From 997729f4111e34a4bd2c31b908449a0393c53a3d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E9=9F=A9=E8=B4=A4=E6=B6=9B?= <601803023@qq.com> Date: Sun, 15 Dec 2024 15:12:00 +0800 Subject: [PATCH] feat: support choosing chatCompletionV2 or chatCompletionPro API for minimax provider (#1593) --- plugins/wasm-go/extensions/ai-proxy/README.md | 32 +++-- .../extensions/ai-proxy/provider/minimax.go | 119 +++++++----------- .../extensions/ai-proxy/provider/provider.go | 6 +- 3 files changed, 68 insertions(+), 89 deletions(-) diff --git a/plugins/wasm-go/extensions/ai-proxy/README.md b/plugins/wasm-go/extensions/ai-proxy/README.md index 8317f653d4..80b7c2a890 100644 --- a/plugins/wasm-go/extensions/ai-proxy/README.md +++ b/plugins/wasm-go/extensions/ai-proxy/README.md @@ -174,9 +174,10 @@ Mistral 所对应的 `type` 为 `mistral`。它并无特有的配置字段。 MiniMax所对应的 `type` 为 `minimax`。它特有的配置字段如下： -| 名称 | 数据类型 | 填写要求 | 默认值 | 描述 | -| ---------------- | -------- | ------------------------------------------------------------ | ------ | ------------------------------------------------------------ | -| `minimaxGroupId` | string | 当使用`abab6.5-chat`, `abab6.5s-chat`, `abab5.5s-chat`, `abab5.5-chat`四种模型时必填 | - | 当使用`abab6.5-chat`, `abab6.5s-chat`, `abab5.5s-chat`, `abab5.5-chat`四种模型时会使用ChatCompletion Pro，需要设置groupID | +| 名称 | 数据类型 | 填写要求 | 默认值 | 描述 | +| ---------------- | -------- | ------------------------------ | ------ |----------------------------------------------------------------| +| `minimaxApiType` | string | v2 和 pro 中选填一项 | v2 | v2 代表 ChatCompletion v2 API，pro 代表 ChatCompletion Pro API | +| `minimaxGroupId` | string | `minimaxApiType` 为 pro 时必填 | - | `minimaxApiType` 为 pro 时使用 ChatCompletion Pro API，需要设置 groupID | #### Anthropic Claude @@ -1000,17 +1001,16 @@ provider: apiTokens: - "YOUR_MINIMAX_API_TOKEN" modelMapping: - "gpt-3": "abab6.5g-chat" - "gpt-4": "abab6.5-chat" - "*": "abab6.5g-chat" - minimaxGroupId: "YOUR_MINIMAX_GROUP_ID" + "gpt-3": "abab6.5s-chat" + "gpt-4": "abab6.5g-chat" + "*": "abab6.5t-chat" ``` **请求示例** ```json { - "model": "gpt-4-turbo", + "model": "gpt-3", "messages": [ { "role": "user", @@ -1025,27 +1025,33 @@ provider: ```json { - "id": "02b2251f8c6c09d68c1743f07c72afd7", + "id": "03ac4fcfe1c6cc9c6a60f9d12046e2b4", "choices": [ { "finish_reason": "stop", "index": 0, "message": { - "content": "你好！我是MM智能助理，一款由MiniMax自研的大型语言模型。我可以帮助你解答问题，提供信息，进行对话等。有什么可以帮助你的吗？", - "role": "assistant" + "content": "你好，我是一个由MiniMax公司研发的大型语言模型，名为MM智能助理。我可以帮助回答问题、提供信息、进行对话和执行多种语言处理任务。如果你有任何问题或需要帮助，请随时告诉我！", + "role": "assistant", + "name": "MM智能助理", + "audio_content": "" } } ], - "created": 1717760544, + "created": 1734155471, "model": "abab6.5s-chat", "object": "chat.completion", "usage": { - "total_tokens": 106 + "total_tokens": 116, + "total_characters": 0, + "prompt_tokens": 70, + "completion_tokens": 46 }, "input_sensitive": false, "output_sensitive": false, "input_sensitive_type": 0, "output_sensitive_type": 0, + "output_sensitive_int": 0, "base_resp": { "status_code": 0, "status_msg": "" diff --git a/plugins/wasm-go/extensions/ai-proxy/provider/minimax.go b/plugins/wasm-go/extensions/ai-proxy/provider/minimax.go index 0bcf7ac326..56e36441a1 100644 --- a/plugins/wasm-go/extensions/ai-proxy/provider/minimax.go +++ b/plugins/wasm-go/extensions/ai-proxy/provider/minimax.go @@ -11,47 +11,37 @@ import ( "github.com/alibaba/higress/plugins/wasm-go/pkg/wrapper" "github.com/higress-group/proxy-wasm-go-sdk/proxywasm" "github.com/higress-group/proxy-wasm-go-sdk/proxywasm/types" + "github.com/tidwall/gjson" + "github.com/tidwall/sjson" ) // minimaxProvider is the provider for minimax service. const ( - minimaxDomain = "api.minimax.chat" - // minimaxChatCompletionV2Path 接口请求响应格式与OpenAI相同 - // 接口文档: https://platform.minimaxi.com/document/guides/chat-model/V2?id=65e0736ab2845de20908e2dd + minimaxApiTypeV2 = "v2" // minimaxApiTypeV2 represents chat completion V2 API. + minimaxApiTypePro = "pro" // minimaxApiTypePro represents chat completion Pro API. + minimaxDomain = "api.minimax.chat" + // minimaxChatCompletionV2Path represents the API path for chat completion V2 API which has a response format similar to OpenAI's. minimaxChatCompletionV2Path = "/v1/text/chatcompletion_v2" - // minimaxChatCompletionProPath 接口请求响应格式与OpenAI不同 - // 接口文档: https://platform.minimaxi.com/document/guides/chat-model/pro/api?id=6569c85948bc7b684b30377e + // minimaxChatCompletionProPath represents the API path for chat completion Pro API which has a different response format from OpenAI's. minimaxChatCompletionProPath = "/v1/text/chatcompletion_pro" - senderTypeUser string = "USER" // 用户发送的内容 - senderTypeBot string = "BOT" // 模型生成的内容 + senderTypeUser string = "USER" // Content sent by the user. + senderTypeBot string = "BOT" // Content generated by the model. - // 默认机器人设置 + // Default bot settings. defaultBotName string = "MM智能助理" defaultBotSettingContent string = "MM智能助理是一款由MiniMax自研的，没有调用其他产品的接口的大型语言模型。MiniMax是一家中国科技公司，一直致力于进行大模型相关的研究。" defaultSenderName string = "小明" ) -// chatCompletionProModels 这些模型对应接口为ChatCompletion Pro -var chatCompletionProModels = map[string]struct{}{ - "abab6.5-chat": {}, - "abab6.5s-chat": {}, - "abab5.5s-chat": {}, - "abab5.5-chat": {}, -} - type minimaxProviderInitializer struct { } func (m *minimaxProviderInitializer) ValidateConfig(config ProviderConfig) error { - // 如果存在模型对应接口为ChatCompletion Pro必须配置minimaxGroupId - if len(config.modelMapping) > 0 && config.minimaxGroupId == "" { - for _, minimaxModel := range config.modelMapping { - if _, exists := chatCompletionProModels[minimaxModel]; exists { - return errors.New(fmt.Sprintf("missing minimaxGroupId in provider config when %s model is provided", minimaxModel)) - } - } + // If using the chat completion Pro API, a group ID must be set. + if minimaxApiTypePro == config.minimaxApiType && config.minimaxGroupId == "" { + return errors.New(fmt.Sprintf("missing minimaxGroupId in provider config when minimaxApiType is %s", minimaxApiTypePro)) } if config.apiTokens == nil || len(config.apiTokens) == 0 { return errors.New("no apiToken found in provider config") @@ -94,23 +84,11 @@ func (m *minimaxProvider) OnRequestBody(ctx wrapper.HttpContext, apiName ApiName if apiName != ApiNameChatCompletion { return types.ActionContinue, errUnsupportedApiName } - // 解析并映射模型,设置上下文 - model, err := m.parseModel(body) - if err != nil { - return types.ActionContinue, err - } - ctx.SetContext(ctxKeyOriginalRequestModel, model) - mappedModel := getMappedModel(model, m.config.modelMapping, log) - if mappedModel == "" { - return types.ActionContinue, errors.New("model becomes empty after applying the configured mapping") - } - ctx.SetContext(ctxKeyFinalRequestModel, mappedModel) - _, ok := chatCompletionProModels[mappedModel] - if ok { - // 使用ChatCompletion Pro接口 + if minimaxApiTypePro == m.config.minimaxApiType { + // Use chat completion Pro API. return m.handleRequestBodyByChatCompletionPro(body, log) } else { - // 使用ChatCompletion v2接口 + // Use chat completion V2 API. return m.config.handleRequestBody(m, m.contextCache, ctx, apiName, body, log) } } @@ -119,14 +97,14 @@ func (m *minimaxProvider) TransformRequestBodyHeaders(ctx wrapper.HttpContext, a return m.handleRequestBodyByChatCompletionV2(body, headers, log) } -// handleRequestBodyByChatCompletionPro 使用ChatCompletion Pro接口处理请求体 +// handleRequestBodyByChatCompletionPro processes the request body using the chat completion Pro API. func (m *minimaxProvider) handleRequestBodyByChatCompletionPro(body []byte, log wrapper.Log) (types.Action, error) { request := &chatCompletionRequest{} if err := decodeChatCompletionRequest(body, request); err != nil { return types.ActionContinue, err } - // 映射模型重写requestPath + // Map the model and rewrite the request path. request.Model = getMappedModel(request.Model, m.config.modelMapping, log) _ = util.OverwriteRequestPath(fmt.Sprintf("%s?GroupId=%s", minimaxChatCompletionProPath, m.config.minimaxGroupId)) @@ -143,9 +121,9 @@ func (m *minimaxProvider) handleRequestBodyByChatCompletionPro(body []byte, log log.Errorf("failed to load context file: %v", err) util.ErrorHandler("ai-proxy.minimax.load_ctx_failed", fmt.Errorf("failed to load context file: %v", err)) } - // 由于 minimaxChatCompletionV2（格式和 OpenAI 一致）和 minimaxChatCompletionPro（格式和 OpenAI 不一致）中 insertHttpContextMessage 的逻辑不同，无法做到同一个 provider 统一 - // 因此对于 minimaxChatCompletionPro 需要手动处理 context 消息 - // minimaxChatCompletionV2 交给默认的 defaultInsertHttpContextMessage 方法插入 context 消息 + // Since minimaxChatCompletionV2 (format consistent with OpenAI) and minimaxChatCompletionPro (different format from OpenAI) have different logic for insertHttpContextMessage, we cannot unify them within one provider. + // For minimaxChatCompletionPro, we need to manually handle context messages. + // minimaxChatCompletionV2 uses the default defaultInsertHttpContextMessage method to insert context messages. minimaxRequest := m.buildMinimaxChatCompletionV2Request(request, content) if err := replaceJsonRequestBody(minimaxRequest, log); err != nil { util.ErrorHandler("ai-proxy.minimax.insert_ctx_failed", fmt.Errorf("failed to replace Request body: %v", err)) @@ -157,54 +135,45 @@ func (m *minimaxProvider) handleRequestBodyByChatCompletionPro(body []byte, log return types.ActionContinue, err } -// handleRequestBodyByChatCompletionV2 使用ChatCompletion v2接口处理请求体 +// handleRequestBodyByChatCompletionV2 processes the request body using the chat completion V2 API. func (m *minimaxProvider) handleRequestBodyByChatCompletionV2(body []byte, headers http.Header, log wrapper.Log) ([]byte, error) { - request := &chatCompletionRequest{} - if err := decodeChatCompletionRequest(body, request); err != nil { - return nil, err - } - - // 映射模型重写requestPath - request.Model = getMappedModel(request.Model, m.config.modelMapping, log) util.OverwriteRequestPathHeader(headers, minimaxChatCompletionV2Path) - return body, nil + rawModel := gjson.GetBytes(body, "model").String() + mappedModel := getMappedModel(rawModel, m.config.modelMapping, log) + return sjson.SetBytes(body, "model", mappedModel) } func (m *minimaxProvider) OnResponseHeaders(ctx wrapper.HttpContext, apiName ApiName, log wrapper.Log) (types.Action, error) { - // 使用minimax接口协议,跳过OnStreamingResponseBody()和OnResponseBody() + // Skip OnStreamingResponseBody() and OnResponseBody() when using original protocol. if m.config.protocol == protocolOriginal { ctx.DontReadResponseBody() return types.ActionContinue, nil } - // 模型对应接口为ChatCompletion v2,跳过OnStreamingResponseBody()和OnResponseBody() - model := ctx.GetStringContext(ctxKeyFinalRequestModel, "") - if model != "" { - _, ok := chatCompletionProModels[model] - if !ok { - ctx.DontReadResponseBody() - return types.ActionContinue, nil - } + // Skip OnStreamingResponseBody() and OnResponseBody() when the model corresponds to the chat completion V2 interface. + if minimaxApiTypePro != m.config.minimaxApiType { + ctx.DontReadResponseBody() + return types.ActionContinue, nil } _ = proxywasm.RemoveHttpResponseHeader("Content-Length") return types.ActionContinue, nil } -// OnStreamingResponseBody 只处理使用OpenAI协议 且 模型对应接口为ChatCompletion Pro的流式响应 +// OnStreamingResponseBody handles streaming response chunks from the Minimax service only for requests using the OpenAI protocol and corresponding to the chat completion Pro API. func (m *minimaxProvider) OnStreamingResponseBody(ctx wrapper.HttpContext, name ApiName, chunk []byte, isLastChunk bool, log wrapper.Log) ([]byte, error) { if isLastChunk || len(chunk) == 0 { return nil, nil } - // sample event response: + // Sample event response: // data: {"created":1689747645,"model":"abab6.5s-chat","reply":"","choices":[{"messages":[{"sender_type":"BOT","sender_name":"MM智能助理","text":"am from China."}]}],"output_sensitive":false} - // sample end event response: + // Sample end event response: // data: {"created":1689747645,"model":"abab6.5s-chat","reply":"I am from China.","choices":[{"finish_reason":"stop","messages":[{"sender_type":"BOT","sender_name":"MM智能助理","text":"I am from China."}]}],"usage":{"total_tokens":187},"input_sensitive":false,"output_sensitive":false,"id":"0106b3bc9fd844a9f3de1aa06004e2ab","base_resp":{"status_code":0,"status_msg":""}} responseBuilder := &strings.Builder{} lines := strings.Split(string(chunk), "\n") for _, data := range lines { if len(data) < 6 { - // ignore blank line or wrong format + // Ignore blank line or improperly formatted lines. continue } data = data[6:] @@ -226,7 +195,7 @@ func (m *minimaxProvider) OnStreamingResponseBody(ctx wrapper.HttpContext, name return []byte(modifiedResponseChunk), nil } -// OnResponseBody 只处理使用OpenAI协议 且 模型对应接口为ChatCompletion Pro的流式响应 +// OnResponseBody handles the final response body from the Minimax service only for requests using the OpenAI protocol and corresponding to the chat completion Pro API. func (m *minimaxProvider) OnResponseBody(ctx wrapper.HttpContext, apiName ApiName, body []byte, log wrapper.Log) (types.Action, error) { minimaxResp := &minimaxChatCompletionV2Resp{} if err := json.Unmarshal(body, minimaxResp); err != nil { @@ -239,39 +208,39 @@ func (m *minimaxProvider) OnResponseBody(ctx wrapper.HttpContext, apiName ApiNam return types.ActionContinue, replaceJsonResponseBody(response, log) } -// minimaxChatCompletionV2Request 表示ChatCompletion V2请求的结构体 +// minimaxChatCompletionV2Request represents the structure of a chat completion V2 request. type minimaxChatCompletionV2Request struct { Model string `json:"model"` Stream bool `json:"stream,omitempty"` TokensToGenerate int64 `json:"tokens_to_generate,omitempty"` Temperature float64 `json:"temperature,omitempty"` TopP float64 `json:"top_p,omitempty"` - MaskSensitiveInfo bool `json:"mask_sensitive_info"` // 是否开启隐私信息打码,默认true + MaskSensitiveInfo bool `json:"mask_sensitive_info"` // Whether to mask sensitive information, defaults to true. Messages []minimaxMessage `json:"messages"` BotSettings []minimaxBotSetting `json:"bot_setting"` ReplyConstraints minimaxReplyConstraints `json:"reply_constraints"` } -// minimaxMessage 表示对话中的消息 +// minimaxMessage represents a message in the conversation. type minimaxMessage struct { SenderType string `json:"sender_type"` SenderName string `json:"sender_name"` Text string `json:"text"` } -// minimaxBotSetting 表示机器人的设置 +// minimaxBotSetting represents the bot's settings. type minimaxBotSetting struct { BotName string `json:"bot_name"` Content string `json:"content"` } -// minimaxReplyConstraints 表示模型回复要求 +// minimaxReplyConstraints represents requirements for model replies. type minimaxReplyConstraints struct { SenderType string `json:"sender_type"` SenderName string `json:"sender_name"` } -// minimaxChatCompletionV2Resp Minimax Chat Completion V2响应结构体 +// minimaxChatCompletionV2Resp represents the structure of a Minimax Chat Completion V2 response. type minimaxChatCompletionV2Resp struct { Created int64 `json:"created"` Model string `json:"model"` @@ -286,20 +255,20 @@ type minimaxChatCompletionV2Resp struct { BaseResp minimaxBaseResp `json:"base_resp"` } -// minimaxBaseResp 包含错误状态码和详情 +// minimaxBaseResp contains error status code and details. type minimaxBaseResp struct { StatusCode int64 `json:"status_code"` StatusMsg string `json:"status_msg"` } -// minimaxChoice 结果选项 +// minimaxChoice represents a result option. type minimaxChoice struct { Messages []minimaxMessage `json:"messages"` Index int64 `json:"index"` FinishReason string `json:"finish_reason"` } -// minimaxUsage 令牌使用情况 +// minimaxUsage represents token usage statistics. type minimaxUsage struct { TotalTokens int64 `json:"total_tokens"` } diff --git a/plugins/wasm-go/extensions/ai-proxy/provider/provider.go b/plugins/wasm-go/extensions/ai-proxy/provider/provider.go index 478f7a24b6..ea1503b1e3 100644 --- a/plugins/wasm-go/extensions/ai-proxy/provider/provider.go +++ b/plugins/wasm-go/extensions/ai-proxy/provider/provider.go @@ -206,8 +206,11 @@ type ProviderConfig struct { // @Title zh-CN hunyuan api id for authorization // @Description zh-CN 仅适用于Hun Yuan AI服务鉴权 hunyuanAuthId string `required:"false" yaml:"hunyuanAuthId" json:"hunyuanAuthId"` + // @Title zh-CN minimax API type + // @Description zh-CN 仅适用于 minimax 服务。minimax API 类型，v2 和 pro 中选填一项，默认值为 v2 + minimaxApiType string `required:"false" yaml:"minimaxApiType" json:"minimaxApiType"` // @Title zh-CN minimax group id - // @Description zh-CN 仅适用于minimax使用ChatCompletion Pro接口的模型 + // @Description zh-CN 仅适用于 minimax 服务。minimax API 类型为 pro 时必填 minimaxGroupId string `required:"false" yaml:"minimaxGroupId" json:"minimaxGroupId"` // @Title zh-CN 模型名称映射表 // @Description zh-CN 用于将请求中的模型名称映射为目标AI服务商支持的模型名称。支持通过“*”来配置全局映射 @@ -303,6 +306,7 @@ func (c *ProviderConfig) FromJson(json gjson.Result) { c.claudeVersion = json.Get("claudeVersion").String() c.hunyuanAuthId = json.Get("hunyuanAuthId").String() c.hunyuanAuthKey = json.Get("hunyuanAuthKey").String() + c.minimaxApiType = json.Get("minimaxApiType").String() c.minimaxGroupId = json.Get("minimaxGroupId").String() c.cloudflareAccountId = json.Get("cloudflareAccountId").String() if c.typ == providerTypeGemini {