fix: try to fix mj

fix: http code is not properly disabled channel

.github/workflows/docker-image-arm64.yml

@@ -4,6 +4,7 @@ on:
   push:
     tags:
       - '*'
+      - '!*-alpha*'
   workflow_dispatch:
     inputs:
       name:

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 +33,51 @@
     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`设置->运营设置->通用设置`设置重试次数，建议开启缓存功能。  
+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
+- `DIFY_DEBUG`：设置 Dify 渠道是否输出工作流和节点信息到客户端，默认为 `true`， 可选值为 `true` 和 `false`
+- `FORCE_STREAM_OPTION`：覆盖客户端stream_options参数，请求上游返回流模式usage，目前仅支持 `OpenAI` 渠道类型
 ## 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 +96,15 @@ 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

@@ -12,7 +12,6 @@ import (
 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 = ""
@@ -22,6 +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
@@ -103,14 +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"
@@ -133,10 +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
@@ -208,35 +208,41 @@ const (
 	ChannelTypeLingYiWanWu    = 31
 	ChannelTypeAws            = 33
 	ChannelTypeCohere         = 34
+	ChannelTypeMiniMax        = 35
+	ChannelTypeSunoAPI        = 36
+	ChannelTypeDify           = 37
+	ChannelTypeJina           = 38
+	ChannelCloudflare         = 39
 
 	ChannelTypeDummy // this one is only for count, do not add any channel after this
+
 )
 
 var ChannelBaseURLs = []string{
-	"",                                  // 0
-	"https://api.openai.com",            // 1
-	"https://oa.api2d.net",              // 2
-	"",                                  // 3
-	"http://localhost:11434",            // 4
-	"https://api.openai-sb.com",         // 5
-	"https://api.openaimax.com",         // 6
-	"https://api.ohmygpt.com",           // 7
-	"",                                  // 8
-	"https://api.caipacity.com",         // 9
-	"https://api.aiproxy.io",            // 10
-	"",                                  // 11
-	"https://api.api2gpt.com",           // 12
-	"https://api.aigc2d.com",            // 13
-	"https://api.anthropic.com",         // 14
-	"https://aip.baidubce.com",          // 15
-	"https://open.bigmodel.cn",          // 16
-	"https://dashscope.aliyuncs.com",    // 17
-	"",                                  // 18
-	"https://ai.360.cn",                 // 19
-	"https://openrouter.ai/api",         // 20
-	"https://api.aiproxy.io",            // 21
-	"https://fastgpt.run/api/openapi",   // 22
-	"https://hunyuan.cloud.tencent.com", //23
+	"",                                    // 0
+	"https://api.openai.com",              // 1
+	"https://oa.api2d.net",                // 2
+	"",                                    // 3
+	"http://localhost:11434",              // 4
+	"https://api.openai-sb.com",           // 5
+	"https://api.openaimax.com",           // 6
+	"https://api.ohmygpt.com",             // 7
+	"",                                    // 8
+	"https://api.caipacity.com",           // 9
+	"https://api.aiproxy.io",              // 10
+	"",                                    // 11
+	"https://api.api2gpt.com",             // 12
+	"https://api.aigc2d.com",              // 13
+	"https://api.anthropic.com",           // 14
+	"https://aip.baidubce.com",            // 15
+	"https://open.bigmodel.cn",            // 16
+	"https://dashscope.aliyuncs.com",      // 17
+	"",                                    // 18
+	"https://ai.360.cn",                   // 19
+	"https://openrouter.ai/api",           // 20
+	"https://api.aiproxy.io",              // 21
+	"https://fastgpt.run/api/openapi",     // 22
+	"https://hunyuan.tencentcloudapi.com", //23
 	"https://generativelanguage.googleapis.com", //24
 	"https://api.moonshot.cn",                   //25
 	"https://open.bigmodel.cn",                  //26
@@ -248,4 +254,9 @@ var ChannelBaseURLs = []string{
 	"",                                          //32
 	"",                                          //33
 	"https://api.cohere.ai",                     //34
+	"https://api.minimax.chat",                  //35
+	"",                                          //36
+	"",                                          //37
+	"https://api.jina.ai",                       //38
+	"https://api.cloudflare.com",                //39
 }

common/env.go

@@ -0,0 +1,38 @@
+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)
+}
+
+func GetEnvOrDefaultBool(env string, defaultValue bool) bool {
+	if env == "" || os.Getenv(env) == "" {
+		return defaultValue
+	}
+	b, err := strconv.ParseBool(os.Getenv(env))
+	if err != nil {
+		SysError(fmt.Sprintf("failed to parse %s: %s, using default value: %t", env, err.Error(), defaultValue))
+		return defaultValue
+	}
+	return b
+}

common/go-channel.go

@@ -3,6 +3,7 @@ package common
 import (
 	"fmt"
 	"runtime/debug"
+	"time"
 )
 
 func SafeGoroutine(f func()) {
@@ -45,3 +46,21 @@ func SafeSendString(ch chan string, value string) (closed bool) {
 	// 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/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
@@ -13,9 +20,11 @@ import (
 // 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-all":     15,
+	"gpt-4o-all":    15,
 	"gpt-4":         15,
 	//"gpt-4-0314":                   15, //deprecated
 	"gpt-4-0613": 15,
@@ -27,83 +36,113 @@ var DefaultModelRatio = map[string]float64{
 	"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, //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-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-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
-	"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-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":                         0.05 * RMB, // ￥0.05 / 1k tokens
+	"glm-4-alltools":                 0.1 * RMB,  // ￥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,
@@ -112,10 +151,14 @@ var DefaultModelRatio = map[string]float64{
 	"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{
-	"dall-e-2":          0.02,
+var defaultModelPrice = map[string]float64{
 	"dall-e-3":          0.04,
 	"gpt-4-gizmo-*":     0.1,
 	"mj_imagine":        0.1,
@@ -139,14 +182,14 @@ var modelPrice map[string]float64 = nil
 var modelRatio map[string]float64 = nil
 
 var CompletionRatio map[string]float64 = nil
-var DefaultCompletionRatio = map[string]float64{
+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 {
@@ -163,7 +206,7 @@ func UpdateModelPriceByJSONString(jsonStr string) error {
 // 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-*"
@@ -178,16 +221,16 @@ func GetModelPrice(name string, printErr bool) (float64, bool) {
 	return price, true
 }
 
-func GetModelPrices() map[string]float64 {
+func GetModelPriceMap() map[string]float64 {
 	if modelPrice == nil {
-		modelPrice = DefaultModelPrice
+		modelPrice = defaultModelPrice
 	}
 	return modelPrice
 }
 
 func ModelRatio2JSONString() string {
 	if modelRatio == nil {
-		modelRatio = DefaultModelRatio
+		modelRatio = defaultModelRatio
 	}
 	jsonBytes, err := json.Marshal(modelRatio)
 	if err != nil {
@@ -203,7 +246,7 @@ 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-*"
@@ -216,16 +259,21 @@ func GetModelRatio(name string) float64 {
 	return ratio
 }
 
-func GetModelRatios() map[string]float64 {
-	if modelRatio == nil {
-		modelRatio = DefaultModelRatio
+func DefaultModelRatio2JSONString() string {
+	jsonBytes, err := json.Marshal(defaultModelRatio)
+	if err != nil {
+		SysError("error marshalling model ratio: " + err.Error())
 	}
-	return modelRatio
+	return string(jsonBytes)
+}
+
+func GetDefaultModelRatioMap() map[string]float64 {
+	return defaultModelRatio
 }
 
 func CompletionRatio2JSONString() string {
 	if CompletionRatio == nil {
-		CompletionRatio = DefaultCompletionRatio
+		CompletionRatio = defaultCompletionRatio
 	}
 	jsonBytes, err := json.Marshal(CompletionRatio)
 	if err != nil {
@@ -240,6 +288,9 @@ func UpdateCompletionRatioByJSONString(jsonStr string) error {
 }
 
 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
@@ -251,8 +302,8 @@ func GetCompletionRatio(name string) float64 {
 		}
 		return 4.0 / 3.0
 	}
-	if strings.HasPrefix(name, "gpt-4") && name != "gpt-4-all" && !strings.HasPrefix(name, "gpt-4-gizmo") {
-		if strings.HasPrefix(name, "gpt-4-turbo") || 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
@@ -283,6 +334,15 @@ func GetCompletionRatio(name string) float64 {
 	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 / 0.64
@@ -297,9 +357,9 @@ func GetCompletionRatio(name string) float64 {
 	return 1
 }
 
-func GetCompletionRatios() map[string]float64 {
+func GetCompletionRatioMap() map[string]float64 {
 	if CompletionRatio == nil {
-		CompletionRatio = DefaultCompletionRatio
+		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

@@ -8,7 +8,6 @@ import (
 	"log"
 	"math/rand"
 	"net"
-	"os"
 	"os/exec"
 	"runtime"
 	"strconv"
@@ -191,25 +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)
 }
@@ -258,3 +238,12 @@ func MapToJsonStrFloat(m map[string]float64) string {
 	}
 	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 +1,11 @@
+package constant
+
+import (
+	"one-api/common"
+)
+
+var StreamingTimeout = common.GetEnvOrDefault("STREAMING_TIMEOUT", 30)
+var DifyDebug = common.GetEnvOrDefaultBool("DIFY_DEBUG", true)
+
+// ForceStreamOption 覆盖请求参数，强制返回usage信息
+var ForceStreamOption = common.GetEnvOrDefaultBool("FORCE_STREAM_OPTION", true)

constant/midjourney.go

@@ -4,6 +4,7 @@ var MjNotifyEnabled = false
 var MjAccountFilterEnabled = false
 var MjModeClearEnabled = false
 var MjForwardUrlEnabled = true
+var MjActionCheckSuccessEnabled = true
 
 const (
 	MjErrorUnknown = 5

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

@@ -6,11 +6,13 @@ import (
 	"errors"
 	"fmt"
 	"io"
+	"math"
 	"net/http"
 	"net/http/httptest"
 	"net/url"
 	"one-api/common"
 	"one-api/dto"
+	"one-api/middleware"
 	"one-api/model"
 	"one-api/relay"
 	relaycommon "one-api/relay/common"
@@ -23,10 +25,14 @@ import (
 	"github.com/gin-gonic/gin"
 )
 
-func testChannel(channel *model.Channel, testModel string) (err error, openaiErr *dto.OpenAIError) {
+func testChannel(channel *model.Channel, testModel string) (err error, openAIErrorWithStatusCode *dto.OpenAIErrorWithStatusCode) {
+	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{
@@ -35,22 +41,37 @@ func testChannel(channel *model.Channel, testModel string) (err error, openaiErr
 		Body:   nil,
 		Header: make(http.Header),
 	}
+
+	if testModel == "" {
+		if channel.TestModel != nil && *channel.TestModel != "" {
+			testModel = *channel.TestModel
+		} else {
+			if len(channel.GetModels()) > 0 {
+				testModel = channel.GetModels()[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 {
+				return err, service.OpenAIErrorWrapperLocal(err, "unmarshal_model_mapping_failed", http.StatusInternalServerError)
+			}
+			if modelMap[testModel] != "" {
+				testModel = modelMap[testModel]
+			}
+		}
+	}
+
 	c.Request.Header.Set("Authorization", "Bearer "+channel.Key)
 	c.Request.Header.Set("Content-Type", "application/json")
 	c.Set("channel", channel.Type)
 	c.Set("base_url", channel.GetBaseURL())
-	switch channel.Type {
-	case common.ChannelTypeAzure:
-		c.Set("api_version", channel.Other)
-	case common.ChannelTypeXunfei:
-		c.Set("api_version", channel.Other)
-	//case common.ChannelTypeAIProxyLibrary:
-	//	c.Set("library_id", channel.Other)
-	case common.ChannelTypeGemini:
-		c.Set("api_version", channel.Other)
-	case common.ChannelTypeAli:
-		c.Set("plugin", channel.Other)
-	}
+
+	middleware.SetupContextForSelectedChannel(c, channel, testModel)
 
 	meta := relaycommon.GenRelayInfo(c)
 	apiType, _ := constant.ChannelType2APIType(channel.Type)
@@ -58,13 +79,7 @@ func testChannel(channel *model.Channel, testModel string) (err error, openaiErr
 	if adaptor == nil {
 		return fmt.Errorf("invalid api type: %d, adaptor is nil", apiType), nil
 	}
-	if testModel == "" {
-		if channel.TestModel != nil && *channel.TestModel != "" {
-			testModel = *channel.TestModel
-		} else {
-			testModel = adaptor.GetModelList()[0]
-		}
-	}
+
 	request := buildTestRequest()
 	request.Model = testModel
 	meta.UpstreamModelName = testModel
@@ -72,7 +87,7 @@ func testChannel(channel *model.Channel, testModel string) (err error, openaiErr
 
 	adaptor.Init(meta, *request)
 
-	convertedRequest, err := adaptor.ConvertRequest(c, constant.RelayModeChatCompletions, request)
+	convertedRequest, err := adaptor.ConvertRequest(c, meta, request)
 	if err != nil {
 		return err, nil
 	}
@@ -88,21 +103,39 @@ func testChannel(channel *model.Channel, testModel string) (err error, openaiErr
 	}
 	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
+		return fmt.Errorf("status code %d: %s", resp.StatusCode, err.Error.Message), err
 	}
 	usage, respErr := adaptor.DoResponse(c, resp, meta)
 	if respErr != nil {
-		return fmt.Errorf("%s", respErr.Error.Message), &respErr.Error
+		return fmt.Errorf("%s", respErr.Error.Message), respErr
 	}
 	if usage == nil {
 		return errors.New("usage is nil"), nil
 	}
 	result := w.Result()
-	// print result.Body
 	respBody, err := io.ReadAll(result.Body)
 	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 +156,7 @@ 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 +164,7 @@ 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,
@@ -188,7 +221,7 @@ func testAllChannels(notify bool) error {
 		for _, channel := range channels {
 			isChannelEnabled := channel.Status == common.ChannelStatusEnabled
 			tik := time.Now()
-			err, openaiErr := testChannel(channel, "")
+			err, openaiWithStatusErr := testChannel(channel, "")
 			tok := time.Now()
 			milliseconds := tok.Sub(tik).Milliseconds()
 
@@ -197,20 +230,29 @@ func testAllChannels(notify bool) error {
 				err = errors.New(fmt.Sprintf("响应时间 %.2fs 超过阈值 %.2fs", float64(milliseconds)/1000.0, float64(disableThreshold)/1000.0))
 				ban = true
 			}
-			if openaiErr != nil {
-				err = errors.New(fmt.Sprintf("type %s, code %v, message %s", openaiErr.Type, openaiErr.Code, openaiErr.Message))
-				ban = true
+
+			// request error disables the channel
+			if openaiWithStatusErr != nil {
+				oaiErr := openaiWithStatusErr.Error
+				err = errors.New(fmt.Sprintf("type %s, httpCode %d, code %v, message %s", oaiErr.Type, openaiWithStatusErr.StatusCode, oaiErr.Code, oaiErr.Message))
+				ban = service.ShouldDisableChannel(channel.Type, openaiWithStatusErr)
 			}
+
 			// parse *int to bool
 			if channel.AutoBan != nil && *channel.AutoBan == 0 {
 				ban = false
 			}
-			if isChannelEnabled && service.ShouldDisableChannel(openaiErr, -1) && ban {
+
+			// disable channel
+			if ban && isChannelEnabled {
 				service.DisableChannel(channel.Id, channel.Name, err.Error())
 			}
-			if !isChannelEnabled && service.ShouldEnableChannel(err, openaiErr, channel.Status) {
+
+			// enable channel
+			if !isChannelEnabled && service.ShouldEnableChannel(err, openaiWithStatusErr, 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

@@ -146,7 +146,7 @@ func UpdateMidjourneyTaskBulk() {
 					buttonStr, _ := json.Marshal(responseItem.Buttons)
 					task.Buttons = string(buttonStr)
 				}
-
+				shouldReturnQuota := false
 				if (task.Progress != "100%" && responseItem.FailReason != "") || (task.Progress == "100%" && task.Status == "FAILURE") {
 					common.LogInfo(ctx, task.MjId+" 构建失败，"+task.FailReason)
 					task.Progress = "100%"
@@ -154,20 +154,23 @@ func UpdateMidjourneyTaskBulk() {
 					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("构图失败 %s，补偿 %s", task.MjId, common.LogQuota(quota))
-							model.RecordLog(task.UserId, model.LogTypeSystem, logContent)
+						if task.Quota != 0 {
+							shouldReturnQuota = true
 						}
 					}
 				}
 				err = task.Update()
 				if err != nil {
 					common.LogError(ctx, "UpdateMidjourneyTask task error: "+err.Error())
+				} else {
+					if shouldReturnQuota {
+						err = model.IncreaseUserQuota(task.UserId, task.Quota)
+						if err != nil {
+							common.LogError(ctx, "fail to increase user quota: "+err.Error())
+						}
+						logContent := fmt.Sprintf("构图失败 %s，补偿 %s", task.MjId, common.LogQuota(task.Quota))
+						model.RecordLog(task.UserId, model.LogTypeSystem, logContent)
+					}
 				}
 			}
 		}
@@ -235,7 +238,7 @@ func GetAllMidjourney(c *gin.Context) {
 	}
 	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
 		}
 	}
@@ -267,7 +270,7 @@ func GetUserMidjourney(c *gin.Context) {
 	}
 	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

@@ -45,7 +45,7 @@ func GetStatus(c *gin.Context) {
 			"footer_html":              common.Footer,
 			"wechat_qrcode":            common.WeChatAccountQRCodeImageURL,
 			"wechat_login":             common.WeChatAuthEnabled,
-			"server_address":           common.ServerAddress,
+			"server_address":           constant.ServerAddress,
 			"price":                    constant.Price,
 			"min_topup":                constant.MinTopUp,
 			"turnstile_check":          common.TurnstileCheckEnabled,
@@ -57,6 +57,7 @@ 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,
@@ -203,7 +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

@@ -11,6 +11,7 @@ import (
 	"one-api/relay"
 	"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"
 	relayconstant "one-api/relay/constant"
@@ -79,7 +80,7 @@ func init() {
 			Id:         modelName,
 			Object:     "model",
 			Created:    1626777600,
-			OwnedBy:    "moonshot",
+			OwnedBy:    moonshot.ChannelName,
 			Permission: permission,
 			Root:       modelName,
 			Parent:     nil,
@@ -90,7 +91,18 @@ func init() {
 			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,
@@ -108,8 +120,8 @@ func init() {
 		})
 	}
 	openAIModelsMap = make(map[string]dto.OpenAIModels)
-	for _, model := range openAIModels {
-		openAIModelsMap[model.Id] = model
+	for _, aiModel := range openAIModels {
+		openAIModelsMap[aiModel.Id] = aiModel
 	}
 	channelId2Models = make(map[int][]string)
 	for i := 1; i <= common.ChannelTypeDummy; i++ {
@@ -174,8 +186,8 @@ func DashboardListModels(c *gin.Context) {
 
 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),
@@ -188,18 +200,3 @@ func RetrieveModel(c *gin.Context) {
 		})
 	}
 }
-
-func GetPricing(c *gin.Context) {
-	userId := c.GetInt("id")
-	user, _ := model.GetUserById(userId, true)
-	groupRatio := common.GetGroupRatio("default")
-	if user != nil {
-		groupRatio = common.GetGroupRatio(user.Group)
-	}
-	pricing := model.GetPricing(user, openAIModels)
-	c.JSON(200, gin.H{
-		"success":     true,
-		"data":        pricing,
-		"group_ratio": groupRatio,
-	})
-}

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

@@ -29,6 +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)
 	}
@@ -40,12 +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)
-	useChannel := []int{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
 	}
@@ -56,7 +59,9 @@ func Relay(c *gin.Context) {
 			break
 		}
 		channelId = channel.Id
-		useChannel = append(useChannel, channelId)
+		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)
 
@@ -64,9 +69,10 @@ 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)
 		}
 	}
+	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)
@@ -122,10 +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, status code: %d): %s", channelId, err.StatusCode, err.Error.Message))
-	if service.ShouldDisableChannel(&err.Error, err.StatusCode) && autoBan {
+	if service.ShouldDisableChannel(channelType, err) && autoBan {
 		channelName := c.GetString("channel_name")
 		service.DisableChannel(channelId, channelName, err.Error.Message)
 	}
@@ -187,3 +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

@@ -5,11 +5,10 @@ import (
 	"github.com/Calcium-Ion/go-epay/epay"
 	"github.com/gin-gonic/gin"
 	"github.com/samber/lo"
-	"one-api/constant"
-
 	"log"
 	"net/url"
 	"one-api/common"
+	"one-api/constant"
 	"one-api/model"
 	"one-api/service"
 	"strconv"
@@ -92,7 +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()

dto/pricing.go

@@ -24,14 +24,3 @@ type OpenAIModels struct {
 	Root       string                  `json:"root"`
 	Parent     *string                 `json:"parent"`
 }
-
-type ModelPricing 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"`
-}

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

@@ -11,6 +11,7 @@ type GeneralOpenAIRequest struct {
 	Messages         []Message       `json:"messages,omitempty"`
 	Prompt           any             `json:"prompt,omitempty"`
 	Stream           bool            `json:"stream,omitempty"`
+	StreamOptions    *StreamOptions  `json:"stream_options,omitempty"`
 	MaxTokens        uint            `json:"max_tokens,omitempty"`
 	Temperature      float64         `json:"temperature,omitempty"`
 	TopP             float64         `json:"top_p,omitempty"`
@@ -43,8 +44,12 @@ type OpenAIFunction struct {
 	Parameters  any    `json:"parameters,omitempty"`
 }
 
-func (r GeneralOpenAIRequest) GetMaxTokens() int64 {
-	return int64(r.MaxTokens)
+type StreamOptions struct {
+	IncludeUsage bool `json:"include_usage,omitempty"`
+}
+
+func (r GeneralOpenAIRequest) GetMaxTokens() int {
+	return int(r.MaxTokens)
 }
 
 func (r GeneralOpenAIRequest) ParseInput() []string {

dto/text_response.go

@@ -66,10 +66,6 @@ type ChatCompletionsStreamResponseChoiceDelta struct {
 	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
 }
@@ -102,10 +98,23 @@ type ChatCompletionsStreamResponse struct {
 	Model             string                                `json:"model"`
 	SystemFingerprint *string                               `json:"system_fingerprint"`
 	Choices           []ChatCompletionsStreamResponseChoice `json:"choices"`
+	Usage             *Usage                                `json:"usage"`
+}
+
+func (c *ChatCompletionsStreamResponse) GetSystemFingerprint() string {
+	if c.SystemFingerprint == nil {
+		return ""
+	}
+	return *c.SystemFingerprint
+}
+
+func (c *ChatCompletionsStreamResponse) SetSystemFingerprint(s string) {
+	c.SystemFingerprint = &s
 }
 
 type ChatCompletionsStreamResponseSimple struct {
 	Choices []ChatCompletionsStreamResponseChoice `json:"choices"`
+	Usage   *Usage                                `json:"usage"`
 }
 
 type CompletionsStreamResponse struct {

go.mod

@@ -17,11 +17,11 @@ 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/jinzhu/copier v0.4.0
 	github.com/pkg/errors v0.9.1
-	github.com/pkoukk/tiktoken-go v0.1.6
+	github.com/pkoukk/tiktoken-go v0.1.7
 	github.com/samber/lo v1.39.0
 	github.com/shirou/gopsutil v3.21.11+incompatible
 	golang.org/x/crypto v0.21.0
@@ -42,7 +42,7 @@ require (
 	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

go.sum

@@ -32,8 +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=
@@ -81,8 +81,8 @@ github.com/golang/protobuf v1.5.0/go.mod h1:FsONVRAS9T7sI+LIUmWTfcYkHO4aIWwzhcaS
 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=
@@ -148,8 +148,8 @@ github.com/pelletier/go-toml/v2 v2.0.8/go.mod h1:vuYfssBdrU2XDZ9bYydBu6t+6a6PYNc
 github.com/pkg/diff v0.0.0-20210226163009-20ebb0f2a09e/go.mod h1:pJLUxLENpZxwdsKMEsNbx1VGcRFpLqf3715MtcvvzbA=
 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 v0.1.6 h1:JF0TlJzhTbrI30wCvFuiw6FzP2+/bR+FIxUdgEAcUsw=
-github.com/pkoukk/tiktoken-go v0.1.6/go.mod h1:9NiV+i9mJKGj1rYOT+njbv+ZwA/zJxYdewGl6qVatpg=
+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=

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")

middleware/distributor.go

@@ -125,6 +125,17 @@ func getModelRequest(c *gin.Context) (*ModelRequest, bool, error) {
 			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)
 	}
@@ -167,6 +178,7 @@ func SetupContextForSelectedChannel(c *gin.Context, channel *model.Channel, mode
 	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 {
@@ -186,11 +198,11 @@ func SetupContextForSelectedChannel(c *gin.Context, channel *model.Channel, mode
 		c.Set("api_version", channel.Other)
 	case common.ChannelTypeXunfei:
 		c.Set("api_version", channel.Other)
-	//case common.ChannelTypeAIProxyLibrary:
-	//	c.Set("library_id", channel.Other)
 	case common.ChannelTypeGemini:
 		c.Set("api_version", channel.Other)
 	case common.ChannelTypeAli:
 		c.Set("plugin", channel.Other)
+	case common.ChannelCloudflare:
+		c.Set("api_version", channel.Other)
 	}
 }

model/ability.go

@@ -56,6 +56,11 @@ func getPriority(group string, model string, retry int) (int, error) {
 		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) {
@@ -199,7 +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

@@ -87,7 +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

model/channel.go

@@ -1,8 +1,10 @@
 package model
 
 import (
+	"encoding/json"
 	"gorm.io/gorm"
 	"one-api/common"
+	"strings"
 )
 
 type Channel struct {
@@ -29,6 +31,38 @@ type Channel struct {
 	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) GetModels() []string {
+	if channel.Models == "" {
+		return []string{}
+	}
+	return strings.Split(strings.Trim(channel.Models, ","), ",")
+}
+
+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) {
@@ -213,15 +247,31 @@ 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

@@ -36,7 +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
 }
 
@@ -142,6 +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

@@ -41,6 +41,7 @@ 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)
@@ -59,6 +60,8 @@ 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"] = ""
@@ -96,6 +99,7 @@ func InitOptionMap() {
 	common.OptionMap["MjAccountFilterEnabled"] = strconv.FormatBool(constant.MjAccountFilterEnabled)
 	common.OptionMap["MjModeClearEnabled"] = strconv.FormatBool(constant.MjModeClearEnabled)
 	common.OptionMap["MjForwardUrlEnabled"] = strconv.FormatBool(constant.MjForwardUrlEnabled)
+	common.OptionMap["MjActionCheckSuccessEnabled"] = strconv.FormatBool(constant.MjActionCheckSuccessEnabled)
 	common.OptionMap["CheckSensitiveEnabled"] = strconv.FormatBool(constant.CheckSensitiveEnabled)
 	common.OptionMap["CheckSensitiveOnPromptEnabled"] = strconv.FormatBool(constant.CheckSensitiveOnPromptEnabled)
 	//common.OptionMap["CheckSensitiveOnCompletionEnabled"] = strconv.FormatBool(constant.CheckSensitiveOnCompletionEnabled)
@@ -193,6 +197,8 @@ 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":
@@ -205,6 +211,8 @@ func updateOptionMap(key string, value string) (err error) {
 			constant.MjModeClearEnabled = boolValue
 		case "MjForwardUrlEnabled":
 			constant.MjForwardUrlEnabled = boolValue
+		case "MjActionCheckSuccessEnabled":
+			constant.MjActionCheckSuccessEnabled = boolValue
 		case "CheckSensitiveEnabled":
 			constant.CheckSensitiveEnabled = boolValue
 		case "CheckSensitiveOnPromptEnabled":
@@ -232,7 +240,11 @@ 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":
 		constant.PayAddress = value
 	case "CustomCallbackAddress":

model/pricing.go

@@ -2,27 +2,37 @@ package model
 
 import (
 	"one-api/common"
-	"one-api/dto"
 	"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         []dto.ModelPricing
+	pricingMap         []Pricing
 	lastGetPricingTime time.Time
 	updatePricingLock  sync.Mutex
 )
 
-func GetPricing(user *User, openAIModels []dto.OpenAIModels) []dto.ModelPricing {
+func GetPricing(group string) []Pricing {
 	updatePricingLock.Lock()
 	defer updatePricingLock.Unlock()
 
 	if time.Since(lastGetPricingTime) > time.Minute*1 || len(pricingMap) == 0 {
-		updatePricing(openAIModels)
+		updatePricing()
 	}
-	if user != nil {
-		userPricingMap := make([]dto.ModelPricing, 0)
-		models := GetGroupModels(user.Group)
+	if group != "" {
+		userPricingMap := make([]Pricing, 0)
+		models := GetGroupModels(group)
 		for _, pricing := range pricingMap {
 			if !common.StringsContains(models, pricing.ModelName) {
 				pricing.Available = false
@@ -34,28 +44,19 @@ func GetPricing(user *User, openAIModels []dto.OpenAIModels) []dto.ModelPricing
 	return pricingMap
 }
 
-func updatePricing(openAIModels []dto.OpenAIModels) {
-	modelRatios := common.GetModelRatios()
+func updatePricing() {
+	//modelRatios := common.GetModelRatios()
 	enabledModels := GetEnabledModels()
-	allModels := make(map[string]string)
-	for _, openAIModel := range openAIModels {
-		if common.StringsContains(enabledModels, openAIModel.Id) {
-			allModels[openAIModel.Id] = openAIModel.OwnedBy
-		}
+	allModels := make(map[string]int)
+	for i, model := range enabledModels {
+		allModels[model] = i
 	}
-	for model, _ := range modelRatios {
-		if common.StringsContains(enabledModels, model) {
-			if _, ok := allModels[model]; !ok {
-				allModels[model] = "custom"
-			}
-		}
-	}
-	pricingMap = make([]dto.ModelPricing, 0)
-	for model, ownerBy := range allModels {
-		pricing := dto.ModelPricing{
+
+	pricingMap = make([]Pricing, 0)
+	for model, _ := range allModels {
+		pricing := Pricing{
 			Available: true,
 			ModelName: model,
-			OwnerBy:   ownerBy,
 		}
 		modelPrice, findPrice := common.GetModelPrice(model, false)
 		if findPrice {

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" `
@@ -249,11 +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
@@ -271,15 +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 {
@@ -297,7 +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/user.go

@@ -298,7 +298,8 @@ func (user *User) ValidateAndFill() (err error) {
 	if user.Username == "" || password == "" {
 		return errors.New("用户名或密码为空")
 	}
-	DB.Where(User{Username: user.Username}).First(user)
+	// find buy username or email
+	DB.Where("username = ? OR email = ?", user.Username, user.Username).First(user)
 	okay := common.ValidatePasswordAndHash(password, user.Password)
 	if !okay || user.Status != common.UserStatusEnabled {
 		return errors.New("用户名或密码错误，或用户已被封禁")

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)
+	ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, 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

@@ -1,6 +1,9 @@
 package ai360
 
 var ModelList = []string{
+	"360gpt-turbo",
+	"360gpt-turbo-responsibility-8k",
+	"360gpt-pro",
 	"360GPT_S2_V9",
 	"embedding-bert-512-v1",
 	"embedding_s1_v1",

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) {
 
 }
@@ -39,11 +42,11 @@ func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *re
 	return nil
 }
 
-func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *dto.GeneralOpenAIRequest) (any, error) {
+func (a *Adaptor) ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, request *dto.GeneralOpenAIRequest) (any, error) {
 	if request == nil {
 		return nil, errors.New("request is nil")
 	}
-	switch relayMode {
+	switch info.RelayMode {
 	case constant.RelayModeEmbeddings:
 		baiduEmbeddingRequest := embeddingRequestOpenAI2Ali(*request)
 		return baiduEmbeddingRequest, nil
@@ -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/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

@@ -20,6 +20,11 @@ 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
@@ -36,7 +41,7 @@ func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *re
 	return nil
 }
 
-func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *dto.GeneralOpenAIRequest) (any, error) {
+func (a *Adaptor) ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, request *dto.GeneralOpenAIRequest) (any, error) {
 	if request == nil {
 		return nil, errors.New("request is nil")
 	}
@@ -53,13 +58,17 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *dto.Gen
 	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)
+		err, usage = awsStreamHandler(c, resp, info, a.RequestMode)
 	} else {
 		err, usage = awsHandler(c, info, a.RequestMode)
 	}

relay/channel/aws/constants.go

@@ -7,6 +7,7 @@ var awsModelIDMap = map[string]string{
 	"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/relay-aws.go

@@ -13,7 +13,9 @@ import (
 	relaymodel "one-api/dto"
 	"one-api/relay/channel/claude"
 	relaycommon "one-api/relay/common"
+	"one-api/service"
 	"strings"
+	"time"
 
 	"github.com/aws/aws-sdk-go-v2/aws"
 	"github.com/aws/aws-sdk-go-v2/credentials"
@@ -111,7 +113,7 @@ func awsHandler(c *gin.Context, info *relaycommon.RelayInfo, requestMode int) (*
 	return nil, &usage
 }
 
-func awsStreamHandler(c *gin.Context, info *relaycommon.RelayInfo, requestMode int) (*relaymodel.OpenAIErrorWithStatusCode, *relaymodel.Usage) {
+func awsStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo, requestMode int) (*relaymodel.OpenAIErrorWithStatusCode, *relaymodel.Usage) {
 	awsCli, err := newAwsClient(c, info)
 	if err != nil {
 		return wrapErr(errors.Wrap(err, "newAwsClient")), nil
@@ -156,16 +158,20 @@ func awsStreamHandler(c *gin.Context, info *relaycommon.RelayInfo, requestMode i
 	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 {
@@ -208,6 +214,17 @@ func awsStreamHandler(c *gin.Context, info *relaycommon.RelayInfo, requestMode i
 			return false
 		}
 	})
-
+	if info.ShouldIncludeUsage {
+		response := service.GenerateFinalUsageResponse(id, createdTime, info.UpstreamModelName, usage)
+		err := service.ObjectData(c, response)
+		if err != nil {
+			common.SysError("send final response failed: " + err.Error())
+		}
+	}
+	service.Done(c)
+	err = resp.Body.Close()
+	if err != nil {
+		return service.OpenAIErrorWrapperLocal(err, "close_response_body_failed", http.StatusInternalServerError), nil
+	}
 	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 {
@@ -51,11 +99,11 @@ func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *re
 	return nil
 }
 
-func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *dto.GeneralOpenAIRequest) (any, error) {
+func (a *Adaptor) ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, request *dto.GeneralOpenAIRequest) (any, error) {
 	if request == nil {
 		return nil, errors.New("request is nil")
 	}
-	switch relayMode {
+	switch info.RelayMode {
 	case constant.RelayModeEmbeddings:
 		baiduEmbeddingRequest := embeddingRequestOpenAI2Baidu(*request)
 		return baiduEmbeddingRequest, 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 +22,33 @@ 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,
+		UserId:         request.User,
+	}
+	if request.MaxTokens != 0 {
+		maxTokens := int(request.MaxTokens)
+		if request.MaxTokens == 1 {
+			maxTokens = 2
+		}
+		baiduRequest.MaxOutputTokens = &maxTokens
+	}
 	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 {

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
@@ -48,7 +53,7 @@ func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *re
 	return nil
 }
 
-func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *dto.GeneralOpenAIRequest) (any, error) {
+func (a *Adaptor) ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, request *dto.GeneralOpenAIRequest) (any, error) {
 	if request == nil {
 		return nil, errors.New("request is nil")
 	}
@@ -59,13 +64,17 @@ 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)
 }
 
 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/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 {
@@ -69,6 +72,19 @@ func RequestOpenAI2ClaudeMessage(textRequest dto.GeneralOpenAIRequest) (*ClaudeR
 	if claudeRequest.MaxTokens == 0 {
 		claudeRequest.MaxTokens = 4096
 	}
+	if textRequest.Stop != nil {
+		// stop maybe string/array string, convert to array string
+		switch textRequest.Stop.(type) {
+		case string:
+			claudeRequest.StopSequences = []string{textRequest.Stop.(string)}
+		case []interface{}:
+			stopSequences := make([]string, 0)
+			for _, stop := range textRequest.Stop.([]interface{}) {
+				stopSequences = append(stopSequences, stop.(string))
+			}
+			claudeRequest.StopSequences = stopSequences
+		}
+	}
 	formatMessages := make([]dto.Message, 0)
 	var lastMessage *dto.Message
 	for i, message := range textRequest.Messages {
@@ -138,11 +154,11 @@ 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
 							}
@@ -246,7 +262,7 @@ 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{}
@@ -265,8 +281,8 @@ 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()
@@ -274,14 +290,23 @@ 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
@@ -302,7 +327,7 @@ 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
@@ -316,30 +341,38 @@ 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)
+			err = service.ObjectData(c, response)
 			if err != nil {
-				common.SysError("error marshalling stream response: " + err.Error())
-				return true
+				common.SysError(err.Error())
 			}
-			c.Render(-1, common.CustomEvent{Data: "data: " + string(jsonStr)})
 			return true
 		case <-stopChan:
-			c.Render(-1, common.CustomEvent{Data: "data: [DONE]"})
 			return false
 		}
 	})
+	if requestMode == RequestModeCompletion {
+		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, info.UpstreamModelName, usage.PromptTokens)
+		}
+	}
+	if info.ShouldIncludeUsage {
+		response := service.GenerateFinalUsageResponse(responseId, createdTime, info.UpstreamModelName, *usage)
+		err := service.ObjectData(c, response)
+		if err != nil {
+			common.SysError("send final response failed: " + err.Error())
+		}
+	}
+	service.Done(c)
 	err := resp.Body.Close()
 	if err != nil {
-		return service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
-	}
-	if requestMode == RequestModeCompletion {
-		usage, _ = service.ResponseText2Usage(responseText, modelName, promptTokens)
-	} else {
-		if usage.CompletionTokens == 0 {
-			usage, _ = service.ResponseText2Usage(responseText, modelName, usage.PromptTokens)
-		}
+		return service.OpenAIErrorWrapperLocal(err, "close_response_body_failed", http.StatusInternalServerError), nil
 	}
 	return nil, usage
 }
@@ -370,7 +403,7 @@ func claudeHandler(requestMode int, c *gin.Context, resp *http.Response, promptT
 		}, nil
 	}
 	fullTextResponse := ResponseClaude2OpenAI(requestMode, &claudeResponse)
-	completionTokens, err, _ := service.CountTokenText(claudeResponse.Completion, model, false)
+	completionTokens, err := service.CountTokenText(claudeResponse.Completion, model)
 	if err != nil {
 		return service.OpenAIErrorWrapper(err, "count_token_text_failed", http.StatusInternalServerError), nil
 	}

relay/channel/cloudflare/adaptor.go

@@ -0,0 +1,76 @@
+package cloudflare
+
+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) {
+	switch info.RelayMode {
+	case constant.RelayModeChatCompletions:
+		return fmt.Sprintf("%s/client/v4/accounts/%s/ai/v1/chat/completions", info.BaseUrl, info.ApiVersion), nil
+	case constant.RelayModeEmbeddings:
+		return fmt.Sprintf("%s/client/v4/accounts/%s/ai/v1/embeddings", info.BaseUrl, info.ApiVersion), nil
+	default:
+		return fmt.Sprintf("%s/client/v4/accounts/%s/ai/run/%s", info.BaseUrl, info.ApiVersion, info.UpstreamModelName), 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, info *relaycommon.RelayInfo, request *dto.GeneralOpenAIRequest) (any, error) {
+	if request == nil {
+		return nil, errors.New("request is nil")
+	}
+	switch info.RelayMode {
+	case constant.RelayModeCompletions:
+		return convertCf2CompletionsRequest(*request), nil
+	default:
+		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.IsStream {
+		err, usage = cfStreamHandler(c, resp, info)
+	} else {
+		err, usage = cfHandler(c, resp, info)
+	}
+	return
+}
+
+func (a *Adaptor) GetModelList() []string {
+	return ModelList
+}
+
+func (a *Adaptor) GetChannelName() string {
+	return ChannelName
+}

relay/channel/cloudflare/constant.go

@@ -0,0 +1,38 @@
+package cloudflare
+
+var ModelList = []string{
+	"@cf/meta/llama-2-7b-chat-fp16",
+	"@cf/meta/llama-2-7b-chat-int8",
+	"@cf/mistral/mistral-7b-instruct-v0.1",
+	"@hf/thebloke/deepseek-coder-6.7b-base-awq",
+	"@hf/thebloke/deepseek-coder-6.7b-instruct-awq",
+	"@cf/deepseek-ai/deepseek-math-7b-base",
+	"@cf/deepseek-ai/deepseek-math-7b-instruct",
+	"@cf/thebloke/discolm-german-7b-v1-awq",
+	"@cf/tiiuae/falcon-7b-instruct",
+	"@cf/google/gemma-2b-it-lora",
+	"@hf/google/gemma-7b-it",
+	"@cf/google/gemma-7b-it-lora",
+	"@hf/nousresearch/hermes-2-pro-mistral-7b",
+	"@hf/thebloke/llama-2-13b-chat-awq",
+	"@cf/meta-llama/llama-2-7b-chat-hf-lora",
+	"@cf/meta/llama-3-8b-instruct",
+	"@hf/thebloke/llamaguard-7b-awq",
+	"@hf/thebloke/mistral-7b-instruct-v0.1-awq",
+	"@hf/mistralai/mistral-7b-instruct-v0.2",
+	"@cf/mistral/mistral-7b-instruct-v0.2-lora",
+	"@hf/thebloke/neural-chat-7b-v3-1-awq",
+	"@cf/openchat/openchat-3.5-0106",
+	"@hf/thebloke/openhermes-2.5-mistral-7b-awq",
+	"@cf/microsoft/phi-2",
+	"@cf/qwen/qwen1.5-0.5b-chat",
+	"@cf/qwen/qwen1.5-1.8b-chat",
+	"@cf/qwen/qwen1.5-14b-chat-awq",
+	"@cf/qwen/qwen1.5-7b-chat-awq",
+	"@cf/defog/sqlcoder-7b-2",
+	"@hf/nexusflow/starling-lm-7b-beta",
+	"@cf/tinyllama/tinyllama-1.1b-chat-v1.0",
+	"@hf/thebloke/zephyr-7b-beta-awq",
+}
+
+var ChannelName = "cloudflare"

relay/channel/cloudflare/model.go

@@ -0,0 +1,13 @@
+package cloudflare
+
+import "one-api/dto"
+
+type CfRequest struct {
+	Messages    []dto.Message `json:"messages,omitempty"`
+	Lora        string        `json:"lora,omitempty"`
+	MaxTokens   int           `json:"max_tokens,omitempty"`
+	Prompt      string        `json:"prompt,omitempty"`
+	Raw         bool          `json:"raw,omitempty"`
+	Stream      bool          `json:"stream,omitempty"`
+	Temperature float64       `json:"temperature,omitempty"`
+}

relay/channel/cloudflare/relay_cloudflare.go

@@ -0,0 +1,121 @@
+package cloudflare
+
+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"
+	"time"
+)
+
+func convertCf2CompletionsRequest(textRequest dto.GeneralOpenAIRequest) *CfRequest {
+	p, _ := textRequest.Prompt.(string)
+	return &CfRequest{
+		Prompt:      p,
+		MaxTokens:   textRequest.GetMaxTokens(),
+		Stream:      textRequest.Stream,
+		Temperature: textRequest.Temperature,
+	}
+}
+
+func cfStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
+	scanner := bufio.NewScanner(resp.Body)
+	scanner.Split(bufio.ScanLines)
+
+	service.SetEventStreamHeaders(c)
+	id := service.GetResponseID(c)
+	var responseText string
+	isFirst := true
+
+	for scanner.Scan() {
+		data := scanner.Text()
+		if len(data) < len("data: ") {
+			continue
+		}
+		data = strings.TrimPrefix(data, "data: ")
+		data = strings.TrimSuffix(data, "\r")
+
+		if data == "[DONE]" {
+			break
+		}
+
+		var response dto.ChatCompletionsStreamResponse
+		err := json.Unmarshal([]byte(data), &response)
+		if err != nil {
+			common.LogError(c, "error_unmarshalling_stream_response: "+err.Error())
+			continue
+		}
+		for _, choice := range response.Choices {
+			choice.Delta.Role = "assistant"
+			responseText += choice.Delta.GetContentString()
+		}
+		response.Id = id
+		response.Model = info.UpstreamModelName
+		err = service.ObjectData(c, response)
+		if isFirst {
+			isFirst = false
+			info.FirstResponseTime = time.Now()
+		}
+		if err != nil {
+			common.LogError(c, "error_rendering_stream_response: "+err.Error())
+		}
+	}
+
+	if err := scanner.Err(); err != nil {
+		common.LogError(c, "error_scanning_stream_response: "+err.Error())
+	}
+	usage, _ := service.ResponseText2Usage(responseText, info.UpstreamModelName, info.PromptTokens)
+	if info.ShouldIncludeUsage {
+		response := service.GenerateFinalUsageResponse(id, info.StartTime.Unix(), info.UpstreamModelName, *usage)
+		err := service.ObjectData(c, response)
+		if err != nil {
+			common.LogError(c, "error_rendering_final_usage_response: "+err.Error())
+		}
+	}
+	service.Done(c)
+
+	err := resp.Body.Close()
+	if err != nil {
+		common.LogError(c, "close_response_body_failed: "+err.Error())
+	}
+
+	return nil, usage
+}
+
+func cfHandler(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.OpenAIErrorWrapperLocal(err, "close_response_body_failed", http.StatusInternalServerError), nil
+	}
+	var response dto.TextResponse
+	err = json.Unmarshal(responseBody, &response)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
+	}
+	response.Model = info.UpstreamModelName
+	var responseText string
+	for _, choice := range response.Choices {
+		responseText += choice.Message.StringContent()
+	}
+	usage, _ := service.ResponseText2Usage(responseText, info.UpstreamModelName, info.PromptTokens)
+	response.Usage = *usage
+	response.Id = service.GetResponseID(c)
+	jsonResponse, err := json.Marshal(response)
+	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)
+	_, _ = c.Writer.Write(jsonResponse)
+	return nil, usage
+}

relay/channel/cohere/adaptor.go

@@ -8,16 +8,24 @@ import (
 	"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) {
-	return fmt.Sprintf("%s/v1/chat", info.BaseUrl), nil
+	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 {
@@ -26,7 +34,7 @@ func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *re
 	return nil
 }
 
-func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *dto.GeneralOpenAIRequest) (any, error) {
+func (a *Adaptor) ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, request *dto.GeneralOpenAIRequest) (any, error) {
 	return requestOpenAI2Cohere(*request), nil
 }
 
@@ -34,11 +42,19 @@ func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, request
 	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.IsStream {
-		err, usage = cohereStreamHandler(c, resp, info.UpstreamModelName, info.PromptTokens)
+	if info.RelayMode == constant.RelayModeRerank {
+		err, usage = cohereRerankHandler(c, resp, info)
 	} else {
-		err, usage = cohereHandler(c, resp, info.UpstreamModelName, info.PromptTokens)
+		if info.IsStream {
+			err, usage = cohereStreamHandler(c, resp, info)
+		} else {
+			err, usage = cohereHandler(c, resp, info.UpstreamModelName, info.PromptTokens)
+		}
 	}
 	return
 }

relay/channel/cohere/constant.go

@@ -2,6 +2,7 @@ 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

@@ -1,11 +1,13 @@
 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"`
+	MaxTokens   int           `json:"max_tokens"`
 }
 
 type ChatHistory struct {
@@ -28,6 +30,19 @@ type CohereResponseResult struct {
 	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"`

relay/channel/cohere/relay-cohere.go

@@ -9,8 +9,10 @@ import (
 	"net/http"
 	"one-api/common"
 	"one-api/dto"
+	relaycommon "one-api/relay/common"
 	"one-api/service"
 	"strings"
+	"time"
 )
 
 func requestOpenAI2Cohere(textRequest dto.GeneralOpenAIRequest) *CohereRequest {
@@ -45,6 +47,20 @@ func requestOpenAI2Cohere(textRequest dto.GeneralOpenAIRequest) *CohereRequest {
 	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":
@@ -56,7 +72,7 @@ func stopReasonCohere2OpenAI(reason string) string {
 	}
 }
 
-func cohereStreamHandler(c *gin.Context, resp *http.Response, modelName string, promptTokens int) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
+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{}
@@ -84,9 +100,14 @@ func cohereStreamHandler(c *gin.Context, resp *http.Response, modelName string,
 		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)
@@ -98,7 +119,7 @@ func cohereStreamHandler(c *gin.Context, resp *http.Response, modelName string,
 			openaiResp.Id = responseId
 			openaiResp.Created = createdTime
 			openaiResp.Object = "chat.completion.chunk"
-			openaiResp.Model = modelName
+			openaiResp.Model = info.UpstreamModelName
 			if cohereResp.IsFinished {
 				finishReason := stopReasonCohere2OpenAI(cohereResp.FinishReason)
 				openaiResp.Choices = []dto.ChatCompletionsStreamResponseChoice{
@@ -137,7 +158,7 @@ func cohereStreamHandler(c *gin.Context, resp *http.Response, modelName string,
 		}
 	})
 	if usage.PromptTokens == 0 {
-		usage, _ = service.ResponseText2Usage(responseText, modelName, promptTokens)
+		usage, _ = service.ResponseText2Usage(responseText, info.UpstreamModelName, info.PromptTokens)
 	}
 	return nil, usage
 }
@@ -187,3 +208,42 @@ func cohereHandler(c *gin.Context, resp *http.Response, modelName string, prompt
 	_, 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, info *relaycommon.RelayInfo, 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"`
+	Answer         string       `json:"answer"`
+	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 +1,156 @@
+package dify
+
+import (
+	"bufio"
+	"encoding/json"
+	"github.com/gin-gonic/gin"
+	"io"
+	"net/http"
+	"one-api/common"
+	"one-api/constant"
+	"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 constant.DifyDebug && difyResponse.Event == "workflow_started" {
+		choice.Delta.SetContentString("Workflow: " + difyResponse.Data.WorkflowId + "\n")
+	} else if constant.DifyDebug && 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.Answer)
+	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

@@ -9,37 +9,40 @@ import (
 	"one-api/dto"
 	"one-api/relay/channel"
 	relaycommon "one-api/relay/common"
-	"one-api/service"
 )
 
 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-ultra":   "v1beta",
+	"gemini-1.5-pro-latest":   "v1beta",
+	"gemini-1.5-flash-latest": "v1beta",
+	"gemini-ultra":            "v1beta",
 }
 
 func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
-    // 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"
-        }
-    }
+	// 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"
-    }
-    return fmt.Sprintf("%s/%s/models/%s:%s", info.BaseUrl, version, info.UpstreamModelName, action), nil
+	action := "generateContent"
+	if info.IsStream {
+		action = "streamGenerateContent"
+	}
+	return fmt.Sprintf("%s/%s/models/%s:%s", info.BaseUrl, version, info.UpstreamModelName, action), nil
 }
 
 func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
@@ -48,22 +51,24 @@ func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *re
 	return nil
 }
 
-func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *dto.GeneralOpenAIRequest) (any, error) {
+func (a *Adaptor) ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, request *dto.GeneralOpenAIRequest) (any, error) {
 	if request == nil {
 		return nil, errors.New("request is nil")
 	}
 	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)
 }
 
 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)
-		usage, _ = service.ResponseText2Usage(responseText, info.UpstreamModelName, info.PromptTokens)
+		err, usage = geminiChatStreamHandler(c, resp, info)
 	} else {
 		err, usage = geminiChatHandler(c, resp, info.PromptTokens, info.UpstreamModelName)
 	}

relay/channel/gemini/constant.go

@@ -5,7 +5,7 @@ const (
 )
 
 var ModelList = []string{
-	"gemini-1.0-pro-latest", "gemini-1.0-pro-001", "gemini-1.5-pro-latest", "gemini-ultra",
+	"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",
 }
 

relay/channel/gemini/dto.go

@@ -59,4 +59,11 @@ type GeminiChatPromptFeedback struct {
 type GeminiChatResponse struct {
 	Candidates     []GeminiChatCandidate    `json:"candidates"`
 	PromptFeedback GeminiChatPromptFeedback `json:"promptFeedback"`
+	UsageMetadata  GeminiUsageMetadata      `json:"usageMetadata"`
+}
+
+type GeminiUsageMetadata struct {
+	PromptTokenCount     int `json:"promptTokenCount"`
+	CandidatesTokenCount int `json:"candidatesTokenCount"`
+	TotalTokenCount      int `json:"totalTokenCount"`
 }

relay/channel/gemini/relay-gemini.go

@@ -5,12 +5,15 @@ import (
 	"encoding/json"
 	"fmt"
 	"io"
+	"log"
 	"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 +77,7 @@ 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,
@@ -160,10 +163,14 @@ 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, *dto.Usage) {
 	responseText := ""
-	dataChan := make(chan string)
-	stopChan := make(chan bool)
+	responseJson := ""
+	id := fmt.Sprintf("chatcmpl-%s", common.GetUUID())
+	createAt := common.GetTimestamp()
+	var usage = &dto.Usage{}
+	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 {
@@ -180,20 +187,30 @@ func geminiChatStreamHandler(c *gin.Context, resp *http.Response) (*dto.OpenAIEr
 	go func() {
 		for scanner.Scan() {
 			data := scanner.Text()
+			responseJson += data
 			data = strings.TrimSpace(data)
 			if !strings.HasPrefix(data, "\"text\": \"") {
 				continue
 			}
 			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 {
@@ -205,10 +222,10 @@ func geminiChatStreamHandler(c *gin.Context, resp *http.Response) (*dto.OpenAIEr
 			var choice dto.ChatCompletionsStreamResponseChoice
 			choice.Delta.SetContentString(dummy.Content)
 			response := dto.ChatCompletionsStreamResponse{
-				Id:      fmt.Sprintf("chatcmpl-%s", common.GetUUID()),
+				Id:      id,
 				Object:  "chat.completion.chunk",
-				Created: common.GetTimestamp(),
-				Model:   "gemini-pro",
+				Created: createAt,
+				Model:   info.UpstreamModelName,
 				Choices: []dto.ChatCompletionsStreamResponseChoice{choice},
 			}
 			jsonResponse, err := json.Marshal(response)
@@ -219,15 +236,34 @@ func geminiChatStreamHandler(c *gin.Context, resp *http.Response) (*dto.OpenAIEr
 			c.Render(-1, common.CustomEvent{Data: "data: " + string(jsonResponse)})
 			return true
 		case <-stopChan:
-			c.Render(-1, common.CustomEvent{Data: "data: [DONE]"})
 			return false
 		}
 	})
-	err := resp.Body.Close()
+	var geminiChatResponses []GeminiChatResponse
+	err := json.Unmarshal([]byte(responseJson), &geminiChatResponses)
 	if err != nil {
-		return service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), ""
+		log.Printf("cannot get gemini usage: %s", err.Error())
+		usage, _ = service.ResponseText2Usage(responseText, info.UpstreamModelName, info.PromptTokens)
+	} else {
+		for _, response := range geminiChatResponses {
+			usage.PromptTokens = response.UsageMetadata.PromptTokenCount
+			usage.CompletionTokens = response.UsageMetadata.CandidatesTokenCount
+		}
+		usage.TotalTokens = usage.PromptTokens + usage.CompletionTokens
 	}
-	return nil, responseText
+	if info.ShouldIncludeUsage {
+		response := service.GenerateFinalUsageResponse(id, createAt, info.UpstreamModelName, *usage)
+		err := service.ObjectData(c, response)
+		if err != nil {
+			common.SysError("send final response failed: " + err.Error())
+		}
+	}
+	service.Done(c)
+	err = resp.Body.Close()
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), usage
+	}
+	return nil, usage
 }
 
 func geminiChatHandler(c *gin.Context, resp *http.Response, promptTokens int, model string) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
@@ -256,11 +292,10 @@ func geminiChatHandler(c *gin.Context, resp *http.Response, promptTokens int, mo
 		}, nil
 	}
 	fullTextResponse := responseGeminiChat2OpenAI(&geminiResponse)
-	completionTokens, _, _ := service.CountTokenText(geminiResponse.GetResponseText(), model, false)
 	usage := dto.Usage{
-		PromptTokens:     promptTokens,
-		CompletionTokens: completionTokens,
-		TotalTokens:      promptTokens + completionTokens,
+		PromptTokens:     geminiResponse.UsageMetadata.PromptTokenCount,
+		CompletionTokens: geminiResponse.UsageMetadata.CandidatesTokenCount,
+		TotalTokens:      geminiResponse.UsageMetadata.TotalTokenCount,
 	}
 	fullTextResponse.Usage = usage
 	jsonResponse, err := json.Marshal(fullTextResponse)

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, info *relaycommon.RelayInfo, 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

@@ -10,12 +10,14 @@ import (
 	"one-api/relay/channel/openai"
 	relaycommon "one-api/relay/common"
 	relayconstant "one-api/relay/constant"
-	"one-api/service"
 )
 
 type Adaptor struct {
 }
 
+func (a *Adaptor) InitRerank(info *relaycommon.RelayInfo, request dto.RerankRequest) {
+}
+
 func (a *Adaptor) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
 }
 
@@ -33,11 +35,11 @@ func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *re
 	return nil
 }
 
-func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *dto.GeneralOpenAIRequest) (any, error) {
+func (a *Adaptor) ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, request *dto.GeneralOpenAIRequest) (any, error) {
 	if request == nil {
 		return nil, errors.New("request is nil")
 	}
-	switch relayMode {
+	switch info.RelayMode {
 	case relayconstant.RelayModeEmbeddings:
 		return requestOpenAI2Embeddings(*request), nil
 	default:
@@ -45,15 +47,17 @@ 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)
 }
 
 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)
-		usage, _ = service.ResponseText2Usage(responseText, info.UpstreamModelName, info.PromptTokens)
+		err, usage = openai.OpenaiStreamHandler(c, resp, info)
 	} else {
 		if info.RelayMode == relayconstant.RelayModeEmbeddings {
 			err, usage = ollamaEmbeddingHandler(c, resp, info.PromptTokens, info.UpstreamModelName, info.RelayMode)

relay/channel/openai/adaptor.go

@@ -11,9 +11,9 @@ 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"
 	"strings"
 )
 
@@ -21,12 +21,20 @@ 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 +45,15 @@ 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 {
@@ -58,10 +73,13 @@ func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *re
 	return nil
 }
 
-func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *dto.GeneralOpenAIRequest) (any, error) {
+func (a *Adaptor) ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, request *dto.GeneralOpenAIRequest) (any, error) {
 	if request == nil {
 		return nil, errors.New("request is nil")
 	}
+	if info.ChannelType != common.ChannelTypeOpenAI {
+		request.StreamOptions = nil
+	}
 	return request, nil
 }
 
@@ -71,11 +89,7 @@ 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
-		var toolCount int
-		err, responseText, toolCount = OpenaiStreamHandler(c, resp, info.RelayMode)
-		usage, _ = service.ResponseText2Usage(responseText, info.UpstreamModelName, info.PromptTokens)
-		usage.CompletionTokens += toolCount * 7
+		err, usage = OpenaiStreamHandler(c, resp, info)
 	} else {
 		err, usage = OpenaiHandler(c, resp, info.PromptTokens, info.UpstreamModelName)
 	}
@@ -90,11 +104,24 @@ 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", "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

@@ -8,41 +8,42 @@ 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"
-	"sync"
 	"time"
 )
 
-func OpenaiStreamHandler(c *gin.Context, resp *http.Response, relayMode int) (*dto.OpenAIErrorWithStatusCode, string, int) {
-	//checkSensitive := constant.ShouldCheckCompletionSensitive()
+func OpenaiStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
+	hasStreamUsage := false
+	responseId := ""
+	var createAt int64 = 0
+	var systemFingerprint string
+	model := info.UpstreamModelName
+
 	var responseTextBuilder strings.Builder
+	var usage = &dto.Usage{}
+	var streamItems []string // store stream items
+
 	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 {
-			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, 5)
-	stopChan := make(chan bool, 2)
+	scanner.Split(bufio.ScanLines)
+
+	service.SetEventStreamHeaders(c)
+
+	ticker := time.NewTicker(time.Duration(constant.StreamingTimeout) * time.Second)
+	defer ticker.Stop()
+
+	stopChan := make(chan bool)
 	defer close(stopChan)
-	defer close(dataChan)
-	var wg sync.WaitGroup
+
 	go func() {
-		wg.Add(1)
-		defer wg.Done()
-		var streamItems []string // store stream items
 		for scanner.Scan() {
+			info.SetFirstResponseTime()
+			ticker.Reset(time.Duration(constant.StreamingTimeout) * time.Second)
 			data := scanner.Text()
 			if len(data) < 6 { // ignore blank line or wrong format
 				continue
@@ -50,39 +51,44 @@ func OpenaiStreamHandler(c *gin.Context, resp *http.Response, relayMode int) (*d
 			if data[:6] != "data: " && data[:6] != "[DONE]" {
 				continue
 			}
-			common.SafeSendString(dataChan, data)
 			data = data[6:]
 			if !strings.HasPrefix(data, "[DONE]") {
+				service.StringData(c, data)
 				streamItems = append(streamItems, data)
 			}
 		}
-		streamResp := "[" + strings.Join(streamItems, ",") + "]"
-		switch relayMode {
-		case relayconstant.RelayModeChatCompletions:
-			var streamResponses []dto.ChatCompletionsStreamResponseSimple
-			err := json.Unmarshal(common.StringToByteSlice(streamResp), &streamResponses)
-			if err != nil {
-				common.SysError("error unmarshalling stream response: " + err.Error())
-				for _, item := range streamItems {
-					var streamResponse dto.ChatCompletionsStreamResponseSimple
-					err := json.Unmarshal(common.StringToByteSlice(item), &streamResponse)
-					if err == nil {
-						for _, choice := range streamResponse.Choices {
-							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)
-								}
-							}
-						}
+		common.SafeSendBool(stopChan, true)
+	}()
+
+	select {
+	case <-ticker.C:
+		// 超时处理逻辑
+		common.LogError(c, "streaming timeout")
+	case <-stopChan:
+		// 正常结束
+	}
+
+	// 计算token
+	streamResp := "[" + strings.Join(streamItems, ",") + "]"
+	switch info.RelayMode {
+	case relayconstant.RelayModeChatCompletions:
+		var streamResponses []dto.ChatCompletionsStreamResponse
+		err := json.Unmarshal(common.StringToByteSlice(streamResp), &streamResponses)
+		if err != nil {
+			// 一次性解析失败，逐个解析
+			common.SysError("error unmarshalling stream response: " + err.Error())
+			for _, item := range streamItems {
+				var streamResponse dto.ChatCompletionsStreamResponse
+				err := json.Unmarshal(common.StringToByteSlice(item), &streamResponse)
+				if err == nil {
+					responseId = streamResponse.Id
+					createAt = streamResponse.Created
+					systemFingerprint = streamResponse.GetSystemFingerprint()
+					model = streamResponse.Model
+					if service.ValidUsage(streamResponse.Usage) {
+						usage = streamResponse.Usage
+						hasStreamUsage = true
 					}
-				}
-			} else {
-				for _, streamResponse := range streamResponses {
 					for _, choice := range streamResponse.Choices {
 						responseTextBuilder.WriteString(choice.Delta.GetContentString())
 						if choice.Delta.ToolCalls != nil {
@@ -97,55 +103,72 @@ func OpenaiStreamHandler(c *gin.Context, resp *http.Response, relayMode int) (*d
 					}
 				}
 			}
-		case relayconstant.RelayModeCompletions:
-			var streamResponses []dto.CompletionsStreamResponse
-			err := json.Unmarshal(common.StringToByteSlice(streamResp), &streamResponses)
-			if err != nil {
-				common.SysError("error unmarshalling stream response: " + err.Error())
-				for _, item := range streamItems {
-					var streamResponse dto.CompletionsStreamResponse
-					err := json.Unmarshal(common.StringToByteSlice(item), &streamResponse)
-					if err == nil {
-						for _, choice := range streamResponse.Choices {
-							responseTextBuilder.WriteString(choice.Text)
+		} else {
+			for _, streamResponse := range streamResponses {
+				responseId = streamResponse.Id
+				createAt = streamResponse.Created
+				systemFingerprint = streamResponse.GetSystemFingerprint()
+				model = streamResponse.Model
+				if service.ValidUsage(streamResponse.Usage) {
+					usage = streamResponse.Usage
+					hasStreamUsage = true
+				}
+				for _, choice := range streamResponse.Choices {
+					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 {
+			}
+		}
+	case relayconstant.RelayModeCompletions:
+		var streamResponses []dto.CompletionsStreamResponse
+		err := json.Unmarshal(common.StringToByteSlice(streamResp), &streamResponses)
+		if err != nil {
+			// 一次性解析失败，逐个解析
+			common.SysError("error unmarshalling stream response: " + err.Error())
+			for _, item := range streamItems {
+				var streamResponse dto.CompletionsStreamResponse
+				err := json.Unmarshal(common.StringToByteSlice(item), &streamResponse)
+				if err == nil {
 					for _, choice := range streamResponse.Choices {
 						responseTextBuilder.WriteString(choice.Text)
 					}
 				}
 			}
-		}
-		if len(dataChan) > 0 {
-			// wait data out
-			time.Sleep(2 * time.Second)
-		}
-		common.SafeSendBool(stopChan, true)
-	}()
-	service.SetEventStreamHeaders(c)
-	c.Stream(func(w io.Writer) bool {
-		select {
-		case data := <-dataChan:
-			if strings.HasPrefix(data, "data: [DONE]") {
-				data = data[:12]
+		} else {
+			for _, streamResponse := range streamResponses {
+				for _, choice := range streamResponse.Choices {
+					responseTextBuilder.WriteString(choice.Text)
+				}
 			}
-			// some implementations may add \r at the end of data
-			data = strings.TrimSuffix(data, "\r")
-			c.Render(-1, common.CustomEvent{Data: data})
-			return true
-		case <-stopChan:
-			return false
 		}
-	})
+	}
+
+	if !hasStreamUsage {
+		usage, _ = service.ResponseText2Usage(responseTextBuilder.String(), info.UpstreamModelName, info.PromptTokens)
+		usage.CompletionTokens += toolCount * 7
+	}
+
+	if info.ShouldIncludeUsage && !hasStreamUsage {
+		response := service.GenerateFinalUsageResponse(responseId, createAt, model, *usage)
+		response.SetSystemFingerprint(systemFingerprint)
+		service.ObjectData(c, response)
+	}
+
+	service.Done(c)
+
 	err := resp.Body.Close()
 	if err != nil {
-		return service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), "", toolCount
+		common.LogError(c, "close_response_body_failed: "+err.Error())
 	}
-	wg.Wait()
-	return nil, responseTextBuilder.String(), toolCount
+	return nil, usage
 }
 
 func OpenaiHandler(c *gin.Context, resp *http.Response, promptTokens int, model string) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
@@ -187,10 +210,10 @@ 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) {
 }
 
@@ -28,13 +33,17 @@ func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *re
 	return nil
 }
 
-func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *dto.GeneralOpenAIRequest) (any, error) {
+func (a *Adaptor) ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, request *dto.GeneralOpenAIRequest) (any, error) {
 	if request == nil {
 		return nil, errors.New("request is nil")
 	}
 	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

@@ -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

@@ -10,12 +10,16 @@ import (
 	"one-api/relay/channel"
 	"one-api/relay/channel/openai"
 	relaycommon "one-api/relay/common"
-	"one-api/service"
 )
 
 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) {
 }
 
@@ -29,7 +33,7 @@ func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *re
 	return nil
 }
 
-func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *dto.GeneralOpenAIRequest) (any, error) {
+func (a *Adaptor) ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, request *dto.GeneralOpenAIRequest) (any, error) {
 	if request == nil {
 		return nil, errors.New("request is nil")
 	}
@@ -39,15 +43,17 @@ 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)
 }
 
 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)
-		usage, _ = service.ResponseText2Usage(responseText, info.UpstreamModelName, info.PromptTokens)
+		err, usage = openai.OpenaiStreamHandler(c, resp, info)
 	} 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"

relay/channel/task/suno/adaptor.go

@@ -0,0 +1,172 @@
+package suno
+
+import (
+	"bytes"
+	"context"
+	"encoding/json"
+	"fmt"
+	"github.com/gin-gonic/gin"
+	"io"
+	"net/http"
+	"one-api/common"
+	"one-api/constant"
+	"one-api/dto"
+	"one-api/relay/channel"
+	relaycommon "one-api/relay/common"
+	"one-api/service"
+	"strings"
+	"time"
+)
+
+type TaskAdaptor struct {
+	ChannelType int
+}
+
+func (a *TaskAdaptor) Init(info *relaycommon.TaskRelayInfo) {
+	a.ChannelType = info.ChannelType
+}
+
+func (a *TaskAdaptor) ValidateRequestAndSetAction(c *gin.Context, info *relaycommon.TaskRelayInfo) (taskErr *dto.TaskError) {
+	action := strings.ToUpper(c.Param("action"))
+
+	var sunoRequest *dto.SunoSubmitReq
+	err := common.UnmarshalBodyReusable(c, &sunoRequest)
+	if err != nil {
+		taskErr = service.TaskErrorWrapperLocal(err, "invalid_request", http.StatusBadRequest)
+		return
+	}
+	err = actionValidate(c, sunoRequest, action)
+	if err != nil {
+		taskErr = service.TaskErrorWrapperLocal(err, "invalid_request", http.StatusBadRequest)
+		return
+	}
+
+	if sunoRequest.ContinueClipId != "" {
+		if sunoRequest.TaskID == "" {
+			taskErr = service.TaskErrorWrapperLocal(fmt.Errorf("task id is empty"), "invalid_request", http.StatusBadRequest)
+			return
+		}
+		info.OriginTaskID = sunoRequest.TaskID
+	}
+
+	info.Action = action
+	c.Set("task_request", sunoRequest)
+	return nil
+}
+
+func (a *TaskAdaptor) BuildRequestURL(info *relaycommon.TaskRelayInfo) (string, error) {
+	baseURL := info.BaseUrl
+	fullRequestURL := fmt.Sprintf("%s%s", baseURL, "/suno/submit/"+info.Action)
+	return fullRequestURL, nil
+}
+
+func (a *TaskAdaptor) BuildRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.TaskRelayInfo) error {
+	req.Header.Set("Content-Type", c.Request.Header.Get("Content-Type"))
+	req.Header.Set("Accept", c.Request.Header.Get("Accept"))
+	req.Header.Set("Authorization", "Bearer "+info.ApiKey)
+	return nil
+}
+
+func (a *TaskAdaptor) BuildRequestBody(c *gin.Context, info *relaycommon.TaskRelayInfo) (io.Reader, error) {
+	sunoRequest, ok := c.Get("task_request")
+	if !ok {
+		err := common.UnmarshalBodyReusable(c, &sunoRequest)
+		if err != nil {
+			return nil, err
+		}
+	}
+	data, err := json.Marshal(sunoRequest)
+	if err != nil {
+		return nil, err
+	}
+	return bytes.NewReader(data), nil
+}
+
+func (a *TaskAdaptor) DoRequest(c *gin.Context, info *relaycommon.TaskRelayInfo, requestBody io.Reader) (*http.Response, error) {
+	return channel.DoTaskApiRequest(a, c, info, requestBody)
+}
+
+func (a *TaskAdaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.TaskRelayInfo) (taskID string, taskData []byte, taskErr *dto.TaskError) {
+	responseBody, err := io.ReadAll(resp.Body)
+	if err != nil {
+		taskErr = service.TaskErrorWrapper(err, "read_response_body_failed", http.StatusInternalServerError)
+		return
+	}
+	var sunoResponse dto.TaskResponse[string]
+	err = json.Unmarshal(responseBody, &sunoResponse)
+	if err != nil {
+		taskErr = service.TaskErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError)
+		return
+	}
+	if !sunoResponse.IsSuccess() {
+		taskErr = service.TaskErrorWrapper(fmt.Errorf(sunoResponse.Message), sunoResponse.Code, http.StatusInternalServerError)
+		return
+	}
+
+	for k, v := range resp.Header {
+		c.Writer.Header().Set(k, v[0])
+	}
+	c.Writer.Header().Set("Content-Type", "application/json")
+	c.Writer.WriteHeader(resp.StatusCode)
+
+	_, err = io.Copy(c.Writer, bytes.NewBuffer(responseBody))
+	if err != nil {
+		taskErr = service.TaskErrorWrapper(err, "copy_response_body_failed", http.StatusInternalServerError)
+		return
+	}
+
+	return sunoResponse.Data, nil, nil
+}
+
+func (a *TaskAdaptor) GetModelList() []string {
+	return ModelList
+}
+
+func (a *TaskAdaptor) GetChannelName() string {
+	return ChannelName
+}
+
+func (a *TaskAdaptor) FetchTask(baseUrl, key string, body map[string]any) (*http.Response, error) {
+	requestUrl := fmt.Sprintf("%s/suno/fetch", baseUrl)
+	byteBody, err := json.Marshal(body)
+	if err != nil {
+		return nil, err
+	}
+
+	req, err := http.NewRequest("POST", requestUrl, bytes.NewBuffer(byteBody))
+	if err != nil {
+		common.SysError(fmt.Sprintf("Get Task error: %v", err))
+		return nil, err
+	}
+	defer req.Body.Close()
+	// 设置超时时间
+	timeout := time.Second * 15
+	ctx, cancel := context.WithTimeout(context.Background(), timeout)
+	defer cancel()
+	// 使用带有超时的 context 创建新的请求
+	req = req.WithContext(ctx)
+	req.Header.Set("Content-Type", "application/json")
+	req.Header.Set("Authorization", "Bearer "+key)
+	resp, err := service.GetHttpClient().Do(req)
+	if err != nil {
+		return nil, err
+	}
+	return resp, nil
+}
+
+func actionValidate(c *gin.Context, sunoRequest *dto.SunoSubmitReq, action string) (err error) {
+	switch action {
+	case constant.SunoActionMusic:
+		if sunoRequest.Mv == "" {
+			sunoRequest.Mv = "chirp-v3-0"
+		}
+	case constant.SunoActionLyrics:
+		if sunoRequest.Prompt == "" {
+			err = fmt.Errorf("prompt_empty")
+			return
+		}
+	default:
+		err = fmt.Errorf("invalid_action")
+	}
+	return
+}

relay/channel/task/suno/models.go

@@ -0,0 +1,7 @@
+package suno
+
+var ModelList = []string{
+	"suno_music", "suno_lyrics",
+}
+
+var ChannelName = "suno"

relay/channel/tencent/adaptor.go

@@ -6,49 +6,68 @@ import (
 	"github.com/gin-gonic/gin"
 	"io"
 	"net/http"
+	"one-api/common"
 	"one-api/dto"
 	"one-api/relay/channel"
 	relaycommon "one-api/relay/common"
 	"one-api/service"
+	"strconv"
 	"strings"
 )
 
 type Adaptor struct {
-	Sign string
+	Sign      string
+	AppID     int64
+	Action    string
+	Version   string
+	Timestamp int64
+}
+
+func (a *Adaptor) InitRerank(info *relaycommon.RelayInfo, request dto.RerankRequest) {
+	//TODO implement me
+
 }
 
 func (a *Adaptor) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
+	a.Action = "ChatCompletions"
+	a.Version = "2023-09-01"
+	a.Timestamp = common.GetTimestamp()
 }
 
 func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
-	return fmt.Sprintf("%s/hyllm/v1/chat/completions", info.BaseUrl), nil
+	return fmt.Sprintf("%s/", 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", a.Sign)
-	req.Header.Set("X-TC-Action", info.UpstreamModelName)
+	req.Header.Set("X-TC-Action", a.Action)
+	req.Header.Set("X-TC-Version", a.Version)
+	req.Header.Set("X-TC-Timestamp", strconv.FormatInt(a.Timestamp, 10))
 	return nil
 }
 
-func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *dto.GeneralOpenAIRequest) (any, error) {
+func (a *Adaptor) ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, request *dto.GeneralOpenAIRequest) (any, error) {
 	if request == nil {
 		return nil, errors.New("request is nil")
 	}
 	apiKey := c.Request.Header.Get("Authorization")
 	apiKey = strings.TrimPrefix(apiKey, "Bearer ")
 	appId, secretId, secretKey, err := parseTencentConfig(apiKey)
+	a.AppID = appId
 	if err != nil {
 		return nil, err
 	}
-	tencentRequest := requestOpenAI2Tencent(*request)
-	tencentRequest.AppId = appId
-	tencentRequest.SecretId = secretId
+	tencentRequest := requestOpenAI2Tencent(a, *request)
 	// we have to calculate the sign here
-	a.Sign = getTencentSign(*tencentRequest, secretKey)
+	a.Sign = getTencentSign(*tencentRequest, a, secretId, secretKey)
 	return tencentRequest, 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/tencent/constants.go

@@ -1,9 +1,10 @@
 package tencent
 
 var ModelList = []string{
-	"ChatPro",
-	"ChatStd",
-	"hunyuan",
+	"hunyuan-lite",
+	"hunyuan-standard",
+	"hunyuan-standard-256K",
+	"hunyuan-pro",
 }
 
 var ChannelName = "tencent"

relay/channel/tencent/dto.go

@@ -1,61 +1,75 @@
 package tencent
 
-import "one-api/dto"
-
 type TencentMessage struct {
-	Role    string `json:"role"`
-	Content string `json:"content"`
+	Role    string `json:"Role"`
+	Content string `json:"Content"`
 }
 
 type TencentChatRequest struct {
-	AppId    int64  `json:"app_id"`    // 腾讯云账号的 APPID
-	SecretId string `json:"secret_id"` // 官网 SecretId
-	// Timestamp当前 UNIX 时间戳，单位为秒，可记录发起 API 请求的时间。
-	// 例如1529223702，如果与当前时间相差过大，会引起签名过期错误
-	Timestamp int64 `json:"timestamp"`
-	// Expired 签名的有效期，是一个符合 UNIX Epoch 时间戳规范的数值，
-	// 单位为秒；Expired 必须大于 Timestamp 且 Expired-Timestamp 小于90天
-	Expired int64  `json:"expired"`
-	QueryID string `json:"query_id"` //请求 Id，用于问题排查
-	// Temperature 较高的数值会使输出更加随机，而较低的数值会使其更加集中和确定
-	// 默认 1.0，取值区间为[0.0,2.0]，非必要不建议使用,不合理的取值会影响效果
-	// 建议该参数和 top_p 只设置1个，不要同时更改 top_p
-	Temperature float64 `json:"temperature"`
-	// TopP 影响输出文本的多样性，取值越大，生成文本的多样性越强
-	// 默认1.0，取值区间为[0.0, 1.0]，非必要不建议使用, 不合理的取值会影响效果
-	// 建议该参数和 temperature 只设置1个，不要同时更改
-	TopP float64 `json:"top_p"`
-	// Stream 0：同步，1：流式 （默认，协议：SSE)
-	// 同步请求超时：60s，如果内容较长建议使用流式
-	Stream int `json:"stream"`
-	// Messages 会话内容, 长度最多为40, 按对话时间从旧到新在数组中排列
-	// 输入 content 总数最大支持 3000 token。
-	Messages []TencentMessage `json:"messages"`
+	// 模型名称，可选值包括 hunyuan-lite、hunyuan-standard、hunyuan-standard-256K、hunyuan-pro。
+	// 各模型介绍请阅读 [产品概述](https://cloud.tencent.com/document/product/1729/104753) 中的说明。
+	//
+	// 注意：
+	// 不同的模型计费不同，请根据 [购买指南](https://cloud.tencent.com/document/product/1729/97731) 按需调用。
+	Model *string `json:"Model"`
+	// 聊天上下文信息。
+	// 说明：
+	// 1. 长度最多为 40，按对话时间从旧到新在数组中排列。
+	// 2. Message.Role 可选值：system、user、assistant。
+	// 其中，system 角色可选，如存在则必须位于列表的最开始。user 和 assistant 需交替出现（一问一答），以 user 提问开始和结束，且 Content 不能为空。Role 的顺序示例：[system（可选） user assistant user assistant user ...]。
+	// 3. Messages 中 Content 总长度不能超过模型输入长度上限（可参考 [产品概述](https://cloud.tencent.com/document/product/1729/104753) 文档），超过则会截断最前面的内容，只保留尾部内容。
+	Messages []*TencentMessage `json:"Messages"`
+	// 流式调用开关。
+	// 说明：
+	// 1. 未传值时默认为非流式调用（false）。
+	// 2. 流式调用时以 SSE 协议增量返回结果（返回值取 Choices[n].Delta 中的值，需要拼接增量数据才能获得完整结果）。
+	// 3. 非流式调用时：
+	// 调用方式与普通 HTTP 请求无异。
+	// 接口响应耗时较长，**如需更低时延建议设置为 true**。
+	// 只返回一次最终结果（返回值取 Choices[n].Message 中的值）。
+	//
+	// 注意：
+	// 通过 SDK 调用时，流式和非流式调用需用**不同的方式**获取返回值，具体参考 SDK 中的注释或示例（在各语言 SDK 代码仓库的 examples/hunyuan/v20230901/ 目录中）。
+	Stream *bool `json:"Stream,omitempty"`
+	// 说明：
+	// 1. 影响输出文本的多样性，取值越大，生成文本的多样性越强。
+	// 2. 取值区间为 [0.0, 1.0]，未传值时使用各模型推荐值。
+	// 3. 非必要不建议使用，不合理的取值会影响效果。
+	TopP *float64 `json:"TopP,omitempty"`
+	// 说明：
+	// 1. 较高的数值会使输出更加随机，而较低的数值会使其更加集中和确定。
+	// 2. 取值区间为 [0.0, 2.0]，未传值时使用各模型推荐值。
+	// 3. 非必要不建议使用，不合理的取值会影响效果。
+	Temperature *float64 `json:"Temperature,omitempty"`
 }
 
 type TencentError struct {
-	Code    int    `json:"code"`
-	Message string `json:"message"`
+	Code    int    `json:"Code"`
+	Message string `json:"Message"`
 }
 
 type TencentUsage struct {
-	InputTokens  int `json:"input_tokens"`
-	OutputTokens int `json:"output_tokens"`
-	TotalTokens  int `json:"total_tokens"`
+	PromptTokens     int `json:"PromptTokens"`
+	CompletionTokens int `json:"CompletionTokens"`
+	TotalTokens      int `json:"TotalTokens"`
 }
 
 type TencentResponseChoices struct {
-	FinishReason string         `json:"finish_reason,omitempty"` // 流式结束标志位，为 stop 则表示尾包
-	Messages     TencentMessage `json:"messages,omitempty"`      // 内容，同步模式返回内容，流模式为 null 输出 content 内容总数最多支持 1024token。
-	Delta        TencentMessage `json:"delta,omitempty"`         // 内容，流模式返回内容，同步模式为 null 输出 content 内容总数最多支持 1024token。
+	FinishReason string         `json:"FinishReason,omitempty"` // 流式结束标志位，为 stop 则表示尾包
+	Messages     TencentMessage `json:"Message,omitempty"`      // 内容，同步模式返回内容，流模式为 null 输出 content 内容总数最多支持 1024token。
+	Delta        TencentMessage `json:"Delta,omitempty"`        // 内容，流模式返回内容，同步模式为 null 输出 content 内容总数最多支持 1024token。
 }
 
 type TencentChatResponse struct {
-	Choices []TencentResponseChoices `json:"choices,omitempty"` // 结果
-	Created string                   `json:"created,omitempty"` // unix 时间戳的字符串
-	Id      string                   `json:"id,omitempty"`      // 会话 id
-	Usage   dto.Usage                `json:"usage,omitempty"`   // token 数量
-	Error   TencentError             `json:"error,omitempty"`   // 错误信息 注意：此字段可能返回 null，表示取不到有效值
-	Note    string                   `json:"note,omitempty"`    // 注释
-	ReqID   string                   `json:"req_id,omitempty"`  // 唯一请求 Id，每次请求都会返回。用于反馈接口入参
+	Choices []TencentResponseChoices `json:"Choices,omitempty"` // 结果
+	Created int64                    `json:"Created,omitempty"` // unix 时间戳的字符串
+	Id      string                   `json:"Id,omitempty"`      // 会话 id
+	Usage   TencentUsage             `json:"Usage,omitempty"`   // token 数量
+	Error   TencentError             `json:"Error,omitempty"`   // 错误信息 注意：此字段可能返回 null，表示取不到有效值
+	Note    string                   `json:"Note,omitempty"`    // 注释
+	ReqID   string                   `json:"Req_id,omitempty"`  // 唯一请求 Id，每次请求都会返回。用于反馈接口入参
+}
+
+type TencentChatResponseSB struct {
+	Response TencentChatResponse `json:"Response,omitempty"`
 }

relay/channel/tencent/relay-tencent.go

@@ -3,8 +3,8 @@ package tencent
 import (
 	"bufio"
 	"crypto/hmac"
-	"crypto/sha1"
-	"encoding/base64"
+	"crypto/sha256"
+	"encoding/hex"
 	"encoding/json"
 	"errors"
 	"fmt"
@@ -15,53 +15,46 @@ import (
 	"one-api/dto"
 	relaycommon "one-api/relay/common"
 	"one-api/service"
-	"sort"
 	"strconv"
 	"strings"
+	"time"
 )
 
 // https://cloud.tencent.com/document/product/1729/97732
 
-func requestOpenAI2Tencent(request dto.GeneralOpenAIRequest) *TencentChatRequest {
-	messages := make([]TencentMessage, 0, len(request.Messages))
+func requestOpenAI2Tencent(a *Adaptor, request dto.GeneralOpenAIRequest) *TencentChatRequest {
+	messages := make([]*TencentMessage, 0, len(request.Messages))
 	for i := 0; i < len(request.Messages); i++ {
 		message := request.Messages[i]
-		if message.Role == "system" {
-			messages = append(messages, TencentMessage{
-				Role:    "user",
-				Content: message.StringContent(),
-			})
-			messages = append(messages, TencentMessage{
-				Role:    "assistant",
-				Content: "Okay",
-			})
-			continue
-		}
-		messages = append(messages, TencentMessage{
+		messages = append(messages, &TencentMessage{
 			Content: message.StringContent(),
 			Role:    message.Role,
 		})
 	}
-	stream := 0
-	if request.Stream {
-		stream = 1
+	var req = TencentChatRequest{
+		Stream:   &request.Stream,
+		Messages: messages,
+		Model:    &request.Model,
 	}
-	return &TencentChatRequest{
-		Timestamp:   common.GetTimestamp(),
-		Expired:     common.GetTimestamp() + 24*60*60,
-		QueryID:     common.GetUUID(),
-		Temperature: request.Temperature,
-		TopP:        request.TopP,
-		Stream:      stream,
-		Messages:    messages,
+	if request.TopP != 0 {
+		req.TopP = &request.TopP
 	}
+	if request.Temperature != 0 {
+		req.Temperature = &request.Temperature
+	}
+	return &req
 }
 
 func responseTencent2OpenAI(response *TencentChatResponse) *dto.OpenAITextResponse {
 	fullTextResponse := dto.OpenAITextResponse{
+		Id:      response.Id,
 		Object:  "chat.completion",
 		Created: common.GetTimestamp(),
-		Usage:   response.Usage,
+		Usage: dto.Usage{
+			PromptTokens:     response.Usage.PromptTokens,
+			CompletionTokens: response.Usage.CompletionTokens,
+			TotalTokens:      response.Usage.TotalTokens,
+		},
 	}
 	if len(response.Choices) > 0 {
 		content, _ := json.Marshal(response.Choices[0].Messages.Content)
@@ -98,69 +91,51 @@ func streamResponseTencent2OpenAI(TencentResponse *TencentChatResponse) *dto.Cha
 func tencentStreamHandler(c *gin.Context, resp *http.Response) (*dto.OpenAIErrorWithStatusCode, string) {
 	var responseText string
 	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()
-			if len(data) < 5 { // ignore blank line or wrong format
-				continue
-			}
-			if data[:5] != "data:" {
-				continue
-			}
-			data = data[5:]
-			dataChan <- data
-		}
-		stopChan <- true
-	}()
+	scanner.Split(bufio.ScanLines)
+
 	service.SetEventStreamHeaders(c)
-	c.Stream(func(w io.Writer) bool {
-		select {
-		case data := <-dataChan:
-			var TencentResponse TencentChatResponse
-			err := json.Unmarshal([]byte(data), &TencentResponse)
-			if err != nil {
-				common.SysError("error unmarshalling stream response: " + err.Error())
-				return true
-			}
-			response := streamResponseTencent2OpenAI(&TencentResponse)
-			if len(response.Choices) != 0 {
-				responseText += response.Choices[0].Delta.GetContentString()
-			}
-			jsonResponse, 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(jsonResponse)})
-			return true
-		case <-stopChan:
-			c.Render(-1, common.CustomEvent{Data: "data: [DONE]"})
-			return false
+
+	for scanner.Scan() {
+		data := scanner.Text()
+		if len(data) < 5 || !strings.HasPrefix(data, "data:") {
+			continue
 		}
-	})
+		data = strings.TrimPrefix(data, "data:")
+
+		var tencentResponse TencentChatResponse
+		err := json.Unmarshal([]byte(data), &tencentResponse)
+		if err != nil {
+			common.SysError("error unmarshalling stream response: " + err.Error())
+			continue
+		}
+
+		response := streamResponseTencent2OpenAI(&tencentResponse)
+		if len(response.Choices) != 0 {
+			responseText += response.Choices[0].Delta.GetContentString()
+		}
+
+		err = service.ObjectData(c, response)
+		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), ""
 	}
+
 	return nil, responseText
 }
 
 func tencentHandler(c *gin.Context, resp *http.Response) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
-	var TencentResponse TencentChatResponse
+	var tencentSb TencentChatResponseSB
 	responseBody, err := io.ReadAll(resp.Body)
 	if err != nil {
 		return service.OpenAIErrorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
@@ -169,20 +144,20 @@ func tencentHandler(c *gin.Context, resp *http.Response) (*dto.OpenAIErrorWithSt
 	if err != nil {
 		return service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
 	}
-	err = json.Unmarshal(responseBody, &TencentResponse)
+	err = json.Unmarshal(responseBody, &tencentSb)
 	if err != nil {
 		return service.OpenAIErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
 	}
-	if TencentResponse.Error.Code != 0 {
+	if tencentSb.Response.Error.Code != 0 {
 		return &dto.OpenAIErrorWithStatusCode{
 			Error: dto.OpenAIError{
-				Message: TencentResponse.Error.Message,
-				Code:    TencentResponse.Error.Code,
+				Message: tencentSb.Response.Error.Message,
+				Code:    tencentSb.Response.Error.Code,
 			},
 			StatusCode: resp.StatusCode,
 		}, nil
 	}
-	fullTextResponse := responseTencent2OpenAI(&TencentResponse)
+	fullTextResponse := responseTencent2OpenAI(&tencentSb.Response)
 	jsonResponse, err := json.Marshal(fullTextResponse)
 	if err != nil {
 		return service.OpenAIErrorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil
@@ -205,29 +180,62 @@ func parseTencentConfig(config string) (appId int64, secretId string, secretKey
 	return
 }
 
-func getTencentSign(req TencentChatRequest, secretKey string) string {
-	params := make([]string, 0)
-	params = append(params, "app_id="+strconv.FormatInt(req.AppId, 10))
-	params = append(params, "secret_id="+req.SecretId)
-	params = append(params, "timestamp="+strconv.FormatInt(req.Timestamp, 10))
-	params = append(params, "query_id="+req.QueryID)
-	params = append(params, "temperature="+strconv.FormatFloat(req.Temperature, 'f', -1, 64))
-	params = append(params, "top_p="+strconv.FormatFloat(req.TopP, 'f', -1, 64))
-	params = append(params, "stream="+strconv.Itoa(req.Stream))
-	params = append(params, "expired="+strconv.FormatInt(req.Expired, 10))
-
-	var messageStr string
-	for _, msg := range req.Messages {
-		messageStr += fmt.Sprintf(`{"role":"%s","content":"%s"},`, msg.Role, msg.Content)
-	}
-	messageStr = strings.TrimSuffix(messageStr, ",")
-	params = append(params, "messages=["+messageStr+"]")
-
-	sort.Sort(sort.StringSlice(params))
-	url := "hunyuan.cloud.tencent.com/hyllm/v1/chat/completions?" + strings.Join(params, "&")
-	mac := hmac.New(sha1.New, []byte(secretKey))
-	signURL := url
-	mac.Write([]byte(signURL))
-	sign := mac.Sum([]byte(nil))
-	return base64.StdEncoding.EncodeToString(sign)
+func sha256hex(s string) string {
+	b := sha256.Sum256([]byte(s))
+	return hex.EncodeToString(b[:])
+}
+
+func hmacSha256(s, key string) string {
+	hashed := hmac.New(sha256.New, []byte(key))
+	hashed.Write([]byte(s))
+	return string(hashed.Sum(nil))
+}
+
+func getTencentSign(req TencentChatRequest, adaptor *Adaptor, secId, secKey string) string {
+	// build canonical request string
+	host := "hunyuan.tencentcloudapi.com"
+	httpRequestMethod := "POST"
+	canonicalURI := "/"
+	canonicalQueryString := ""
+	canonicalHeaders := fmt.Sprintf("content-type:%s\nhost:%s\nx-tc-action:%s\n",
+		"application/json", host, strings.ToLower(adaptor.Action))
+	signedHeaders := "content-type;host;x-tc-action"
+	payload, _ := json.Marshal(req)
+	hashedRequestPayload := sha256hex(string(payload))
+	canonicalRequest := fmt.Sprintf("%s\n%s\n%s\n%s\n%s\n%s",
+		httpRequestMethod,
+		canonicalURI,
+		canonicalQueryString,
+		canonicalHeaders,
+		signedHeaders,
+		hashedRequestPayload)
+	// build string to sign
+	algorithm := "TC3-HMAC-SHA256"
+	requestTimestamp := strconv.FormatInt(adaptor.Timestamp, 10)
+	timestamp, _ := strconv.ParseInt(requestTimestamp, 10, 64)
+	t := time.Unix(timestamp, 0).UTC()
+	// must be the format 2006-01-02, ref to package time for more info
+	date := t.Format("2006-01-02")
+	credentialScope := fmt.Sprintf("%s/%s/tc3_request", date, "hunyuan")
+	hashedCanonicalRequest := sha256hex(canonicalRequest)
+	string2sign := fmt.Sprintf("%s\n%s\n%s\n%s",
+		algorithm,
+		requestTimestamp,
+		credentialScope,
+		hashedCanonicalRequest)
+
+	// sign string
+	secretDate := hmacSha256(date, "TC3"+secKey)
+	secretService := hmacSha256("hunyuan", secretDate)
+	secretKey := hmacSha256("tc3_request", secretService)
+	signature := hex.EncodeToString([]byte(hmacSha256(string2sign, secretKey)))
+
+	// build authorization
+	authorization := fmt.Sprintf("%s Credential=%s/%s, SignedHeaders=%s, Signature=%s",
+		algorithm,
+		secId,
+		credentialScope,
+		signedHeaders,
+		signature)
+	return authorization
 }