCode/100 == 2 {
+		return false
+	}
+	return true
+}

controller/task.go

@@ -0,0 +1,284 @@
+package controller
+
+import (
+	"context"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"github.com/gin-gonic/gin"
+	"github.com/samber/lo"
+	"io"
+	"net/http"
+	"one-api/common"
+	"one-api/constant"
+	"one-api/dto"
+	"one-api/model"
+	"one-api/relay"
+	"sort"
+	"strconv"
+	"time"
+)
+
+func UpdateTaskBulk() {
+	//revocer
+	//imageModel := "midjourney"
+	for {
+		time.Sleep(time.Duration(15) * time.Second)
+		common.SysLog("任务进度轮询开始")
+		ctx := context.TODO()
+		allTasks := model.GetAllUnFinishSyncTasks(500)
+		platformTask := make(map[constant.TaskPlatform][]*model.Task)
+		for _, t := range allTasks {
+			platformTask[t.Platform] = append(platformTask[t.Platform], t)
+		}
+		for platform, tasks := range platformTask {
+			if len(tasks) == 0 {
+				continue
+			}
+			taskChannelM := make(map[int][]string)
+			taskM := make(map[string]*model.Task)
+			nullTaskIds := make([]int64, 0)
+			for _, task := range tasks {
+				if task.TaskID == "" {
+					// 统计失败的未完成任务
+					nullTaskIds = append(nullTaskIds, task.ID)
+					continue
+				}
+				taskM[task.TaskID] = task
+				taskChannelM[task.ChannelId] = append(taskChannelM[task.ChannelId], task.TaskID)
+			}
+			if len(nullTaskIds) > 0 {
+				err := model.TaskBulkUpdateByID(nullTaskIds, map[string]any{
+					"status":   "FAILURE",
+					"progress": "100%",
+				})
+				if err != nil {
+					common.LogError(ctx, fmt.Sprintf("Fix null task_id task error: %v", err))
+				} else {
+					common.LogInfo(ctx, fmt.Sprintf("Fix null task_id task success: %v", nullTaskIds))
+				}
+			}
+			if len(taskChannelM) == 0 {
+				continue
+			}
+
+			UpdateTaskByPlatform(platform, taskChannelM, taskM)
+		}
+		common.SysLog("任务进度轮询完成")
+	}
+}
+
+func UpdateTaskByPlatform(platform constant.TaskPlatform, taskChannelM map[int][]string, taskM map[string]*model.Task) {
+	switch platform {
+	case constant.TaskPlatformMidjourney:
+		//_ = UpdateMidjourneyTaskAll(context.Background(), tasks)
+	case constant.TaskPlatformSuno:
+		_ = UpdateSunoTaskAll(context.Background(), taskChannelM, taskM)
+	default:
+		common.SysLog("未知平台")
+	}
+}
+
+func UpdateSunoTaskAll(ctx context.Context, taskChannelM map[int][]string, taskM map[string]*model.Task) error {
+	for channelId, taskIds := range taskChannelM {
+		err := updateSunoTaskAll(ctx, channelId, taskIds, taskM)
+		if err != nil {
+			common.LogError(ctx, fmt.Sprintf("渠道 #%d 更新异步任务失败: %d", channelId, err.Error()))
+		}
+	}
+	return nil
+}
+
+func updateSunoTaskAll(ctx context.Context, channelId int, taskIds []string, taskM map[string]*model.Task) error {
+	common.LogInfo(ctx, fmt.Sprintf("渠道 #%d 未完成的任务有: %d", channelId, len(taskIds)))
+	if len(taskIds) == 0 {
+		return nil
+	}
+	channel, err := model.CacheGetChannel(channelId)
+	if err != nil {
+		common.SysLog(fmt.Sprintf("CacheGetChannel: %v", err))
+		err = model.TaskBulkUpdate(taskIds, map[string]any{
+			"fail_reason": fmt.Sprintf("获取渠道信息失败，请联系管理员，渠道ID：%d", channelId),
+			"status":      "FAILURE",
+			"progress":    "100%",
+		})
+		if err != nil {
+			common.SysError(fmt.Sprintf("UpdateMidjourneyTask error2: %v", err))
+		}
+		return err
+	}
+	adaptor := relay.GetTaskAdaptor(constant.TaskPlatformSuno)
+	if adaptor == nil {
+		return errors.New("adaptor not found")
+	}
+	resp, err := adaptor.FetchTask(*channel.BaseURL, channel.Key, map[string]any{
+		"ids": taskIds,
+	})
+	if err != nil {
+		common.SysError(fmt.Sprintf("Get Task Do req error: %v", err))
+		return err
+	}
+	if resp.StatusCode != http.StatusOK {
+		common.LogError(ctx, fmt.Sprintf("Get Task status code: %d", resp.StatusCode))
+		return errors.New(fmt.Sprintf("Get Task status code: %d", resp.StatusCode))
+	}
+	defer resp.Body.Close()
+	responseBody, err := io.ReadAll(resp.Body)
+	if err != nil {
+		common.SysError(fmt.Sprintf("Get Task parse body error: %v", err))
+		return err
+	}
+	var responseItems dto.TaskResponse[[]dto.SunoDataResponse]
+	err = json.Unmarshal(responseBody, &responseItems)
+	if err != nil {
+		common.LogError(ctx, fmt.Sprintf("Get Task parse body error2: %v, body: %s", err, string(responseBody)))
+		return err
+	}
+	if !responseItems.IsSuccess() {
+		common.SysLog(fmt.Sprintf("渠道 #%d 未完成的任务有: %d, 成功获取到任务数: %d", channelId, len(taskIds), string(responseBody)))
+		return err
+	}
+
+	for _, responseItem := range responseItems.Data {
+		task := taskM[responseItem.TaskID]
+		if !checkTaskNeedUpdate(task, responseItem) {
+			continue
+		}
+
+		task.Status = lo.If(model.TaskStatus(responseItem.Status) != "", model.TaskStatus(responseItem.Status)).Else(task.Status)
+		task.FailReason = lo.If(responseItem.FailReason != "", responseItem.FailReason).Else(task.FailReason)
+		task.SubmitTime = lo.If(responseItem.SubmitTime != 0, responseItem.SubmitTime).Else(task.SubmitTime)
+		task.StartTime = lo.If(responseItem.StartTime != 0, responseItem.StartTime).Else(task.StartTime)
+		task.FinishTime = lo.If(responseItem.FinishTime != 0, responseItem.FinishTime).Else(task.FinishTime)
+		if responseItem.FailReason != "" || task.Status == model.TaskStatusFailure {
+			common.LogInfo(ctx, task.TaskID+" 构建失败，"+task.FailReason)
+			task.Progress = "100%"
+			err = model.CacheUpdateUserQuota(task.UserId)
+			if err != nil {
+				common.LogError(ctx, "error update user quota cache: "+err.Error())
+			} else {
+				quota := task.Quota
+				if quota != 0 {
+					err = model.IncreaseUserQuota(task.UserId, quota)
+					if err != nil {
+						common.LogError(ctx, "fail to increase user quota: "+err.Error())
+					}
+					logContent := fmt.Sprintf("异步任务执行失败 %s，补偿 %s", task.TaskID, common.LogQuota(quota))
+					model.RecordLog(task.UserId, model.LogTypeSystem, logContent)
+				}
+			}
+		}
+		if responseItem.Status == model.TaskStatusSuccess {
+			task.Progress = "100%"
+		}
+		task.Data = responseItem.Data
+
+		err = task.Update()
+		if err != nil {
+			common.SysError("UpdateMidjourneyTask task error: " + err.Error())
+		}
+	}
+	return nil
+}
+
+func checkTaskNeedUpdate(oldTask *model.Task, newTask dto.SunoDataResponse) bool {
+
+	if oldTask.SubmitTime != newTask.SubmitTime {
+		return true
+	}
+	if oldTask.StartTime != newTask.StartTime {
+		return true
+	}
+	if oldTask.FinishTime != newTask.FinishTime {
+		return true
+	}
+	if string(oldTask.Status) != newTask.Status {
+		return true
+	}
+	if oldTask.FailReason != newTask.FailReason {
+		return true
+	}
+	if oldTask.FinishTime != newTask.FinishTime {
+		return true
+	}
+
+	if (oldTask.Status == model.TaskStatusFailure || oldTask.Status == model.TaskStatusSuccess) && oldTask.Progress != "100%" {
+		return true
+	}
+
+	oldData, _ := json.Marshal(oldTask.Data)
+	newData, _ := json.Marshal(newTask.Data)
+
+	sort.Slice(oldData, func(i, j int) bool {
+		return oldData[i] < oldData[j]
+	})
+	sort.Slice(newData, func(i, j int) bool {
+		return newData[i] < newData[j]
+	})
+
+	if string(oldData) != string(newData) {
+		return true
+	}
+	return false
+}
+
+func GetAllTask(c *gin.Context) {
+	p, _ := strconv.Atoi(c.Query("p"))
+	if p < 0 {
+		p = 0
+	}
+	startTimestamp, _ := strconv.ParseInt(c.Query("start_timestamp"), 10, 64)
+	endTimestamp, _ := strconv.ParseInt(c.Query("end_timestamp"), 10, 64)
+	// 解析其他查询参数
+	queryParams := model.SyncTaskQueryParams{
+		Platform:       constant.TaskPlatform(c.Query("platform")),
+		TaskID:         c.Query("task_id"),
+		Status:         c.Query("status"),
+		Action:         c.Query("action"),
+		StartTimestamp: startTimestamp,
+		EndTimestamp:   endTimestamp,
+	}
+
+	logs := model.TaskGetAllTasks(p*common.ItemsPerPage, common.ItemsPerPage, queryParams)
+	if logs == nil {
+		logs = make([]*model.Task, 0)
+	}
+
+	c.JSON(200, gin.H{
+		"success": true,
+		"message": "",
+		"data":    logs,
+	})
+}
+
+func GetUserTask(c *gin.Context) {
+	p, _ := strconv.Atoi(c.Query("p"))
+	if p < 0 {
+		p = 0
+	}
+
+	userId := c.GetInt("id")
+
+	startTimestamp, _ := strconv.ParseInt(c.Query("start_timestamp"), 10, 64)
+	endTimestamp, _ := strconv.ParseInt(c.Query("end_timestamp"), 10, 64)
+
+	queryParams := model.SyncTaskQueryParams{
+		Platform:       constant.TaskPlatform(c.Query("platform")),
+		TaskID:         c.Query("task_id"),
+		Status:         c.Query("status"),
+		Action:         c.Query("action"),
+		StartTimestamp: startTimestamp,
+		EndTimestamp:   endTimestamp,
+	}
+
+	logs := model.TaskGetAllUserTask(userId, p*common.ItemsPerPage, common.ItemsPerPage, queryParams)
+	if logs == nil {
+		logs = make([]*model.Task, 0)
+	}
+
+	c.JSON(200, gin.H{
+		"success": true,
+		"message": "",
+		"data":    logs,
+	})
+}

controller/topup.go

@@ -2,12 +2,13 @@ package controller
 
 import (
 	"fmt"
+	"github.com/Calcium-Ion/go-epay/epay"
 	"github.com/gin-gonic/gin"
 	"github.com/samber/lo"
-	epay "github.com/star-horizon/go-epay"
 	"log"
 	"net/url"
 	"one-api/common"
+	"one-api/constant"
 	"one-api/model"
 	"one-api/service"
 	"strconv"
@@ -27,13 +28,13 @@ type AmountRequest struct {
 }
 
 func GetEpayClient() *epay.Client {
-	if common.PayAddress == "" || common.EpayId == "" || common.EpayKey == "" {
+	if constant.PayAddress == "" || constant.EpayId == "" || constant.EpayKey == "" {
 		return nil
 	}
-	withUrl, err := epay.NewClientWithUrl(&epay.Config{
-		PartnerID: common.EpayId,
-		Key:       common.EpayKey,
-	}, common.PayAddress)
+	withUrl, err := epay.NewClient(&epay.Config{
+		PartnerID: constant.EpayId,
+		Key:       constant.EpayKey,
+	}, constant.PayAddress)
 	if err != nil {
 		return nil
 	}
@@ -49,12 +50,12 @@ func getPayMoney(amount float64, user model.User) float64 {
 	if topupGroupRatio == 0 {
 		topupGroupRatio = 1
 	}
-	payMoney := amount * common.Price * topupGroupRatio
+	payMoney := amount * constant.Price * topupGroupRatio
 	return payMoney
 }
 
 func getMinTopup() int {
-	minTopup := common.MinTopUp
+	minTopup := constant.MinTopUp
 	if !common.DisplayInCurrencyEnabled {
 		minTopup = minTopup * int(common.QuotaPerUnit)
 	}
@@ -90,7 +91,7 @@ func RequestEpay(c *gin.Context) {
 		payType = epay.WechatPay
 	}
 	callBackAddress := service.GetCallbackAddress()
-	returnUrl, _ := url.Parse(common.ServerAddress + "/log")
+	returnUrl, _ := url.Parse(constant.ServerAddress + "/log")
 	notifyUrl, _ := url.Parse(callBackAddress + "/api/user/epay/notify")
 	tradeNo := fmt.Sprintf("%s%d", common.GetRandomString(6), time.Now().Unix())
 	client := GetEpayClient()

controller/user.go

@@ -216,7 +216,8 @@ func GetAllUsers(c *gin.Context) {
 
 func SearchUsers(c *gin.Context) {
 	keyword := c.Query("keyword")
-	users, err := model.SearchUsers(keyword)
+	group := c.Query("group")
+	users, err := model.SearchUsers(keyword, group)
 	if err != nil {
 		c.JSON(http.StatusOK, gin.H{
 			"success": false,
@@ -452,7 +453,7 @@ func UpdateUser(c *gin.Context) {
 		updatedUser.Password = "" // rollback to what it should be
 	}
 	updatePassword := updatedUser.Password != ""
-	if err := updatedUser.Update(updatePassword); err != nil {
+	if err := updatedUser.Edit(updatePassword); err != nil {
 		c.JSON(http.StatusOK, gin.H{
 			"success": false,
 			"message": err.Error(),
@@ -725,7 +726,7 @@ func ManageUser(c *gin.Context) {
 		user.Role = common.RoleCommonUser
 	}
 
-	if err := user.UpdateAll(false); err != nil {
+	if err := user.Update(false); err != nil {
 		c.JSON(http.StatusOK, gin.H{
 			"success": false,
 			"message": err.Error(),

dto/pricing.go

@@ -0,0 +1,26 @@
+package dto
+
+type OpenAIModelPermission struct {
+	Id                 string  `json:"id"`
+	Object             string  `json:"object"`
+	Created            int     `json:"created"`
+	AllowCreateEngine  bool    `json:"allow_create_engine"`
+	AllowSampling      bool    `json:"allow_sampling"`
+	AllowLogprobs      bool    `json:"allow_logprobs"`
+	AllowSearchIndices bool    `json:"allow_search_indices"`
+	AllowView          bool    `json:"allow_view"`
+	AllowFineTuning    bool    `json:"allow_fine_tuning"`
+	Organization       string  `json:"organization"`
+	Group              *string `json:"group"`
+	IsBlocking         bool    `json:"is_blocking"`
+}
+
+type OpenAIModels struct {
+	Id         string                  `json:"id"`
+	Object     string                  `json:"object"`
+	Created    int                     `json:"created"`
+	OwnedBy    string                  `json:"owned_by"`
+	Permission []OpenAIModelPermission `json:"permission"`
+	Root       string                  `json:"root"`
+	Parent     *string                 `json:"parent"`
+}

dto/rerank.go

@@ -0,0 +1,19 @@
+package dto
+
+type RerankRequest struct {
+	Documents []any  `json:"documents"`
+	Query     string `json:"query"`
+	Model     string `json:"model"`
+	TopN      int    `json:"top_n"`
+}
+
+type RerankResponseDocument struct {
+	Document       any     `json:"document"`
+	Index          int     `json:"index"`
+	RelevanceScore float64 `json:"relevance_score"`
+}
+
+type RerankResponse struct {
+	Results []RerankResponseDocument `json:"results"`
+	Usage   Usage                    `json:"usage"`
+}

dto/suno.go

@@ -0,0 +1,129 @@
+package dto
+
+import (
+	"encoding/json"
+)
+
+type TaskData interface {
+	SunoDataResponse | []SunoDataResponse | string | any
+}
+
+type SunoSubmitReq struct {
+	GptDescriptionPrompt string  `json:"gpt_description_prompt,omitempty"`
+	Prompt               string  `json:"prompt,omitempty"`
+	Mv                   string  `json:"mv,omitempty"`
+	Title                string  `json:"title,omitempty"`
+	Tags                 string  `json:"tags,omitempty"`
+	ContinueAt           float64 `json:"continue_at,omitempty"`
+	TaskID               string  `json:"task_id,omitempty"`
+	ContinueClipId       string  `json:"continue_clip_id,omitempty"`
+	MakeInstrumental     bool    `json:"make_instrumental"`
+}
+
+type FetchReq struct {
+	IDs []string `json:"ids"`
+}
+
+type SunoDataResponse struct {
+	TaskID     string          `json:"task_id" gorm:"type:varchar(50);index"`
+	Action     string          `json:"action" gorm:"type:varchar(40);index"` // 任务类型, song, lyrics, description-mode
+	Status     string          `json:"status" gorm:"type:varchar(20);index"` // 任务状态, submitted, queueing, processing, success, failed
+	FailReason string          `json:"fail_reason"`
+	SubmitTime int64           `json:"submit_time" gorm:"index"`
+	StartTime  int64           `json:"start_time" gorm:"index"`
+	FinishTime int64           `json:"finish_time" gorm:"index"`
+	Data       json.RawMessage `json:"data" gorm:"type:json"`
+}
+
+type SunoSong struct {
+	ID                string       `json:"id"`
+	VideoURL          string       `json:"video_url"`
+	AudioURL          string       `json:"audio_url"`
+	ImageURL          string       `json:"image_url"`
+	ImageLargeURL     string       `json:"image_large_url"`
+	MajorModelVersion string       `json:"major_model_version"`
+	ModelName         string       `json:"model_name"`
+	Status            string       `json:"status"`
+	Title             string       `json:"title"`
+	Text              string       `json:"text"`
+	Metadata          SunoMetadata `json:"metadata"`
+}
+
+type SunoMetadata struct {
+	Tags                 string      `json:"tags"`
+	Prompt               string      `json:"prompt"`
+	GPTDescriptionPrompt interface{} `json:"gpt_description_prompt"`
+	AudioPromptID        interface{} `json:"audio_prompt_id"`
+	Duration             interface{} `json:"duration"`
+	ErrorType            interface{} `json:"error_type"`
+	ErrorMessage         interface{} `json:"error_message"`
+}
+
+type SunoLyrics struct {
+	ID     string `json:"id"`
+	Status string `json:"status"`
+	Title  string `json:"title"`
+	Text   string `json:"text"`
+}
+
+const TaskSuccessCode = "success"
+
+type TaskResponse[T TaskData] struct {
+	Code    string `json:"code"`
+	Message string `json:"message"`
+	Data    T      `json:"data"`
+}
+
+func (t *TaskResponse[T]) IsSuccess() bool {
+	return t.Code == TaskSuccessCode
+}
+
+type TaskDto struct {
+	TaskID     string          `json:"task_id"` // 第三方id，不一定有/ song id\ Task id
+	Action     string          `json:"action"`  // 任务类型, song, lyrics, description-mode
+	Status     string          `json:"status"`  // 任务状态, submitted, queueing, processing, success, failed
+	FailReason string          `json:"fail_reason"`
+	SubmitTime int64           `json:"submit_time"`
+	StartTime  int64           `json:"start_time"`
+	FinishTime int64           `json:"finish_time"`
+	Progress   string          `json:"progress"`
+	Data       json.RawMessage `json:"data"`
+}
+
+type SunoGoAPISubmitReq struct {
+	CustomMode bool `json:"custom_mode"`
+
+	Input SunoGoAPISubmitReqInput `json:"input"`
+
+	NotifyHook string `json:"notify_hook,omitempty"`
+}
+
+type SunoGoAPISubmitReqInput struct {
+	GptDescriptionPrompt string  `json:"gpt_description_prompt"`
+	Prompt               string  `json:"prompt"`
+	Mv                   string  `json:"mv"`
+	Title                string  `json:"title"`
+	Tags                 string  `json:"tags"`
+	ContinueAt           float64 `json:"continue_at"`
+	TaskID               string  `json:"task_id"`
+	ContinueClipId       string  `json:"continue_clip_id"`
+	MakeInstrumental     bool    `json:"make_instrumental"`
+}
+
+type GoAPITaskResponse[T any] struct {
+	Code         int    `json:"code"`
+	Message      string `json:"message"`
+	Data         T      `json:"data"`
+	ErrorMessage string `json:"error_message,omitempty"`
+}
+
+type GoAPITaskResponseData struct {
+	TaskID string `json:"task_id"`
+}
+
+type GoAPIFetchResponseData struct {
+	TaskID string              `json:"task_id"`
+	Status string              `json:"status"`
+	Input  string              `json:"input"`
+	Clips  map[string]SunoSong `json:"clips"`
+}

dto/task.go

@@ -0,0 +1,10 @@
+package dto
+
+type TaskError struct {
+	Code       string `json:"code"`
+	Message    string `json:"message"`
+	Data       any    `json:"data"`
+	StatusCode int    `json:"-"`
+	LocalError bool   `json:"-"`
+	Error      error  `json:"-"`
+}

dto/text_request.go

@@ -32,6 +32,21 @@ type GeneralOpenAIRequest struct {
 	TopLogProbs      int             `json:"top_logprobs,omitempty"`
 }
 
+type OpenAITools struct {
+	Type     string         `json:"type"`
+	Function OpenAIFunction `json:"function"`
+}
+
+type OpenAIFunction struct {
+	Description string `json:"description,omitempty"`
+	Name        string `json:"name"`
+	Parameters  any    `json:"parameters,omitempty"`
+}
+
+func (r GeneralOpenAIRequest) GetMaxTokens() int64 {
+	return int64(r.MaxTokens)
+}
+
 func (r GeneralOpenAIRequest) ParseInput() []string {
 	if r.Input == nil {
 		return nil

dto/text_response.go

@@ -54,21 +54,54 @@ type OpenAIEmbeddingResponse struct {
 }
 
 type ChatCompletionsStreamResponseChoice struct {
-	Delta struct {
-		Content   string `json:"content"`
-		Role      string `json:"role,omitempty"`
-		ToolCalls any    `json:"tool_calls,omitempty"`
-	} `json:"delta"`
-	FinishReason *string `json:"finish_reason,omitempty"`
-	Index        int     `json:"index,omitempty"`
+	Delta        ChatCompletionsStreamResponseChoiceDelta `json:"delta,omitempty"`
+	Logprobs     *any                                     `json:"logprobs"`
+	FinishReason *string                                  `json:"finish_reason"`
+	Index        int                                      `json:"index"`
+}
+
+type ChatCompletionsStreamResponseChoiceDelta struct {
+	Content   *string    `json:"content,omitempty"`
+	Role      string     `json:"role,omitempty"`
+	ToolCalls []ToolCall `json:"tool_calls,omitempty"`
+}
+
+func (c *ChatCompletionsStreamResponseChoiceDelta) IsEmpty() bool {
+	return c.Content == nil && len(c.ToolCalls) == 0
+}
+
+func (c *ChatCompletionsStreamResponseChoiceDelta) SetContentString(s string) {
+	c.Content = &s
+}
+
+func (c *ChatCompletionsStreamResponseChoiceDelta) GetContentString() string {
+	if c.Content == nil {
+		return ""
+	}
+	return *c.Content
+}
+
+type ToolCall struct {
+	// Index is not nil only in chat completion chunk object
+	Index    *int         `json:"index,omitempty"`
+	ID       string       `json:"id"`
+	Type     any          `json:"type"`
+	Function FunctionCall `json:"function"`
+}
+
+type FunctionCall struct {
+	Name string `json:"name,omitempty"`
+	// call function with arguments in JSON format
+	Arguments string `json:"arguments,omitempty"`
 }
 
 type ChatCompletionsStreamResponse struct {
-	Id      string                                `json:"id"`
-	Object  string                                `json:"object"`
-	Created int64                                 `json:"created"`
-	Model   string                                `json:"model"`
-	Choices []ChatCompletionsStreamResponseChoice `json:"choices"`
+	Id                string                                `json:"id"`
+	Object            string                                `json:"object"`
+	Created           int64                                 `json:"created"`
+	Model             string                                `json:"model"`
+	SystemFingerprint *string                               `json:"system_fingerprint"`
+	Choices           []ChatCompletionsStreamResponseChoice `json:"choices"`
 }
 
 type ChatCompletionsStreamResponseSimple struct {

go.mod

@@ -4,7 +4,11 @@ module one-api
 go 1.18
 
 require (
+	github.com/Calcium-Ion/go-epay v0.0.2
 	github.com/anknown/ahocorasick v0.0.0-20190904063843-d75dbd5169c0
+	github.com/aws/aws-sdk-go-v2 v1.26.1
+	github.com/aws/aws-sdk-go-v2/credentials v1.17.11
+	github.com/aws/aws-sdk-go-v2/service/bedrockruntime v1.7.4
 	github.com/gin-contrib/cors v1.4.0
 	github.com/gin-contrib/gzip v0.0.6
 	github.com/gin-contrib/sessions v0.0.5
@@ -13,12 +17,13 @@ require (
 	github.com/go-playground/validator/v10 v10.19.0
 	github.com/go-redis/redis/v8 v8.11.5
 	github.com/golang-jwt/jwt v3.2.2+incompatible
-	github.com/google/uuid v1.3.0
+	github.com/google/uuid v1.6.0
 	github.com/gorilla/websocket v1.5.0
-	github.com/pkoukk/tiktoken-go v0.1.6
-	github.com/samber/lo v1.38.1
+	github.com/jinzhu/copier v0.4.0
+	github.com/pkg/errors v0.9.1
+	github.com/pkoukk/tiktoken-go v0.1.7
+	github.com/samber/lo v1.39.0
 	github.com/shirou/gopsutil v3.21.11+incompatible
-	github.com/star-horizon/go-epay v0.0.0-20230204124159-fa2e2293fdc2
 	golang.org/x/crypto v0.21.0
 	golang.org/x/image v0.15.0
 	gorm.io/driver/mysql v1.4.3
@@ -29,11 +34,15 @@ require (
 
 require (
 	github.com/anknown/darts v0.0.0-20151216065714-83ff685239e6 // indirect
+	github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.6.2 // indirect
+	github.com/aws/aws-sdk-go-v2/internal/configsources v1.3.5 // indirect
+	github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.6.5 // indirect
+	github.com/aws/smithy-go v1.20.2 // indirect
 	github.com/bytedance/sonic v1.9.1 // indirect
 	github.com/cespare/xxhash/v2 v2.1.2 // indirect
 	github.com/chenzhuoyu/base64x v0.0.0-20221115062448-fe3a3abad311 // indirect
 	github.com/dgryski/go-rendezvous v0.0.0-20200823014737-9f7001d12a5f // indirect
-	github.com/dlclark/regexp2 v1.10.0 // indirect
+	github.com/dlclark/regexp2 v1.11.0 // indirect
 	github.com/gabriel-vasile/mimetype v1.4.3 // indirect
 	github.com/gin-contrib/sse v0.1.0 // indirect
 	github.com/go-ole/go-ole v1.2.6 // indirect
@@ -65,9 +74,9 @@ require (
 	github.com/ugorji/go/codec v1.2.11 // indirect
 	github.com/yusufpapurcu/wmi v1.2.3 // indirect
 	golang.org/x/arch v0.3.0 // indirect
-	golang.org/x/exp v0.0.0-20220303212507-bbda1eaf7a17 // indirect
+	golang.org/x/exp v0.0.0-20240404231335-c0f41cb1a7a0 // indirect
 	golang.org/x/net v0.21.0 // indirect
-	golang.org/x/sync v0.1.0 // indirect
+	golang.org/x/sync v0.7.0 // indirect
 	golang.org/x/sys v0.18.0 // indirect
 	golang.org/x/text v0.14.0 // indirect
 	google.golang.org/protobuf v1.30.0 // indirect

go.sum

@@ -1,7 +1,23 @@
+github.com/Calcium-Ion/go-epay v0.0.2 h1:3knFBuaBFpHzsGeGQU/QxUqZSHh5s0+jGo0P62pJzWc=
+github.com/Calcium-Ion/go-epay v0.0.2/go.mod h1:cxo/ZOg8ClvE3VAnCmEzbuyAZINSq7kFEN9oHj5WQ2U=
 github.com/anknown/ahocorasick v0.0.0-20190904063843-d75dbd5169c0 h1:onfun1RA+KcxaMk1lfrRnwCd1UUuOjJM/lri5eM1qMs=
 github.com/anknown/ahocorasick v0.0.0-20190904063843-d75dbd5169c0/go.mod h1:4yg+jNTYlDEzBjhGS96v+zjyA3lfXlFd5CiTLIkPBLI=
 github.com/anknown/darts v0.0.0-20151216065714-83ff685239e6 h1:HblK3eJHq54yET63qPCTJnks3loDse5xRmmqHgHzwoI=
 github.com/anknown/darts v0.0.0-20151216065714-83ff685239e6/go.mod h1:pbiaLIeYLUbgMY1kwEAdwO6UKD5ZNwdPGQlwokS9fe8=
+github.com/aws/aws-sdk-go-v2 v1.26.1 h1:5554eUqIYVWpU0YmeeYZ0wU64H2VLBs8TlhRB2L+EkA=
+github.com/aws/aws-sdk-go-v2 v1.26.1/go.mod h1:ffIFB97e2yNsv4aTSGkqtHnppsIJzw7G7BReUZ3jCXM=
+github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.6.2 h1:x6xsQXGSmW6frevwDA+vi/wqhp1ct18mVXYN08/93to=
+github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.6.2/go.mod h1:lPprDr1e6cJdyYeGXnRaJoP4Md+cDBvi2eOj00BlGmg=
+github.com/aws/aws-sdk-go-v2/credentials v1.17.11 h1:YuIB1dJNf1Re822rriUOTxopaHHvIq0l/pX3fwO+Tzs=
+github.com/aws/aws-sdk-go-v2/credentials v1.17.11/go.mod h1:AQtFPsDH9bI2O+71anW6EKL+NcD7LG3dpKGMV4SShgo=
+github.com/aws/aws-sdk-go-v2/internal/configsources v1.3.5 h1:aw39xVGeRWlWx9EzGVnhOR4yOjQDHPQ6o6NmBlscyQg=
+github.com/aws/aws-sdk-go-v2/internal/configsources v1.3.5/go.mod h1:FSaRudD0dXiMPK2UjknVwwTYyZMRsHv3TtkabsZih5I=
+github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.6.5 h1:PG1F3OD1szkuQPzDw3CIQsRIrtTlUC3lP84taWzHlq0=
+github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.6.5/go.mod h1:jU1li6RFryMz+so64PpKtudI+QzbKoIEivqdf6LNpOc=
+github.com/aws/aws-sdk-go-v2/service/bedrockruntime v1.7.4 h1:JgHnonzbnA3pbqj76wYsSZIZZQYBxkmMEjvL6GHy8XU=
+github.com/aws/aws-sdk-go-v2/service/bedrockruntime v1.7.4/go.mod h1:nZspkhg+9p8iApLFoyAqfyuMP0F38acy2Hm3r5r95Cg=
+github.com/aws/smithy-go v1.20.2 h1:tbp628ireGtzcHDDmLT/6ADHidqnwgF57XOXZe6tp4Q=
+github.com/aws/smithy-go v1.20.2/go.mod h1:krry+ya/rV9RDcV/Q16kpu6ypI4K2czasz0NC3qS14E=
 github.com/bytedance/sonic v1.5.0/go.mod h1:ED5hyg4y6t3/9Ku1R6dU/4KyJ48DZ4jPhfY1O2AihPM=
 github.com/bytedance/sonic v1.9.1 h1:6iJ6NqdoxCDr6mbY8h18oSO+cShGSMRGCEo7F2h0x8s=
 github.com/bytedance/sonic v1.9.1/go.mod h1:i736AoUSYt75HyZLoJW9ERYxcy6eaN6h4BZXU064P/U=
@@ -16,8 +32,8 @@ github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c
 github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/dgryski/go-rendezvous v0.0.0-20200823014737-9f7001d12a5f h1:lO4WD4F/rVNCu3HqELle0jiPLLBs70cWOduZpkS1E78=
 github.com/dgryski/go-rendezvous v0.0.0-20200823014737-9f7001d12a5f/go.mod h1:cuUVRXasLTGF7a8hSLbxyZXjz+1KgoB3wDUb6vlszIc=
-github.com/dlclark/regexp2 v1.10.0 h1:+/GIL799phkJqYW+3YbOd8LCcbHzT0Pbo8zl70MHsq0=
-github.com/dlclark/regexp2 v1.10.0/go.mod h1:DHkYz0B9wPfa6wondMfaivmHpzrQ3v9q8cnmRbL6yW8=
+github.com/dlclark/regexp2 v1.11.0 h1:G/nrcoOa7ZXlpoa/91N3X7mM3r8eIlMBBJZvsz/mxKI=
+github.com/dlclark/regexp2 v1.11.0/go.mod h1:DHkYz0B9wPfa6wondMfaivmHpzrQ3v9q8cnmRbL6yW8=
 github.com/fsnotify/fsnotify v1.4.9 h1:hsms1Qyu0jgnwNXIxa+/V/PDsU6CfLf6CNO8H7IWoS4=
 github.com/gabriel-vasile/mimetype v1.4.3 h1:in2uUcidCuFcDKtdcBxlR0rJ1+fsokWf+uqxgUFjbI0=
 github.com/gabriel-vasile/mimetype v1.4.3/go.mod h1:d8uq/6HKRL6CGdk+aubisF/M5GcPfT7nKyLpA0lbSSk=
@@ -62,11 +78,11 @@ github.com/golang-jwt/jwt v3.2.2+incompatible h1:IfV12K8xAKAnZqdXVzCZ+TOjboZ2keL
 github.com/golang-jwt/jwt v3.2.2+incompatible/go.mod h1:8pz2t5EyA70fFQQSrl6XZXzqecmYZeUEB8OUGHkxJ+I=
 github.com/golang/protobuf v1.3.3/go.mod h1:vzj43D7+SQXF/4pzW/hwtAqwc6iTitCiVSaWz5lYuqw=
 github.com/golang/protobuf v1.5.0/go.mod h1:FsONVRAS9T7sI+LIUmWTfcYkHO4aIWwzhcaSAoJOfIk=
-github.com/google/go-cmp v0.5.5 h1:Khx7svrCpmxxtHBq5j2mp/xVjsi8hQMfNLvJFAlrGgU=
 github.com/google/go-cmp v0.5.5/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
+github.com/google/go-cmp v0.5.8 h1:e6P7q2lk1O+qJJb4BtCQXlK8vWEO8V1ZeuEdJNOqZyg=
 github.com/google/gofuzz v1.0.0/go.mod h1:dBl0BpW6vV/+mYPU4Po3pmUjxk6FQPldtuIdl/M65Eg=
-github.com/google/uuid v1.3.0 h1:t6JiXgmwXMjEs8VusXIJk2BXHsn+wx8BZdTaoZ5fu7I=
-github.com/google/uuid v1.3.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
+github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0=
+github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
 github.com/gorilla/context v1.1.1 h1:AWwleXJkX/nhcU9bZSnZoi3h/qGYqQAGhq6zZe/aQW8=
 github.com/gorilla/context v1.1.1/go.mod h1:kBGZzfjB9CEq2AlWe17Uuf7NDRt0dE0s8S51q0aT7Yg=
 github.com/gorilla/securecookie v1.1.1 h1:miw7JPhV+b/lAHSXz4qd/nN9jRiAFV5FwjeKyCS8BvQ=
@@ -83,6 +99,8 @@ github.com/jackc/pgx/v5 v5.5.1 h1:5I9etrGkLrN+2XPCsi6XLlV5DITbSL/xBZdmAxFcXPI=
 github.com/jackc/pgx/v5 v5.5.1/go.mod h1:Ig06C2Vu0t5qXC60W8sqIthScaEnFvojjj9dSljmHRA=
 github.com/jackc/puddle/v2 v2.2.1 h1:RhxXJtFG022u4ibrCSMSiu5aOq1i77R3OHKNJj77OAk=
 github.com/jackc/puddle/v2 v2.2.1/go.mod h1:vriiEXHvEE654aYKXXjOvZM39qJ0q+azkZFrfEOc3H4=
+github.com/jinzhu/copier v0.4.0 h1:w3ciUoD19shMCRargcpm0cm91ytaBhDvuRpz1ODO/U8=
+github.com/jinzhu/copier v0.4.0/go.mod h1:DfbEm0FYsaqBcKcFuvmOZb218JkPGtvSHsKg8S8hyyg=
 github.com/jinzhu/inflection v1.0.0 h1:K317FqzuhWc8YvSVlFMCCUb36O/S9MCKRDI7QkRKD/E=
 github.com/jinzhu/inflection v1.0.0/go.mod h1:h+uFLlag+Qp1Va5pdKtLDYj+kHp5pxUVkryuEj+Srlc=
 github.com/jinzhu/now v1.1.4/go.mod h1:d3SSVoowX0Lcu0IBviAWJpolVfI5UJVZZ7cO71lE/z8=
@@ -128,19 +146,19 @@ github.com/pelletier/go-toml/v2 v2.0.1/go.mod h1:r9LEWfGN8R5k0VXJ+0BkIe7MYkRdwZO
 github.com/pelletier/go-toml/v2 v2.0.8 h1:0ctb6s9mE31h0/lhu+J6OPmVeDxJn+kYnJc2jZR9tGQ=
 github.com/pelletier/go-toml/v2 v2.0.8/go.mod h1:vuYfssBdrU2XDZ9bYydBu6t+6a6PYNcZljzZR9VXg+4=
 github.com/pkg/diff v0.0.0-20210226163009-20ebb0f2a09e/go.mod h1:pJLUxLENpZxwdsKMEsNbx1VGcRFpLqf3715MtcvvzbA=
-github.com/pkoukk/tiktoken-go v0.1.6 h1:JF0TlJzhTbrI30wCvFuiw6FzP2+/bR+FIxUdgEAcUsw=
-github.com/pkoukk/tiktoken-go v0.1.6/go.mod h1:9NiV+i9mJKGj1rYOT+njbv+ZwA/zJxYdewGl6qVatpg=
+github.com/pkg/errors v0.9.1 h1:FEBLx1zS214owpjy7qsBeixbURkuhQAwrK5UwLGTwt4=
+github.com/pkg/errors v0.9.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
+github.com/pkoukk/tiktoken-go v0.1.7 h1:qOBHXX4PHtvIvmOtyg1EeKlwFRiMKAcoMp4Q+bLQDmw=
+github.com/pkoukk/tiktoken-go v0.1.7/go.mod h1:9NiV+i9mJKGj1rYOT+njbv+ZwA/zJxYdewGl6qVatpg=
 github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
 github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
 github.com/rogpeppe/go-internal v1.6.1/go.mod h1:xXDCJY+GAPziupqXw64V24skbSoqbTEfhy4qGm1nDQc=
 github.com/rogpeppe/go-internal v1.8.0 h1:FCbCCtXNOY3UtUuHUYaghJg4y7Fd14rXifAYUAtL9R8=
 github.com/rogpeppe/go-internal v1.8.0/go.mod h1:WmiCO8CzOY8rg0OYDC4/i/2WRWAB6poM+XZ2dLUbcbE=
-github.com/samber/lo v1.38.1 h1:j2XEAqXKb09Am4ebOg31SpvzUTTs6EN3VfgeLUhPdXM=
-github.com/samber/lo v1.38.1/go.mod h1:+m/ZKRl6ClXCE2Lgf3MsQlWfh4bn1bz6CXEOxnEXnEA=
+github.com/samber/lo v1.39.0 h1:4gTz1wUhNYLhFSKl6O+8peW0v2F4BCY034GRpU9WnuA=
+github.com/samber/lo v1.39.0/go.mod h1:+m/ZKRl6ClXCE2Lgf3MsQlWfh4bn1bz6CXEOxnEXnEA=
 github.com/shirou/gopsutil v3.21.11+incompatible h1:+1+c1VGhc88SSonWP6foOcLhvnKlUeu/erjjvaPEYiI=
 github.com/shirou/gopsutil v3.21.11+incompatible/go.mod h1:5b4v6he4MtMOwMlS0TUMTu2PcXUg8+E1lC7eC3UO/RA=
-github.com/star-horizon/go-epay v0.0.0-20230204124159-fa2e2293fdc2 h1:avbt5a8F/zbYwFzTugrqWOBJe/K1cJj6+xpr+x1oVAI=
-github.com/star-horizon/go-epay v0.0.0-20230204124159-fa2e2293fdc2/go.mod h1:SiffGCWGGMVwujne2dUQbJ5zUVD1V1Yj0hDuTfqFNEo=
 github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
 github.com/stretchr/objx v0.4.0/go.mod h1:YvHI0jy2hoMjB+UWwv71VJQ9isScKT/TqJzVSSt89Yw=
 github.com/stretchr/objx v0.5.0/go.mod h1:Yh+to48EsGEfYuaHDzXPcE3xhTkx73EhmCGUpEOglKo=
@@ -173,15 +191,15 @@ golang.org/x/arch v0.3.0/go.mod h1:5om86z9Hs0C8fWVUuoMHwpExlXzs5Tkyp9hOrfG7pp8=
 golang.org/x/crypto v0.0.0-20210711020723-a769d52b0f97/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
 golang.org/x/crypto v0.21.0 h1:X31++rzVUdKhX5sWmSOFZxx8UW/ldWx55cbf08iNAMA=
 golang.org/x/crypto v0.21.0/go.mod h1:0BP7YvVV9gBbVKyeTG0Gyn+gZm94bibOW5BjDEYAOMs=
-golang.org/x/exp v0.0.0-20220303212507-bbda1eaf7a17 h1:3MTrJm4PyNL9NBqvYDSj3DHl46qQakyfqfWo4jgfaEM=
-golang.org/x/exp v0.0.0-20220303212507-bbda1eaf7a17/go.mod h1:lgLbSvA5ygNOMpwM/9anMpWVlVJ7Z+cHWq/eFuinpGE=
+golang.org/x/exp v0.0.0-20240404231335-c0f41cb1a7a0 h1:985EYyeCOxTpcgOTJpflJUwOeEz0CQOdPt73OzpE9F8=
+golang.org/x/exp v0.0.0-20240404231335-c0f41cb1a7a0/go.mod h1:/lliqkxwWAhPjf5oSOIJup2XcqJaw8RGS6k3TGEc7GI=
 golang.org/x/image v0.15.0 h1:kOELfmgrmJlw4Cdb7g/QGuB3CvDrXbqEIww/pNtNBm8=
 golang.org/x/image v0.15.0/go.mod h1:HUYqC05R2ZcZ3ejNQsIHQDQiwWM4JBqmm6MKANTp4LE=
 golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg=
 golang.org/x/net v0.21.0 h1:AQyQV4dYCvJ7vGmJyKki9+PBdyvhkSd8EIx/qb0AYv4=
 golang.org/x/net v0.21.0/go.mod h1:bIjVDfnllIU7BJ2DNgfnXvpSvtn8VRwhlsaeUTyUS44=
-golang.org/x/sync v0.1.0 h1:wsuoTGHzEhffawBOhz5CYhcrV4IdKZbEyZjBMuTp12o=
-golang.org/x/sync v0.1.0/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
+golang.org/x/sync v0.7.0 h1:YsImfSBoP9QPYL0xyKJPq0gcaJdG3rInoqxTWbfQu9M=
+golang.org/x/sync v0.7.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk=
 golang.org/x/sys v0.0.0-20190916202348-b4ddaad3f8a3/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20200116001909-b77594299b42/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
@@ -202,7 +220,6 @@ golang.org/x/text v0.14.0 h1:ScX5w1eTa3QqT8oi6+ziP7dTV1S2+ALU0bI+0zXKWiQ=
 golang.org/x/text v0.14.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=
 golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
 golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
-golang.org/x/xerrors v0.0.0-20200804184101-5ec99f83aff1 h1:go1bK/D/BFZV2I8cIQd1NKEZ+0owSTG1fDTci4IqFcE=
 google.golang.org/protobuf v1.26.0-rc.1/go.mod h1:jlhhOSvTdKEhbULTjvd4ARK9grFBp09yW+WbY/TyQbw=
 google.golang.org/protobuf v1.28.0/go.mod h1:HV8QOd/L58Z+nl8r43ehVNZIU/HEI6OcFqwMG9pJV4I=
 google.golang.org/protobuf v1.30.0 h1:kPPoIgf3TsEvrm0PFe15JQ+570QVxYzEvvHqChK+cng=

main.go

@@ -89,9 +89,14 @@ func main() {
 		}
 		go controller.AutomaticallyTestChannels(frequency)
 	}
-	common.SafeGoroutine(func() {
-		controller.UpdateMidjourneyTaskBulk()
-	})
+	if common.IsMasterNode {
+		common.SafeGoroutine(func() {
+			controller.UpdateMidjourneyTaskBulk()
+		})
+		common.SafeGoroutine(func() {
+			controller.UpdateTaskBulk()
+		})
+	}
 	if os.Getenv("BATCH_UPDATE_ENABLED") == "true" {
 		common.BatchUpdateEnabled = true
 		common.SysLog("batch update enabled with interval " + strconv.Itoa(common.BatchUpdateInterval) + "s")

makefile

@@ -7,7 +7,7 @@ all: build-frontend start-backend
 
 build-frontend:
 	@echo "Building frontend..."
-	@cd $(FRONTEND_DIR) && npm install && DISABLE_ESLINT_PLUGIN='true' REACT_APP_VERSION=$(cat VERSION) npm run build npm run build
+	@cd $(FRONTEND_DIR) && npm install && DISABLE_ESLINT_PLUGIN='true' VITE_REACT_APP_VERSION=$(cat VERSION) npm run build
 
 start-backend:
 	@echo "Starting backend dev server..."

middleware/auth.go

@@ -64,6 +64,17 @@ func authHelper(c *gin.Context, minRole int) {
 	c.Next()
 }
 
+func TryUserAuth() func(c *gin.Context) {
+	return func(c *gin.Context) {
+		session := sessions.Default(c)
+		id := session.Get("id")
+		if id != nil {
+			c.Set("id", id)
+		}
+		c.Next()
+	}
+}
+
 func UserAuth() func(c *gin.Context) {
 	return func(c *gin.Context) {
 		authHelper(c, common.RoleCommonUser)

middleware/distributor.go

@@ -24,6 +24,9 @@ func Distribute() func(c *gin.Context) {
 		userId := c.GetInt("id")
 		var channel *model.Channel
 		channelId, ok := c.Get("specific_channel_id")
+		modelRequest, shouldSelectChannel, err := getModelRequest(c)
+		userGroup, _ := model.CacheGetUserGroup(userId)
+		c.Set("group", userGroup)
 		if ok {
 			id, err := strconv.Atoi(channelId.(string))
 			if err != nil {
@@ -40,72 +43,7 @@ func Distribute() func(c *gin.Context) {
 				return
 			}
 		} else {
-			shouldSelectChannel := true
 			// Select a channel for the user
-			var modelRequest ModelRequest
-			var err error
-			if strings.Contains(c.Request.URL.Path, "/mj/") {
-				relayMode := relayconstant.Path2RelayModeMidjourney(c.Request.URL.Path)
-				if relayMode == relayconstant.RelayModeMidjourneyTaskFetch ||
-					relayMode == relayconstant.RelayModeMidjourneyTaskFetchByCondition ||
-					relayMode == relayconstant.RelayModeMidjourneyNotify ||
-					relayMode == relayconstant.RelayModeMidjourneyTaskImageSeed {
-					shouldSelectChannel = false
-				} else {
-					midjourneyRequest := dto.MidjourneyRequest{}
-					err = common.UnmarshalBodyReusable(c, &midjourneyRequest)
-					if err != nil {
-						abortWithMidjourneyMessage(c, http.StatusBadRequest, constant.MjErrorUnknown, "无效的请求, "+err.Error())
-						return
-					}
-					midjourneyModel, mjErr, success := service.GetMjRequestModel(relayMode, &midjourneyRequest)
-					if mjErr != nil {
-						abortWithMidjourneyMessage(c, http.StatusBadRequest, mjErr.Code, mjErr.Description)
-						return
-					}
-					if midjourneyModel == "" {
-						if !success {
-							abortWithMidjourneyMessage(c, http.StatusBadRequest, constant.MjErrorUnknown, "无效的请求, 无法解析模型")
-							return
-						} else {
-							// task fetch, task fetch by condition, notify
-							shouldSelectChannel = false
-						}
-					}
-					modelRequest.Model = midjourneyModel
-				}
-				c.Set("relay_mode", relayMode)
-			} else if !strings.HasPrefix(c.Request.URL.Path, "/v1/audio/transcriptions") {
-				err = common.UnmarshalBodyReusable(c, &modelRequest)
-			}
-			if err != nil {
-				abortWithOpenAiMessage(c, http.StatusBadRequest, "无效的请求, "+err.Error())
-				return
-			}
-			if strings.HasPrefix(c.Request.URL.Path, "/v1/moderations") {
-				if modelRequest.Model == "" {
-					modelRequest.Model = "text-moderation-stable"
-				}
-			}
-			if strings.HasSuffix(c.Request.URL.Path, "embeddings") {
-				if modelRequest.Model == "" {
-					modelRequest.Model = c.Param("model")
-				}
-			}
-			if strings.HasPrefix(c.Request.URL.Path, "/v1/images/generations") {
-				if modelRequest.Model == "" {
-					modelRequest.Model = "dall-e"
-				}
-			}
-			if strings.HasPrefix(c.Request.URL.Path, "/v1/audio") {
-				if modelRequest.Model == "" {
-					if strings.HasPrefix(c.Request.URL.Path, "/v1/audio/speech") {
-						modelRequest.Model = "tts-1"
-					} else {
-						modelRequest.Model = "whisper-1"
-					}
-				}
-			}
 			// check token model mapping
 			modelLimitEnable := c.GetBool("token_model_limit_enabled")
 			if modelLimitEnable {
@@ -128,8 +66,6 @@ func Distribute() func(c *gin.Context) {
 				}
 			}
 
-			userGroup, _ := model.CacheGetUserGroup(userId)
-			c.Set("group", userGroup)
 			if shouldSelectChannel {
 				channel, err = model.CacheGetRandomSatisfiedChannel(userGroup, modelRequest.Model, 0)
 				if err != nil {
@@ -147,17 +83,102 @@ func Distribute() func(c *gin.Context) {
 					abortWithOpenAiMessage(c, http.StatusServiceUnavailable, fmt.Sprintf("当前分组 %s 下对于模型 %s 无可用渠道（数据库一致性已被破坏）", userGroup, modelRequest.Model))
 					return
 				}
-				SetupContextForSelectedChannel(c, channel, modelRequest.Model)
 			}
 		}
+		SetupContextForSelectedChannel(c, channel, modelRequest.Model)
 		c.Next()
 	}
 }
 
+func getModelRequest(c *gin.Context) (*ModelRequest, bool, error) {
+	var modelRequest ModelRequest
+	shouldSelectChannel := true
+	var err error
+	if strings.Contains(c.Request.URL.Path, "/mj/") {
+		relayMode := relayconstant.Path2RelayModeMidjourney(c.Request.URL.Path)
+		if relayMode == relayconstant.RelayModeMidjourneyTaskFetch ||
+			relayMode == relayconstant.RelayModeMidjourneyTaskFetchByCondition ||
+			relayMode == relayconstant.RelayModeMidjourneyNotify ||
+			relayMode == relayconstant.RelayModeMidjourneyTaskImageSeed {
+			shouldSelectChannel = false
+		} else {
+			midjourneyRequest := dto.MidjourneyRequest{}
+			err = common.UnmarshalBodyReusable(c, &midjourneyRequest)
+			if err != nil {
+				abortWithMidjourneyMessage(c, http.StatusBadRequest, constant.MjErrorUnknown, "无效的请求, "+err.Error())
+				return nil, false, err
+			}
+			midjourneyModel, mjErr, success := service.GetMjRequestModel(relayMode, &midjourneyRequest)
+			if mjErr != nil {
+				abortWithMidjourneyMessage(c, http.StatusBadRequest, mjErr.Code, mjErr.Description)
+				return nil, false, fmt.Errorf(mjErr.Description)
+			}
+			if midjourneyModel == "" {
+				if !success {
+					abortWithMidjourneyMessage(c, http.StatusBadRequest, constant.MjErrorUnknown, "无效的请求, 无法解析模型")
+					return nil, false, fmt.Errorf("无效的请求, 无法解析模型")
+				} else {
+					// task fetch, task fetch by condition, notify
+					shouldSelectChannel = false
+				}
+			}
+			modelRequest.Model = midjourneyModel
+		}
+		c.Set("relay_mode", relayMode)
+	} else if strings.Contains(c.Request.URL.Path, "/suno/") {
+		relayMode := relayconstant.Path2RelaySuno(c.Request.Method, c.Request.URL.Path)
+		if relayMode == relayconstant.RelayModeSunoFetch ||
+			relayMode == relayconstant.RelayModeSunoFetchByID {
+			shouldSelectChannel = false
+		} else {
+			modelName := service.CoverTaskActionToModelName(constant.TaskPlatformSuno, c.Param("action"))
+			modelRequest.Model = modelName
+		}
+		c.Set("platform", string(constant.TaskPlatformSuno))
+		c.Set("relay_mode", relayMode)
+	} else if !strings.HasPrefix(c.Request.URL.Path, "/v1/audio/transcriptions") {
+		err = common.UnmarshalBodyReusable(c, &modelRequest)
+	}
+	if err != nil {
+		abortWithOpenAiMessage(c, http.StatusBadRequest, "无效的请求, "+err.Error())
+		return nil, false, err
+	}
+	if strings.HasPrefix(c.Request.URL.Path, "/v1/moderations") {
+		if modelRequest.Model == "" {
+			modelRequest.Model = "text-moderation-stable"
+		}
+	}
+	if strings.HasSuffix(c.Request.URL.Path, "embeddings") {
+		if modelRequest.Model == "" {
+			modelRequest.Model = c.Param("model")
+		}
+	}
+	if strings.HasPrefix(c.Request.URL.Path, "/v1/images/generations") {
+		if modelRequest.Model == "" {
+			modelRequest.Model = "dall-e"
+		}
+	}
+	if strings.HasPrefix(c.Request.URL.Path, "/v1/audio") {
+		if modelRequest.Model == "" {
+			if strings.HasPrefix(c.Request.URL.Path, "/v1/audio/speech") {
+				modelRequest.Model = "tts-1"
+			} else {
+				modelRequest.Model = "whisper-1"
+			}
+		}
+	}
+	return &modelRequest, shouldSelectChannel, nil
+}
+
 func SetupContextForSelectedChannel(c *gin.Context, channel *model.Channel, modelName string) {
+	c.Set("original_model", modelName) // for retry
+	if channel == nil {
+		return
+	}
 	c.Set("channel", channel.Type)
 	c.Set("channel_id", channel.Id)
 	c.Set("channel_name", channel.Name)
+	c.Set("channel_type", channel.Type)
 	ban := true
 	// parse *int to bool
 	if channel.AutoBan != nil && *channel.AutoBan == 0 {
@@ -168,7 +189,7 @@ func SetupContextForSelectedChannel(c *gin.Context, channel *model.Channel, mode
 	}
 	c.Set("auto_ban", ban)
 	c.Set("model_mapping", channel.GetModelMapping())
-	c.Set("original_model", modelName) // for retry
+	c.Set("status_code_mapping", channel.GetStatusCodeMapping())
 	c.Request.Header.Set("Authorization", fmt.Sprintf("Bearer %s", channel.Key))
 	c.Set("base_url", channel.GetBaseURL())
 	// TODO: api_version统一

model/ability.go

@@ -3,6 +3,8 @@ package model
 import (
 	"errors"
 	"fmt"
+	"github.com/samber/lo"
+	"gorm.io/gorm"
 	"one-api/common"
 	"strings"
 )
@@ -27,8 +29,14 @@ func GetGroupModels(group string) []string {
 	return models
 }
 
-func GetRandomSatisfiedChannel(group string, model string) (*Channel, error) {
-	var abilities []Ability
+func GetEnabledModels() []string {
+	var models []string
+	// Find distinct models
+	DB.Table("abilities").Where("enabled = ?", true).Distinct("model").Pluck("model", &models)
+	return models
+}
+
+func getPriority(group string, model string, retry int) (int, error) {
 	groupCol := "`group`"
 	trueVal := "1"
 	if common.UsingPostgreSQL {
@@ -36,9 +44,60 @@ func GetRandomSatisfiedChannel(group string, model string) (*Channel, error) {
 		trueVal = "true"
 	}
 
-	var err error = nil
+	var priorities []int
+	err := DB.Model(&Ability{}).
+		Select("DISTINCT(priority)").
+		Where(groupCol+" = ? and model = ? and enabled = "+trueVal, group, model).
+		Order("priority DESC").              // 按优先级降序排序
+		Pluck("priority", &priorities).Error // Pluck用于将查询的结果直接扫描到一个切片中
+
+	if err != nil {
+		// 处理错误
+		return 0, err
+	}
+
+	if len(priorities) == 0 {
+		// 如果没有查询到优先级，则返回错误
+		return 0, errors.New("数据库一致性被破坏")
+	}
+
+	// 确定要使用的优先级
+	var priorityToUse int
+	if retry >= len(priorities) {
+		// 如果重试次数大于优先级数，则使用最小的优先级
+		priorityToUse = priorities[len(priorities)-1]
+	} else {
+		priorityToUse = priorities[retry]
+	}
+	return priorityToUse, nil
+}
+
+func getChannelQuery(group string, model string, retry int) *gorm.DB {
+	groupCol := "`group`"
+	trueVal := "1"
+	if common.UsingPostgreSQL {
+		groupCol = `"group"`
+		trueVal = "true"
+	}
 	maxPrioritySubQuery := DB.Model(&Ability{}).Select("MAX(priority)").Where(groupCol+" = ? and model = ? and enabled = "+trueVal, group, model)
 	channelQuery := DB.Where(groupCol+" = ? and model = ? and enabled = "+trueVal+" and priority = (?)", group, model, maxPrioritySubQuery)
+	if retry != 0 {
+		priority, err := getPriority(group, model, retry)
+		if err != nil {
+			common.SysError(fmt.Sprintf("Get priority failed: %s", err.Error()))
+		} else {
+			channelQuery = DB.Where(groupCol+" = ? and model = ? and enabled = "+trueVal+" and priority = ?", group, model, priority)
+		}
+	}
+
+	return channelQuery
+}
+
+func GetRandomSatisfiedChannel(group string, model string, retry int) (*Channel, error) {
+	var abilities []Ability
+
+	var err error = nil
+	channelQuery := getChannelQuery(group, model, retry)
 	if common.UsingSQLite || common.UsingPostgreSQL {
 		err = channelQuery.Order("weight DESC").Find(&abilities).Error
 	} else {
@@ -88,7 +147,16 @@ func (channel *Channel) AddAbilities() error {
 			abilities = append(abilities, ability)
 		}
 	}
-	return DB.Create(&abilities).Error
+	if len(abilities) == 0 {
+		return nil
+	}
+	for _, chunk := range lo.Chunk(abilities, 50) {
+		err := DB.Create(&chunk).Error
+		if err != nil {
+			return err
+		}
+	}
+	return nil
 }
 
 func (channel *Channel) DeleteAbilities() error {
@@ -136,7 +204,7 @@ func FixAbility() (int, error) {
 
 	// Use channelIds to find channel not in abilities table
 	var abilityChannelIds []int
-	err = DB.Model(&Ability{}).Pluck("channel_id", &abilityChannelIds).Error
+	err = DB.Table("abilities").Distinct("channel_id").Pluck("channel_id", &abilityChannelIds).Error
 	if err != nil {
 		common.SysError(fmt.Sprintf("Get channel ids from abilities table failed: %s", err.Error()))
 		return 0, err

model/cache.go

@@ -25,9 +25,6 @@ var token2UserId = make(map[string]int)
 var token2UserIdLock sync.RWMutex
 
 func cacheSetToken(token *Token) error {
-	if !common.RedisEnabled {
-		return token.SelectUpdate()
-	}
 	jsonBytes, err := json.Marshal(token)
 	if err != nil {
 		return err
@@ -90,7 +87,7 @@ func SyncTokenCache(frequency int) {
 				}
 			} else {
 				// 如果数据库中存在，先检查redis
-				_, err := common.RedisGet(fmt.Sprintf("token:%s", key))
+				_, err = common.RedisGet(fmt.Sprintf("token:%s", key))
 				if err != nil {
 					// 如果redis中不存在，则跳过
 					continue
@@ -168,7 +165,11 @@ func CacheUpdateUserQuota(id int) error {
 	if err != nil {
 		return err
 	}
-	err = common.RedisSet(fmt.Sprintf("user_quota:%d", id), fmt.Sprintf("%d", quota), time.Duration(UserId2QuotaCacheSeconds)*time.Second)
+	return cacheSetUserQuota(id, quota)
+}
+
+func cacheSetUserQuota(id int, quota int) error {
+	err := common.RedisSet(fmt.Sprintf("user_quota:%d", id), fmt.Sprintf("%d", quota), time.Duration(UserId2QuotaCacheSeconds)*time.Second)
 	return err
 }
 
@@ -272,7 +273,7 @@ func CacheGetRandomSatisfiedChannel(group string, model string, retry int) (*Cha
 
 	// if memory cache is disabled, get channel directly from database
 	if !common.MemoryCacheEnabled {
-		return GetRandomSatisfiedChannel(group, model)
+		return GetRandomSatisfiedChannel(group, model, retry)
 	}
 	channelSyncLock.RLock()
 	defer channelSyncLock.RUnlock()

model/channel.go

@@ -1,6 +1,7 @@
 package model
 
 import (
+	"encoding/json"
 	"gorm.io/gorm"
 	"one-api/common"
 )
@@ -25,8 +26,35 @@ type Channel struct {
 	Group              string  `json:"group" gorm:"type:varchar(64);default:'default'"`
 	UsedQuota          int64   `json:"used_quota" gorm:"bigint;default:0"`
 	ModelMapping       *string `json:"model_mapping" gorm:"type:varchar(1024);default:''"`
-	Priority           *int64  `json:"priority" gorm:"bigint;default:0"`
-	AutoBan            *int    `json:"auto_ban" gorm:"default:1"`
+	//MaxInputTokens     *int    `json:"max_input_tokens" gorm:"default:0"`
+	StatusCodeMapping *string `json:"status_code_mapping" gorm:"type:varchar(1024);default:''"`
+	Priority          *int64  `json:"priority" gorm:"bigint;default:0"`
+	AutoBan           *int    `json:"auto_ban" gorm:"default:1"`
+	OtherInfo         string  `json:"other_info"`
+}
+
+func (channel *Channel) GetOtherInfo() map[string]interface{} {
+	otherInfo := make(map[string]interface{})
+	if channel.OtherInfo != "" {
+		err := json.Unmarshal([]byte(channel.OtherInfo), &otherInfo)
+		if err != nil {
+			common.SysError("failed to unmarshal other info: " + err.Error())
+		}
+	}
+	return otherInfo
+}
+
+func (channel *Channel) SetOtherInfo(otherInfo map[string]interface{}) {
+	otherInfoBytes, err := json.Marshal(otherInfo)
+	if err != nil {
+		common.SysError("failed to marshal other info: " + err.Error())
+		return
+	}
+	channel.OtherInfo = string(otherInfoBytes)
+}
+
+func (channel *Channel) Save() error {
+	return DB.Save(channel).Error
 }
 
 func GetAllChannels(startIdx int, num int, selectAll bool, idSort bool) ([]*Channel, error) {
@@ -153,6 +181,13 @@ func (channel *Channel) GetModelMapping() string {
 	return *channel.ModelMapping
 }
 
+func (channel *Channel) GetStatusCodeMapping() string {
+	if channel.StatusCodeMapping == nil {
+		return ""
+	}
+	return *channel.StatusCodeMapping
+}
+
 func (channel *Channel) Insert() error {
 	var err error
 	err = DB.Create(channel).Error
@@ -204,15 +239,31 @@ func (channel *Channel) Delete() error {
 	return err
 }
 
-func UpdateChannelStatusById(id int, status int) {
+func UpdateChannelStatusById(id int, status int, reason string) {
 	err := UpdateAbilityStatus(id, status == common.ChannelStatusEnabled)
 	if err != nil {
 		common.SysError("failed to update ability status: " + err.Error())
 	}
-	err = DB.Model(&Channel{}).Where("id = ?", id).Update("status", status).Error
+	channel, err := GetChannelById(id, true)
 	if err != nil {
-		common.SysError("failed to update channel status: " + err.Error())
+		// find channel by id error, directly update status
+		err = DB.Model(&Channel{}).Where("id = ?", id).Update("status", status).Error
+		if err != nil {
+			common.SysError("failed to update channel status: " + err.Error())
+		}
+	} else {
+		// find channel by id success, update status and other info
+		info := channel.GetOtherInfo()
+		info["status_reason"] = reason
+		info["status_time"] = common.GetTimestamp()
+		channel.SetOtherInfo(info)
+		channel.Status = status
+		err = channel.Save()
+		if err != nil {
+			common.SysError("failed to update channel status: " + err.Error())
+		}
 	}
+
 }
 
 func UpdateChannelUsedQuota(id int, quota int) {

model/log.go

@@ -24,6 +24,7 @@ type Log struct {
 	IsStream         bool   `json:"is_stream" gorm:"default:false"`
 	ChannelId        int    `json:"channel" gorm:"index"`
 	TokenId          int    `json:"token_id" gorm:"default:0;index"`
+	Other            string `json:"other"`
 }
 
 const (
@@ -35,7 +36,7 @@ const (
 )
 
 func GetLogByKey(key string) (logs []*Log, err error) {
-	err = DB.Joins("left join tokens on tokens.id = logs.token_id").Where("tokens.key = ?", strings.Split(key, "-")[1]).Find(&logs).Error
+	err = DB.Joins("left join tokens on tokens.id = logs.token_id").Where("tokens.key = ?", strings.TrimPrefix(key, "sk-")).Find(&logs).Error
 	return logs, err
 }
 
@@ -57,12 +58,13 @@ func RecordLog(userId int, logType int, content string) {
 	}
 }
 
-func RecordConsumeLog(ctx context.Context, userId int, channelId int, promptTokens int, completionTokens int, modelName string, tokenName string, quota int, content string, tokenId int, userQuota int, useTimeSeconds int, isStream bool) {
+func RecordConsumeLog(ctx context.Context, userId int, channelId int, promptTokens int, completionTokens int, modelName string, tokenName string, quota int, content string, tokenId int, userQuota int, useTimeSeconds int, isStream bool, other map[string]interface{}) {
 	common.LogInfo(ctx, fmt.Sprintf("record consume log: userId=%d, 用户调用前余额=%d, channelId=%d, promptTokens=%d, completionTokens=%d, modelName=%s, tokenName=%s, quota=%d, content=%s", userId, userQuota, channelId, promptTokens, completionTokens, modelName, tokenName, quota, content))
 	if !common.LogConsumeEnabled {
 		return
 	}
 	username, _ := CacheGetUsername(userId)
+	otherStr := common.MapToJsonStr(other)
 	log := &Log{
 		UserId:           userId,
 		Username:         username,
@@ -78,6 +80,7 @@ func RecordConsumeLog(ctx context.Context, userId int, channelId int, promptToke
 		TokenId:          tokenId,
 		UseTime:          useTimeSeconds,
 		IsStream:         isStream,
+		Other:            otherStr,
 	}
 	err := DB.Create(log).Error
 	if err != nil {
@@ -139,6 +142,15 @@ func GetUserLogs(userId int, logType int, startTimestamp int64, endTimestamp int
 		tx = tx.Where("created_at <= ?", endTimestamp)
 	}
 	err = tx.Order("id desc").Limit(num).Offset(startIdx).Omit("id").Find(&logs).Error
+	for i := range logs {
+		var otherMap map[string]interface{}
+		otherMap = common.StrToMap(logs[i].Other)
+		if otherMap != nil {
+			// delete admin
+			delete(otherMap, "admin_info")
+		}
+		logs[i].Other = common.MapToJsonStr(otherMap)
+	}
 	return logs, err
 }
 

model/main.go

@@ -86,19 +86,19 @@ func InitDB() (err error) {
 		if err != nil {
 			return err
 		}
-		sqlDB.SetMaxIdleConns(common.GetOrDefault("SQL_MAX_IDLE_CONNS", 100))
-		sqlDB.SetMaxOpenConns(common.GetOrDefault("SQL_MAX_OPEN_CONNS", 1000))
-		sqlDB.SetConnMaxLifetime(time.Second * time.Duration(common.GetOrDefault("SQL_MAX_LIFETIME", 60)))
+		sqlDB.SetMaxIdleConns(common.GetEnvOrDefault("SQL_MAX_IDLE_CONNS", 100))
+		sqlDB.SetMaxOpenConns(common.GetEnvOrDefault("SQL_MAX_OPEN_CONNS", 1000))
+		sqlDB.SetConnMaxLifetime(time.Second * time.Duration(common.GetEnvOrDefault("SQL_MAX_LIFETIME", 60)))
 
 		if !common.IsMasterNode {
 			return nil
 		}
-		if common.UsingMySQL {
-			_, _ = sqlDB.Exec("DROP INDEX idx_channels_key ON channels;")             // TODO: delete this line when most users have upgraded
-			_, _ = sqlDB.Exec("ALTER TABLE midjourneys MODIFY action VARCHAR(40);")   // TODO: delete this line when most users have upgraded
-			_, _ = sqlDB.Exec("ALTER TABLE midjourneys MODIFY progress VARCHAR(30);") // TODO: delete this line when most users have upgraded
-			_, _ = sqlDB.Exec("ALTER TABLE midjourneys MODIFY status VARCHAR(20);")   // TODO: delete this line when most users have upgraded
-		}
+		//if common.UsingMySQL {
+		//	_, _ = sqlDB.Exec("DROP INDEX idx_channels_key ON channels;")             // TODO: delete this line when most users have upgraded
+		//	_, _ = sqlDB.Exec("ALTER TABLE midjourneys MODIFY action VARCHAR(40);")   // TODO: delete this line when most users have upgraded
+		//	_, _ = sqlDB.Exec("ALTER TABLE midjourneys MODIFY progress VARCHAR(30);") // TODO: delete this line when most users have upgraded
+		//	_, _ = sqlDB.Exec("ALTER TABLE midjourneys MODIFY status VARCHAR(20);")   // TODO: delete this line when most users have upgraded
+		//}
 		common.SysLog("database migration started")
 		err = db.AutoMigrate(&Channel{})
 		if err != nil {
@@ -140,6 +140,10 @@ func InitDB() (err error) {
 		if err != nil {
 			return err
 		}
+		err = db.AutoMigrate(&Task{})
+		if err != nil {
+			return err
+		}
 		common.SysLog("database migrated")
 		err = createRootAccountIfNeed()
 		return err

model/option.go

@@ -41,9 +41,11 @@ func InitOptionMap() {
 	common.OptionMap["DisplayInCurrencyEnabled"] = strconv.FormatBool(common.DisplayInCurrencyEnabled)
 	common.OptionMap["DisplayTokenStatEnabled"] = strconv.FormatBool(common.DisplayTokenStatEnabled)
 	common.OptionMap["DrawingEnabled"] = strconv.FormatBool(common.DrawingEnabled)
+	common.OptionMap["TaskEnabled"] = strconv.FormatBool(common.TaskEnabled)
 	common.OptionMap["DataExportEnabled"] = strconv.FormatBool(common.DataExportEnabled)
 	common.OptionMap["ChannelDisableThreshold"] = strconv.FormatFloat(common.ChannelDisableThreshold, 'f', -1, 64)
 	common.OptionMap["EmailDomainRestrictionEnabled"] = strconv.FormatBool(common.EmailDomainRestrictionEnabled)
+	common.OptionMap["EmailAliasRestrictionEnabled"] = strconv.FormatBool(common.EmailAliasRestrictionEnabled)
 	common.OptionMap["EmailDomainWhitelist"] = strings.Join(common.EmailDomainWhitelist, ",")
 	common.OptionMap["SMTPServer"] = ""
 	common.OptionMap["SMTPFrom"] = ""
@@ -58,12 +60,14 @@ func InitOptionMap() {
 	common.OptionMap["SystemName"] = common.SystemName
 	common.OptionMap["Logo"] = common.Logo
 	common.OptionMap["ServerAddress"] = ""
+	common.OptionMap["WorkerUrl"] = constant.WorkerUrl
+	common.OptionMap["WorkerValidKey"] = constant.WorkerValidKey
 	common.OptionMap["PayAddress"] = ""
 	common.OptionMap["CustomCallbackAddress"] = ""
 	common.OptionMap["EpayId"] = ""
 	common.OptionMap["EpayKey"] = ""
-	common.OptionMap["Price"] = strconv.FormatFloat(common.Price, 'f', -1, 64)
-	common.OptionMap["MinTopUp"] = strconv.Itoa(common.MinTopUp)
+	common.OptionMap["Price"] = strconv.FormatFloat(constant.Price, 'f', -1, 64)
+	common.OptionMap["MinTopUp"] = strconv.Itoa(constant.MinTopUp)
 	common.OptionMap["TopupGroupRatio"] = common.TopupGroupRatio2JSONString()
 	common.OptionMap["GitHubClientId"] = ""
 	common.OptionMap["GitHubClientSecret"] = ""
@@ -82,6 +86,7 @@ func InitOptionMap() {
 	common.OptionMap["ModelRatio"] = common.ModelRatio2JSONString()
 	common.OptionMap["ModelPrice"] = common.ModelPrice2JSONString()
 	common.OptionMap["GroupRatio"] = common.GroupRatio2JSONString()
+	common.OptionMap["CompletionRatio"] = common.CompletionRatio2JSONString()
 	common.OptionMap["TopUpLink"] = common.TopUpLink
 	common.OptionMap["ChatLink"] = common.ChatLink
 	common.OptionMap["ChatLink2"] = common.ChatLink2
@@ -91,6 +96,9 @@ func InitOptionMap() {
 	common.OptionMap["DataExportDefaultTime"] = common.DataExportDefaultTime
 	common.OptionMap["DefaultCollapseSidebar"] = strconv.FormatBool(common.DefaultCollapseSidebar)
 	common.OptionMap["MjNotifyEnabled"] = strconv.FormatBool(constant.MjNotifyEnabled)
+	common.OptionMap["MjAccountFilterEnabled"] = strconv.FormatBool(constant.MjAccountFilterEnabled)
+	common.OptionMap["MjModeClearEnabled"] = strconv.FormatBool(constant.MjModeClearEnabled)
+	common.OptionMap["MjForwardUrlEnabled"] = strconv.FormatBool(constant.MjForwardUrlEnabled)
 	common.OptionMap["CheckSensitiveEnabled"] = strconv.FormatBool(constant.CheckSensitiveEnabled)
 	common.OptionMap["CheckSensitiveOnPromptEnabled"] = strconv.FormatBool(constant.CheckSensitiveOnPromptEnabled)
 	//common.OptionMap["CheckSensitiveOnCompletionEnabled"] = strconv.FormatBool(constant.CheckSensitiveOnCompletionEnabled)
@@ -174,6 +182,8 @@ func updateOptionMap(key string, value string) (err error) {
 			common.RegisterEnabled = boolValue
 		case "EmailDomainRestrictionEnabled":
 			common.EmailDomainRestrictionEnabled = boolValue
+		case "EmailAliasRestrictionEnabled":
+			common.EmailAliasRestrictionEnabled = boolValue
 		case "AutomaticDisableChannelEnabled":
 			common.AutomaticDisableChannelEnabled = boolValue
 		case "AutomaticEnableChannelEnabled":
@@ -186,12 +196,20 @@ func updateOptionMap(key string, value string) (err error) {
 			common.DisplayTokenStatEnabled = boolValue
 		case "DrawingEnabled":
 			common.DrawingEnabled = boolValue
+		case "TaskEnabled":
+			common.TaskEnabled = boolValue
 		case "DataExportEnabled":
 			common.DataExportEnabled = boolValue
 		case "DefaultCollapseSidebar":
 			common.DefaultCollapseSidebar = boolValue
 		case "MjNotifyEnabled":
 			constant.MjNotifyEnabled = boolValue
+		case "MjAccountFilterEnabled":
+			constant.MjAccountFilterEnabled = boolValue
+		case "MjModeClearEnabled":
+			constant.MjModeClearEnabled = boolValue
+		case "MjForwardUrlEnabled":
+			constant.MjForwardUrlEnabled = boolValue
 		case "CheckSensitiveEnabled":
 			constant.CheckSensitiveEnabled = boolValue
 		case "CheckSensitiveOnPromptEnabled":
@@ -219,19 +237,23 @@ func updateOptionMap(key string, value string) (err error) {
 	case "SMTPToken":
 		common.SMTPToken = value
 	case "ServerAddress":
-		common.ServerAddress = value
+		constant.ServerAddress = value
+	case "WorkerUrl":
+		constant.WorkerUrl = value
+	case "WorkerValidKey":
+		constant.WorkerValidKey = value
 	case "PayAddress":
-		common.PayAddress = value
+		constant.PayAddress = value
 	case "CustomCallbackAddress":
-		common.CustomCallbackAddress = value
+		constant.CustomCallbackAddress = value
 	case "EpayId":
-		common.EpayId = value
+		constant.EpayId = value
 	case "EpayKey":
-		common.EpayKey = value
+		constant.EpayKey = value
 	case "Price":
-		common.Price, _ = strconv.ParseFloat(value, 64)
+		constant.Price, _ = strconv.ParseFloat(value, 64)
 	case "MinTopUp":
-		common.MinTopUp, _ = strconv.Atoi(value)
+		constant.MinTopUp, _ = strconv.Atoi(value)
 	case "TopupGroupRatio":
 		err = common.UpdateTopupGroupRatioByJSONString(value)
 	case "GitHubClientId":
@@ -278,6 +300,8 @@ func updateOptionMap(key string, value string) (err error) {
 		err = common.UpdateModelRatioByJSONString(value)
 	case "GroupRatio":
 		err = common.UpdateGroupRatioByJSONString(value)
+	case "CompletionRatio":
+		err = common.UpdateCompletionRatioByJSONString(value)
 	case "ModelPrice":
 		err = common.UpdateModelPriceByJSONString(value)
 	case "TopUpLink":

model/pricing.go

@@ -0,0 +1,73 @@
+package model
+
+import (
+	"one-api/common"
+	"sync"
+	"time"
+)
+
+type Pricing struct {
+	Available       bool     `json:"available"`
+	ModelName       string   `json:"model_name"`
+	QuotaType       int      `json:"quota_type"`
+	ModelRatio      float64  `json:"model_ratio"`
+	ModelPrice      float64  `json:"model_price"`
+	OwnerBy         string   `json:"owner_by"`
+	CompletionRatio float64  `json:"completion_ratio"`
+	EnableGroup     []string `json:"enable_group,omitempty"`
+}
+
+var (
+	pricingMap         []Pricing
+	lastGetPricingTime time.Time
+	updatePricingLock  sync.Mutex
+)
+
+func GetPricing(group string) []Pricing {
+	updatePricingLock.Lock()
+	defer updatePricingLock.Unlock()
+
+	if time.Since(lastGetPricingTime) > time.Minute*1 || len(pricingMap) == 0 {
+		updatePricing()
+	}
+	if group != "" {
+		userPricingMap := make([]Pricing, 0)
+		models := GetGroupModels(group)
+		for _, pricing := range pricingMap {
+			if !common.StringsContains(models, pricing.ModelName) {
+				pricing.Available = false
+			}
+			userPricingMap = append(userPricingMap, pricing)
+		}
+		return userPricingMap
+	}
+	return pricingMap
+}
+
+func updatePricing() {
+	//modelRatios := common.GetModelRatios()
+	enabledModels := GetEnabledModels()
+	allModels := make(map[string]int)
+	for i, model := range enabledModels {
+		allModels[model] = i
+	}
+
+	pricingMap = make([]Pricing, 0)
+	for model, _ := range allModels {
+		pricing := Pricing{
+			Available: true,
+			ModelName: model,
+		}
+		modelPrice, findPrice := common.GetModelPrice(model, false)
+		if findPrice {
+			pricing.ModelPrice = modelPrice
+			pricing.QuotaType = 1
+		} else {
+			pricing.ModelRatio = common.GetModelRatio(model)
+			pricing.CompletionRatio = common.GetCompletionRatio(model)
+			pricing.QuotaType = 0
+		}
+		pricingMap = append(pricingMap, pricing)
+	}
+	lastGetPricingTime = time.Now()
+}

model/redemption.go

@@ -78,7 +78,7 @@ func Redeem(key string, userId int) (quota int, err error) {
 	if err != nil {
 		return 0, errors.New("兑换失败，" + err.Error())
 	}
-	RecordLog(userId, LogTypeTopup, fmt.Sprintf("通过兑换码充值 %s", common.LogQuota(redemption.Quota)))
+	RecordLog(userId, LogTypeTopup, fmt.Sprintf("通过兑换码充值 %s，兑换码ID %d", common.LogQuota(redemption.Quota), redemption.Id))
 	return redemption.Quota, nil
 }
 

model/task.go

@@ -0,0 +1,304 @@
+package model
+
+import (
+	"database/sql/driver"
+	"encoding/json"
+	"one-api/constant"
+	commonRelay "one-api/relay/common"
+	"time"
+)
+
+type TaskStatus string
+
+const (
+	TaskStatusNotStart   TaskStatus = "NOT_START"
+	TaskStatusSubmitted             = "SUBMITTED"
+	TaskStatusQueued                = "QUEUED"
+	TaskStatusInProgress            = "IN_PROGRESS"
+	TaskStatusFailure               = "FAILURE"
+	TaskStatusSuccess               = "SUCCESS"
+	TaskStatusUnknown               = "UNKNOWN"
+)
+
+type Task struct {
+	ID         int64                 `json:"id" gorm:"primary_key;AUTO_INCREMENT"`
+	CreatedAt  int64                 `json:"created_at" gorm:"index"`
+	UpdatedAt  int64                 `json:"updated_at"`
+	TaskID     string                `json:"task_id" gorm:"type:varchar(50);index"`  // 第三方id，不一定有/ song id\ Task id
+	Platform   constant.TaskPlatform `json:"platform" gorm:"type:varchar(30);index"` // 平台
+	UserId     int                   `json:"user_id" gorm:"index"`
+	ChannelId  int                   `json:"channel_id" gorm:"index"`
+	Quota      int                   `json:"quota"`
+	Action     string                `json:"action" gorm:"type:varchar(40);index"` // 任务类型, song, lyrics, description-mode
+	Status     TaskStatus            `json:"status" gorm:"type:varchar(20);index"` // 任务状态
+	FailReason string                `json:"fail_reason"`
+	SubmitTime int64                 `json:"submit_time" gorm:"index"`
+	StartTime  int64                 `json:"start_time" gorm:"index"`
+	FinishTime int64                 `json:"finish_time" gorm:"index"`
+	Progress   string                `json:"progress" gorm:"type:varchar(20);index"`
+	Properties Properties            `json:"properties" gorm:"type:json"`
+
+	Data json.RawMessage `json:"data" gorm:"type:json"`
+}
+
+func (t *Task) SetData(data any) {
+	b, _ := json.Marshal(data)
+	t.Data = json.RawMessage(b)
+}
+
+func (t *Task) GetData(v any) error {
+	err := json.Unmarshal(t.Data, &v)
+	return err
+}
+
+type Properties struct {
+	Input string `json:"input"`
+}
+
+func (m *Properties) Scan(val interface{}) error {
+	bytesValue, _ := val.([]byte)
+	return json.Unmarshal(bytesValue, m)
+}
+
+func (m Properties) Value() (driver.Value, error) {
+	return json.Marshal(m)
+}
+
+// SyncTaskQueryParams 用于包含所有搜索条件的结构体，可以根据需求添加更多字段
+type SyncTaskQueryParams struct {
+	Platform       constant.TaskPlatform
+	ChannelID      string
+	TaskID         string
+	UserID         string
+	Action         string
+	Status         string
+	StartTimestamp int64
+	EndTimestamp   int64
+	UserIDs        []int
+}
+
+func InitTask(platform constant.TaskPlatform, relayInfo *commonRelay.TaskRelayInfo) *Task {
+	t := &Task{
+		UserId:     relayInfo.UserId,
+		SubmitTime: time.Now().Unix(),
+		Status:     TaskStatusNotStart,
+		Progress:   "0%",
+		ChannelId:  relayInfo.ChannelId,
+		Platform:   platform,
+	}
+	return t
+}
+
+func TaskGetAllUserTask(userId int, startIdx int, num int, queryParams SyncTaskQueryParams) []*Task {
+	var tasks []*Task
+	var err error
+
+	// 初始化查询构建器
+	query := DB.Where("user_id = ?", userId)
+
+	if queryParams.TaskID != "" {
+		query = query.Where("task_id = ?", queryParams.TaskID)
+	}
+	if queryParams.Action != "" {
+		query = query.Where("action = ?", queryParams.Action)
+	}
+	if queryParams.Status != "" {
+		query = query.Where("status = ?", queryParams.Status)
+	}
+	if queryParams.Platform != "" {
+		query = query.Where("platform = ?", queryParams.Platform)
+	}
+	if queryParams.StartTimestamp != 0 {
+		// 假设您已将前端传来的时间戳转换为数据库所需的时间格式，并处理了时间戳的验证和解析
+		query = query.Where("submit_time >= ?", queryParams.StartTimestamp)
+	}
+	if queryParams.EndTimestamp != 0 {
+		query = query.Where("submit_time <= ?", queryParams.EndTimestamp)
+	}
+
+	// 获取数据
+	err = query.Omit("channel_id").Order("id desc").Limit(num).Offset(startIdx).Find(&tasks).Error
+	if err != nil {
+		return nil
+	}
+
+	return tasks
+}
+
+func TaskGetAllTasks(startIdx int, num int, queryParams SyncTaskQueryParams) []*Task {
+	var tasks []*Task
+	var err error
+
+	// 初始化查询构建器
+	query := DB
+
+	// 添加过滤条件
+	if queryParams.ChannelID != "" {
+		query = query.Where("channel_id = ?", queryParams.ChannelID)
+	}
+	if queryParams.Platform != "" {
+		query = query.Where("platform = ?", queryParams.Platform)
+	}
+	if queryParams.UserID != "" {
+		query = query.Where("user_id = ?", queryParams.UserID)
+	}
+	if len(queryParams.UserIDs) != 0 {
+		query = query.Where("user_id in (?)", queryParams.UserIDs)
+	}
+	if queryParams.TaskID != "" {
+		query = query.Where("task_id = ?", queryParams.TaskID)
+	}
+	if queryParams.Action != "" {
+		query = query.Where("action = ?", queryParams.Action)
+	}
+	if queryParams.Status != "" {
+		query = query.Where("status = ?", queryParams.Status)
+	}
+	if queryParams.StartTimestamp != 0 {
+		query = query.Where("submit_time >= ?", queryParams.StartTimestamp)
+	}
+	if queryParams.EndTimestamp != 0 {
+		query = query.Where("submit_time <= ?", queryParams.EndTimestamp)
+	}
+
+	// 获取数据
+	err = query.Order("id desc").Limit(num).Offset(startIdx).Find(&tasks).Error
+	if err != nil {
+		return nil
+	}
+
+	return tasks
+}
+
+func GetAllUnFinishSyncTasks(limit int) []*Task {
+	var tasks []*Task
+	var err error
+	// get all tasks progress is not 100%
+	err = DB.Where("progress != ?", "100%").Limit(limit).Order("id").Find(&tasks).Error
+	if err != nil {
+		return nil
+	}
+	return tasks
+}
+
+func GetByOnlyTaskId(taskId string) (*Task, bool, error) {
+	if taskId == "" {
+		return nil, false, nil
+	}
+	var task *Task
+	var err error
+	err = DB.Where("task_id = ?", taskId).First(&task).Error
+	exist, err := RecordExist(err)
+	if err != nil {
+		return nil, false, err
+	}
+	return task, exist, err
+}
+
+func GetByTaskId(userId int, taskId string) (*Task, bool, error) {
+	if taskId == "" {
+		return nil, false, nil
+	}
+	var task *Task
+	var err error
+	err = DB.Where("user_id = ? and task_id = ?", userId, taskId).
+		First(&task).Error
+	exist, err := RecordExist(err)
+	if err != nil {
+		return nil, false, err
+	}
+	return task, exist, err
+}
+
+func GetByTaskIds(userId int, taskIds []any) ([]*Task, error) {
+	if len(taskIds) == 0 {
+		return nil, nil
+	}
+	var task []*Task
+	var err error
+	err = DB.Where("user_id = ? and task_id in (?)", userId, taskIds).
+		Find(&task).Error
+	if err != nil {
+		return nil, err
+	}
+	return task, nil
+}
+
+func TaskUpdateProgress(id int64, progress string) error {
+	return DB.Model(&Task{}).Where("id = ?", id).Update("progress", progress).Error
+}
+
+func (Task *Task) Insert() error {
+	var err error
+	err = DB.Create(Task).Error
+	return err
+}
+
+func (Task *Task) Update() error {
+	var err error
+	err = DB.Save(Task).Error
+	return err
+}
+
+func TaskBulkUpdate(TaskIds []string, params map[string]any) error {
+	if len(TaskIds) == 0 {
+		return nil
+	}
+	return DB.Model(&Task{}).
+		Where("task_id in (?)", TaskIds).
+		Updates(params).Error
+}
+
+func TaskBulkUpdateByTaskIds(taskIDs []int64, params map[string]any) error {
+	if len(taskIDs) == 0 {
+		return nil
+	}
+	return DB.Model(&Task{}).
+		Where("id in (?)", taskIDs).
+		Updates(params).Error
+}
+
+func TaskBulkUpdateByID(ids []int64, params map[string]any) error {
+	if len(ids) == 0 {
+		return nil
+	}
+	return DB.Model(&Task{}).
+		Where("id in (?)", ids).
+		Updates(params).Error
+}
+
+type TaskQuotaUsage struct {
+	Mode  string  `json:"mode"`
+	Count float64 `json:"count"`
+}
+
+func SumUsedTaskQuota(queryParams SyncTaskQueryParams) (stat []TaskQuotaUsage, err error) {
+	query := DB.Model(Task{})
+	// 添加过滤条件
+	if queryParams.ChannelID != "" {
+		query = query.Where("channel_id = ?", queryParams.ChannelID)
+	}
+	if queryParams.UserID != "" {
+		query = query.Where("user_id = ?", queryParams.UserID)
+	}
+	if len(queryParams.UserIDs) != 0 {
+		query = query.Where("user_id in (?)", queryParams.UserIDs)
+	}
+	if queryParams.TaskID != "" {
+		query = query.Where("task_id = ?", queryParams.TaskID)
+	}
+	if queryParams.Action != "" {
+		query = query.Where("action = ?", queryParams.Action)
+	}
+	if queryParams.Status != "" {
+		query = query.Where("status = ?", queryParams.Status)
+	}
+	if queryParams.StartTimestamp != 0 {
+		query = query.Where("submit_time >= ?", queryParams.StartTimestamp)
+	}
+	if queryParams.EndTimestamp != 0 {
+		query = query.Where("submit_time <= ?", queryParams.EndTimestamp)
+	}
+	err = query.Select("mode, sum(quota) as count").Group("mode").Find(&stat).Error
+	return stat, err
+}

model/token.go

@@ -5,13 +5,14 @@ import (
 	"fmt"
 	"gorm.io/gorm"
 	"one-api/common"
+	"one-api/constant"
 	"strconv"
 	"strings"
 )
 
 type Token struct {
 	Id                 int            `json:"id"`
-	UserId             int            `json:"user_id"`
+	UserId             int            `json:"user_id" gorm:"index"`
 	Key                string         `json:"key" gorm:"type:char(48);uniqueIndex"`
 	Status             int            `json:"status" gorm:"default:1"`
 	Name               string         `json:"name" gorm:"index" `
@@ -102,6 +103,11 @@ func GetTokenById(id int) (*Token, error) {
 	token := Token{Id: id}
 	var err error = nil
 	err = DB.First(&token, "id = ?", id).Error
+	if err != nil {
+		if common.RedisEnabled {
+			go cacheSetToken(&token)
+		}
+	}
 	return &token, err
 }
 
@@ -244,11 +250,9 @@ func PreConsumeTokenQuota(tokenId int, quota int) (userQuota int, err error) {
 	if userQuota < quota {
 		return 0, errors.New(fmt.Sprintf("用户额度不足，剩余额度为 %d", userQuota))
 	}
-	if !token.UnlimitedQuota {
-		err = DecreaseTokenQuota(tokenId, quota)
-		if err != nil {
-			return 0, err
-		}
+	err = DecreaseTokenQuota(tokenId, quota)
+	if err != nil {
+		return 0, err
 	}
 	err = DecreaseUserQuota(token.UserId, quota)
 	return userQuota - quota, err
@@ -266,15 +270,13 @@ func PostConsumeTokenQuota(tokenId int, userQuota int, quota int, preConsumedQuo
 		return err
 	}
 
-	if !token.UnlimitedQuota {
-		if quota > 0 {
-			err = DecreaseTokenQuota(tokenId, quota)
-		} else {
-			err = IncreaseTokenQuota(tokenId, -quota)
-		}
-		if err != nil {
-			return err
-		}
+	if quota > 0 {
+		err = DecreaseTokenQuota(tokenId, quota)
+	} else {
+		err = IncreaseTokenQuota(tokenId, -quota)
+	}
+	if err != nil {
+		return err
 	}
 
 	if sendEmail {
@@ -292,7 +294,7 @@ func PostConsumeTokenQuota(tokenId int, userQuota int, quota int, preConsumedQuo
 						prompt = "您的额度已用尽"
 					}
 					if email != "" {
-						topUpLink := fmt.Sprintf("%s/topup", common.ServerAddress)
+						topUpLink := fmt.Sprintf("%s/topup", constant.ServerAddress)
 						err = common.SendEmail(prompt, email,
 							fmt.Sprintf("%s，当前剩余额度为 %d，为了不影响您的使用，请及时充值。<br/>充值链接：<a href='%s'>%s</a>", prompt, userQuota, topUpLink, topUpLink))
 						if err != nil {

model/usedata.go

@@ -45,6 +45,7 @@ func logQuotaDataCache(userId int, username string, modelName string, quota int,
 	if ok {
 		quotaData.Count += 1
 		quotaData.Quota += quota
+		quotaData.TokenUsed += tokenUsed
 	} else {
 		quotaData = &QuotaData{
 			UserID:    userId,

model/user.go

@@ -73,25 +73,34 @@ func GetAllUsers(startIdx int, num int) (users []*User, err error) {
 	return users, err
 }
 
-func SearchUsers(keyword string) ([]*User, error) {
+func SearchUsers(keyword string, group string) ([]*User, error) {
 	var users []*User
 	var err error
 
 	// 尝试将关键字转换为整数ID
 	keywordInt, err := strconv.Atoi(keyword)
 	if err == nil {
-		// 如果转换成功，按照ID搜索用户
-		err = DB.Unscoped().Omit("password").Where("id = ?", keywordInt).Find(&users).Error
+		// 如果转换成功，按照ID和可选的组别搜索用户
+		query := DB.Unscoped().Omit("password").Where("`id` = ?", keywordInt)
+		if group != "" {
+			query = query.Where("`group` = ?", group) // 使用反引号包围group
+		}
+		err = query.Find(&users).Error
 		if err != nil || len(users) > 0 {
-			// 如果依据ID找到用户或者发生错误，返回结果或错误
 			return users, err
 		}
 	}
 
-	// 如果ID转换失败或者没有找到用户，依据其他字段进行模糊搜索
-	err = DB.Unscoped().Omit("password").
-		Where("username LIKE ? OR email LIKE ? OR display_name LIKE ?", keyword+"%", keyword+"%", keyword+"%").
-		Find(&users).Error
+	err = nil
+
+	query := DB.Unscoped().Omit("password")
+	likeCondition := "`username` LIKE ? OR `email` LIKE ? OR `display_name` LIKE ?"
+	if group != "" {
+		query = query.Where("("+likeCondition+") AND `group` = ?", "%"+keyword+"%", "%"+keyword+"%", "%"+keyword+"%", group)
+	} else {
+		query = query.Where(likeCondition, "%"+keyword+"%", "%"+keyword+"%", "%"+keyword+"%")
+	}
+	err = query.Find(&users).Error
 
 	return users, err
 }
@@ -235,7 +244,7 @@ func (user *User) Update(updatePassword bool) error {
 	return err
 }
 
-func (user *User) UpdateAll(updatePassword bool) error {
+func (user *User) Edit(updatePassword bool) error {
 	var err error
 	if updatePassword {
 		user.Password, err = common.Password2Hash(user.Password)
@@ -244,8 +253,17 @@ func (user *User) UpdateAll(updatePassword bool) error {
 		}
 	}
 	newUser := *user
+	updates := map[string]interface{}{
+		"username":     newUser.Username,
+		"display_name": newUser.DisplayName,
+		"group":        newUser.Group,
+		"quota":        newUser.Quota,
+	}
+	if updatePassword {
+		updates["password"] = newUser.Password
+	}
 	DB.First(&user, user.Id)
-	err = DB.Model(user).Select("*").Updates(newUser).Error
+	err = DB.Model(user).Updates(updates).Error
 	if err == nil {
 		if common.RedisEnabled {
 			_ = common.RedisSet(fmt.Sprintf("user_group:%d", user.Id), user.Group, time.Duration(UserId2GroupCacheSeconds)*time.Second)
@@ -410,6 +428,11 @@ func ValidateAccessToken(token string) (user *User) {
 
 func GetUserQuota(id int) (quota int, err error) {
 	err = DB.Model(&User{}).Where("id = ?", id).Select("quota").Find(&quota).Error
+	if err != nil {
+		if common.RedisEnabled {
+			go cacheSetUserQuota(id, quota)
+		}
+	}
 	return quota, err
 }
 

model/utils.go

@@ -1,6 +1,8 @@
 package model
 
 import (
+	"errors"
+	"gorm.io/gorm"
 	"one-api/common"
 	"sync"
 	"time"
@@ -75,3 +77,13 @@ func batchUpdate() {
 	}
 	common.SysLog("batch update finished")
 }
+
+func RecordExist(err error) (bool, error) {
+	if err == nil {
+		return true, nil
+	}
+	if errors.Is(err, gorm.ErrRecordNotFound) {
+		return false, nil
+	}
+	return false, err
+}

relay/channel/adapter.go

@@ -11,11 +11,32 @@ import (
 type Adaptor interface {
 	// Init IsStream bool
 	Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest)
+	InitRerank(info *relaycommon.RelayInfo, request dto.RerankRequest)
 	GetRequestURL(info *relaycommon.RelayInfo) (string, error)
 	SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error
 	ConvertRequest(c *gin.Context, relayMode int, request *dto.GeneralOpenAIRequest) (any, error)
+	ConvertRerankRequest(c *gin.Context, relayMode int, request dto.RerankRequest) (any, error)
 	DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error)
 	DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode)
 	GetModelList() []string
 	GetChannelName() string
 }
+
+type TaskAdaptor interface {
+	Init(info *relaycommon.TaskRelayInfo)
+
+	ValidateRequestAndSetAction(c *gin.Context, info *relaycommon.TaskRelayInfo) *dto.TaskError
+
+	BuildRequestURL(info *relaycommon.TaskRelayInfo) (string, error)
+	BuildRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.TaskRelayInfo) error
+	BuildRequestBody(c *gin.Context, info *relaycommon.TaskRelayInfo) (io.Reader, error)
+
+	DoRequest(c *gin.Context, info *relaycommon.TaskRelayInfo, requestBody io.Reader) (*http.Response, error)
+	DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.TaskRelayInfo) (taskID string, taskData []byte, err *dto.TaskError)
+
+	GetModelList() []string
+	GetChannelName() string
+
+	// FetchTask
+	FetchTask(baseUrl, key string, body map[string]any) (*http.Response, error)
+}

relay/channel/ai360/constants.go

@@ -1,8 +1,13 @@
 package ai360
 
 var ModelList = []string{
+	"360gpt-turbo",
+	"360gpt-turbo-responsibility-8k",
+	"360gpt-pro",
 	"360GPT_S2_V9",
 	"embedding-bert-512-v1",
 	"embedding_s1_v1",
 	"semantic_similarity_s1_v1",
 }
+
+var ChannelName = "ai360"

relay/channel/ali/adaptor.go

@@ -15,6 +15,9 @@ import (
 type Adaptor struct {
 }
 
+func (a *Adaptor) InitRerank(info *relaycommon.RelayInfo, request dto.RerankRequest) {
+}
+
 func (a *Adaptor) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
 
 }
@@ -53,6 +56,10 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *dto.Gen
 	}
 }
 
+func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dto.RerankRequest) (any, error) {
+	return nil, nil
+}
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

relay/channel/ali/relay-ali.go

@@ -136,7 +136,7 @@ func responseAli2OpenAI(response *AliChatResponse) *dto.OpenAITextResponse {
 
 func streamResponseAli2OpenAI(aliResponse *AliChatResponse) *dto.ChatCompletionsStreamResponse {
 	var choice dto.ChatCompletionsStreamResponseChoice
-	choice.Delta.Content = aliResponse.Output.Text
+	choice.Delta.SetContentString(aliResponse.Output.Text)
 	if aliResponse.Output.FinishReason != "null" {
 		finishReason := aliResponse.Output.FinishReason
 		choice.FinishReason = &finishReason
@@ -199,7 +199,7 @@ func aliStreamHandler(c *gin.Context, resp *http.Response) (*dto.OpenAIErrorWith
 				usage.TotalTokens = aliResponse.Usage.InputTokens + aliResponse.Usage.OutputTokens
 			}
 			response := streamResponseAli2OpenAI(&aliResponse)
-			response.Choices[0].Delta.Content = strings.TrimPrefix(response.Choices[0].Delta.Content, lastResponseText)
+			response.Choices[0].Delta.SetContentString(strings.TrimPrefix(response.Choices[0].Delta.GetContentString(), lastResponseText))
 			lastResponseText = aliResponse.Output.Text
 			jsonResponse, err := json.Marshal(response)
 			if err != nil {

relay/channel/api_request.go

@@ -50,3 +50,27 @@ func doRequest(c *gin.Context, req *http.Request) (*http.Response, error) {
 	_ = c.Request.Body.Close()
 	return resp, nil
 }
+
+func DoTaskApiRequest(a TaskAdaptor, c *gin.Context, info *common.TaskRelayInfo, requestBody io.Reader) (*http.Response, error) {
+	fullRequestURL, err := a.BuildRequestURL(info)
+	if err != nil {
+		return nil, err
+	}
+	req, err := http.NewRequest(c.Request.Method, fullRequestURL, requestBody)
+	if err != nil {
+		return nil, fmt.Errorf("new request failed: %w", err)
+	}
+	req.GetBody = func() (io.ReadCloser, error) {
+		return io.NopCloser(requestBody), nil
+	}
+
+	err = a.BuildRequestHeader(c, req, info)
+	if err != nil {
+		return nil, fmt.Errorf("setup request header failed: %w", err)
+	}
+	resp, err := doRequest(c, req)
+	if err != nil {
+		return nil, fmt.Errorf("do request failed: %w", err)
+	}
+	return resp, nil
+}

relay/channel/aws/adaptor.go

@@ -0,0 +1,88 @@
+package aws
+
+import (
+	"errors"
+	"github.com/gin-gonic/gin"
+	"io"
+	"net/http"
+	"one-api/dto"
+	"one-api/relay/channel/claude"
+	relaycommon "one-api/relay/common"
+	"strings"
+)
+
+const (
+	RequestModeCompletion = 1
+	RequestModeMessage    = 2
+)
+
+type Adaptor struct {
+	RequestMode int
+}
+
+func (a *Adaptor) InitRerank(info *relaycommon.RelayInfo, request dto.RerankRequest) {
+	//TODO implement me
+
+}
+
+func (a *Adaptor) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
+	if strings.HasPrefix(info.UpstreamModelName, "claude-3") {
+		a.RequestMode = RequestModeMessage
+	} else {
+		a.RequestMode = RequestModeCompletion
+	}
+}
+
+func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
+	return "", nil
+}
+
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
+	return nil
+}
+
+func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *dto.GeneralOpenAIRequest) (any, error) {
+	if request == nil {
+		return nil, errors.New("request is nil")
+	}
+
+	var claudeReq *claude.ClaudeRequest
+	var err error
+	if a.RequestMode == RequestModeCompletion {
+		claudeReq = claude.RequestOpenAI2ClaudeComplete(*request)
+	} else {
+		claudeReq, err = claude.RequestOpenAI2ClaudeMessage(*request)
+	}
+	c.Set("request_model", request.Model)
+	c.Set("converted_request", claudeReq)
+	return claudeReq, err
+}
+
+func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dto.RerankRequest) (any, error) {
+	return nil, nil
+}
+
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+	return nil, nil
+}
+
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
+	if info.IsStream {
+		err, usage = awsStreamHandler(c, info, a.RequestMode)
+	} else {
+		err, usage = awsHandler(c, info, a.RequestMode)
+	}
+	return
+}
+
+func (a *Adaptor) GetModelList() (models []string) {
+	for n := range awsModelIDMap {
+		models = append(models, n)
+	}
+
+	return
+}
+
+func (a *Adaptor) GetChannelName() string {
+	return ChannelName
+}

relay/channel/aws/constants.go

@@ -0,0 +1,13 @@
+package aws
+
+var awsModelIDMap = map[string]string{
+	"claude-instant-1.2":       "anthropic.claude-instant-v1",
+	"claude-2.0":               "anthropic.claude-v2",
+	"claude-2.1":               "anthropic.claude-v2:1",
+	"claude-3-sonnet-20240229": "anthropic.claude-3-sonnet-20240229-v1:0",
+	"claude-3-opus-20240229":   "anthropic.claude-3-opus-20240229-v1:0",
+	"claude-3-haiku-20240307":  "anthropic.claude-3-haiku-20240307-v1:0",
+	"claude-3-5-sonnet-20240620": "anthropic.claude-3-5-sonnet-20240620-v1:0",
+}
+
+var ChannelName = "aws"

relay/channel/aws/dto.go

@@ -0,0 +1,15 @@
+package aws
+
+import "one-api/relay/channel/claude"
+
+type AwsClaudeRequest struct {
+	// AnthropicVersion should be "bedrock-2023-05-31"
+	AnthropicVersion string                 `json:"anthropic_version"`
+	System           string                 `json:"system"`
+	Messages         []claude.ClaudeMessage `json:"messages"`
+	MaxTokens        int                    `json:"max_tokens,omitempty"`
+	Temperature      float64                `json:"temperature,omitempty"`
+	TopP             float64                `json:"top_p,omitempty"`
+	TopK             int                    `json:"top_k,omitempty"`
+	StopSequences    []string               `json:"stop_sequences,omitempty"`
+}

relay/channel/aws/relay-aws.go

@@ -0,0 +1,219 @@
+package aws
+
+import (
+	"bytes"
+	"encoding/json"
+	"fmt"
+	"github.com/gin-gonic/gin"
+	"github.com/jinzhu/copier"
+	"github.com/pkg/errors"
+	"io"
+	"net/http"
+	"one-api/common"
+	relaymodel "one-api/dto"
+	"one-api/relay/channel/claude"
+	relaycommon "one-api/relay/common"
+	"strings"
+	"time"
+
+	"github.com/aws/aws-sdk-go-v2/aws"
+	"github.com/aws/aws-sdk-go-v2/credentials"
+	"github.com/aws/aws-sdk-go-v2/service/bedrockruntime"
+	"github.com/aws/aws-sdk-go-v2/service/bedrockruntime/types"
+)
+
+func newAwsClient(c *gin.Context, info *relaycommon.RelayInfo) (*bedrockruntime.Client, error) {
+	awsSecret := strings.Split(info.ApiKey, "|")
+	if len(awsSecret) != 3 {
+		return nil, errors.New("invalid aws secret key")
+	}
+	ak := awsSecret[0]
+	sk := awsSecret[1]
+	region := awsSecret[2]
+	client := bedrockruntime.New(bedrockruntime.Options{
+		Region:      region,
+		Credentials: aws.NewCredentialsCache(credentials.NewStaticCredentialsProvider(ak, sk, "")),
+	})
+
+	return client, nil
+}
+
+func wrapErr(err error) *relaymodel.OpenAIErrorWithStatusCode {
+	return &relaymodel.OpenAIErrorWithStatusCode{
+		StatusCode: http.StatusInternalServerError,
+		Error: relaymodel.OpenAIError{
+			Message: fmt.Sprintf("%s", err.Error()),
+		},
+	}
+}
+
+func awsModelID(requestModel string) (string, error) {
+	if awsModelID, ok := awsModelIDMap[requestModel]; ok {
+		return awsModelID, nil
+	}
+
+	return "", errors.Errorf("model %s not found", requestModel)
+}
+
+func awsHandler(c *gin.Context, info *relaycommon.RelayInfo, requestMode int) (*relaymodel.OpenAIErrorWithStatusCode, *relaymodel.Usage) {
+	awsCli, err := newAwsClient(c, info)
+	if err != nil {
+		return wrapErr(errors.Wrap(err, "newAwsClient")), nil
+	}
+
+	awsModelId, err := awsModelID(c.GetString("request_model"))
+	if err != nil {
+		return wrapErr(errors.Wrap(err, "awsModelID")), nil
+	}
+
+	awsReq := &bedrockruntime.InvokeModelInput{
+		ModelId:     aws.String(awsModelId),
+		Accept:      aws.String("application/json"),
+		ContentType: aws.String("application/json"),
+	}
+
+	claudeReq_, ok := c.Get("converted_request")
+	if !ok {
+		return wrapErr(errors.New("request not found")), nil
+	}
+	claudeReq := claudeReq_.(*claude.ClaudeRequest)
+	awsClaudeReq := &AwsClaudeRequest{
+		AnthropicVersion: "bedrock-2023-05-31",
+	}
+	if err = copier.Copy(awsClaudeReq, claudeReq); err != nil {
+		return wrapErr(errors.Wrap(err, "copy request")), nil
+	}
+
+	awsReq.Body, err = json.Marshal(awsClaudeReq)
+	if err != nil {
+		return wrapErr(errors.Wrap(err, "marshal request")), nil
+	}
+
+	awsResp, err := awsCli.InvokeModel(c.Request.Context(), awsReq)
+	if err != nil {
+		return wrapErr(errors.Wrap(err, "InvokeModel")), nil
+	}
+
+	claudeResponse := new(claude.ClaudeResponse)
+	err = json.Unmarshal(awsResp.Body, claudeResponse)
+	if err != nil {
+		return wrapErr(errors.Wrap(err, "unmarshal response")), nil
+	}
+
+	openaiResp := claude.ResponseClaude2OpenAI(requestMode, claudeResponse)
+	usage := relaymodel.Usage{
+		PromptTokens:     claudeResponse.Usage.InputTokens,
+		CompletionTokens: claudeResponse.Usage.OutputTokens,
+		TotalTokens:      claudeResponse.Usage.InputTokens + claudeResponse.Usage.OutputTokens,
+	}
+	openaiResp.Usage = usage
+
+	c.JSON(http.StatusOK, openaiResp)
+	return nil, &usage
+}
+
+func awsStreamHandler(c *gin.Context, info *relaycommon.RelayInfo, requestMode int) (*relaymodel.OpenAIErrorWithStatusCode, *relaymodel.Usage) {
+	awsCli, err := newAwsClient(c, info)
+	if err != nil {
+		return wrapErr(errors.Wrap(err, "newAwsClient")), nil
+	}
+
+	awsModelId, err := awsModelID(c.GetString("request_model"))
+	if err != nil {
+		return wrapErr(errors.Wrap(err, "awsModelID")), nil
+	}
+
+	awsReq := &bedrockruntime.InvokeModelWithResponseStreamInput{
+		ModelId:     aws.String(awsModelId),
+		Accept:      aws.String("application/json"),
+		ContentType: aws.String("application/json"),
+	}
+
+	claudeReq_, ok := c.Get("converted_request")
+	if !ok {
+		return wrapErr(errors.New("request not found")), nil
+	}
+	claudeReq := claudeReq_.(*claude.ClaudeRequest)
+
+	awsClaudeReq := &AwsClaudeRequest{
+		AnthropicVersion: "bedrock-2023-05-31",
+	}
+	if err = copier.Copy(awsClaudeReq, claudeReq); err != nil {
+		return wrapErr(errors.Wrap(err, "copy request")), nil
+	}
+	awsReq.Body, err = json.Marshal(awsClaudeReq)
+	if err != nil {
+		return wrapErr(errors.Wrap(err, "marshal request")), nil
+	}
+
+	awsResp, err := awsCli.InvokeModelWithResponseStream(c.Request.Context(), awsReq)
+	if err != nil {
+		return wrapErr(errors.Wrap(err, "InvokeModelWithResponseStream")), nil
+	}
+	stream := awsResp.GetStream()
+	defer stream.Close()
+
+	c.Writer.Header().Set("Content-Type", "text/event-stream")
+	var usage relaymodel.Usage
+	var id string
+	var model string
+	isFirst := true
+	createdTime := common.GetTimestamp()
+	c.Stream(func(w io.Writer) bool {
+		event, ok := <-stream.Events()
+		if !ok {
+			c.Render(-1, common.CustomEvent{Data: "data: [DONE]"})
+			return false
+		}
+
+		switch v := event.(type) {
+		case *types.ResponseStreamMemberChunk:
+			if isFirst {
+				isFirst = false
+				info.FirstResponseTime = time.Now()
+			}
+			claudeResp := new(claude.ClaudeResponse)
+			err := json.NewDecoder(bytes.NewReader(v.Value.Bytes)).Decode(claudeResp)
+			if err != nil {
+				common.SysError("error unmarshalling stream response: " + err.Error())
+				return false
+			}
+
+			response, claudeUsage := claude.StreamResponseClaude2OpenAI(requestMode, claudeResp)
+			if claudeUsage != nil {
+				usage.PromptTokens += claudeUsage.InputTokens
+				usage.CompletionTokens += claudeUsage.OutputTokens
+			}
+
+			if response == nil {
+				return true
+			}
+
+			if response.Id != "" {
+				id = response.Id
+			}
+			if response.Model != "" {
+				model = response.Model
+			}
+			response.Created = createdTime
+			response.Id = id
+			response.Model = model
+
+			jsonStr, err := json.Marshal(response)
+			if err != nil {
+				common.SysError("error marshalling stream response: " + err.Error())
+				return true
+			}
+			c.Render(-1, common.CustomEvent{Data: "data: " + string(jsonStr)})
+			return true
+		case *types.UnknownUnionMember:
+			fmt.Println("unknown tag:", v.Tag)
+			return false
+		default:
+			fmt.Println("union is nil or unknown type")
+			return false
+		}
+	})
+
+	return nil, &usage
+}

relay/channel/baidu/adaptor.go

@@ -2,6 +2,7 @@ package baidu
 
 import (
 	"errors"
+	"fmt"
 	"github.com/gin-gonic/gin"
 	"io"
 	"net/http"
@@ -9,33 +10,80 @@ import (
 	"one-api/relay/channel"
 	relaycommon "one-api/relay/common"
 	"one-api/relay/constant"
+	"strings"
 )
 
 type Adaptor struct {
 }
 
+func (a *Adaptor) InitRerank(info *relaycommon.RelayInfo, request dto.RerankRequest) {
+	//TODO implement me
+
+}
+
 func (a *Adaptor) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
 
 }
 
 func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
-	var fullRequestURL string
-	switch info.UpstreamModelName {
-	case "ERNIE-Bot-4":
-		fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/completions_pro"
-	case "ERNIE-Bot-8K":
-		fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/ernie_bot_8k"
-	case "ERNIE-Bot":
-		fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/completions"
-	case "ERNIE-Speed":
-		fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/ernie_speed"
-	case "ERNIE-Bot-turbo":
-		fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/eb-instant"
-	case "BLOOMZ-7B":
-		fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/bloomz_7b1"
-	case "Embedding-V1":
-		fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/embeddings/embedding-v1"
+	// https://cloud.baidu.com/doc/WENXINWORKSHOP/s/clntwmv7t
+	suffix := "chat/"
+	if strings.HasPrefix(info.UpstreamModelName, "Embedding") {
+		suffix = "embeddings/"
 	}
+	if strings.HasPrefix(info.UpstreamModelName, "bge-large") {
+		suffix = "embeddings/"
+	}
+	if strings.HasPrefix(info.UpstreamModelName, "tao-8k") {
+		suffix = "embeddings/"
+	}
+	switch info.UpstreamModelName {
+	case "ERNIE-4.0":
+		suffix += "completions_pro"
+	case "ERNIE-Bot-4":
+		suffix += "completions_pro"
+	case "ERNIE-Bot":
+		suffix += "completions"
+	case "ERNIE-Bot-turbo":
+		suffix += "eb-instant"
+	case "ERNIE-Speed":
+		suffix += "ernie_speed"
+	case "ERNIE-4.0-8K":
+		suffix += "completions_pro"
+	case "ERNIE-3.5-8K":
+		suffix += "completions"
+	case "ERNIE-3.5-8K-0205":
+		suffix += "ernie-3.5-8k-0205"
+	case "ERNIE-3.5-8K-1222":
+		suffix += "ernie-3.5-8k-1222"
+	case "ERNIE-Bot-8K":
+		suffix += "ernie_bot_8k"
+	case "ERNIE-3.5-4K-0205":
+		suffix += "ernie-3.5-4k-0205"
+	case "ERNIE-Speed-8K":
+		suffix += "ernie_speed"
+	case "ERNIE-Speed-128K":
+		suffix += "ernie-speed-128k"
+	case "ERNIE-Lite-8K-0922":
+		suffix += "eb-instant"
+	case "ERNIE-Lite-8K-0308":
+		suffix += "ernie-lite-8k"
+	case "ERNIE-Tiny-8K":
+		suffix += "ernie-tiny-8k"
+	case "BLOOMZ-7B":
+		suffix += "bloomz_7b1"
+	case "Embedding-V1":
+		suffix += "embedding-v1"
+	case "bge-large-zh":
+		suffix += "bge_large_zh"
+	case "bge-large-en":
+		suffix += "bge_large_en"
+	case "tao-8k":
+		suffix += "tao_8k"
+	default:
+		suffix += strings.ToLower(info.UpstreamModelName)
+	}
+	fullRequestURL := fmt.Sprintf("%s/rpc/2.0/ai_custom/v1/wenxinworkshop/%s", info.BaseUrl, suffix)
 	var accessToken string
 	var err error
 	if accessToken, err = getBaiduAccessToken(info.ApiKey); err != nil {
@@ -65,6 +113,10 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *dto.Gen
 	}
 }
 
+func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dto.RerankRequest) (any, error) {
+	return nil, nil
+}
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

relay/channel/baidu/constants.go

@@ -1,12 +1,22 @@
 package baidu
 
 var ModelList = []string{
-	"ERNIE-Bot-4",
+	"ERNIE-4.0-8K",
+	"ERNIE-3.5-8K",
+	"ERNIE-3.5-8K-0205",
+	"ERNIE-3.5-8K-1222",
 	"ERNIE-Bot-8K",
-	"ERNIE-Bot",
-	"ERNIE-Speed",
-	"ERNIE-Bot-turbo",
+	"ERNIE-3.5-4K-0205",
+	"ERNIE-Speed-8K",
+	"ERNIE-Speed-128K",
+	"ERNIE-Lite-8K-0922",
+	"ERNIE-Lite-8K-0308",
+	"ERNIE-Tiny-8K",
+	"BLOOMZ-7B",
 	"Embedding-V1",
+	"bge-large-zh",
+	"bge-large-en",
+	"tao-8k",
 }
 
 var ChannelName = "baidu"

relay/channel/baidu/dto.go

@@ -11,9 +11,16 @@ type BaiduMessage struct {
 }
 
 type BaiduChatRequest struct {
-	Messages []BaiduMessage `json:"messages"`
-	Stream   bool           `json:"stream"`
-	UserId   string         `json:"user_id,omitempty"`
+	Messages        []BaiduMessage `json:"messages"`
+	Temperature     float64        `json:"temperature,omitempty"`
+	TopP            float64        `json:"top_p,omitempty"`
+	PenaltyScore    float64        `json:"penalty_score,omitempty"`
+	Stream          bool           `json:"stream,omitempty"`
+	System          string         `json:"system,omitempty"`
+	DisableSearch   bool           `json:"disable_search,omitempty"`
+	EnableCitation  bool           `json:"enable_citation,omitempty"`
+	MaxOutputTokens int            `json:"max_output_tokens,omitempty"`
+	UserId          string         `json:"user_id,omitempty"`
 }
 
 type Error struct {

relay/channel/baidu/relay-baidu.go

@@ -22,17 +22,27 @@ import (
 var baiduTokenStore sync.Map
 
 func requestOpenAI2Baidu(request dto.GeneralOpenAIRequest) *BaiduChatRequest {
-	messages := make([]BaiduMessage, 0, len(request.Messages))
+	baiduRequest := BaiduChatRequest{
+		Temperature:     request.Temperature,
+		TopP:            request.TopP,
+		PenaltyScore:    request.FrequencyPenalty,
+		Stream:          request.Stream,
+		DisableSearch:   false,
+		EnableCitation:  false,
+		MaxOutputTokens: int(request.MaxTokens),
+		UserId:          request.User,
+	}
 	for _, message := range request.Messages {
-		messages = append(messages, BaiduMessage{
-			Role:    message.Role,
-			Content: message.StringContent(),
-		})
-	}
-	return &BaiduChatRequest{
-		Messages: messages,
-		Stream:   request.Stream,
+		if message.Role == "system" {
+			baiduRequest.System = message.StringContent()
+		} else {
+			baiduRequest.Messages = append(baiduRequest.Messages, BaiduMessage{
+				Role:    message.Role,
+				Content: message.StringContent(),
+			})
+		}
 	}
+	return &baiduRequest
 }
 
 func responseBaidu2OpenAI(response *BaiduChatResponse) *dto.OpenAITextResponse {
@@ -57,7 +67,7 @@ func responseBaidu2OpenAI(response *BaiduChatResponse) *dto.OpenAITextResponse {
 
 func streamResponseBaidu2OpenAI(baiduResponse *BaiduChatStreamResponse) *dto.ChatCompletionsStreamResponse {
 	var choice dto.ChatCompletionsStreamResponseChoice
-	choice.Delta.Content = baiduResponse.Result
+	choice.Delta.SetContentString(baiduResponse.Result)
 	if baiduResponse.IsEnd {
 		choice.FinishReason = &relaycommon.StopFinishReason
 	}

relay/channel/claude/adaptor.go

@@ -21,6 +21,11 @@ type Adaptor struct {
 	RequestMode int
 }
 
+func (a *Adaptor) InitRerank(info *relaycommon.RelayInfo, request dto.RerankRequest) {
+	//TODO implement me
+
+}
+
 func (a *Adaptor) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
 	if strings.HasPrefix(info.UpstreamModelName, "claude-3") {
 		a.RequestMode = RequestModeMessage
@@ -53,19 +58,23 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *dto.Gen
 		return nil, errors.New("request is nil")
 	}
 	if a.RequestMode == RequestModeCompletion {
-		return requestOpenAI2ClaudeComplete(*request), nil
+		return RequestOpenAI2ClaudeComplete(*request), nil
 	} else {
-		return requestOpenAI2ClaudeMessage(*request)
+		return RequestOpenAI2ClaudeMessage(*request)
 	}
 }
 
+func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dto.RerankRequest) (any, error) {
+	return nil, nil
+}
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }
 
 func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
 	if info.IsStream {
-		err, usage = claudeStreamHandler(a.RequestMode, info.UpstreamModelName, info.PromptTokens, c, resp)
+		err, usage = claudeStreamHandler(c, resp, info, a.RequestMode)
 	} else {
 		err, usage = claudeHandler(a.RequestMode, c, resp, info.PromptTokens, info.UpstreamModelName)
 	}

relay/channel/claude/constants.go

@@ -8,6 +8,7 @@ var ModelList = []string{
 	"claude-3-sonnet-20240229",
 	"claude-3-opus-20240229",
 	"claude-3-haiku-20240307",
+	"claude-3-5-sonnet-20240620",
 }
 
 var ChannelName = "claude"

relay/channel/claude/dto.go

@@ -28,8 +28,8 @@ type ClaudeRequest struct {
 	Prompt            string          `json:"prompt,omitempty"`
 	System            string          `json:"system,omitempty"`
 	Messages          []ClaudeMessage `json:"messages,omitempty"`
-	MaxTokensToSample uint            `json:"max_tokens_to_sample,omitempty"`
 	MaxTokens         uint            `json:"max_tokens,omitempty"`
+	MaxTokensToSample uint            `json:"max_tokens_to_sample,omitempty"`
 	StopSequences     []string        `json:"stop_sequences,omitempty"`
 	Temperature       float64         `json:"temperature,omitempty"`
 	TopP              float64         `json:"top_p,omitempty"`

relay/channel/claude/relay-claude.go

@@ -8,9 +8,12 @@ import (
 	"io"
 	"net/http"
 	"one-api/common"
+	"one-api/constant"
 	"one-api/dto"
+	relaycommon "one-api/relay/common"
 	"one-api/service"
 	"strings"
+	"time"
 )
 
 func stopReasonClaude2OpenAI(reason string) string {
@@ -20,25 +23,24 @@ func stopReasonClaude2OpenAI(reason string) string {
 	case "end_turn":
 		return "stop"
 	case "max_tokens":
-		return "length"
+		return "max_tokens"
 	default:
 		return reason
 	}
 }
 
-func requestOpenAI2ClaudeComplete(textRequest dto.GeneralOpenAIRequest) *ClaudeRequest {
+func RequestOpenAI2ClaudeComplete(textRequest dto.GeneralOpenAIRequest) *ClaudeRequest {
 	claudeRequest := ClaudeRequest{
-		Model:             textRequest.Model,
-		Prompt:            "",
-		MaxTokensToSample: textRequest.MaxTokens,
-		StopSequences:     nil,
-		Temperature:       textRequest.Temperature,
-		TopP:              textRequest.TopP,
-		TopK:              textRequest.TopK,
-		Stream:            textRequest.Stream,
+		Model:         textRequest.Model,
+		Prompt:        "",
+		StopSequences: nil,
+		Temperature:   textRequest.Temperature,
+		TopP:          textRequest.TopP,
+		TopK:          textRequest.TopK,
+		Stream:        textRequest.Stream,
 	}
 	if claudeRequest.MaxTokensToSample == 0 {
-		claudeRequest.MaxTokensToSample = 1000000
+		claudeRequest.MaxTokensToSample = 4096
 	}
 	prompt := ""
 	for _, message := range textRequest.Messages {
@@ -57,7 +59,7 @@ func requestOpenAI2ClaudeComplete(textRequest dto.GeneralOpenAIRequest) *ClaudeR
 	return &claudeRequest
 }
 
-func requestOpenAI2ClaudeMessage(textRequest dto.GeneralOpenAIRequest) (*ClaudeRequest, error) {
+func RequestOpenAI2ClaudeMessage(textRequest dto.GeneralOpenAIRequest) (*ClaudeRequest, error) {
 	claudeRequest := ClaudeRequest{
 		Model:         textRequest.Model,
 		MaxTokens:     textRequest.MaxTokens,
@@ -70,10 +72,52 @@ func requestOpenAI2ClaudeMessage(textRequest dto.GeneralOpenAIRequest) (*ClaudeR
 	if claudeRequest.MaxTokens == 0 {
 		claudeRequest.MaxTokens = 4096
 	}
+	formatMessages := make([]dto.Message, 0)
+	var lastMessage *dto.Message
+	for i, message := range textRequest.Messages {
+		//if message.Role == "system" {
+		//	if i != 0 {
+		//		message.Role = "user"
+		//	}
+		//}
+		if message.Role == "" {
+			textRequest.Messages[i].Role = "user"
+		}
+		fmtMessage := dto.Message{
+			Role:    message.Role,
+			Content: message.Content,
+		}
+		if lastMessage != nil && lastMessage.Role == message.Role {
+			if lastMessage.IsStringContent() && message.IsStringContent() {
+				content, _ := json.Marshal(strings.Trim(fmt.Sprintf("%s %s", lastMessage.StringContent(), message.StringContent()), "\""))
+				fmtMessage.Content = content
+				// delete last message
+				formatMessages = formatMessages[:len(formatMessages)-1]
+			}
+		}
+		if fmtMessage.Content == nil {
+			content, _ := json.Marshal("...")
+			fmtMessage.Content = content
+		}
+		formatMessages = append(formatMessages, fmtMessage)
+		lastMessage = &textRequest.Messages[i]
+	}
+
 	claudeMessages := make([]ClaudeMessage, 0)
-	for _, message := range textRequest.Messages {
+	for _, message := range formatMessages {
 		if message.Role == "system" {
-			claudeRequest.System = message.StringContent()
+			if message.IsStringContent() {
+				claudeRequest.System = message.StringContent()
+			} else {
+				contents := message.ParseContent()
+				content := ""
+				for _, ctx := range contents {
+					if ctx.Type == "text" {
+						content += ctx.Text
+					}
+				}
+				claudeRequest.System = content
+			}
 		} else {
 			claudeMessage := ClaudeMessage{
 				Role: message.Role,
@@ -97,11 +141,11 @@ func requestOpenAI2ClaudeMessage(textRequest dto.GeneralOpenAIRequest) (*ClaudeR
 						// 判断是否是url
 						if strings.HasPrefix(imageUrl.Url, "http") {
 							// 是url，获取图片的类型和base64编码的数据
-							mimeType, data, _ := common.GetImageFromUrl(imageUrl.Url)
+							mimeType, data, _ := service.GetImageFromUrl(imageUrl.Url)
 							claudeMediaMessage.Source.MediaType = mimeType
 							claudeMediaMessage.Source.Data = data
 						} else {
-							_, format, base64String, err := common.DecodeBase64ImageData(imageUrl.Url)
+							_, format, base64String, err := service.DecodeBase64ImageData(imageUrl.Url)
 							if err != nil {
 								return nil, err
 							}
@@ -118,11 +162,10 @@ func requestOpenAI2ClaudeMessage(textRequest dto.GeneralOpenAIRequest) (*ClaudeR
 	}
 	claudeRequest.Prompt = ""
 	claudeRequest.Messages = claudeMessages
-
 	return &claudeRequest, nil
 }
 
-func streamResponseClaude2OpenAI(reqMode int, claudeResponse *ClaudeResponse) (*dto.ChatCompletionsStreamResponse, *ClaudeUsage) {
+func StreamResponseClaude2OpenAI(reqMode int, claudeResponse *ClaudeResponse) (*dto.ChatCompletionsStreamResponse, *ClaudeUsage) {
 	var response dto.ChatCompletionsStreamResponse
 	var claudeUsage *ClaudeUsage
 	response.Object = "chat.completion.chunk"
@@ -130,7 +173,7 @@ func streamResponseClaude2OpenAI(reqMode int, claudeResponse *ClaudeResponse) (*
 	response.Choices = make([]dto.ChatCompletionsStreamResponseChoice, 0)
 	var choice dto.ChatCompletionsStreamResponseChoice
 	if reqMode == RequestModeCompletion {
-		choice.Delta.Content = claudeResponse.Completion
+		choice.Delta.SetContentString(claudeResponse.Completion)
 		finishReason := stopReasonClaude2OpenAI(claudeResponse.StopReason)
 		if finishReason != "null" {
 			choice.FinishReason = &finishReason
@@ -140,25 +183,34 @@ func streamResponseClaude2OpenAI(reqMode int, claudeResponse *ClaudeResponse) (*
 			response.Id = claudeResponse.Message.Id
 			response.Model = claudeResponse.Message.Model
 			claudeUsage = &claudeResponse.Message.Usage
+			choice.Delta.SetContentString("")
+			choice.Delta.Role = "assistant"
+		} else if claudeResponse.Type == "content_block_start" {
+			return nil, nil
 		} else if claudeResponse.Type == "content_block_delta" {
 			choice.Index = claudeResponse.Index
-			choice.Delta.Content = claudeResponse.Delta.Text
+			choice.Delta.SetContentString(claudeResponse.Delta.Text)
 		} else if claudeResponse.Type == "message_delta" {
 			finishReason := stopReasonClaude2OpenAI(*claudeResponse.Delta.StopReason)
 			if finishReason != "null" {
 				choice.FinishReason = &finishReason
 			}
 			claudeUsage = &claudeResponse.Usage
+		} else if claudeResponse.Type == "message_stop" {
+			return nil, nil
+		} else {
+			return nil, nil
 		}
 	}
 	if claudeUsage == nil {
 		claudeUsage = &ClaudeUsage{}
 	}
 	response.Choices = append(response.Choices, choice)
+
 	return &response, claudeUsage
 }
 
-func responseClaude2OpenAI(reqMode int, claudeResponse *ClaudeResponse) *dto.OpenAITextResponse {
+func ResponseClaude2OpenAI(reqMode int, claudeResponse *ClaudeResponse) *dto.OpenAITextResponse {
 	choices := make([]dto.OpenAITextResponseChoice, 0)
 	fullTextResponse := dto.OpenAITextResponse{
 		Id:      fmt.Sprintf("chatcmpl-%s", common.GetUUID()),
@@ -197,7 +249,7 @@ func responseClaude2OpenAI(reqMode int, claudeResponse *ClaudeResponse) *dto.Ope
 	return &fullTextResponse
 }
 
-func claudeStreamHandler(requestMode int, modelName string, promptTokens int, c *gin.Context, resp *http.Response) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
+func claudeStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo, requestMode int) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
 	responseId := fmt.Sprintf("chatcmpl-%s", common.GetUUID())
 	var usage *dto.Usage
 	usage = &dto.Usage{}
@@ -216,8 +268,8 @@ func claudeStreamHandler(requestMode int, modelName string, promptTokens int, c
 		}
 		return 0, nil, nil
 	})
-	dataChan := make(chan string)
-	stopChan := make(chan bool)
+	dataChan := make(chan string, 5)
+	stopChan := make(chan bool, 2)
 	go func() {
 		for scanner.Scan() {
 			data := scanner.Text()
@@ -225,14 +277,23 @@ func claudeStreamHandler(requestMode int, modelName string, promptTokens int, c
 				continue
 			}
 			data = strings.TrimPrefix(data, "data: ")
-			dataChan <- data
+			if !common.SafeSendStringTimeout(dataChan, data, constant.StreamingTimeout) {
+				// send data timeout, stop the stream
+				common.LogError(c, "send data timeout, stop the stream")
+				break
+			}
 		}
 		stopChan <- true
 	}()
+	isFirst := true
 	service.SetEventStreamHeaders(c)
 	c.Stream(func(w io.Writer) bool {
 		select {
 		case data := <-dataChan:
+			if isFirst {
+				isFirst = false
+				info.FirstResponseTime = time.Now()
+			}
 			// some implementations may add \r at the end of data
 			data = strings.TrimSuffix(data, "\r")
 			var claudeResponse ClaudeResponse
@@ -242,7 +303,10 @@ func claudeStreamHandler(requestMode int, modelName string, promptTokens int, c
 				return true
 			}
 
-			response, claudeUsage := streamResponseClaude2OpenAI(requestMode, &claudeResponse)
+			response, claudeUsage := StreamResponseClaude2OpenAI(requestMode, &claudeResponse)
+			if response == nil {
+				return true
+			}
 			if requestMode == RequestModeCompletion {
 				responseText += claudeResponse.Completion
 				responseId = response.Id
@@ -250,7 +314,7 @@ func claudeStreamHandler(requestMode int, modelName string, promptTokens int, c
 				if claudeResponse.Type == "message_start" {
 					// message_start, 获取usage
 					responseId = claudeResponse.Message.Id
-					modelName = claudeResponse.Message.Model
+					info.UpstreamModelName = claudeResponse.Message.Model
 					usage.PromptTokens = claudeUsage.InputTokens
 				} else if claudeResponse.Type == "content_block_delta" {
 					responseText += claudeResponse.Delta.Text
@@ -264,7 +328,7 @@ func claudeStreamHandler(requestMode int, modelName string, promptTokens int, c
 			//response.Id = responseId
 			response.Id = responseId
 			response.Created = createdTime
-			response.Model = modelName
+			response.Model = info.UpstreamModelName
 
 			jsonStr, err := json.Marshal(response)
 			if err != nil {
@@ -283,10 +347,13 @@ func claudeStreamHandler(requestMode int, modelName string, promptTokens int, c
 		return service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
 	}
 	if requestMode == RequestModeCompletion {
-		usage, _ = service.ResponseText2Usage(responseText, modelName, promptTokens)
+		usage, _ = service.ResponseText2Usage(responseText, info.UpstreamModelName, info.PromptTokens)
 	} else {
+		if usage.PromptTokens == 0 {
+			usage.PromptTokens = info.PromptTokens
+		}
 		if usage.CompletionTokens == 0 {
-			usage, _ = service.ResponseText2Usage(responseText, modelName, usage.PromptTokens)
+			usage, _ = service.ResponseText2Usage(responseText, info.UpstreamModelName, usage.PromptTokens)
 		}
 	}
 	return nil, usage
@@ -317,8 +384,8 @@ func claudeHandler(requestMode int, c *gin.Context, resp *http.Response, promptT
 			StatusCode: resp.StatusCode,
 		}, nil
 	}
-	fullTextResponse := responseClaude2OpenAI(requestMode, &claudeResponse)
-	completionTokens, err, _ := service.CountTokenText(claudeResponse.Completion, model, false)
+	fullTextResponse := ResponseClaude2OpenAI(requestMode, &claudeResponse)
+	completionTokens, err := service.CountTokenText(claudeResponse.Completion, model)
 	if err != nil {
 		return service.OpenAIErrorWrapper(err, "count_token_text_failed", http.StatusInternalServerError), nil
 	}

relay/channel/cohere/adaptor.go

@@ -0,0 +1,68 @@
+package cohere
+
+import (
+	"fmt"
+	"github.com/gin-gonic/gin"
+	"io"
+	"net/http"
+	"one-api/dto"
+	"one-api/relay/channel"
+	relaycommon "one-api/relay/common"
+	"one-api/relay/constant"
+)
+
+type Adaptor struct {
+}
+
+func (a *Adaptor) InitRerank(info *relaycommon.RelayInfo, request dto.RerankRequest) {
+}
+
+func (a *Adaptor) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
+}
+
+func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
+	if info.RelayMode == constant.RelayModeRerank {
+		return fmt.Sprintf("%s/v1/rerank", info.BaseUrl), nil
+	} else {
+		return fmt.Sprintf("%s/v1/chat", info.BaseUrl), nil
+	}
+}
+
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
+	channel.SetupApiRequestHeader(info, c, req)
+	req.Header.Set("Authorization", fmt.Sprintf("Bearer %s", info.ApiKey))
+	return nil
+}
+
+func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *dto.GeneralOpenAIRequest) (any, error) {
+	return requestOpenAI2Cohere(*request), nil
+}
+
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+	return channel.DoApiRequest(a, c, info, requestBody)
+}
+
+func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dto.RerankRequest) (any, error) {
+	return requestConvertRerank2Cohere(request), nil
+}
+
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
+	if info.RelayMode == constant.RelayModeRerank {
+		err, usage = cohereRerankHandler(c, resp, info)
+	} else {
+		if info.IsStream {
+			err, usage = cohereStreamHandler(c, resp, info)
+		} else {
+			err, usage = cohereHandler(c, resp, info.UpstreamModelName, info.PromptTokens)
+		}
+	}
+	return
+}
+
+func (a *Adaptor) GetModelList() []string {
+	return ModelList
+}
+
+func (a *Adaptor) GetChannelName() string {
+	return ChannelName
+}

relay/channel/cohere/constant.go

@@ -0,0 +1,8 @@
+package cohere
+
+var ModelList = []string{
+	"command-r", "command-r-plus", "command-light", "command-light-nightly", "command", "command-nightly",
+	"rerank-english-v3.0", "rerank-multilingual-v3.0", "rerank-english-v2.0", "rerank-multilingual-v2.0",
+}
+
+var ChannelName = "cohere"

relay/channel/cohere/dto.go

@@ -0,0 +1,59 @@
+package cohere
+
+import "one-api/dto"
+
+type CohereRequest struct {
+	Model       string        `json:"model"`
+	ChatHistory []ChatHistory `json:"chat_history"`
+	Message     string        `json:"message"`
+	Stream      bool          `json:"stream"`
+	MaxTokens   int64         `json:"max_tokens"`
+}
+
+type ChatHistory struct {
+	Role    string `json:"role"`
+	Message string `json:"message"`
+}
+
+type CohereResponse struct {
+	IsFinished   bool                  `json:"is_finished"`
+	EventType    string                `json:"event_type"`
+	Text         string                `json:"text,omitempty"`
+	FinishReason string                `json:"finish_reason,omitempty"`
+	Response     *CohereResponseResult `json:"response"`
+}
+
+type CohereResponseResult struct {
+	ResponseId   string     `json:"response_id"`
+	FinishReason string     `json:"finish_reason,omitempty"`
+	Text         string     `json:"text"`
+	Meta         CohereMeta `json:"meta"`
+}
+
+type CohereRerankRequest struct {
+	Documents       []any  `json:"documents"`
+	Query           string `json:"query"`
+	Model           string `json:"model"`
+	TopN            int    `json:"top_n"`
+	ReturnDocuments bool   `json:"return_documents"`
+}
+
+type CohereRerankResponseResult struct {
+	Results []dto.RerankResponseDocument `json:"results"`
+	Meta    CohereMeta                   `json:"meta"`
+}
+
+type CohereMeta struct {
+	//Tokens CohereTokens `json:"tokens"`
+	BilledUnits CohereBilledUnits `json:"billed_units"`
+}
+
+type CohereBilledUnits struct {
+	InputTokens  int `json:"input_tokens"`
+	OutputTokens int `json:"output_tokens"`
+}
+
+type CohereTokens struct {
+	InputTokens  int `json:"input_tokens"`
+	OutputTokens int `json:"output_tokens"`
+}

relay/channel/cohere/relay-cohere.go

@@ -0,0 +1,249 @@
+package cohere
+
+import (
+	"bufio"
+	"encoding/json"
+	"fmt"
+	"github.com/gin-gonic/gin"
+	"io"
+	"net/http"
+	"one-api/common"
+	"one-api/dto"
+	relaycommon "one-api/relay/common"
+	"one-api/service"
+	"strings"
+	"time"
+)
+
+func requestOpenAI2Cohere(textRequest dto.GeneralOpenAIRequest) *CohereRequest {
+	cohereReq := CohereRequest{
+		Model:       textRequest.Model,
+		ChatHistory: []ChatHistory{},
+		Message:     "",
+		Stream:      textRequest.Stream,
+		MaxTokens:   textRequest.GetMaxTokens(),
+	}
+	if cohereReq.MaxTokens == 0 {
+		cohereReq.MaxTokens = 4000
+	}
+	for _, msg := range textRequest.Messages {
+		if msg.Role == "user" {
+			cohereReq.Message = msg.StringContent()
+		} else {
+			var role string
+			if msg.Role == "assistant" {
+				role = "CHATBOT"
+			} else if msg.Role == "system" {
+				role = "SYSTEM"
+			} else {
+				role = "USER"
+			}
+			cohereReq.ChatHistory = append(cohereReq.ChatHistory, ChatHistory{
+				Role:    role,
+				Message: msg.StringContent(),
+			})
+		}
+	}
+	return &cohereReq
+}
+
+func requestConvertRerank2Cohere(rerankRequest dto.RerankRequest) *CohereRerankRequest {
+	if rerankRequest.TopN == 0 {
+		rerankRequest.TopN = 1
+	}
+	cohereReq := CohereRerankRequest{
+		Query:           rerankRequest.Query,
+		Documents:       rerankRequest.Documents,
+		Model:           rerankRequest.Model,
+		TopN:            rerankRequest.TopN,
+		ReturnDocuments: true,
+	}
+	return &cohereReq
+}
+
+func stopReasonCohere2OpenAI(reason string) string {
+	switch reason {
+	case "COMPLETE":
+		return "stop"
+	case "MAX_TOKENS":
+		return "max_tokens"
+	default:
+		return reason
+	}
+}
+
+func cohereStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
+	responseId := fmt.Sprintf("chatcmpl-%s", common.GetUUID())
+	createdTime := common.GetTimestamp()
+	usage := &dto.Usage{}
+	responseText := ""
+	scanner := bufio.NewScanner(resp.Body)
+	scanner.Split(func(data []byte, atEOF bool) (advance int, token []byte, err error) {
+		if atEOF && len(data) == 0 {
+			return 0, nil, nil
+		}
+		if i := strings.Index(string(data), "\n"); i >= 0 {
+			return i + 1, data[0:i], nil
+		}
+		if atEOF {
+			return len(data), data, nil
+		}
+		return 0, nil, nil
+	})
+	dataChan := make(chan string)
+	stopChan := make(chan bool)
+	go func() {
+		for scanner.Scan() {
+			data := scanner.Text()
+			dataChan <- data
+		}
+		stopChan <- true
+	}()
+	service.SetEventStreamHeaders(c)
+	isFirst := true
+	c.Stream(func(w io.Writer) bool {
+		select {
+		case data := <-dataChan:
+			if isFirst {
+				isFirst = false
+				info.FirstResponseTime = time.Now()
+			}
+			data = strings.TrimSuffix(data, "\r")
+			var cohereResp CohereResponse
+			err := json.Unmarshal([]byte(data), &cohereResp)
+			if err != nil {
+				common.SysError("error unmarshalling stream response: " + err.Error())
+				return true
+			}
+			var openaiResp dto.ChatCompletionsStreamResponse
+			openaiResp.Id = responseId
+			openaiResp.Created = createdTime
+			openaiResp.Object = "chat.completion.chunk"
+			openaiResp.Model = info.UpstreamModelName
+			if cohereResp.IsFinished {
+				finishReason := stopReasonCohere2OpenAI(cohereResp.FinishReason)
+				openaiResp.Choices = []dto.ChatCompletionsStreamResponseChoice{
+					{
+						Delta:        dto.ChatCompletionsStreamResponseChoiceDelta{},
+						Index:        0,
+						FinishReason: &finishReason,
+					},
+				}
+				if cohereResp.Response != nil {
+					usage.PromptTokens = cohereResp.Response.Meta.BilledUnits.InputTokens
+					usage.CompletionTokens = cohereResp.Response.Meta.BilledUnits.OutputTokens
+				}
+			} else {
+				openaiResp.Choices = []dto.ChatCompletionsStreamResponseChoice{
+					{
+						Delta: dto.ChatCompletionsStreamResponseChoiceDelta{
+							Role:    "assistant",
+							Content: &cohereResp.Text,
+						},
+						Index: 0,
+					},
+				}
+				responseText += cohereResp.Text
+			}
+			jsonStr, err := json.Marshal(openaiResp)
+			if err != nil {
+				common.SysError("error marshalling stream response: " + err.Error())
+				return true
+			}
+			c.Render(-1, common.CustomEvent{Data: "data: " + string(jsonStr)})
+			return true
+		case <-stopChan:
+			c.Render(-1, common.CustomEvent{Data: "data: [DONE]"})
+			return false
+		}
+	})
+	if usage.PromptTokens == 0 {
+		usage, _ = service.ResponseText2Usage(responseText, info.UpstreamModelName, info.PromptTokens)
+	}
+	return nil, usage
+}
+
+func cohereHandler(c *gin.Context, resp *http.Response, modelName string, promptTokens int) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
+	createdTime := common.GetTimestamp()
+	responseBody, err := io.ReadAll(resp.Body)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
+	}
+	err = resp.Body.Close()
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
+	}
+	var cohereResp CohereResponseResult
+	err = json.Unmarshal(responseBody, &cohereResp)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
+	}
+	usage := dto.Usage{}
+	usage.PromptTokens = cohereResp.Meta.BilledUnits.InputTokens
+	usage.CompletionTokens = cohereResp.Meta.BilledUnits.OutputTokens
+	usage.TotalTokens = cohereResp.Meta.BilledUnits.InputTokens + cohereResp.Meta.BilledUnits.OutputTokens
+
+	var openaiResp dto.TextResponse
+	openaiResp.Id = cohereResp.ResponseId
+	openaiResp.Created = createdTime
+	openaiResp.Object = "chat.completion"
+	openaiResp.Model = modelName
+	openaiResp.Usage = usage
+
+	content, _ := json.Marshal(cohereResp.Text)
+	openaiResp.Choices = []dto.OpenAITextResponseChoice{
+		{
+			Index:        0,
+			Message:      dto.Message{Content: content, Role: "assistant"},
+			FinishReason: stopReasonCohere2OpenAI(cohereResp.FinishReason),
+		},
+	}
+
+	jsonResponse, err := json.Marshal(openaiResp)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil
+	}
+	c.Writer.Header().Set("Content-Type", "application/json")
+	c.Writer.WriteHeader(resp.StatusCode)
+	_, err = c.Writer.Write(jsonResponse)
+	return nil, &usage
+}
+
+func cohereRerankHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
+	responseBody, err := io.ReadAll(resp.Body)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
+	}
+	err = resp.Body.Close()
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
+	}
+	var cohereResp CohereRerankResponseResult
+	err = json.Unmarshal(responseBody, &cohereResp)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
+	}
+	usage := dto.Usage{}
+	if cohereResp.Meta.BilledUnits.InputTokens == 0 {
+		usage.PromptTokens = info.PromptTokens
+		usage.CompletionTokens = 0
+		usage.TotalTokens = info.PromptTokens
+	} else {
+		usage.PromptTokens = cohereResp.Meta.BilledUnits.InputTokens
+		usage.CompletionTokens = cohereResp.Meta.BilledUnits.OutputTokens
+		usage.TotalTokens = cohereResp.Meta.BilledUnits.InputTokens + cohereResp.Meta.BilledUnits.OutputTokens
+	}
+
+	var rerankResp dto.RerankResponse
+	rerankResp.Results = cohereResp.Results
+	rerankResp.Usage = usage
+
+	jsonResponse, err := json.Marshal(rerankResp)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil
+	}
+	c.Writer.Header().Set("Content-Type", "application/json")
+	c.Writer.WriteHeader(resp.StatusCode)
+	_, err = c.Writer.Write(jsonResponse)
+	return nil, &usage
+}

relay/channel/dify/adaptor.go

@@ -0,0 +1,65 @@
+package dify
+
+import (
+	"errors"
+	"fmt"
+	"github.com/gin-gonic/gin"
+	"io"
+	"net/http"
+	"one-api/dto"
+	"one-api/relay/channel"
+	relaycommon "one-api/relay/common"
+)
+
+type Adaptor struct {
+}
+
+func (a *Adaptor) InitRerank(info *relaycommon.RelayInfo, request dto.RerankRequest) {
+	//TODO implement me
+
+}
+
+func (a *Adaptor) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
+}
+
+func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
+	return fmt.Sprintf("%s/v1/chat-messages", info.BaseUrl), nil
+}
+
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
+	channel.SetupApiRequestHeader(info, c, req)
+	req.Header.Set("Authorization", "Bearer "+info.ApiKey)
+	return nil
+}
+
+func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *dto.GeneralOpenAIRequest) (any, error) {
+	if request == nil {
+		return nil, errors.New("request is nil")
+	}
+	return requestOpenAI2Dify(*request), nil
+}
+
+func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dto.RerankRequest) (any, error) {
+	return nil, nil
+}
+
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+	return channel.DoApiRequest(a, c, info, requestBody)
+}
+
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
+	if info.IsStream {
+		err, usage = difyStreamHandler(c, resp, info)
+	} else {
+		err, usage = difyHandler(c, resp, info)
+	}
+	return
+}
+
+func (a *Adaptor) GetModelList() []string {
+	return ModelList
+}
+
+func (a *Adaptor) GetChannelName() string {
+	return ChannelName
+}

relay/channel/dify/constants.go

@@ -0,0 +1,5 @@
+package dify
+
+var ModelList []string
+
+var ChannelName = "dify"

relay/channel/dify/dto.go

@@ -0,0 +1,35 @@
+package dify
+
+import "one-api/dto"
+
+type DifyChatRequest struct {
+	Inputs           map[string]interface{} `json:"inputs"`
+	Query            string                 `json:"query"`
+	ResponseMode     string                 `json:"response_mode"`
+	User             string                 `json:"user"`
+	AutoGenerateName bool                   `json:"auto_generate_name"`
+}
+
+type DifyMetaData struct {
+	Usage dto.Usage `json:"usage"`
+}
+
+type DifyData struct {
+	WorkflowId string `json:"workflow_id"`
+	NodeId     string `json:"node_id"`
+}
+
+type DifyChatCompletionResponse struct {
+	ConversationId string       `json:"conversation_id"`
+	Answers        string       `json:"answers"`
+	CreateAt       int64        `json:"create_at"`
+	MetaData       DifyMetaData `json:"metadata"`
+}
+
+type DifyChunkChatCompletionResponse struct {
+	Event          string       `json:"event"`
+	ConversationId string       `json:"conversation_id"`
+	Answer         string       `json:"answer"`
+	Data           DifyData     `json:"data"`
+	MetaData       DifyMetaData `json:"metadata"`
+}

relay/channel/dify/relay-dify.go

@@ -0,0 +1,154 @@
+package dify
+
+import (
+	"bufio"
+	"encoding/json"
+	"github.com/gin-gonic/gin"
+	"io"
+	"net/http"
+	"one-api/common"
+	"one-api/dto"
+	relaycommon "one-api/relay/common"
+	"one-api/service"
+	"strings"
+)
+
+func requestOpenAI2Dify(request dto.GeneralOpenAIRequest) *DifyChatRequest {
+	content := ""
+	for _, message := range request.Messages {
+		if message.Role == "system" {
+			content += "SYSTEM: \n" + message.StringContent() + "\n"
+		} else if message.Role == "assistant" {
+			content += "ASSISTANT: \n" + message.StringContent() + "\n"
+		} else {
+			content += "USER: \n" + message.StringContent() + "\n"
+		}
+	}
+	mode := "blocking"
+	if request.Stream {
+		mode = "streaming"
+	}
+	user := request.User
+	if user == "" {
+		user = "api-user"
+	}
+	return &DifyChatRequest{
+		Inputs:           make(map[string]interface{}),
+		Query:            content,
+		ResponseMode:     mode,
+		User:             user,
+		AutoGenerateName: false,
+	}
+}
+
+func streamResponseDify2OpenAI(difyResponse DifyChunkChatCompletionResponse) *dto.ChatCompletionsStreamResponse {
+	response := dto.ChatCompletionsStreamResponse{
+		Object:  "chat.completion.chunk",
+		Created: common.GetTimestamp(),
+		Model:   "dify",
+	}
+	var choice dto.ChatCompletionsStreamResponseChoice
+	if difyResponse.Event == "workflow_started" {
+		choice.Delta.SetContentString("Workflow: " + difyResponse.Data.WorkflowId + "\n")
+	} else if difyResponse.Event == "node_started" {
+		choice.Delta.SetContentString("Node: " + difyResponse.Data.NodeId + "\n")
+	} else if difyResponse.Event == "message" {
+		choice.Delta.SetContentString(difyResponse.Answer)
+	}
+	response.Choices = append(response.Choices, choice)
+	return &response
+}
+
+func difyStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
+	var responseText string
+	usage := &dto.Usage{}
+	scanner := bufio.NewScanner(resp.Body)
+	scanner.Split(bufio.ScanLines)
+
+	service.SetEventStreamHeaders(c)
+
+	for scanner.Scan() {
+		data := scanner.Text()
+		if len(data) < 5 || !strings.HasPrefix(data, "data:") {
+			continue
+		}
+		data = strings.TrimPrefix(data, "data:")
+		var difyResponse DifyChunkChatCompletionResponse
+		err := json.Unmarshal([]byte(data), &difyResponse)
+		if err != nil {
+			common.SysError("error unmarshalling stream response: " + err.Error())
+			continue
+		}
+		var openaiResponse dto.ChatCompletionsStreamResponse
+		if difyResponse.Event == "message_end" {
+			usage = &difyResponse.MetaData.Usage
+			break
+		} else if difyResponse.Event == "error" {
+			break
+		} else {
+			openaiResponse = *streamResponseDify2OpenAI(difyResponse)
+			if len(openaiResponse.Choices) != 0 {
+				responseText += openaiResponse.Choices[0].Delta.GetContentString()
+			}
+		}
+		err = service.ObjectData(c, openaiResponse)
+		if err != nil {
+			common.SysError(err.Error())
+		}
+	}
+	if err := scanner.Err(); err != nil {
+		common.SysError("error reading stream: " + err.Error())
+	}
+	service.Done(c)
+	err := resp.Body.Close()
+	if err != nil {
+		//return service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
+		common.SysError("close_response_body_failed: " + err.Error())
+	}
+	if usage.TotalTokens == 0 {
+		usage.PromptTokens = info.PromptTokens
+		usage.CompletionTokens, _ = service.CountTokenText("gpt-3.5-turbo", responseText)
+		usage.TotalTokens = usage.PromptTokens + usage.CompletionTokens
+	}
+	return nil, usage
+}
+
+func difyHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
+	var difyResponse DifyChatCompletionResponse
+	responseBody, err := io.ReadAll(resp.Body)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
+	}
+	err = resp.Body.Close()
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
+	}
+	err = json.Unmarshal(responseBody, &difyResponse)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
+	}
+	fullTextResponse := dto.OpenAITextResponse{
+		Id:      difyResponse.ConversationId,
+		Object:  "chat.completion",
+		Created: common.GetTimestamp(),
+		Usage:   difyResponse.MetaData.Usage,
+	}
+	content, _ := json.Marshal(difyResponse.Answers)
+	choice := dto.OpenAITextResponseChoice{
+		Index: 0,
+		Message: dto.Message{
+			Role:    "assistant",
+			Content: content,
+		},
+		FinishReason: "stop",
+	}
+	fullTextResponse.Choices = append(fullTextResponse.Choices, choice)
+	jsonResponse, err := json.Marshal(fullTextResponse)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil
+	}
+	c.Writer.Header().Set("Content-Type", "application/json")
+	c.Writer.WriteHeader(resp.StatusCode)
+	_, err = c.Writer.Write(jsonResponse)
+	return nil, &difyResponse.MetaData.Usage
+}

relay/channel/gemini/adaptor.go

@@ -15,14 +15,30 @@ import (
 type Adaptor struct {
 }
 
+func (a *Adaptor) InitRerank(info *relaycommon.RelayInfo, request dto.RerankRequest) {
+}
+
 func (a *Adaptor) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
 }
 
+// 定义一个映射，存储模型名称和对应的版本
+var modelVersionMap = map[string]string{
+	"gemini-1.5-pro-latest":   "v1beta",
+	"gemini-1.5-flash-latest": "v1beta",
+	"gemini-ultra":            "v1beta",
+}
+
 func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
-	version := "v1"
-	if info.ApiVersion != "" {
-		version = info.ApiVersion
+	// 从映射中获取模型名称对应的版本，如果找不到就使用 info.ApiVersion 或默认的版本 "v1"
+	version, beta := modelVersionMap[info.UpstreamModelName]
+	if !beta {
+		if info.ApiVersion != "" {
+			version = info.ApiVersion
+		} else {
+			version = "v1"
+		}
 	}
+
 	action := "generateContent"
 	if info.IsStream {
 		action = "streamGenerateContent"
@@ -43,6 +59,10 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *dto.Gen
 	return CovertGemini2OpenAI(*request), nil
 }
 
+func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dto.RerankRequest) (any, error) {
+	return nil, nil
+}
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }
@@ -50,7 +70,7 @@ func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, request
 func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
 	if info.IsStream {
 		var responseText string
-		err, responseText = geminiChatStreamHandler(c, resp)
+		err, responseText = geminiChatStreamHandler(c, resp, info)
 		usage, _ = service.ResponseText2Usage(responseText, info.UpstreamModelName, info.PromptTokens)
 	} else {
 		err, usage = geminiChatHandler(c, resp, info.PromptTokens, info.UpstreamModelName)

relay/channel/gemini/constant.go

@@ -5,8 +5,8 @@ const (
 )
 
 var ModelList = []string{
-	"gemini-pro", "gemini-1.0-pro-001", "gemini-1.5-pro",
-	"gemini-pro-vision", "gemini-1.0-pro-vision-001",
+	"gemini-1.0-pro-latest", "gemini-1.0-pro-001", "gemini-1.5-pro-latest", "gemini-1.5-flash-latest", "gemini-ultra",
+	"gemini-1.0-pro-vision-latest", "gemini-1.0-pro-vision-001",
 }
 
 var ChannelName = "google gemini"

relay/channel/gemini/relay-gemini.go

@@ -7,10 +7,12 @@ import (
 	"io"
 	"net/http"
 	"one-api/common"
+	"one-api/constant"
 	"one-api/dto"
 	relaycommon "one-api/relay/common"
 	"one-api/service"
 	"strings"
+	"time"
 
 	"github.com/gin-gonic/gin"
 )
@@ -74,7 +76,7 @@ func CovertGemini2OpenAI(textRequest dto.GeneralOpenAIRequest) *GeminiChatReques
 				if imageNum > GeminiVisionMaxImageNum {
 					continue
 				}
-				mimeType, data, _ := common.GetImageFromUrl(part.ImageUrl.(dto.MessageImageUrl).Url)
+				mimeType, data, _ := service.GetImageFromUrl(part.ImageUrl.(dto.MessageImageUrl).Url)
 				parts = append(parts, GeminiPart{
 					InlineData: &GeminiInlineData{
 						MimeType: mimeType,
@@ -151,7 +153,7 @@ func responseGeminiChat2OpenAI(response *GeminiChatResponse) *dto.OpenAITextResp
 
 func streamResponseGeminiChat2OpenAI(geminiResponse *GeminiChatResponse) *dto.ChatCompletionsStreamResponse {
 	var choice dto.ChatCompletionsStreamResponseChoice
-	choice.Delta.Content = geminiResponse.GetResponseText()
+	choice.Delta.SetContentString(geminiResponse.GetResponseText())
 	choice.FinishReason = &relaycommon.StopFinishReason
 	var response dto.ChatCompletionsStreamResponse
 	response.Object = "chat.completion.chunk"
@@ -160,10 +162,10 @@ func streamResponseGeminiChat2OpenAI(geminiResponse *GeminiChatResponse) *dto.Ch
 	return &response
 }
 
-func geminiChatStreamHandler(c *gin.Context, resp *http.Response) (*dto.OpenAIErrorWithStatusCode, string) {
+func geminiChatStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (*dto.OpenAIErrorWithStatusCode, string) {
 	responseText := ""
-	dataChan := make(chan string)
-	stopChan := make(chan bool)
+	dataChan := make(chan string, 5)
+	stopChan := make(chan bool, 2)
 	scanner := bufio.NewScanner(resp.Body)
 	scanner.Split(func(data []byte, atEOF bool) (advance int, token []byte, err error) {
 		if atEOF && len(data) == 0 {
@@ -186,14 +188,23 @@ func geminiChatStreamHandler(c *gin.Context, resp *http.Response) (*dto.OpenAIEr
 			}
 			data = strings.TrimPrefix(data, "\"text\": \"")
 			data = strings.TrimSuffix(data, "\"")
-			dataChan <- data
+			if !common.SafeSendStringTimeout(dataChan, data, constant.StreamingTimeout) {
+				// send data timeout, stop the stream
+				common.LogError(c, "send data timeout, stop the stream")
+				break
+			}
 		}
 		stopChan <- true
 	}()
+	isFirst := true
 	service.SetEventStreamHeaders(c)
 	c.Stream(func(w io.Writer) bool {
 		select {
 		case data := <-dataChan:
+			if isFirst {
+				isFirst = false
+				info.FirstResponseTime = time.Now()
+			}
 			// this is used to prevent annoying \ related format bug
 			data = fmt.Sprintf("{\"content\": \"%s\"}", data)
 			type dummyStruct struct {
@@ -203,7 +214,7 @@ func geminiChatStreamHandler(c *gin.Context, resp *http.Response) (*dto.OpenAIEr
 			err := json.Unmarshal([]byte(data), &dummy)
 			responseText += dummy.Content
 			var choice dto.ChatCompletionsStreamResponseChoice
-			choice.Delta.Content = dummy.Content
+			choice.Delta.SetContentString(dummy.Content)
 			response := dto.ChatCompletionsStreamResponse{
 				Id:      fmt.Sprintf("chatcmpl-%s", common.GetUUID()),
 				Object:  "chat.completion.chunk",
@@ -256,7 +267,7 @@ func geminiChatHandler(c *gin.Context, resp *http.Response, promptTokens int, mo
 		}, nil
 	}
 	fullTextResponse := responseGeminiChat2OpenAI(&geminiResponse)
-	completionTokens, _, _ := service.CountTokenText(geminiResponse.GetResponseText(), model, false)
+	completionTokens, _ := service.CountTokenText(geminiResponse.GetResponseText(), model)
 	usage := dto.Usage{
 		PromptTokens:     promptTokens,
 		CompletionTokens: completionTokens,

relay/channel/jina/adaptor.go

@@ -0,0 +1,64 @@
+package jina
+
+import (
+	"errors"
+	"fmt"
+	"github.com/gin-gonic/gin"
+	"io"
+	"net/http"
+	"one-api/dto"
+	"one-api/relay/channel"
+	relaycommon "one-api/relay/common"
+	"one-api/relay/constant"
+)
+
+type Adaptor struct {
+}
+
+func (a *Adaptor) InitRerank(info *relaycommon.RelayInfo, request dto.RerankRequest) {
+}
+
+func (a *Adaptor) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
+}
+
+func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
+	if info.RelayMode == constant.RelayModeRerank {
+		return fmt.Sprintf("%s/v1/rerank", info.BaseUrl), nil
+	} else if info.RelayMode == constant.RelayModeEmbeddings {
+		return fmt.Sprintf("%s/v1/embeddings ", info.BaseUrl), nil
+	}
+	return "", errors.New("invalid relay mode")
+}
+
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
+	channel.SetupApiRequestHeader(info, c, req)
+	req.Header.Set("Authorization", fmt.Sprintf("Bearer %s", info.ApiKey))
+	return nil
+}
+
+func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *dto.GeneralOpenAIRequest) (any, error) {
+	return request, nil
+}
+
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+	return channel.DoApiRequest(a, c, info, requestBody)
+}
+
+func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dto.RerankRequest) (any, error) {
+	return request, nil
+}
+
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
+	if info.RelayMode == constant.RelayModeRerank {
+		err, usage = jinaRerankHandler(c, resp)
+	}
+	return
+}
+
+func (a *Adaptor) GetModelList() []string {
+	return ModelList
+}
+
+func (a *Adaptor) GetChannelName() string {
+	return ChannelName
+}

relay/channel/jina/constant.go

@@ -0,0 +1,8 @@
+package jina
+
+var ModelList = []string{
+	"jina-clip-v1",
+	"jina-reranker-v2-base-multilingual",
+}
+
+var ChannelName = "jina"

relay/channel/jina/relay-jina.go

@@ -0,0 +1,35 @@
+package jina
+
+import (
+	"encoding/json"
+	"github.com/gin-gonic/gin"
+	"io"
+	"net/http"
+	"one-api/dto"
+	"one-api/service"
+)
+
+func jinaRerankHandler(c *gin.Context, resp *http.Response) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
+	responseBody, err := io.ReadAll(resp.Body)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
+	}
+	err = resp.Body.Close()
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
+	}
+	var jinaResp dto.RerankResponse
+	err = json.Unmarshal(responseBody, &jinaResp)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
+	}
+
+	jsonResponse, err := json.Marshal(jinaResp)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil
+	}
+	c.Writer.Header().Set("Content-Type", "application/json")
+	c.Writer.WriteHeader(resp.StatusCode)
+	_, err = c.Writer.Write(jsonResponse)
+	return nil, &jinaResp.Usage
+}

relay/channel/lingyiwanwu/constrants.go

@@ -1,9 +1,9 @@
-package lingyiwanwu
-
-// https://platform.lingyiwanwu.com/docs
-
-var ModelList = []string{
-	"yi-34b-chat-0205",
-	"yi-34b-chat-200k",
-	"yi-vl-plus",
-}
+package lingyiwanwu
+
+// https://platform.lingyiwanwu.com/docs
+
+var ModelList = []string{
+	"yi-large", "yi-medium", "yi-vision", "yi-medium-200k", "yi-spark", "yi-large-rag", "yi-large-turbo", "yi-large-preview", "yi-large-rag-preview",
+}
+
+var ChannelName = "lingyiwanwu"

relay/channel/minimax/constants.go

@@ -0,0 +1,13 @@
+package minimax
+
+// https://www.minimaxi.com/document/guides/chat-model/V2?id=65e0736ab2845de20908e2dd
+
+var ModelList = []string{
+	"abab6.5-chat",
+	"abab6.5s-chat",
+	"abab6-chat",
+	"abab5.5-chat",
+	"abab5.5s-chat",
+}
+
+var ChannelName = "minimax"

relay/channel/minimax/relay-minimax.go

@@ -0,0 +1,10 @@
+package minimax
+
+import (
+	"fmt"
+	relaycommon "one-api/relay/common"
+)
+
+func GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
+	return fmt.Sprintf("%s/v1/text/chatcompletion_v2", info.BaseUrl), nil
+}

relay/channel/moonshot/constants.go

@@ -5,3 +5,5 @@ var ModelList = []string{
 	"moonshot-v1-32k",
 	"moonshot-v1-128k",
 }
+
+var ChannelName = "moonshot"

relay/channel/ollama/adaptor.go

@@ -16,6 +16,9 @@ import (
 type Adaptor struct {
 }
 
+func (a *Adaptor) InitRerank(info *relaycommon.RelayInfo, request dto.RerankRequest) {
+}
+
 func (a *Adaptor) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
 }
 
@@ -45,6 +48,10 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *dto.Gen
 	}
 }
 
+func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dto.RerankRequest) (any, error) {
+	return nil, nil
+}
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }
@@ -52,7 +59,7 @@ func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, request
 func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
 	if info.IsStream {
 		var responseText string
-		err, responseText = openai.OpenaiStreamHandler(c, resp, info.RelayMode)
+		err, responseText, _ = openai.OpenaiStreamHandler(c, resp, info)
 		usage, _ = service.ResponseText2Usage(responseText, info.UpstreamModelName, info.PromptTokens)
 	} else {
 		if info.RelayMode == relayconstant.RelayModeEmbeddings {

relay/channel/ollama/constants.go

@@ -1,5 +1,7 @@
 package ollama
 
-var ModelList []string
+var ModelList = []string{
+	"llama3-7b",
+}
 
 var ChannelName = "ollama"

relay/channel/ollama/relay-ollama.go

@@ -9,6 +9,7 @@ import (
 	"net/http"
 	"one-api/dto"
 	"one-api/service"
+	"strings"
 )
 
 func requestOpenAI2Ollama(request dto.GeneralOpenAIRequest) *OllamaRequest {
@@ -41,7 +42,7 @@ func requestOpenAI2Ollama(request dto.GeneralOpenAIRequest) *OllamaRequest {
 func requestOpenAI2Embeddings(request dto.GeneralOpenAIRequest) *OllamaEmbeddingRequest {
 	return &OllamaEmbeddingRequest{
 		Model:  request.Model,
-		Prompt: request.Input,
+		Prompt: strings.Join(request.ParseInput(), " "),
 	}
 }
 

relay/channel/openai/adaptor.go

@@ -11,6 +11,7 @@ import (
 	"one-api/relay/channel"
 	"one-api/relay/channel/ai360"
 	"one-api/relay/channel/lingyiwanwu"
+	"one-api/relay/channel/minimax"
 	"one-api/relay/channel/moonshot"
 	relaycommon "one-api/relay/common"
 	"one-api/service"
@@ -21,12 +22,20 @@ type Adaptor struct {
 	ChannelType int
 }
 
+func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dto.RerankRequest) (any, error) {
+	return nil, nil
+}
+
+func (a *Adaptor) InitRerank(info *relaycommon.RelayInfo, request dto.RerankRequest) {
+}
+
 func (a *Adaptor) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
 	a.ChannelType = info.ChannelType
 }
 
 func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
-	if info.ChannelType == common.ChannelTypeAzure {
+	switch info.ChannelType {
+	case common.ChannelTypeAzure:
 		// https://learn.microsoft.com/en-us/azure/cognitive-services/openai/chatgpt-quickstart?pivots=rest-api&tabs=command-line#rest-api
 		requestURL := strings.Split(info.RequestURLPath, "?")[0]
 		requestURL = fmt.Sprintf("%s?api-version=%s", requestURL, info.ApiVersion)
@@ -37,8 +46,15 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 
 		requestURL = fmt.Sprintf("/openai/deployments/%s/%s", model_, task)
 		return relaycommon.GetFullRequestURL(info.BaseUrl, requestURL, info.ChannelType), nil
+	case common.ChannelTypeMiniMax:
+		return minimax.GetRequestURL(info)
+	case common.ChannelTypeCustom:
+		url := info.BaseUrl
+		url = strings.Replace(url, "{model}", info.UpstreamModelName, -1)
+		return url, nil
+	default:
+		return relaycommon.GetFullRequestURL(info.BaseUrl, info.RequestURLPath, info.ChannelType), nil
 	}
-	return relaycommon.GetFullRequestURL(info.BaseUrl, info.RequestURLPath, info.ChannelType), nil
 }
 
 func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
@@ -72,8 +88,10 @@ func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, request
 func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
 	if info.IsStream {
 		var responseText string
-		err, responseText = OpenaiStreamHandler(c, resp, info.RelayMode)
+		var toolCount int
+		err, responseText, toolCount = OpenaiStreamHandler(c, resp, info)
 		usage, _ = service.ResponseText2Usage(responseText, info.UpstreamModelName, info.PromptTokens)
+		usage.CompletionTokens += toolCount * 7
 	} else {
 		err, usage = OpenaiHandler(c, resp, info.PromptTokens, info.UpstreamModelName)
 	}
@@ -88,11 +106,24 @@ func (a *Adaptor) GetModelList() []string {
 		return moonshot.ModelList
 	case common.ChannelTypeLingYiWanWu:
 		return lingyiwanwu.ModelList
+	case common.ChannelTypeMiniMax:
+		return minimax.ModelList
 	default:
 		return ModelList
 	}
 }
 
 func (a *Adaptor) GetChannelName() string {
-	return ChannelName
+	switch a.ChannelType {
+	case common.ChannelType360:
+		return ai360.ChannelName
+	case common.ChannelTypeMoonshot:
+		return moonshot.ChannelName
+	case common.ChannelTypeLingYiWanWu:
+		return lingyiwanwu.ChannelName
+	case common.ChannelTypeMiniMax:
+		return minimax.ChannelName
+	default:
+		return ChannelName
+	}
 }

relay/channel/openai/constant.go

@@ -1,19 +1,20 @@
 package openai
 
 var ModelList = []string{
-	"gpt-3.5-turbo", "gpt-3.5-turbo-0301", "gpt-3.5-turbo-0613", "gpt-3.5-turbo-1106", "gpt-3.5-turbo-0125",
+	"gpt-3.5-turbo", "gpt-3.5-turbo-0613", "gpt-3.5-turbo-1106", "gpt-3.5-turbo-0125",
 	"gpt-3.5-turbo-16k", "gpt-3.5-turbo-16k-0613",
 	"gpt-3.5-turbo-instruct",
-	"gpt-4", "gpt-4-0314", "gpt-4-0613", "gpt-4-1106-preview", "gpt-4-0125-preview",
-	"gpt-4-32k", "gpt-4-32k-0314", "gpt-4-32k-0613",
-	"gpt-4-turbo-preview",
+	"gpt-4", "gpt-4-0613", "gpt-4-1106-preview", "gpt-4-0125-preview",
+	"gpt-4-32k", "gpt-4-32k-0613",
+	"gpt-4-turbo-preview", "gpt-4-turbo", "gpt-4-turbo-2024-04-09",
 	"gpt-4-vision-preview",
+	"gpt-4o", "gpt-4o-2024-05-13",
 	"text-embedding-ada-002", "text-embedding-3-small", "text-embedding-3-large",
-	"text-curie-001", "text-babbage-001", "text-ada-001", "text-davinci-002", "text-davinci-003",
+	"text-curie-001", "text-babbage-001", "text-ada-001",
 	"text-moderation-latest", "text-moderation-stable",
 	"text-davinci-edit-001",
 	"davinci-002", "babbage-002",
-	"dall-e-2", "dall-e-3",
+	"dall-e-3",
 	"whisper-1",
 	"tts-1", "tts-1-1106", "tts-1-hd", "tts-1-hd-1106",
 }

relay/channel/openai/relay-openai.go

@@ -8,7 +8,9 @@ import (
 	"io"
 	"net/http"
 	"one-api/common"
+	"one-api/constant"
 	"one-api/dto"
+	relaycommon "one-api/relay/common"
 	relayconstant "one-api/relay/constant"
 	"one-api/service"
 	"strings"
@@ -16,9 +18,10 @@ import (
 	"time"
 )
 
-func OpenaiStreamHandler(c *gin.Context, resp *http.Response, relayMode int) (*dto.OpenAIErrorWithStatusCode, string) {
+func OpenaiStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (*dto.OpenAIErrorWithStatusCode, string, int) {
 	//checkSensitive := constant.ShouldCheckCompletionSensitive()
 	var responseTextBuilder strings.Builder
+	toolCount := 0
 	scanner := bufio.NewScanner(resp.Body)
 	scanner.Split(func(data []byte, atEOF bool) (advance int, token []byte, err error) {
 		if atEOF && len(data) == 0 {
@@ -49,14 +52,18 @@ func OpenaiStreamHandler(c *gin.Context, resp *http.Response, relayMode int) (*d
 			if data[:6] != "data: " && data[:6] != "[DONE]" {
 				continue
 			}
-			dataChan <- data
+			if !common.SafeSendStringTimeout(dataChan, data, constant.StreamingTimeout) {
+				// send data timeout, stop the stream
+				common.LogError(c, "send data timeout, stop the stream")
+				break
+			}
 			data = data[6:]
 			if !strings.HasPrefix(data, "[DONE]") {
 				streamItems = append(streamItems, data)
 			}
 		}
 		streamResp := "[" + strings.Join(streamItems, ",") + "]"
-		switch relayMode {
+		switch info.RelayMode {
 		case relayconstant.RelayModeChatCompletions:
 			var streamResponses []dto.ChatCompletionsStreamResponseSimple
 			err := json.Unmarshal(common.StringToByteSlice(streamResp), &streamResponses)
@@ -67,14 +74,32 @@ func OpenaiStreamHandler(c *gin.Context, resp *http.Response, relayMode int) (*d
 					err := json.Unmarshal(common.StringToByteSlice(item), &streamResponse)
 					if err == nil {
 						for _, choice := range streamResponse.Choices {
-							responseTextBuilder.WriteString(choice.Delta.Content)
+							responseTextBuilder.WriteString(choice.Delta.GetContentString())
+							if choice.Delta.ToolCalls != nil {
+								if len(choice.Delta.ToolCalls) > toolCount {
+									toolCount = len(choice.Delta.ToolCalls)
+								}
+								for _, tool := range choice.Delta.ToolCalls {
+									responseTextBuilder.WriteString(tool.Function.Name)
+									responseTextBuilder.WriteString(tool.Function.Arguments)
+								}
+							}
 						}
 					}
 				}
 			} else {
 				for _, streamResponse := range streamResponses {
 					for _, choice := range streamResponse.Choices {
-						responseTextBuilder.WriteString(choice.Delta.Content)
+						responseTextBuilder.WriteString(choice.Delta.GetContentString())
+						if choice.Delta.ToolCalls != nil {
+							if len(choice.Delta.ToolCalls) > toolCount {
+								toolCount = len(choice.Delta.ToolCalls)
+							}
+							for _, tool := range choice.Delta.ToolCalls {
+								responseTextBuilder.WriteString(tool.Function.Name)
+								responseTextBuilder.WriteString(tool.Function.Arguments)
+							}
+						}
 					}
 				}
 			}
@@ -104,12 +129,23 @@ func OpenaiStreamHandler(c *gin.Context, resp *http.Response, relayMode int) (*d
 			// wait data out
 			time.Sleep(2 * time.Second)
 		}
-		common.SafeSend(stopChan, true)
+		common.SafeSendBool(stopChan, true)
 	}()
 	service.SetEventStreamHeaders(c)
+	isFirst := true
+	ticker := time.NewTicker(time.Duration(constant.StreamingTimeout))
+	defer ticker.Stop()
 	c.Stream(func(w io.Writer) bool {
 		select {
+		case <-ticker.C:
+			common.LogError(c, "reading data from upstream timeout")
+			return false
 		case data := <-dataChan:
+			if isFirst {
+				isFirst = false
+				info.FirstResponseTime = time.Now()
+			}
+			ticker.Reset(time.Duration(constant.StreamingTimeout))
 			if strings.HasPrefix(data, "data: [DONE]") {
 				data = data[:12]
 			}
@@ -123,10 +159,10 @@ func OpenaiStreamHandler(c *gin.Context, resp *http.Response, relayMode int) (*d
 	})
 	err := resp.Body.Close()
 	if err != nil {
-		return service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), ""
+		return service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), "", toolCount
 	}
 	wg.Wait()
-	return nil, responseTextBuilder.String()
+	return nil, responseTextBuilder.String(), toolCount
 }
 
 func OpenaiHandler(c *gin.Context, resp *http.Response, promptTokens int, model string) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
@@ -168,10 +204,10 @@ func OpenaiHandler(c *gin.Context, resp *http.Response, promptTokens int, model
 		return service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
 	}
 
-	if simpleResponse.Usage.TotalTokens == 0 {
+	if simpleResponse.Usage.TotalTokens == 0 || (simpleResponse.Usage.PromptTokens == 0 && simpleResponse.Usage.CompletionTokens == 0) {
 		completionTokens := 0
 		for _, choice := range simpleResponse.Choices {
-			ctkm, _, _ := service.CountTokenText(string(choice.Message.Content), model, false)
+			ctkm, _ := service.CountTokenText(string(choice.Message.Content), model)
 			completionTokens += ctkm
 		}
 		simpleResponse.Usage = dto.Usage{

relay/channel/palm/adaptor.go

@@ -15,6 +15,11 @@ import (
 type Adaptor struct {
 }
 
+func (a *Adaptor) InitRerank(info *relaycommon.RelayInfo, request dto.RerankRequest) {
+	//TODO implement me
+
+}
+
 func (a *Adaptor) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
 }
 
@@ -35,6 +40,10 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *dto.Gen
 	return request, nil
 }
 
+func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dto.RerankRequest) (any, error) {
+	return nil, nil
+}
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

relay/channel/palm/relay-palm.go

@@ -61,7 +61,7 @@ func responsePaLM2OpenAI(response *PaLMChatResponse) *dto.OpenAITextResponse {
 func streamResponsePaLM2OpenAI(palmResponse *PaLMChatResponse) *dto.ChatCompletionsStreamResponse {
 	var choice dto.ChatCompletionsStreamResponseChoice
 	if len(palmResponse.Candidates) > 0 {
-		choice.Delta.Content = palmResponse.Candidates[0].Content
+		choice.Delta.SetContentString(palmResponse.Candidates[0].Content)
 	}
 	choice.FinishReason = &relaycommon.StopFinishReason
 	var response dto.ChatCompletionsStreamResponse
@@ -156,7 +156,7 @@ func palmHandler(c *gin.Context, resp *http.Response, promptTokens int, model st
 		}, nil
 	}
 	fullTextResponse := responsePaLM2OpenAI(&palmResponse)
-	completionTokens, _, _ := service.CountTokenText(palmResponse.Candidates[0].Content, model, false)
+	completionTokens, _ := service.CountTokenText(palmResponse.Candidates[0].Content, model)
 	usage := dto.Usage{
 		PromptTokens:     promptTokens,
 		CompletionTokens: completionTokens,

relay/channel/perplexity/adaptor.go

@@ -16,6 +16,11 @@ import (
 type Adaptor struct {
 }
 
+func (a *Adaptor) InitRerank(info *relaycommon.RelayInfo, request dto.RerankRequest) {
+	//TODO implement me
+
+}
+
 func (a *Adaptor) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
 }
 
@@ -39,6 +44,10 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *dto.Gen
 	return requestOpenAI2Perplexity(*request), nil
 }
 
+func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dto.RerankRequest) (any, error) {
+	return nil, nil
+}
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }
@@ -46,7 +55,7 @@ func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, request
 func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
 	if info.IsStream {
 		var responseText string
-		err, responseText = openai.OpenaiStreamHandler(c, resp, info.RelayMode)
+		err, responseText, _ = openai.OpenaiStreamHandler(c, resp, info)
 		usage, _ = service.ResponseText2Usage(responseText, info.UpstreamModelName, info.PromptTokens)
 	} else {
 		err, usage = openai.OpenaiHandler(c, resp, info.PromptTokens, info.UpstreamModelName)

relay/channel/perplexity/constants.go

@@ -1,7 +1,7 @@
 package perplexity
 
 var ModelList = []string{
-	"sonar-small-chat", "sonar-small-online", "sonar-medium-chat", "sonar-medium-online", "mistral-7b-instruct", "mixtral-8x7b-instruct",
+	"llama-3-sonar-small-32k-chat", "llama-3-sonar-small-32k-online", "llama-3-sonar-large-32k-chat", "llama-3-sonar-large-32k-online", "llama-3-8b-instruct", "llama-3-70b-instruct", "mixtral-8x7b-instruct",
 }
 
 var ChannelName = "perplexity"