import { GoogleCustomSearch } from "openai-function-calling-tools"; import { DEFAULT_SYSTEM_PROMPT, DEFAULT_TEMPERATURE } from '@/utils/app/const'; import { LLMError, LLMStream } from './stream'; // @ts-expect-error import wasm from '../../node_modules/@dqbd/tiktoken/lite/tiktoken_bg.wasm?module'; import tiktokenModel from '@dqbd/tiktoken/encoders/cl100k_base.json'; import { Tiktoken, init } from '@dqbd/tiktoken/lite/init'; export const config = { runtime: 'edge', }; const handler = async (req) => { try { const { question } = (await req.json()); await init((imports) => WebAssembly.instantiate(wasm, imports)); const googleCustomSearch = new GoogleCustomSearch({ apiKey: process.env.API_KEY, googleCSEId: process.env.CONTEXT_KEY, }); const messages = [ { role: "user", content: question, }, ]; const functions = { googleCustomSearch, }; const encoding = new Tiktoken( tiktokenModel.bpe_ranks, tiktokenModel.special_tokens, tiktokenModel.pat_str, ); let promptToSend = question; if (!promptToSend) { promptToSend = DEFAULT_SYSTEM_PROMPT; } let temperatureToUse = temperature; if (temperatureToUse == null) { temperatureToUse = DEFAULT_TEMPERATURE; } const prompt_tokens = encoding.encode(promptToSend); let tokenCount = prompt_tokens.length; let messagesToSend = []; for (let i = messages.length - 1; i >= 0; i--) { const message = messages[i]; const tokens = encoding.encode(message.content); if (tokenCount + tokens.length + 1000 > model.tokenLimit) { break; } tokenCount += tokens.length; messagesToSend = [message, ...messagesToSend]; } encoding.free(); const stream = await LLMStream(model, promptToSend, temperatureToUse, key, messagesToSend, functions); return new Response(stream); } catch (error) { console.error(error); if (error instanceof LLMError) { return new Response('Error', { status: 500, statusText: error.message }); } else { return new Response('Error', { status: 500 }); } } }; export default handler;