add moonshot api
This commit is contained in:
parent
f5499ff699
commit
40cbabc330
|
@ -85,6 +85,9 @@ export function auth(req: NextRequest, modelProvider: ModelProvider) {
|
|||
case ModelProvider.Qwen:
|
||||
systemApiKey = serverConfig.alibabaApiKey;
|
||||
break;
|
||||
case ModelProvider.Moonshot:
|
||||
systemApiKey = serverConfig.moonshotApiKey;
|
||||
break;
|
||||
case ModelProvider.GPT:
|
||||
default:
|
||||
if (req.nextUrl.pathname.includes("azure/deployments")) {
|
||||
|
|
|
@ -0,0 +1,154 @@
|
|||
import { getServerSideConfig } from "@/app/config/server";
|
||||
import {
|
||||
Moonshot,
|
||||
MOONSHOT_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 { isModelAvailableInServer } from "@/app/utils/model";
|
||||
import type { RequestPayload } from "@/app/client/platforms/openai";
|
||||
|
||||
const serverConfig = getServerSideConfig();
|
||||
|
||||
async function handle(
|
||||
req: NextRequest,
|
||||
{ params }: { params: { path: string[] } },
|
||||
) {
|
||||
console.log("[Moonshot Route] params ", params);
|
||||
|
||||
if (req.method === "OPTIONS") {
|
||||
return NextResponse.json({ body: "OK" }, { status: 200 });
|
||||
}
|
||||
|
||||
const authResult = auth(req, ModelProvider.Moonshot);
|
||||
if (authResult.error) {
|
||||
return NextResponse.json(authResult, {
|
||||
status: 401,
|
||||
});
|
||||
}
|
||||
|
||||
try {
|
||||
const response = await request(req);
|
||||
return response;
|
||||
} catch (e) {
|
||||
console.error("[Moonshot] ", e);
|
||||
return NextResponse.json(prettyObject(e));
|
||||
}
|
||||
}
|
||||
|
||||
export const GET = handle;
|
||||
export const POST = handle;
|
||||
|
||||
export const runtime = "edge";
|
||||
export const preferredRegion = [
|
||||
"arn1",
|
||||
"bom1",
|
||||
"cdg1",
|
||||
"cle1",
|
||||
"cpt1",
|
||||
"dub1",
|
||||
"fra1",
|
||||
"gru1",
|
||||
"hnd1",
|
||||
"iad1",
|
||||
"icn1",
|
||||
"kix1",
|
||||
"lhr1",
|
||||
"pdx1",
|
||||
"sfo1",
|
||||
"sin1",
|
||||
"syd1",
|
||||
];
|
||||
|
||||
async function request(req: NextRequest) {
|
||||
const controller = new AbortController();
|
||||
|
||||
// alibaba use base url or just remove the path
|
||||
let path = `${req.nextUrl.pathname}`.replaceAll(ApiPath.Moonshot, "");
|
||||
|
||||
let baseUrl = serverConfig.moonshotUrl || MOONSHOT_BASE_URL;
|
||||
|
||||
if (!baseUrl.startsWith("http")) {
|
||||
baseUrl = `https://${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 (
|
||||
isModelAvailableInServer(
|
||||
serverConfig.customModels,
|
||||
jsonBody?.model as string,
|
||||
ServiceProvider.Moonshot as string,
|
||||
)
|
||||
) {
|
||||
return NextResponse.json(
|
||||
{
|
||||
error: true,
|
||||
message: `you are not allowed to use ${jsonBody?.model} model`,
|
||||
},
|
||||
{
|
||||
status: 403,
|
||||
},
|
||||
);
|
||||
}
|
||||
} catch (e) {
|
||||
console.error(`[Moonshot] 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);
|
||||
}
|
||||
}
|
|
@ -12,6 +12,7 @@ import { ClaudeApi } from "./platforms/anthropic";
|
|||
import { ErnieApi } from "./platforms/baidu";
|
||||
import { DoubaoApi } from "./platforms/bytedance";
|
||||
import { QwenApi } from "./platforms/alibaba";
|
||||
import { MoonshotApi } from "./platforms/moonshot";
|
||||
|
||||
export const ROLES = ["system", "user", "assistant"] as const;
|
||||
export type MessageRole = (typeof ROLES)[number];
|
||||
|
@ -117,6 +118,9 @@ export class ClientApi {
|
|||
case ModelProvider.Qwen:
|
||||
this.llm = new QwenApi();
|
||||
break;
|
||||
case ModelProvider.Moonshot:
|
||||
this.llm = new MoonshotApi();
|
||||
break;
|
||||
default:
|
||||
this.llm = new ChatGPTApi();
|
||||
}
|
||||
|
@ -199,6 +203,7 @@ export function getHeaders() {
|
|||
const isBaidu = modelConfig.providerName == ServiceProvider.Baidu;
|
||||
const isByteDance = modelConfig.providerName === ServiceProvider.ByteDance;
|
||||
const isAlibaba = modelConfig.providerName === ServiceProvider.Alibaba;
|
||||
const isMoonshot = modelConfig.providerName === ServiceProvider.Moonshot;
|
||||
const isEnabledAccessControl = accessStore.enabledAccessControl();
|
||||
const apiKey = isGoogle
|
||||
? accessStore.googleApiKey
|
||||
|
@ -210,6 +215,8 @@ export function getHeaders() {
|
|||
? accessStore.bytedanceApiKey
|
||||
: isAlibaba
|
||||
? accessStore.alibabaApiKey
|
||||
: isMoonshot
|
||||
? accessStore.moonshotApiKey
|
||||
: accessStore.openaiApiKey;
|
||||
return {
|
||||
isGoogle,
|
||||
|
@ -218,6 +225,7 @@ export function getHeaders() {
|
|||
isBaidu,
|
||||
isByteDance,
|
||||
isAlibaba,
|
||||
isMoonshot,
|
||||
apiKey,
|
||||
isEnabledAccessControl,
|
||||
};
|
||||
|
@ -267,6 +275,8 @@ export function getClientApi(provider: ServiceProvider): ClientApi {
|
|||
return new ClientApi(ModelProvider.Doubao);
|
||||
case ServiceProvider.Alibaba:
|
||||
return new ClientApi(ModelProvider.Qwen);
|
||||
case ServiceProvider.Moonshot:
|
||||
return new ClientApi(ModelProvider.Moonshot);
|
||||
default:
|
||||
return new ClientApi(ModelProvider.GPT);
|
||||
}
|
||||
|
|
|
@ -0,0 +1,251 @@
|
|||
"use client";
|
||||
// azure and openai, using same models. so using same LLMApi.
|
||||
import {
|
||||
ApiPath,
|
||||
DEFAULT_API_HOST,
|
||||
DEFAULT_MODELS,
|
||||
Moonshot,
|
||||
REQUEST_TIMEOUT_MS,
|
||||
ServiceProvider,
|
||||
} from "@/app/constant";
|
||||
import { useAccessStore, useAppConfig, useChatStore } from "@/app/store";
|
||||
import { collectModelsWithDefaultModel } from "@/app/utils/model";
|
||||
import { preProcessImageContent } from "@/app/utils/chat";
|
||||
import { cloudflareAIGatewayUrl } from "@/app/utils/cloudflare";
|
||||
|
||||
import {
|
||||
ChatOptions,
|
||||
getHeaders,
|
||||
LLMApi,
|
||||
LLMModel,
|
||||
LLMUsage,
|
||||
MultimodalContent,
|
||||
} from "../api";
|
||||
import Locale from "../../locales";
|
||||
import {
|
||||
EventStreamContentType,
|
||||
fetchEventSource,
|
||||
} from "@fortaine/fetch-event-source";
|
||||
import { prettyObject } from "@/app/utils/format";
|
||||
import { getClientConfig } from "@/app/config/client";
|
||||
import { getMessageTextContent } from "@/app/utils";
|
||||
|
||||
import { OpenAIListModelResponse, RequestPayload } from "./openai";
|
||||
|
||||
export class MoonshotApi implements LLMApi {
|
||||
private disableListModels = true;
|
||||
|
||||
path(path: string): string {
|
||||
const accessStore = useAccessStore.getState();
|
||||
|
||||
let baseUrl = "";
|
||||
|
||||
if (accessStore.useCustomConfig) {
|
||||
baseUrl = accessStore.moonshotUrl;
|
||||
}
|
||||
|
||||
if (baseUrl.length === 0) {
|
||||
const isApp = !!getClientConfig()?.isApp;
|
||||
const apiPath = ApiPath.Moonshot;
|
||||
baseUrl = isApp ? DEFAULT_API_HOST + "/proxy" + apiPath : apiPath;
|
||||
}
|
||||
|
||||
if (baseUrl.endsWith("/")) {
|
||||
baseUrl = baseUrl.slice(0, baseUrl.length - 1);
|
||||
}
|
||||
if (!baseUrl.startsWith("http") && !baseUrl.startsWith(ApiPath.Moonshot)) {
|
||||
baseUrl = "https://" + baseUrl;
|
||||
}
|
||||
|
||||
console.log("[Proxy Endpoint] ", baseUrl, path);
|
||||
|
||||
return [baseUrl, path].join("/");
|
||||
}
|
||||
|
||||
extractMessage(res: any) {
|
||||
return res.choices?.at(0)?.message?.content ?? "";
|
||||
}
|
||||
|
||||
async chat(options: ChatOptions) {
|
||||
const messages: ChatOptions["messages"] = [];
|
||||
for (const v of options.messages) {
|
||||
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(Moonshot.ChatPath);
|
||||
const chatPayload = {
|
||||
method: "POST",
|
||||
body: JSON.stringify(requestPayload),
|
||||
signal: controller.signal,
|
||||
headers: getHeaders(),
|
||||
};
|
||||
|
||||
// make a fetch request
|
||||
const requestTimeoutId = setTimeout(
|
||||
() => controller.abort(),
|
||||
REQUEST_TIMEOUT_MS,
|
||||
);
|
||||
|
||||
if (shouldStream) {
|
||||
let responseText = "";
|
||||
let remainText = "";
|
||||
let finished = false;
|
||||
|
||||
// animate response to make it looks smooth
|
||||
function animateResponseText() {
|
||||
if (finished || controller.signal.aborted) {
|
||||
responseText += remainText;
|
||||
console.log("[Response Animation] finished");
|
||||
if (responseText?.length === 0) {
|
||||
options.onError?.(new Error("empty response from server"));
|
||||
}
|
||||
return;
|
||||
}
|
||||
|
||||
if (remainText.length > 0) {
|
||||
const fetchCount = Math.max(1, Math.round(remainText.length / 60));
|
||||
const fetchText = remainText.slice(0, fetchCount);
|
||||
responseText += fetchText;
|
||||
remainText = remainText.slice(fetchCount);
|
||||
options.onUpdate?.(responseText, fetchText);
|
||||
}
|
||||
|
||||
requestAnimationFrame(animateResponseText);
|
||||
}
|
||||
|
||||
// start animaion
|
||||
animateResponseText();
|
||||
|
||||
const finish = () => {
|
||||
if (!finished) {
|
||||
finished = true;
|
||||
options.onFinish(responseText + remainText);
|
||||
}
|
||||
};
|
||||
|
||||
controller.signal.onabort = finish;
|
||||
|
||||
fetchEventSource(chatPath, {
|
||||
...chatPayload,
|
||||
async onopen(res) {
|
||||
clearTimeout(requestTimeoutId);
|
||||
const contentType = res.headers.get("content-type");
|
||||
console.log(
|
||||
"[OpenAI] request response content type: ",
|
||||
contentType,
|
||||
);
|
||||
|
||||
if (contentType?.startsWith("text/plain")) {
|
||||
responseText = await res.clone().text();
|
||||
return finish();
|
||||
}
|
||||
|
||||
if (
|
||||
!res.ok ||
|
||||
!res.headers
|
||||
.get("content-type")
|
||||
?.startsWith(EventStreamContentType) ||
|
||||
res.status !== 200
|
||||
) {
|
||||
const responseTexts = [responseText];
|
||||
let extraInfo = await res.clone().text();
|
||||
try {
|
||||
const resJson = await res.clone().json();
|
||||
extraInfo = prettyObject(resJson);
|
||||
} catch {}
|
||||
|
||||
if (res.status === 401) {
|
||||
responseTexts.push(Locale.Error.Unauthorized);
|
||||
}
|
||||
|
||||
if (extraInfo) {
|
||||
responseTexts.push(extraInfo);
|
||||
}
|
||||
|
||||
responseText = responseTexts.join("\n\n");
|
||||
|
||||
return finish();
|
||||
}
|
||||
},
|
||||
onmessage(msg) {
|
||||
if (msg.data === "[DONE]" || finished) {
|
||||
return finish();
|
||||
}
|
||||
const text = msg.data;
|
||||
try {
|
||||
const json = JSON.parse(text);
|
||||
const choices = json.choices as Array<{
|
||||
delta: { content: string };
|
||||
}>;
|
||||
const delta = choices[0]?.delta?.content;
|
||||
const textmoderation = json?.prompt_filter_results;
|
||||
|
||||
if (delta) {
|
||||
remainText += delta;
|
||||
}
|
||||
} catch (e) {
|
||||
console.error("[Request] parse error", text, msg);
|
||||
}
|
||||
},
|
||||
onclose() {
|
||||
finish();
|
||||
},
|
||||
onerror(e) {
|
||||
options.onError?.(e);
|
||||
throw e;
|
||||
},
|
||||
openWhenHidden: true,
|
||||
});
|
||||
} else {
|
||||
const res = await fetch(chatPath, chatPayload);
|
||||
clearTimeout(requestTimeoutId);
|
||||
|
||||
const resJson = await res.json();
|
||||
const message = this.extractMessage(resJson);
|
||||
options.onFinish(message);
|
||||
}
|
||||
} 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<LLMModel[]> {
|
||||
return [];
|
||||
}
|
||||
}
|
|
@ -57,6 +57,10 @@ declare global {
|
|||
ALIBABA_URL?: string;
|
||||
ALIBABA_API_KEY?: string;
|
||||
|
||||
// moonshot only
|
||||
MOONSHOT_URL?: string;
|
||||
MOONSHOT_API_KEY?: string;
|
||||
|
||||
// custom template for preprocessing user input
|
||||
DEFAULT_INPUT_TEMPLATE?: string;
|
||||
}
|
||||
|
@ -120,6 +124,7 @@ export const getServerSideConfig = () => {
|
|||
const isBaidu = !!process.env.BAIDU_API_KEY;
|
||||
const isBytedance = !!process.env.BYTEDANCE_API_KEY;
|
||||
const isAlibaba = !!process.env.ALIBABA_API_KEY;
|
||||
const isMoonshot = !!process.env.MOONSHOT_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);
|
||||
|
@ -168,6 +173,10 @@ export const getServerSideConfig = () => {
|
|||
alibabaUrl: process.env.ALIBABA_URL,
|
||||
alibabaApiKey: getApiKey(process.env.ALIBABA_API_KEY),
|
||||
|
||||
isMoonshot,
|
||||
moonshotUrl: process.env.MOONSHOT_URL,
|
||||
moonshotApiKey: getApiKey(process.env.MOONSHOT_API_KEY),
|
||||
|
||||
gtmId: process.env.GTM_ID,
|
||||
|
||||
needCode: ACCESS_CODES.size > 0,
|
||||
|
|
|
@ -22,6 +22,7 @@ export const BAIDU_OATUH_URL = `${BAIDU_BASE_URL}/oauth/2.0/token`;
|
|||
export const BYTEDANCE_BASE_URL = "https://ark.cn-beijing.volces.com";
|
||||
|
||||
export const ALIBABA_BASE_URL = "https://dashscope.aliyuncs.com/api/";
|
||||
export const MOONSHOT_BASE_URL = "https://api.moonshot.cn";
|
||||
|
||||
export const CACHE_URL_PREFIX = "/api/cache";
|
||||
export const UPLOAD_URL = `${CACHE_URL_PREFIX}/upload`;
|
||||
|
@ -46,6 +47,7 @@ export enum ApiPath {
|
|||
Baidu = "/api/baidu",
|
||||
ByteDance = "/api/bytedance",
|
||||
Alibaba = "/api/alibaba",
|
||||
Moonshot = "/api/moonshot",
|
||||
Stability = "/api/stability",
|
||||
}
|
||||
|
||||
|
@ -94,6 +96,7 @@ export enum ServiceProvider {
|
|||
Baidu = "Baidu",
|
||||
ByteDance = "ByteDance",
|
||||
Alibaba = "Alibaba",
|
||||
Moonshot = "Moonshot",
|
||||
Stability = "Stability",
|
||||
}
|
||||
|
||||
|
@ -114,6 +117,7 @@ export enum ModelProvider {
|
|||
Ernie = "Ernie",
|
||||
Doubao = "Doubao",
|
||||
Qwen = "Qwen",
|
||||
Moonshot = "Moonshot",
|
||||
}
|
||||
|
||||
export const Stability = {
|
||||
|
@ -177,6 +181,11 @@ export const Alibaba = {
|
|||
ChatPath: "v1/services/aigc/text-generation/generation",
|
||||
};
|
||||
|
||||
export const Moonshot = {
|
||||
ExampleEndpoint: MOONSHOT_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}}.
|
||||
|
@ -283,6 +292,8 @@ const alibabaModes = [
|
|||
"qwen-max-longcontext",
|
||||
];
|
||||
|
||||
const moonshotModes = ["moonshot-v1-8k", "moonshot-v1-32k", "moonshot-v1-128k"];
|
||||
|
||||
export const DEFAULT_MODELS = [
|
||||
...openaiModels.map((name) => ({
|
||||
name,
|
||||
|
@ -347,6 +358,15 @@ export const DEFAULT_MODELS = [
|
|||
providerType: "alibaba",
|
||||
},
|
||||
})),
|
||||
...moonshotModes.map((name) => ({
|
||||
name,
|
||||
available: true,
|
||||
provider: {
|
||||
id: "moonshot",
|
||||
providerName: "Moonshot",
|
||||
providerType: "moonshot",
|
||||
},
|
||||
})),
|
||||
] as const;
|
||||
|
||||
export const CHAT_PAGE_SIZE = 15;
|
||||
|
|
|
@ -39,6 +39,10 @@ const DEFAULT_ALIBABA_URL = isApp
|
|||
? DEFAULT_API_HOST + "/api/proxy/alibaba"
|
||||
: ApiPath.Alibaba;
|
||||
|
||||
const DEFAULT_MOONSHOT_URL = isApp
|
||||
? DEFAULT_API_HOST + "/api/proxy/moonshot"
|
||||
: ApiPath.Moonshot;
|
||||
|
||||
const DEFAULT_STABILITY_URL = isApp
|
||||
? DEFAULT_API_HOST + "/api/proxy/stability"
|
||||
: ApiPath.Stability;
|
||||
|
@ -82,6 +86,10 @@ const DEFAULT_ACCESS_STATE = {
|
|||
alibabaUrl: DEFAULT_ALIBABA_URL,
|
||||
alibabaApiKey: "",
|
||||
|
||||
// moonshot
|
||||
moonshotUrl: DEFAULT_MOONSHOT_URL,
|
||||
moonshotApiKey: "",
|
||||
|
||||
//stability
|
||||
stabilityUrl: DEFAULT_STABILITY_URL,
|
||||
stabilityApiKey: "",
|
||||
|
@ -134,6 +142,10 @@ export const useAccessStore = createPersistStore(
|
|||
return ensure(get(), ["alibabaApiKey"]);
|
||||
},
|
||||
|
||||
isValidMoonshot() {
|
||||
return ensure(get(), ["moonshotApiKey"]);
|
||||
},
|
||||
|
||||
isAuthorized() {
|
||||
this.fetch();
|
||||
|
||||
|
@ -146,6 +158,7 @@ export const useAccessStore = createPersistStore(
|
|||
this.isValidBaidu() ||
|
||||
this.isValidByteDance() ||
|
||||
this.isValidAlibaba() ||
|
||||
this.isValidMoonshot() ||
|
||||
!this.enabledAccessControl() ||
|
||||
(this.enabledAccessControl() && ensure(get(), ["accessCode"]))
|
||||
);
|
||||
|
|
Loading…
Reference in New Issue