diff --git a/README.md b/README.md index 3c23f4993..d391bdbff 100644 --- a/README.md +++ b/README.md @@ -1,11 +1,12 @@
- icon + icon +

NextChat (ChatGPT Next Web)

English / [简体中文](./README_CN.md) @@ -13,8 +14,7 @@ English / [简体中文](./README_CN.md) ChatGPTNextWeb%2FChatGPT-Next-Web | Trendshift - -One-Click to get a well-designed cross-platform ChatGPT web UI, with Claude, GPT4 & Gemini Pro support. +✨ Light and Fast AI Assistant,with Claude, DeepSeek, GPT4 & Gemini Pro support. [![Saas][Saas-image]][saas-url] [![Web][Web-image]][web-url] @@ -22,7 +22,7 @@ One-Click to get a well-designed cross-platform ChatGPT web UI, with Claude, GPT [![MacOS][MacOS-image]][download-url] [![Linux][Linux-image]][download-url] -[NextChatAI](https://nextchat.dev/chat?utm_source=readme) / [Web App Demo](https://app.nextchat.dev) / [Desktop App](https://github.com/Yidadaa/ChatGPT-Next-Web/releases) / [Discord](https://discord.gg/YCkeafCafC) / [Enterprise Edition](#enterprise-edition) / [Twitter](https://twitter.com/NextChatDev) +[NextChatAI](https://nextchat.dev/chat?utm_source=readme) / [Web App Demo](https://app.nextchat.dev) / [Desktop App](https://github.com/Yidadaa/ChatGPT-Next-Web/releases) [saas-url]: https://nextchat.dev/chat?utm_source=readme @@ -34,9 +34,9 @@ One-Click to get a well-designed cross-platform ChatGPT web UI, with Claude, GPT [MacOS-image]: https://img.shields.io/badge/-MacOS-black?logo=apple [Linux-image]: https://img.shields.io/badge/-Linux-333?logo=ubuntu -[Deploy on Vercel](https://vercel.com/new/clone?repository-url=https%3A%2F%2Fgithub.com%2FChatGPTNextWeb%2FChatGPT-Next-Web&env=OPENAI_API_KEY&env=CODE&project-name=nextchat&repository-name=NextChat) [Deploy on Zeabur](https://zeabur.com/templates/ZBUEFA) [Open in Gitpod](https://gitpod.io/#https://github.com/Yidadaa/ChatGPT-Next-Web) [BT Deply Install](https://www.bt.cn/new/download.html) +[Deploy on Zeabur](https://zeabur.com/templates/ZBUEFA) [Deploy on Vercel](https://vercel.com/new/clone?repository-url=https%3A%2F%2Fgithub.com%2FChatGPTNextWeb%2FChatGPT-Next-Web&env=OPENAI_API_KEY&env=CODE&project-name=nextchat&repository-name=NextChat) [Open in Gitpod](https://gitpod.io/#https://github.com/ChatGPTNextWeb/NextChat) -[](https://monica.im/?utm=nxcrp) +[](https://monica.im/?utm=nxcrp)
@@ -352,6 +352,13 @@ Customize Stability API url. Enable MCP（Model Context Protocol）Feature +### `SILICONFLOW_API_KEY` (optional) + +SiliconFlow API Key. + +### `SILICONFLOW_URL` (optional) + +SiliconFlow API URL. ## Requirements diff --git a/README_CN.md b/README_CN.md index 9348176e5..f6f4c0be5 100644 --- a/README_CN.md +++ b/README_CN.md @@ -89,7 +89,7 @@ code1,code2,code3 ### `OPENAI_API_KEY` （必填项） -OpanAI 密钥，你在 openai 账户页面申请的 api key，使用英文逗号隔开多个 key，这样可以随机轮询这些 key。 +OpenAI 密钥，你在 openai 账户页面申请的 api key，使用英文逗号隔开多个 key，这样可以随机轮询这些 key。 ### `CODE` （可选） @@ -267,6 +267,13 @@ Stability API密钥 启用MCP（Model Context Protocol）功能 +### `SILICONFLOW_API_KEY` (optional) + +SiliconFlow API Key. + +### `SILICONFLOW_URL` (optional) + +SiliconFlow API URL. ## 开发 diff --git a/app/api/[provider]/[...path]/route.ts b/app/api/[provider]/[...path]/route.ts index 3b5833d7e..8975bf971 100644 --- a/app/api/[provider]/[...path]/route.ts +++ b/app/api/[provider]/[...path]/route.ts @@ -11,6 +11,7 @@ import { handle as moonshotHandler } from "../../moonshot"; import { handle as stabilityHandler } from "../../stability"; import { handle as iflytekHandler } from "../../iflytek"; import { handle as deepseekHandler } from "../../deepseek"; +import { handle as siliconflowHandler } from "../../siliconflow"; import { handle as xaiHandler } from "../../xai"; import { handle as chatglmHandler } from "../../glm"; import { handle as proxyHandler } from "../../proxy"; @@ -47,6 +48,8 @@ async function handle( return xaiHandler(req, { params }); case ApiPath.ChatGLM: return chatglmHandler(req, { params }); + case ApiPath.SiliconFlow: + return siliconflowHandler(req, { params }); case ApiPath.OpenAI: return openaiHandler(req, { params }); default: diff --git a/app/api/auth.ts b/app/api/auth.ts index 1760c249c..8c78c70c8 100644 --- a/app/api/auth.ts +++ b/app/api/auth.ts @@ -101,6 +101,9 @@ export function auth(req: NextRequest, modelProvider: ModelProvider) { case ModelProvider.ChatGLM: systemApiKey = serverConfig.chatglmApiKey; break; + case ModelProvider.SiliconFlow: + systemApiKey = serverConfig.siliconFlowApiKey; + break; case ModelProvider.GPT: default: if (req.nextUrl.pathname.includes("azure/deployments")) { diff --git a/app/api/openai.ts b/app/api/openai.ts index 2b5deca8b..e97dfbfe7 100644 --- a/app/api/openai.ts +++ b/app/api/openai.ts @@ -14,7 +14,7 @@ function getModels(remoteModelRes: OpenAIListModelResponse) { if (config.disableGPT4) { remoteModelRes.data = remoteModelRes.data.filter( (m) => - !(m.id.startsWith("gpt-4") || m.id.startsWith("chatgpt-4o") || m.id.startsWith("o1")) || + !(m.id.startsWith("gpt-4") || m.id.startsWith("chatgpt-4o") || m.id.startsWith("o1") || m.id.startsWith("o3")) || m.id.startsWith("gpt-4o-mini"), ); } diff --git a/app/api/siliconflow.ts b/app/api/siliconflow.ts new file mode 100644 index 000000000..e298a21d4 --- /dev/null +++ b/app/api/siliconflow.ts @@ -0,0 +1,128 @@ +import { getServerSideConfig } from "@/app/config/server"; +import { + SILICONFLOW_BASE_URL, + ApiPath, + ModelProvider, + ServiceProvider, +} from "@/app/constant"; +import { prettyObject } from "@/app/utils/format"; +import { NextRequest, NextResponse } from "next/server"; +import { auth } from "@/app/api/auth"; +import { isModelNotavailableInServer } from "@/app/utils/model"; + +const serverConfig = getServerSideConfig(); + +export async function handle( + req: NextRequest, + { params }: { params: { path: string[] } }, +) { + console.log("[SiliconFlow Route] params ", params); + + if (req.method === "OPTIONS") { + return NextResponse.json({ body: "OK" }, { status: 200 }); + } + + const authResult = auth(req, ModelProvider.SiliconFlow); + if (authResult.error) { + return NextResponse.json(authResult, { + status: 401, + }); + } + + try { + const response = await request(req); + return response; + } catch (e) { + console.error("[SiliconFlow] ", e); + return NextResponse.json(prettyObject(e)); + } +} + +async function request(req: NextRequest) { + const controller = new AbortController(); + + // alibaba use base url or just remove the path + let path = `${req.nextUrl.pathname}`.replaceAll(ApiPath.SiliconFlow, ""); + + let baseUrl = serverConfig.siliconFlowUrl || SILICONFLOW_BASE_URL; + + if (!baseUrl.startsWith("http")) { + baseUrl = `https://${baseUrl}`; + } + + if (baseUrl.endsWith("/")) { + baseUrl = baseUrl.slice(0, -1); + } + + console.log("[Proxy] ", path); + console.log("[Base Url]", baseUrl); + + const timeoutId = setTimeout( + () => { + controller.abort(); + }, + 10 * 60 * 1000, + ); + + const fetchUrl = `${baseUrl}${path}`; + const fetchOptions: RequestInit = { + headers: { + "Content-Type": "application/json", + Authorization: req.headers.get("Authorization") ?? "", + }, + method: req.method, + body: req.body, + redirect: "manual", + // @ts-ignore + duplex: "half", + signal: controller.signal, + }; + + // #1815 try to refuse some request to some models + if (serverConfig.customModels && req.body) { + try { + const clonedBody = await req.text(); + fetchOptions.body = clonedBody; + + const jsonBody = JSON.parse(clonedBody) as { model?: string }; + + // not undefined and is false + if ( + isModelNotavailableInServer( + serverConfig.customModels, + jsonBody?.model as string, + ServiceProvider.SiliconFlow as string, + ) + ) { + return NextResponse.json( + { + error: true, + message: `you are not allowed to use ${jsonBody?.model} model`, + }, + { + status: 403, + }, + ); + } + } catch (e) { + console.error(`[SiliconFlow] filter`, e); + } + } + try { + const res = await fetch(fetchUrl, fetchOptions); + + // to prevent browser prompt for credentials + const newHeaders = new Headers(res.headers); + newHeaders.delete("www-authenticate"); + // to disable nginx buffering + newHeaders.set("X-Accel-Buffering", "no"); + + return new Response(res.body, { + status: res.status, + statusText: res.statusText, + headers: newHeaders, + }); + } finally { + clearTimeout(timeoutId); + } +} diff --git a/app/client/api.ts b/app/client/api.ts index 8f263763b..64ac82b2a 100644 --- a/app/client/api.ts +++ b/app/client/api.ts @@ -23,6 +23,7 @@ import { SparkApi } from "./platforms/iflytek"; import { DeepSeekApi } from "./platforms/deepseek"; import { XAIApi } from "./platforms/xai"; import { ChatGLMApi } from "./platforms/glm"; +import { SiliconflowApi } from "./platforms/siliconflow"; export const ROLES = ["system", "user", "assistant"] as const; export type MessageRole = (typeof ROLES)[number]; @@ -164,6 +165,9 @@ export class ClientApi { case ModelProvider.ChatGLM: this.llm = new ChatGLMApi(); break; + case ModelProvider.SiliconFlow: + this.llm = new SiliconflowApi(); + break; default: this.llm = new ChatGPTApi(); } @@ -254,6 +258,8 @@ export function getHeaders(ignoreHeaders: boolean = false) { const isDeepSeek = modelConfig.providerName === ServiceProvider.DeepSeek; const isXAI = modelConfig.providerName === ServiceProvider.XAI; const isChatGLM = modelConfig.providerName === ServiceProvider.ChatGLM; + const isSiliconFlow = + modelConfig.providerName === ServiceProvider.SiliconFlow; const isEnabledAccessControl = accessStore.enabledAccessControl(); const apiKey = isGoogle ? accessStore.googleApiKey @@ -273,6 +279,8 @@ export function getHeaders(ignoreHeaders: boolean = false) { ? accessStore.deepseekApiKey : isChatGLM ? accessStore.chatglmApiKey + : isSiliconFlow + ? accessStore.siliconflowApiKey : isIflytek ? accessStore.iflytekApiKey && accessStore.iflytekApiSecret ? accessStore.iflytekApiKey + ":" + accessStore.iflytekApiSecret @@ -290,6 +298,7 @@ export function getHeaders(ignoreHeaders: boolean = false) { isDeepSeek, isXAI, isChatGLM, + isSiliconFlow, apiKey, isEnabledAccessControl, }; @@ -317,6 +326,7 @@ export function getHeaders(ignoreHeaders: boolean = false) { isDeepSeek, isXAI, isChatGLM, + isSiliconFlow, apiKey, isEnabledAccessControl, } = getConfig(); @@ -365,6 +375,8 @@ export function getClientApi(provider: ServiceProvider): ClientApi { return new ClientApi(ModelProvider.XAI); case ServiceProvider.ChatGLM: return new ClientApi(ModelProvider.ChatGLM); + case ServiceProvider.SiliconFlow: + return new ClientApi(ModelProvider.SiliconFlow); default: return new ClientApi(ModelProvider.GPT); } diff --git a/app/client/platforms/openai.ts b/app/client/platforms/openai.ts index 5a110b84b..467bb82e0 100644 --- a/app/client/platforms/openai.ts +++ b/app/client/platforms/openai.ts @@ -195,7 +195,7 @@ export class ChatGPTApi implements LLMApi { let requestPayload: RequestPayload | DalleRequestPayload; const isDalle3 = _isDalle3(options.config.model); - const isO1 = options.config.model.startsWith("o1"); + const isO1OrO3 = options.config.model.startsWith("o1") || options.config.model.startsWith("o3"); if (isDalle3) { const prompt = getMessageTextContent( options.messages.slice(-1)?.pop() as any, @@ -217,7 +217,7 @@ export class ChatGPTApi implements LLMApi { const content = visionModel ? await preProcessImageContent(v.content) : getMessageTextContent(v); - if (!(isO1 && v.role === "system")) + if (!(isO1OrO3 && v.role === "system")) messages.push({ role: v.role, content }); } @@ -226,16 +226,16 @@ export class ChatGPTApi implements LLMApi { messages, stream: options.config.stream, model: modelConfig.model, - temperature: !isO1 ? modelConfig.temperature : 1, - presence_penalty: !isO1 ? modelConfig.presence_penalty : 0, - frequency_penalty: !isO1 ? modelConfig.frequency_penalty : 0, - top_p: !isO1 ? modelConfig.top_p : 1, + temperature: !isO1OrO3 ? modelConfig.temperature : 1, + presence_penalty: !isO1OrO3 ? modelConfig.presence_penalty : 0, + frequency_penalty: !isO1OrO3 ? modelConfig.frequency_penalty : 0, + top_p: !isO1OrO3 ? modelConfig.top_p : 1, // max_tokens: Math.max(modelConfig.max_tokens, 1024), // Please do not ask me why not send max_tokens, no reason, this param is just shit, I dont want to explain anymore. }; // O1 使用 max_completion_tokens 控制token数 (https://platform.openai.com/docs/guides/reasoning#controlling-costs) - if (isO1) { + if (isO1OrO3) { requestPayload["max_completion_tokens"] = modelConfig.max_tokens; } @@ -359,7 +359,7 @@ export class ChatGPTApi implements LLMApi { // make a fetch request const requestTimeoutId = setTimeout( () => controller.abort(), - isDalle3 || isO1 ? REQUEST_TIMEOUT_MS * 4 : REQUEST_TIMEOUT_MS, // dalle3 using b64_json is slow. + isDalle3 || isO1OrO3 ? REQUEST_TIMEOUT_MS * 4 : REQUEST_TIMEOUT_MS, // dalle3 using b64_json is slow. ); const res = await fetch(chatPath, chatPayload); diff --git a/app/client/platforms/siliconflow.ts b/app/client/platforms/siliconflow.ts new file mode 100644 index 000000000..fe2f9862b --- /dev/null +++ b/app/client/platforms/siliconflow.ts @@ -0,0 +1,243 @@ +"use client"; +// azure and openai, using same models. so using same LLMApi. +import { + ApiPath, + SILICONFLOW_BASE_URL, + SiliconFlow, + REQUEST_TIMEOUT_MS, +} from "@/app/constant"; +import { + useAccessStore, + useAppConfig, + useChatStore, + ChatMessageTool, + usePluginStore, +} from "@/app/store"; +import { streamWithThink } from "@/app/utils/chat"; +import { + ChatOptions, + getHeaders, + LLMApi, + LLMModel, + SpeechOptions, +} from "../api"; +import { getClientConfig } from "@/app/config/client"; +import { + getMessageTextContent, + getMessageTextContentWithoutThinking, +} from "@/app/utils"; +import { RequestPayload } from "./openai"; +import { fetch } from "@/app/utils/stream"; + +export class SiliconflowApi implements LLMApi { + private disableListModels = true; + + path(path: string): string { + const accessStore = useAccessStore.getState(); + + let baseUrl = ""; + + if (accessStore.useCustomConfig) { + baseUrl = accessStore.siliconflowUrl; + } + + if (baseUrl.length === 0) { + const isApp = !!getClientConfig()?.isApp; + const apiPath = ApiPath.SiliconFlow; + baseUrl = isApp ? SILICONFLOW_BASE_URL : apiPath; + } + + if (baseUrl.endsWith("/")) { + baseUrl = baseUrl.slice(0, baseUrl.length - 1); + } + if ( + !baseUrl.startsWith("http") && + !baseUrl.startsWith(ApiPath.SiliconFlow) + ) { + baseUrl = "https://" + baseUrl; + } + + console.log("[Proxy Endpoint] ", baseUrl, path); + + return [baseUrl, path].join("/"); + } + + extractMessage(res: any) { + return res.choices?.at(0)?.message?.content ?? ""; + } + + speech(options: SpeechOptions): Promise { + throw new Error("Method not implemented."); + } + + async chat(options: ChatOptions) { + const messages: ChatOptions["messages"] = []; + for (const v of options.messages) { + if (v.role === "assistant") { + const content = getMessageTextContentWithoutThinking(v); + messages.push({ role: v.role, content }); + } else { + const content = getMessageTextContent(v); + messages.push({ role: v.role, content }); + } + } + + const modelConfig = { + ...useAppConfig.getState().modelConfig, + ...useChatStore.getState().currentSession().mask.modelConfig, + ...{ + model: options.config.model, + providerName: options.config.providerName, + }, + }; + + const requestPayload: RequestPayload = { + messages, + stream: options.config.stream, + model: modelConfig.model, + temperature: modelConfig.temperature, + presence_penalty: modelConfig.presence_penalty, + frequency_penalty: modelConfig.frequency_penalty, + top_p: modelConfig.top_p, + // max_tokens: Math.max(modelConfig.max_tokens, 1024), + // Please do not ask me why not send max_tokens, no reason, this param is just shit, I dont want to explain anymore. + }; + + console.log("[Request] openai payload: ", requestPayload); + + const shouldStream = !!options.config.stream; + const controller = new AbortController(); + options.onController?.(controller); + + try { + const chatPath = this.path(SiliconFlow.ChatPath); + const chatPayload = { + method: "POST", + body: JSON.stringify(requestPayload), + signal: controller.signal, + headers: getHeaders(), + }; + + // console.log(chatPayload); + + // make a fetch request + const requestTimeoutId = setTimeout( + () => controller.abort(), + REQUEST_TIMEOUT_MS, + ); + + if (shouldStream) { + const [tools, funcs] = usePluginStore + .getState() + .getAsTools( + useChatStore.getState().currentSession().mask?.plugin || [], + ); + return streamWithThink( + chatPath, + requestPayload, + getHeaders(), + tools as any, + funcs, + controller, + // parseSSE + (text: string, runTools: ChatMessageTool[]) => { + // console.log("parseSSE", text, runTools); + const json = JSON.parse(text); + const choices = json.choices as Array<{ + delta: { + content: string | null; + tool_calls: ChatMessageTool[]; + reasoning_content: string | null; + }; + }>; + const tool_calls = choices[0]?.delta?.tool_calls; + if (tool_calls?.length > 0) { + const index = tool_calls[0]?.index; + const id = tool_calls[0]?.id; + const args = tool_calls[0]?.function?.arguments; + if (id) { + runTools.push({ + id, + type: tool_calls[0]?.type, + function: { + name: tool_calls[0]?.function?.name as string, + arguments: args, + }, + }); + } else { + // @ts-ignore + runTools[index]["function"]["arguments"] += args; + } + } + const reasoning = choices[0]?.delta?.reasoning_content; + const content = choices[0]?.delta?.content; + + // Skip if both content and reasoning_content are empty or null + if ( + (!reasoning || reasoning.trim().length === 0) && + (!content || content.trim().length === 0) + ) { + return { + isThinking: false, + content: "", + }; + } + + if (reasoning && reasoning.trim().length > 0) { + return { + isThinking: true, + content: reasoning, + }; + } else if (content && content.trim().length > 0) { + return { + isThinking: false, + content: content, + }; + } + + return { + isThinking: false, + content: "", + }; + }, + // processToolMessage, include tool_calls message and tool call results + ( + requestPayload: RequestPayload, + toolCallMessage: any, + toolCallResult: any[], + ) => { + // @ts-ignore + requestPayload?.messages?.splice( + // @ts-ignore + requestPayload?.messages?.length, + 0, + toolCallMessage, + ...toolCallResult, + ); + }, + options, + ); + } else { + const res = await fetch(chatPath, chatPayload); + clearTimeout(requestTimeoutId); + + const resJson = await res.json(); + const message = this.extractMessage(resJson); + options.onFinish(message, res); + } + } catch (e) { + console.log("[Request] failed to make a chat request", e); + options.onError?.(e as Error); + } + } + async usage() { + return { + used: 0, + total: 0, + }; + } + + async models(): Promise { + return []; + } +} diff --git a/app/components/emoji.tsx b/app/components/emoji.tsx index d75cdda92..54d1c1c99 100644 --- a/app/components/emoji.tsx +++ b/app/components/emoji.tsx @@ -38,7 +38,8 @@ export function Avatar(props: { model?: ModelType; avatar?: string }) {
{props.model?.startsWith("gpt-4") || props.model?.startsWith("chatgpt-4o") || - props.model?.startsWith("o1") ? ( + props.model?.startsWith("o1") || + props.model?.startsWith("o3") ? ( ) : ( diff --git a/app/components/settings.tsx b/app/components/settings.tsx index 3b990ed2c..68ebcf084 100644 --- a/app/components/settings.tsx +++ b/app/components/settings.tsx @@ -74,6 +74,7 @@ import { SAAS_CHAT_URL, ChatGLM, DeepSeek, + SiliconFlow, } from "../constant"; import { Prompt, SearchService, usePromptStore } from "../store/prompt"; import { ErrorBoundary } from "./error"; @@ -1318,6 +1319,46 @@ export function Settings() { ); + const siliconflowConfigComponent = accessStore.provider === + ServiceProvider.SiliconFlow && ( + <> + + + accessStore.update( + (access) => (access.siliconflowUrl = e.currentTarget.value), + ) + } + > + + + { + accessStore.update( + (access) => (access.siliconflowApiKey = e.currentTarget.value), + ); + }} + /> + + + ); const stabilityConfigComponent = accessStore.provider === ServiceProvider.Stability && ( @@ -1780,6 +1821,7 @@ export function Settings() { {lflytekConfigComponent} {XAIConfigComponent} {chatglmConfigComponent} + {siliconflowConfigComponent} )} diff --git a/app/config/server.ts b/app/config/server.ts index 1166805b5..43d4ff833 100644 --- a/app/config/server.ts +++ b/app/config/server.ts @@ -84,6 +84,10 @@ declare global { CHATGLM_URL?: string; CHATGLM_API_KEY?: string; + // siliconflow only + SILICONFLOW_URL?: string; + SILICONFLOW_API_KEY?: string; + // custom template for preprocessing user input DEFAULT_INPUT_TEMPLATE?: string; @@ -158,6 +162,7 @@ export const getServerSideConfig = () => { const isDeepSeek = !!process.env.DEEPSEEK_API_KEY; const isXAI = !!process.env.XAI_API_KEY; const isChatGLM = !!process.env.CHATGLM_API_KEY; + const isSiliconFlow = !!process.env.SILICONFLOW_API_KEY; // const apiKeyEnvVar = process.env.OPENAI_API_KEY ?? ""; // const apiKeys = apiKeyEnvVar.split(",").map((v) => v.trim()); // const randomIndex = Math.floor(Math.random() * apiKeys.length); @@ -237,6 +242,10 @@ export const getServerSideConfig = () => { cloudflareKVApiKey: getApiKey(process.env.CLOUDFLARE_KV_API_KEY), cloudflareKVTTL: process.env.CLOUDFLARE_KV_TTL, + isSiliconFlow, + siliconFlowUrl: process.env.SILICONFLOW_URL, + siliconFlowApiKey: getApiKey(process.env.SILICONFLOW_API_KEY), + gtmId: process.env.GTM_ID, gaId: process.env.GA_ID || DEFAULT_GA_ID, diff --git a/app/constant.ts b/app/constant.ts index a7567f1d7..32e5a2263 100644 --- a/app/constant.ts +++ b/app/constant.ts @@ -34,6 +34,8 @@ export const XAI_BASE_URL = "https://api.x.ai"; export const CHATGLM_BASE_URL = "https://open.bigmodel.cn"; +export const SILICONFLOW_BASE_URL = "https://api.siliconflow.cn"; + export const CACHE_URL_PREFIX = "/api/cache"; export const UPLOAD_URL = `${CACHE_URL_PREFIX}/upload`; @@ -69,6 +71,7 @@ export enum ApiPath { XAI = "/api/xai", ChatGLM = "/api/chatglm", DeepSeek = "/api/deepseek", + SiliconFlow = "/api/siliconflow", } export enum SlotID { @@ -125,6 +128,7 @@ export enum ServiceProvider { XAI = "XAI", ChatGLM = "ChatGLM", DeepSeek = "DeepSeek", + SiliconFlow = "SiliconFlow", } // Google API safety settings, see https://ai.google.dev/gemini-api/docs/safety-settings @@ -150,6 +154,7 @@ export enum ModelProvider { XAI = "XAI", ChatGLM = "ChatGLM", DeepSeek = "DeepSeek", + SiliconFlow = "SiliconFlow", } export const Stability = { @@ -249,6 +254,11 @@ export const ChatGLM = { VideoPath: "api/paas/v4/videos/generations", }; +export const SiliconFlow = { + ExampleEndpoint: SILICONFLOW_BASE_URL, + ChatPath: "v1/chat/completions", +}; + export const DEFAULT_INPUT_TEMPLATE = `{{input}}`; // input / time / model / lang // export const DEFAULT_SYSTEM_TEMPLATE = ` // You are ChatGPT, a large language model trained by {{ServiceProvider}}. @@ -408,8 +418,14 @@ export const KnowledgeCutOffDate: Record = { "gpt-4o-mini": "2023-10", "gpt-4o-mini-2024-07-18": "2023-10", "gpt-4-vision-preview": "2023-04", + "o1-mini-2024-09-12": "2023-10", "o1-mini": "2023-10", + "o1-preview-2024-09-12": "2023-10", "o1-preview": "2023-10", + "o1-2024-12-17": "2023-10", + o1: "2023-10", + "o3-mini-2025-01-31": "2023-10", + "o3-mini": "2023-10", // After improvements, // it's now easier to add "KnowledgeCutOffDate" instead of stupid hardcoding it, as was done previously. "gemini-pro": "2023-12", @@ -494,7 +510,9 @@ const googleModels = [ "gemini-exp-1121", "gemini-exp-1206", "gemini-2.0-flash-exp", + "gemini-2.0-flash-thinking-exp", "gemini-2.0-flash-thinking-exp-1219", + "gemini-2.0-flash-thinking-exp-01-21", ]; const anthropicModels = [ @@ -589,6 +607,21 @@ const chatglmModels = [ // "cogvideox-flash", // free ]; +const siliconflowModels = [ + "Qwen/Qwen2.5-7B-Instruct", + "Qwen/Qwen2.5-72B-Instruct", + "deepseek-ai/DeepSeek-R1", + "deepseek-ai/DeepSeek-R1-Distill-Llama-70B", + "deepseek-ai/DeepSeek-R1-Distill-Llama-8B", + "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B", + "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B", + "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B", + "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B", + "deepseek-ai/DeepSeek-V3", + "meta-llama/Llama-3.3-70B-Instruct", + "THUDM/glm-4-9b-chat", +]; + let seq = 1000; // 内置的模型序号生成器从1000开始 export const DEFAULT_MODELS = [ ...openaiModels.map((name) => ({ @@ -734,6 +767,17 @@ export const DEFAULT_MODELS = [ sorted: 13, }, })), + ...siliconflowModels.map((name) => ({ + name, + available: true, + sorted: seq++, + provider: { + id: "siliconflow", + providerName: "SiliconFlow", + providerType: "siliconflow", + sorted: 14, + }, + })), ] as const; export const CHAT_PAGE_SIZE = 15; diff --git a/app/locales/cn.ts b/app/locales/cn.ts index 39498f662..81b609cde 100644 --- a/app/locales/cn.ts +++ b/app/locales/cn.ts @@ -496,6 +496,17 @@ const cn = { SubTitle: "样例：", }, }, + SiliconFlow: { + ApiKey: { + Title: "接口密钥", + SubTitle: "使用自定义硅基流动 API Key", + Placeholder: "硅基流动 API Key", + }, + Endpoint: { + Title: "接口地址", + SubTitle: "样例：", + }, + }, Stability: { ApiKey: { Title: "接口密钥", diff --git a/app/locales/en.ts b/app/locales/en.ts index 8c2c19f18..8fecf8bf7 100644 --- a/app/locales/en.ts +++ b/app/locales/en.ts @@ -480,6 +480,17 @@ const en: LocaleType = { SubTitle: "Example: ", }, }, + SiliconFlow: { + ApiKey: { + Title: "SiliconFlow API Key", + SubTitle: "Use a custom SiliconFlow API Key", + Placeholder: "SiliconFlow API Key", + }, + Endpoint: { + Title: "Endpoint Address", + SubTitle: "Example: ", + }, + }, Stability: { ApiKey: { Title: "Stability API Key", diff --git a/app/store/access.ts b/app/store/access.ts index 1fed5dfed..7025a1814 100644 --- a/app/store/access.ts +++ b/app/store/access.ts @@ -16,6 +16,7 @@ import { DEEPSEEK_BASE_URL, XAI_BASE_URL, CHATGLM_BASE_URL, + SILICONFLOW_BASE_URL, } from "../constant"; import { getHeaders } from "../client/api"; import { getClientConfig } from "../config/client"; @@ -54,6 +55,10 @@ const DEFAULT_XAI_URL = isApp ? XAI_BASE_URL : ApiPath.XAI; const DEFAULT_CHATGLM_URL = isApp ? CHATGLM_BASE_URL : ApiPath.ChatGLM; +const DEFAULT_SILICONFLOW_URL = isApp + ? SILICONFLOW_BASE_URL + : ApiPath.SiliconFlow; + const DEFAULT_ACCESS_STATE = { accessCode: "", useCustomConfig: false, @@ -123,6 +128,10 @@ const DEFAULT_ACCESS_STATE = { chatglmUrl: DEFAULT_CHATGLM_URL, chatglmApiKey: "", + // siliconflow + siliconflowUrl: DEFAULT_SILICONFLOW_URL, + siliconflowApiKey: "", + // server config needCode: true, hideUserApiKey: false, @@ -206,6 +215,10 @@ export const useAccessStore = createPersistStore( return ensure(get(), ["chatglmApiKey"]); }, + isValidSiliconFlow() { + return ensure(get(), ["siliconflowApiKey"]); + }, + isAuthorized() { this.fetch(); @@ -224,6 +237,7 @@ export const useAccessStore = createPersistStore( this.isValidDeepSeek() || this.isValidXAI() || this.isValidChatGLM() || + this.isValidSiliconFlow() || !this.enabledAccessControl() || (this.enabledAccessControl() && ensure(get(), ["accessCode"])) ); diff --git a/app/utils/model.ts b/app/utils/model.ts index a1a38a2f8..f460babcd 100644 --- a/app/utils/model.ts +++ b/app/utils/model.ts @@ -1,4 +1,4 @@ -import { DEFAULT_MODELS } from "../constant"; +import { DEFAULT_MODELS, ServiceProvider } from "../constant"; import { LLMModel } from "../client/api"; const CustomSeq = { @@ -246,6 +246,11 @@ export function isModelNotavailableInServer( ? providerNames : [providerNames]; for (const providerName of providerNamesArray) { + // if model provider is bytedance, use model config name to check if not avaliable + if (providerName === ServiceProvider.ByteDance) { + return !Object.values(modelTable).filter((v) => v.name === modelName)?.[0] + ?.available; + } const fullName = `${modelName}@${providerName.toLowerCase()}`; if (modelTable?.[fullName]?.available === true) return false; }