Merge remote-tracking branch 'origin/upstream/main'

relay/adaptor/cloudflare/constant.go

@@ -1,6 +1,7 @@
 package cloudflare
 
 var ModelList = []string{
+	"@cf/meta/llama-3.1-8b-instruct",
 	"@cf/meta/llama-2-7b-chat-fp16",
 	"@cf/meta/llama-2-7b-chat-int8",
 	"@cf/mistral/mistral-7b-instruct-v0.1",

relay/adaptor/gemini/constants.go

@@ -3,6 +3,5 @@ package gemini
 // https://ai.google.dev/models/gemini
 
 var ModelList = []string{
-	"gemini-pro", "gemini-1.0-pro-001", "gemini-1.5-pro",
-	"gemini-pro-vision", "gemini-1.0-pro-vision-001", "embedding-001", "text-embedding-004",
+	"gemini-pro", "gemini-1.0-pro", "gemini-1.5-flash", "gemini-1.5-pro", "text-embedding-004", "aqa",
 }

relay/adaptor/groq/constants.go

@@ -4,9 +4,14 @@ package groq
 
 var ModelList = []string{
 	"gemma-7b-it",
-	"llama2-7b-2048",
-	"llama2-70b-4096",
 	"mixtral-8x7b-32768",
 	"llama3-8b-8192",
 	"llama3-70b-8192",
+	"gemma2-9b-it",
+	"llama-3.1-405b-reasoning",
+	"llama-3.1-70b-versatile",
+	"llama-3.1-8b-instant",
+	"llama3-groq-70b-8192-tool-use-preview",
+	"llama3-groq-8b-8192-tool-use-preview",
+	"whisper-large-v3",
 }

relay/adaptor/ollama/adaptor.go

@@ -24,7 +24,7 @@ func (a *Adaptor) GetRequestURL(meta *meta.Meta) (string, error) {
 	// https://github.com/ollama/ollama/blob/main/docs/api.md
 	fullRequestURL := fmt.Sprintf("%s/api/chat", meta.BaseURL)
 	if meta.Mode == relaymode.Embeddings {
-		fullRequestURL = fmt.Sprintf("%s/api/embeddings", meta.BaseURL)
+		fullRequestURL = fmt.Sprintf("%s/api/embed", meta.BaseURL)
 	}
 	return fullRequestURL, nil
 }

relay/adaptor/ollama/main.go

@@ -30,6 +30,8 @@ func ConvertRequest(request model.GeneralOpenAIRequest) *ChatRequest {
 			TopP:             request.TopP,
 			FrequencyPenalty: request.FrequencyPenalty,
 			PresencePenalty:  request.PresencePenalty,
+			NumPredict:  	  request.MaxTokens,
+			NumCtx:  	  request.NumCtx,
 		},
 		Stream: request.Stream,
 	}
@@ -117,8 +119,10 @@ func StreamHandler(c *gin.Context, resp *http.Response) (*model.ErrorWithStatusC
 	common.SetEventStreamHeaders(c)
 
 	for scanner.Scan() {
-		data := strings.TrimPrefix(scanner.Text(), "}")
-		data = data + "}"
+		data := scanner.Text()
+		if strings.HasPrefix(data, "}") {
+		    data = strings.TrimPrefix(data, "}") + "}"
+		}
 
 		var ollamaResponse ChatResponse
 		err := json.Unmarshal([]byte(data), &ollamaResponse)
@@ -156,8 +160,15 @@ func StreamHandler(c *gin.Context, resp *http.Response) (*model.ErrorWithStatusC
 
 func ConvertEmbeddingRequest(request model.GeneralOpenAIRequest) *EmbeddingRequest {
 	return &EmbeddingRequest{
-		Model:  request.Model,
-		Prompt: strings.Join(request.ParseInput(), " "),
+		Model: request.Model,
+		Input: request.ParseInput(),
+		Options: &Options{
+			Seed:             int(request.Seed),
+			Temperature:      request.Temperature,
+			TopP:             request.TopP,
+			FrequencyPenalty: request.FrequencyPenalty,
+			PresencePenalty:  request.PresencePenalty,
+		},
 	}
 }
 
@@ -200,15 +211,17 @@ func embeddingResponseOllama2OpenAI(response *EmbeddingResponse) *openai.Embeddi
 	openAIEmbeddingResponse := openai.EmbeddingResponse{
 		Object: "list",
 		Data:   make([]openai.EmbeddingResponseItem, 0, 1),
-		Model:  "text-embedding-v1",
+		Model:  response.Model,
 		Usage:  model.Usage{TotalTokens: 0},
 	}
 
-	openAIEmbeddingResponse.Data = append(openAIEmbeddingResponse.Data, openai.EmbeddingResponseItem{
-		Object:    `embedding`,
-		Index:     0,
-		Embedding: response.Embedding,
-	})
+	for i, embedding := range response.Embeddings {
+		openAIEmbeddingResponse.Data = append(openAIEmbeddingResponse.Data, openai.EmbeddingResponseItem{
+			Object:    `embedding`,
+			Index:     i,
+			Embedding: embedding,
+		})
+	}
 	return &openAIEmbeddingResponse
 }
 

relay/adaptor/ollama/model.go

@@ -7,6 +7,8 @@ type Options struct {
 	TopP             float64 `json:"top_p,omitempty"`
 	FrequencyPenalty float64 `json:"frequency_penalty,omitempty"`
 	PresencePenalty  float64 `json:"presence_penalty,omitempty"`
+	NumPredict  	 int 	 `json:"num_predict,omitempty"`
+	NumCtx  	 int 	 `json:"num_ctx,omitempty"`
 }
 
 type Message struct {
@@ -37,11 +39,15 @@ type ChatResponse struct {
 }
 
 type EmbeddingRequest struct {
-	Model  string `json:"model"`
-	Prompt string `json:"prompt"`
+	Model string   `json:"model"`
+	Input []string `json:"input"`
+	// Truncate  bool     `json:"truncate,omitempty"`
+	Options *Options `json:"options,omitempty"`
+	// KeepAlive string   `json:"keep_alive,omitempty"`
 }
 
 type EmbeddingResponse struct {
-	Error     string    `json:"error,omitempty"`
-	Embedding []float64 `json:"embedding,omitempty"`
+	Error      string      `json:"error,omitempty"`
+	Model      string      `json:"model"`
+	Embeddings [][]float64 `json:"embeddings"`
 }

relay/adaptor/openai/compatible.go

@@ -13,6 +13,7 @@ import (
 	"github.com/songquanpeng/one-api/relay/adaptor/novita"
 	"github.com/songquanpeng/one-api/relay/adaptor/stepfun"
 	"github.com/songquanpeng/one-api/relay/adaptor/togetherai"
+	"github.com/songquanpeng/one-api/relay/adaptor/siliconflow"
 	"github.com/songquanpeng/one-api/relay/channeltype"
 )
 
@@ -30,6 +31,7 @@ var CompatibleChannels = []int{
 	channeltype.DeepSeek,
 	channeltype.TogetherAI,
 	channeltype.Novita,
+	channeltype.SiliconFlow,
 }
 
 func GetCompatibleChannelMeta(channelType int) (string, []string) {
@@ -60,6 +62,8 @@ func GetCompatibleChannelMeta(channelType int) (string, []string) {
 		return "doubao", doubao.ModelList
 	case channeltype.Novita:
 		return "novita", novita.ModelList
+	case channeltype.SiliconFlow:
+		return "siliconflow", siliconflow.ModelList
 	default:
 		return "openai", ModelList
 	}

relay/adaptor/siliconflow/constants.go

@@ -0,0 +1,36 @@
+package siliconflow
+
+// https://docs.siliconflow.cn/docs/getting-started
+
+var ModelList = []string{
+	"deepseek-ai/deepseek-llm-67b-chat",
+	"Qwen/Qwen1.5-14B-Chat",
+	"Qwen/Qwen1.5-7B-Chat",
+	"Qwen/Qwen1.5-110B-Chat",
+	"Qwen/Qwen1.5-32B-Chat",
+	"01-ai/Yi-1.5-6B-Chat",
+	"01-ai/Yi-1.5-9B-Chat-16K",
+	"01-ai/Yi-1.5-34B-Chat-16K",
+	"THUDM/chatglm3-6b",
+	"deepseek-ai/DeepSeek-V2-Chat",
+	"THUDM/glm-4-9b-chat",
+	"Qwen/Qwen2-72B-Instruct",
+	"Qwen/Qwen2-7B-Instruct",
+	"Qwen/Qwen2-57B-A14B-Instruct",
+	"deepseek-ai/DeepSeek-Coder-V2-Instruct",
+	"Qwen/Qwen2-1.5B-Instruct",
+	"internlm/internlm2_5-7b-chat",
+	"BAAI/bge-large-en-v1.5",
+	"BAAI/bge-large-zh-v1.5",
+	"Pro/Qwen/Qwen2-7B-Instruct",
+	"Pro/Qwen/Qwen2-1.5B-Instruct",
+	"Pro/Qwen/Qwen1.5-7B-Chat",
+	"Pro/THUDM/glm-4-9b-chat",
+	"Pro/THUDM/chatglm3-6b",
+	"Pro/01-ai/Yi-1.5-9B-Chat-16K",
+	"Pro/01-ai/Yi-1.5-6B-Chat",
+	"Pro/google/gemma-2-9b-it",
+	"Pro/internlm/internlm2_5-7b-chat",
+	"Pro/meta-llama/Meta-Llama-3-8B-Instruct",
+	"Pro/mistralai/Mistral-7B-Instruct-v0.2",
+}