From f1fb7b32a351005c429bfa24e56904aa80550020 Mon Sep 17 00:00:00 2001
From: CaIon <1808837298@qq.com>
Date: Mon, 25 Mar 2024 16:17:35 +0800
Subject: [PATCH 01/12] chore: update model ratio

---
 common/model-ratio.go | 28 +++++++++++++++-------------
 1 file changed, 15 insertions(+), 13 deletions(-)

diff --git a/common/model-ratio.go b/common/model-ratio.go
index 7c6a012..63d3247 100644
--- a/common/model-ratio.go
+++ b/common/model-ratio.go
@@ -3,7 +3,6 @@ package common
 import (
 	"encoding/json"
 	"strings"
-	"time"
 )
 
 // modelRatio
@@ -27,7 +26,7 @@ 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-3.5-turbo":             0.75, // $0.0015 / 1K tokens
+	"gpt-3.5-turbo":             0.25, // $0.0015 / 1K tokens
 	"gpt-3.5-turbo-0301":        0.75,
 	"gpt-3.5-turbo-0613":        0.75,
 	"gpt-3.5-turbo-16k":         1.5, // $0.003 / 1K tokens
@@ -188,22 +187,15 @@ func GetModelRatio(name string) float64 {
 
 func GetCompletionRatio(name string) float64 {
 	if strings.HasPrefix(name, "gpt-3.5") {
-		if strings.HasSuffix(name, "0125") {
+		if name == "gpt-3.5-turbo" || strings.HasSuffix(name, "0125") {
+			// https://openai.com/blog/new-embedding-models-and-api-updates
+			// Updated GPT-3.5 Turbo model and lower pricing
 			return 3
 		}
 		if strings.HasSuffix(name, "1106") {
 			return 2
 		}
-		if name == "gpt-3.5-turbo" || name == "gpt-3.5-turbo-16k" {
-			// TODO: clear this after 2023-12-11
-			now := time.Now()
-			// https://platform.openai.com/docs/models/continuous-model-upgrades
-			// if after 2023-12-11, use 2
-			if now.After(time.Date(2023, 12, 11, 0, 0, 0, 0, time.UTC)) {
-				return 2
-			}
-		}
-		return 1.333333
+		return 4.0 / 3.0
 	}
 	if strings.HasPrefix(name, "gpt-4") {
 		if strings.HasSuffix(name, "preview") {
@@ -218,5 +210,15 @@ func GetCompletionRatio(name string) float64 {
 	} else if strings.HasPrefix(name, "claude-3") {
 		return 5
 	}
+	if strings.HasPrefix(name, "mistral-") {
+		return 3
+	}
+	if strings.HasPrefix(name, "gemini-") {
+		return 3
+	}
+	switch name {
+	case "llama2-70b-4096":
+		return 0.8 / 0.7
+	}
 	return 1
 }

From b2a280c1ec14e902a9f61a6c5e60185a855f5ab5 Mon Sep 17 00:00:00 2001
From: CaIon <1808837298@qq.com>
Date: Mon, 25 Mar 2024 16:49:53 +0800
Subject: [PATCH 02/12] =?UTF-8?q?fix:=20=E6=97=A0=E6=B3=95=E5=A4=8D?=
 =?UTF-8?q?=E5=88=B6=E5=BC=B9=E7=AA=97=E8=BF=87=E5=B0=8F?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 web/src/components/TokensTable.js | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/web/src/components/TokensTable.js b/web/src/components/TokensTable.js
index 4687ce9..015a5d2 100644
--- a/web/src/components/TokensTable.js
+++ b/web/src/components/TokensTable.js
@@ -426,8 +426,11 @@ const TokensTable = () => {
     if (await copy(text)) {
       showSuccess('已复制到剪贴板！');
     } else {
-      // setSearchKeyword(text);
-      Modal.error({ title: '无法复制到剪贴板，请手动复制', content: text });
+      Modal.error({
+        title: '无法复制到剪贴板，请手动复制',
+        content: text,
+        size: 'large',
+      });
     }
   };
 

From a7a1fc615d6ceab5e4e954047130eefe0ed00b44 Mon Sep 17 00:00:00 2001
From: CaIon <1808837298@qq.com>
Date: Mon, 25 Mar 2024 22:33:33 +0800
Subject: [PATCH 03/12] feat: remove azure model TrimPrefix

---
 relay/channel/openai/adaptor.go | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/relay/channel/openai/adaptor.go b/relay/channel/openai/adaptor.go
index 8d8da3e..7dc591e 100644
--- a/relay/channel/openai/adaptor.go
+++ b/relay/channel/openai/adaptor.go
@@ -10,8 +10,8 @@ import (
 	"one-api/dto"
 	"one-api/relay/channel"
 	"one-api/relay/channel/ai360"
-	"one-api/relay/channel/moonshot"
 	"one-api/relay/channel/lingyiwanwu"
+	"one-api/relay/channel/moonshot"
 	relaycommon "one-api/relay/common"
 	"one-api/service"
 	"strings"
@@ -34,9 +34,6 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 		model_ := info.UpstreamModelName
 		model_ = strings.Replace(model_, ".", "", -1)
 		// https://github.com/songquanpeng/one-api/issues/67
-		model_ = strings.TrimSuffix(model_, "-0301")
-		model_ = strings.TrimSuffix(model_, "-0314")
-		model_ = strings.TrimSuffix(model_, "-0613")
 
 		requestURL = fmt.Sprintf("/openai/deployments/%s/%s", model_, task)
 		return relaycommon.GetFullRequestURL(info.BaseUrl, requestURL, info.ChannelType), nil

From 1587ea565b1bd98879f9b7bcfd0d4ba0f9a440b6 Mon Sep 17 00:00:00 2001
From: CaIon <1808837298@qq.com>
Date: Mon, 25 Mar 2024 22:33:46 +0800
Subject: [PATCH 04/12] feat: support gemini-1.5

---
 common/model-ratio.go            | 7 +++++--
 relay/channel/gemini/constant.go | 4 ++--
 2 files changed, 7 insertions(+), 4 deletions(-)

diff --git a/common/model-ratio.go b/common/model-ratio.go
index 63d3247..f618af8 100644
--- a/common/model-ratio.go
+++ b/common/model-ratio.go
@@ -71,8 +71,11 @@ var DefaultModelRatio = map[string]float64{
 	"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-pro":                1, // $0.00025 / 1k characters -> $0.001 / 1k tokens
+	"gemini-pro-vision":         1, // $0.00025 / 1k characters -> $0.001 / 1k tokens
+	"gemini-1.0-pro-vision-001": 1,
+	"gemini-1.0-pro-001":        1,
+	"gemini-1.5-pro":            1,
 	"chatglm_turbo":             0.3572, // ￥0.005 / 1k tokens
 	"chatglm_pro":               0.7143, // ￥0.01 / 1k tokens
 	"chatglm_std":               0.3572, // ￥0.005 / 1k tokens
diff --git a/relay/channel/gemini/constant.go b/relay/channel/gemini/constant.go
index 24e85a8..582f4c0 100644
--- a/relay/channel/gemini/constant.go
+++ b/relay/channel/gemini/constant.go
@@ -5,8 +5,8 @@ const (
 )
 
 var ModelList = []string{
-	"gemini-pro",
-	"gemini-pro-vision",
+	"gemini-pro", "gemini-1.0-pro-001", "gemini-1.5-pro",
+	"gemini-pro-vision", "gemini-1.0-pro-vision-001",
 }
 
 var ChannelName = "google gemini"

From cc8cc8b386de432dc78a7279c94f56e054d2d186 Mon Sep 17 00:00:00 2001
From: CaIon <1808837298@qq.com>
Date: Mon, 25 Mar 2024 22:51:31 +0800
Subject: [PATCH 05/12] fix: try to fix 307

---
 relay/relay-text.go | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/relay/relay-text.go b/relay/relay-text.go
index a8ba0e8..ec64e04 100644
--- a/relay/relay-text.go
+++ b/relay/relay-text.go
@@ -162,7 +162,7 @@ func TextHelper(c *gin.Context) *dto.OpenAIErrorWithStatusCode {
 
 	if resp.StatusCode != http.StatusOK {
 		returnPreConsumedQuota(c, relayInfo.TokenId, userQuota, preConsumedQuota)
-		return service.RelayErrorHandler(resp)
+		return service.OpenAIErrorWrapper(fmt.Errorf("bad response status code: %d", resp.StatusCode), "bad_response_status_code", resp.StatusCode)
 	}
 
 	usage, openaiErr, sensitiveResp := adaptor.DoResponse(c, resp, relayInfo)

From d8c91fa4487416eba3e16775466790044d4671dd Mon Sep 17 00:00:00 2001
From: CaIon <1808837298@qq.com>
Date: Mon, 25 Mar 2024 22:54:15 +0800
Subject: [PATCH 06/12] =?UTF-8?q?feat:=20=E8=BF=9B=E4=B8=80=E6=AD=A5?=
 =?UTF-8?q?=E9=98=B2=E6=AD=A2=E6=9A=B4=E9=9C=B2=E6=95=B0=E4=B8=8A=E6=B8=B8?=
 =?UTF-8?q?=E4=BB=A5=E5=8F=8A=E6=95=B0=E6=8D=AE=E5=BA=93=E5=9C=B0=E5=9D=80?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 service/error.go | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/service/error.go b/service/error.go
index 424be5d..cda26b3 100644
--- a/service/error.go
+++ b/service/error.go
@@ -29,7 +29,7 @@ func MidjourneyErrorWithStatusCodeWrapper(code int, desc string, statusCode int)
 func OpenAIErrorWrapper(err error, code string, statusCode int) *dto.OpenAIErrorWithStatusCode {
 	text := err.Error()
 	// 定义一个正则表达式匹配URL
-	if strings.Contains(text, "Post") {
+	if strings.Contains(text, "Post") || strings.Contains(text, "dial") {
 		common.SysLog(fmt.Sprintf("error: %s", text))
 		text = "请求上游地址失败"
 	}

From 2a345ae07081503c18777ff94c36288d5069f723 Mon Sep 17 00:00:00 2001
From: CaIon <1808837298@qq.com>
Date: Mon, 25 Mar 2024 22:55:33 +0800
Subject: [PATCH 07/12] ci: update ci

---
 .github/workflows/docker-image-amd64.yml | 1 -
 .github/workflows/docker-image-arm64.yml | 1 -
 2 files changed, 2 deletions(-)

diff --git a/.github/workflows/docker-image-amd64.yml b/.github/workflows/docker-image-amd64.yml
index d0882d9..36236df 100644
--- a/.github/workflows/docker-image-amd64.yml
+++ b/.github/workflows/docker-image-amd64.yml
@@ -4,7 +4,6 @@ on:
   push:
     tags:
       - '*'
-      - '!*-alpha*'
   workflow_dispatch:
     inputs:
       name:
diff --git a/.github/workflows/docker-image-arm64.yml b/.github/workflows/docker-image-arm64.yml
index 44aec80..d86ec5b 100644
--- a/.github/workflows/docker-image-arm64.yml
+++ b/.github/workflows/docker-image-arm64.yml
@@ -4,7 +4,6 @@ on:
   push:
     tags:
       - '*'
-      - '!*-alpha*'
   workflow_dispatch:
     inputs:
       name:

From 3cf2f0d5cbdfa485d4df832b125ba4d74557ad0a Mon Sep 17 00:00:00 2001
From: CaIon <1808837298@qq.com>
Date: Tue, 26 Mar 2024 18:21:38 +0800
Subject: [PATCH 08/12] fix: CountTokenInput

---
 service/token_counter.go | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/service/token_counter.go b/service/token_counter.go
index 2147e88..f2e7a03 100644
--- a/service/token_counter.go
+++ b/service/token_counter.go
@@ -208,7 +208,7 @@ func CountTokenInput(input any, model string, check bool) (int, error, bool) {
 		}
 		return CountTokenText(text, model, check)
 	}
-	return 0, errors.New("unsupported input type"), false
+	return 0, nil, false
 }
 
 func CountAudioToken(text string, model string, check bool) (int, error, bool) {

From 6114c9bb964317300c0daf6660fedbbcac7179ae Mon Sep 17 00:00:00 2001
From: CaIon <1808837298@qq.com>
Date: Tue, 26 Mar 2024 18:49:53 +0800
Subject: [PATCH 09/12] fix: CountTokenInput

---
 service/token_counter.go | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/service/token_counter.go b/service/token_counter.go
index f2e7a03..5255c80 100644
--- a/service/token_counter.go
+++ b/service/token_counter.go
@@ -208,7 +208,7 @@ func CountTokenInput(input any, model string, check bool) (int, error, bool) {
 		}
 		return CountTokenText(text, model, check)
 	}
-	return 0, nil, false
+	return CountTokenInput(fmt.Sprintf("%v", input), model, check)
 }
 
 func CountAudioToken(text string, model string, check bool) (int, error, bool) {

From 319e97d677ae82baa0f23bcc1fc765ce2cd3bb8a Mon Sep 17 00:00:00 2001
From: CaIon <1808837298@qq.com>
Date: Tue, 26 Mar 2024 19:27:11 +0800
Subject: [PATCH 10/12] fix: ollama channel test

---
 controller/channel-test.go           | 1 +
 relay/channel/ollama/adaptor.go      | 3 +--
 relay/channel/ollama/relay-ollama.go | 4 +++-
 3 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/controller/channel-test.go b/controller/channel-test.go
index 2eee554..6d64a24 100644
--- a/controller/channel-test.go
+++ b/controller/channel-test.go
@@ -108,6 +108,7 @@ func buildTestRequest() *dto.GeneralOpenAIRequest {
 	testRequest := &dto.GeneralOpenAIRequest{
 		Model:     "", // this will be set later
 		MaxTokens: 1,
+		Stream:    false,
 	}
 	content, _ := json.Marshal("hi")
 	testMessage := dto.Message{
diff --git a/relay/channel/ollama/adaptor.go b/relay/channel/ollama/adaptor.go
index 69a97e3..4c17252 100644
--- a/relay/channel/ollama/adaptor.go
+++ b/relay/channel/ollama/adaptor.go
@@ -2,7 +2,6 @@ package ollama
 
 import (
 	"errors"
-	"fmt"
 	"github.com/gin-gonic/gin"
 	"io"
 	"net/http"
@@ -20,7 +19,7 @@ func (a *Adaptor) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIReq
 }
 
 func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
-	return fmt.Sprintf("%s/api/chat", info.BaseUrl), 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 {
diff --git a/relay/channel/ollama/relay-ollama.go b/relay/channel/ollama/relay-ollama.go
index 0662ddd..41a2a15 100644
--- a/relay/channel/ollama/relay-ollama.go
+++ b/relay/channel/ollama/relay-ollama.go
@@ -1,6 +1,8 @@
 package ollama
 
-import "one-api/dto"
+import (
+	"one-api/dto"
+)
 
 func requestOpenAI2Ollama(request dto.GeneralOpenAIRequest) *OllamaRequest {
 	messages := make([]dto.Message, 0, len(request.Messages))

From 8eedad9470ee723f7cd8fe8229f77c39f934b8cb Mon Sep 17 00:00:00 2001
From: CaIon <1808837298@qq.com>
Date: Tue, 26 Mar 2024 19:53:53 +0800
Subject: [PATCH 11/12] feat: support ollama embedding

---
 relay/channel/ollama/adaptor.go      | 21 ++++++-
 relay/channel/ollama/dto.go          | 28 ++++++---
 relay/channel/ollama/relay-ollama.go | 94 +++++++++++++++++++++++++---
 3 files changed, 120 insertions(+), 23 deletions(-)

diff --git a/relay/channel/ollama/adaptor.go b/relay/channel/ollama/adaptor.go
index 4c17252..f66d9a9 100644
--- a/relay/channel/ollama/adaptor.go
+++ b/relay/channel/ollama/adaptor.go
@@ -9,6 +9,7 @@ import (
 	"one-api/relay/channel"
 	"one-api/relay/channel/openai"
 	relaycommon "one-api/relay/common"
+	relayconstant "one-api/relay/constant"
 	"one-api/service"
 )
 
@@ -19,7 +20,12 @@ func (a *Adaptor) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIReq
 }
 
 func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
-	return relaycommon.GetFullRequestURL(info.BaseUrl, info.RequestURLPath, info.ChannelType), nil
+	switch info.RelayMode {
+	case relayconstant.RelayModeEmbeddings:
+		return info.BaseUrl + "/api/embeddings", nil
+	default:
+		return relaycommon.GetFullRequestURL(info.BaseUrl, info.RequestURLPath, info.ChannelType), nil
+	}
 }
 
 func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
@@ -31,7 +37,12 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *dto.Gen
 	if request == nil {
 		return nil, errors.New("request is nil")
 	}
-	return requestOpenAI2Ollama(*request), nil
+	switch relayMode {
+	case relayconstant.RelayModeEmbeddings:
+		return requestOpenAI2Embeddings(*request), nil
+	default:
+		return requestOpenAI2Ollama(*request), nil
+	}
 }
 
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
@@ -44,7 +55,11 @@ func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycom
 		err, responseText = openai.OpenaiStreamHandler(c, resp, info.RelayMode)
 		usage, _ = service.ResponseText2Usage(responseText, info.UpstreamModelName, info.PromptTokens)
 	} else {
-		err, usage, sensitiveResp = openai.OpenaiHandler(c, resp, info.PromptTokens, info.UpstreamModelName, info.RelayMode)
+		if info.RelayMode == relayconstant.RelayModeEmbeddings {
+			err, usage, sensitiveResp = ollamaEmbeddingHandler(c, resp, info.PromptTokens, info.UpstreamModelName, info.RelayMode)
+		} else {
+			err, usage, sensitiveResp = openai.OpenaiHandler(c, resp, info.PromptTokens, info.UpstreamModelName, info.RelayMode)
+		}
 	}
 	return
 }
diff --git a/relay/channel/ollama/dto.go b/relay/channel/ollama/dto.go
index a43fb84..a6d6238 100644
--- a/relay/channel/ollama/dto.go
+++ b/relay/channel/ollama/dto.go
@@ -3,16 +3,24 @@ package ollama
 import "one-api/dto"
 
 type OllamaRequest struct {
-	Model    string         `json:"model,omitempty"`
-	Messages []dto.Message  `json:"messages,omitempty"`
-	Stream   bool           `json:"stream,omitempty"`
-	Options  *OllamaOptions `json:"options,omitempty"`
+	Model       string        `json:"model,omitempty"`
+	Messages    []dto.Message `json:"messages,omitempty"`
+	Stream      bool          `json:"stream,omitempty"`
+	Temperature float64       `json:"temperature,omitempty"`
+	Seed        float64       `json:"seed,omitempty"`
+	Topp        float64       `json:"top_p,omitempty"`
+	TopK        int           `json:"top_k,omitempty"`
+	Stop        any           `json:"stop,omitempty"`
 }
 
-type OllamaOptions struct {
-	Temperature float64 `json:"temperature,omitempty"`
-	Seed        float64 `json:"seed,omitempty"`
-	Topp        float64 `json:"top_p,omitempty"`
-	TopK        int     `json:"top_k,omitempty"`
-	Stop        any     `json:"stop,omitempty"`
+type OllamaEmbeddingRequest struct {
+	Model  string `json:"model,omitempty"`
+	Prompt any    `json:"prompt,omitempty"`
 }
+
+type OllamaEmbeddingResponse struct {
+	Embedding []float64 `json:"embedding,omitempty"`
+}
+
+//type OllamaOptions struct {
+//}
diff --git a/relay/channel/ollama/relay-ollama.go b/relay/channel/ollama/relay-ollama.go
index 41a2a15..fa5f818 100644
--- a/relay/channel/ollama/relay-ollama.go
+++ b/relay/channel/ollama/relay-ollama.go
@@ -1,7 +1,14 @@
 package ollama
 
 import (
+	"bytes"
+	"encoding/json"
+	"fmt"
+	"github.com/gin-gonic/gin"
+	"io"
+	"net/http"
 	"one-api/dto"
+	"one-api/service"
 )
 
 func requestOpenAI2Ollama(request dto.GeneralOpenAIRequest) *OllamaRequest {
@@ -20,15 +27,82 @@ func requestOpenAI2Ollama(request dto.GeneralOpenAIRequest) *OllamaRequest {
 		Stop, _ = request.Stop.([]string)
 	}
 	return &OllamaRequest{
-		Model:    request.Model,
-		Messages: messages,
-		Stream:   request.Stream,
-		Options: &OllamaOptions{
-			Temperature: request.Temperature,
-			Seed:        request.Seed,
-			Topp:        request.TopP,
-			TopK:        request.TopK,
-			Stop:        Stop,
-		},
+		Model:       request.Model,
+		Messages:    messages,
+		Stream:      request.Stream,
+		Temperature: request.Temperature,
+		Seed:        request.Seed,
+		Topp:        request.TopP,
+		TopK:        request.TopK,
+		Stop:        Stop,
 	}
 }
+
+func requestOpenAI2Embeddings(request dto.GeneralOpenAIRequest) *OllamaEmbeddingRequest {
+	return &OllamaEmbeddingRequest{
+		Model:  request.Model,
+		Prompt: request.Input,
+	}
+}
+
+func ollamaEmbeddingHandler(c *gin.Context, resp *http.Response, promptTokens int, model string, relayMode int) (*dto.OpenAIErrorWithStatusCode, *dto.Usage, *dto.SensitiveResponse) {
+	var ollamaEmbeddingResponse OllamaEmbeddingResponse
+	responseBody, err := io.ReadAll(resp.Body)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil, nil
+	}
+	err = resp.Body.Close()
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil, nil
+	}
+	err = json.Unmarshal(responseBody, &ollamaEmbeddingResponse)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil, nil
+	}
+	data := make([]dto.OpenAIEmbeddingResponseItem, 0, 1)
+	data = append(data, dto.OpenAIEmbeddingResponseItem{
+		Embedding: ollamaEmbeddingResponse.Embedding,
+		Object:    "embedding",
+	})
+	usage := &dto.Usage{
+		TotalTokens:      promptTokens,
+		CompletionTokens: 0,
+		PromptTokens:     promptTokens,
+	}
+	embeddingResponse := &dto.OpenAIEmbeddingResponse{
+		Object: "list",
+		Data:   data,
+		Model:  model,
+		Usage:  *usage,
+	}
+	doResponseBody, err := json.Marshal(embeddingResponse)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil, nil
+	}
+	resp.Body = io.NopCloser(bytes.NewBuffer(doResponseBody))
+	// We shouldn't set the header before we parse the response body, because the parse part may fail.
+	// And then we will have to send an error response, but in this case, the header has already been set.
+	// So the httpClient will be confused by the response.
+	// For example, Postman will report error, and we cannot check the response at all.
+	// Copy headers
+	for k, v := range resp.Header {
+		// 删除任何现有的相同头部，以防止重复添加头部
+		c.Writer.Header().Del(k)
+		for _, vv := range v {
+			c.Writer.Header().Add(k, vv)
+		}
+	}
+	// reset content length
+	c.Writer.Header().Del("Content-Length")
+	c.Writer.Header().Set("Content-Length", fmt.Sprintf("%d", len(doResponseBody)))
+	c.Writer.WriteHeader(resp.StatusCode)
+	_, err = io.Copy(c.Writer, resp.Body)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "copy_response_body_failed", http.StatusInternalServerError), nil, nil
+	}
+	err = resp.Body.Close()
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil, nil
+	}
+	return nil, usage, nil
+}

From 786ccc7da0c040f95d8f4277be5cde0d6a51f838 Mon Sep 17 00:00:00 2001
From: CaIon <1808837298@qq.com>
Date: Tue, 26 Mar 2024 23:00:04 +0800
Subject: [PATCH 12/12] =?UTF-8?q?feat:=20=E5=BC=80=E5=90=AFredis=E7=9A=84?=
 =?UTF-8?q?=E6=83=85=E5=86=B5=E4=B8=8B=E8=AE=BE=E7=BD=AESYNC=5FFREQUENCY?=
 =?UTF-8?q?=E9=BB=98=E8=AE=A4=E4=B8=BA60?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 common/redis.go | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/common/redis.go b/common/redis.go
index 2e3e56d..6a35235 100644
--- a/common/redis.go
+++ b/common/redis.go
@@ -18,9 +18,8 @@ func InitRedisClient() (err error) {
 		return nil
 	}
 	if os.Getenv("SYNC_FREQUENCY") == "" {
-		RedisEnabled = false
-		SysLog("SYNC_FREQUENCY not set, Redis is disabled")
-		return nil
+		SysLog("SYNC_FREQUENCY not set, use default value 60")
+		SyncFrequency = 60
 	}
 	SysLog("Redis is enabled")
 	opt, err := redis.ParseURL(os.Getenv("REDIS_CONN_STRING"))