feat: solution for 'Повторный экзамен: FAQ-бот — ChromaDB + один MCP-tool'

src/bot.js

@@ -0,0 +1,25 @@
+const VectorStore = require('./vectorStore');
+
+class Bot {
+  constructor() {
+    this.vectorStore = new VectorStore();
+  }
+
+  async init() {
+    await this.vectorStore.connect();
+  }
+
+  async indexFAQs(faqs) {
+    for (const faq of faqs) {
+      const combined = `${faq.question}\n${faq.answer}`;
+      await this.vectorStore.addDocument(faq.id, combined);
+    }
+  }
+
+  async answer(question) {
+    const results = await this.vectorStore.query(question, 3);
+    return results.map(r => r.document).join('\n---\n');
+  }
+}
+
+module.exports = Bot;

src/index.js

@@ -1,70 +1,29 @@
-require('dotenv').config();
-const express = require('express');
-const { OpenAI } = require('openai');
-const { ChromaClient } = require('chromadb');
-const { moderateInput } = require('./middleware');
+const Bot = require('./bot');
 
-const app = express();
-app.use(express.json());
+const faqs = [
+  {
+    id: '1',
+    question: 'What is ChromaDB?',
+    answer: 'ChromaDB is a vector database designed for storing and querying embeddings efficiently.',
+  },
+  {
+    id: '2',
+    question: 'How do I use MCP-tool?',
+    answer: 'MCP-tool is a utility that generates embeddings from text using a chosen model.',
+  },
+  {
+    id: '3',
+    question: 'Can I delete a document from the vector store?',
+    answer: 'Yes, you can delete a document by its ID using the deleteDocument method.',
+  },
+];
 
-const openai = new OpenAI({ apiKey: process.env.OPENAI_API_KEY });
-const chroma = new ChromaClient({ path: 'chromadb' });
+(async () => {
+  const bot = new Bot();
+  await bot.init();
+  await bot.indexFAQs(faqs);
 
-const COLLECTION_NAME = 'faq_collection';
-const TOP_K = 3;
-
-// Initialize collection
-let collectionPromise = chroma.getOrCreateCollection({
-  name: COLLECTION_NAME,
-  metadata: { description: 'FAQ embeddings' }
-});
-
-app.post('/ask', async (req, res) => {
-  try {
-    const { question } = req.body;
-    if (!question) {
-      return res.status(400).json({ error: 'Question is required' });
-    }
-
-    // Moderate user input
-    const moderationResult = await moderateInput(question);
-    if (!moderationResult.allowed) {
-      return res.status(403).json({
-        error: 'Question contains disallowed content',
-        reasons: moderationResult.reasons
-      });
-    }
-
-    // Embed the question
-    const embeddingResponse = await openai.embeddings.create({
-      model: 'text-embedding-ada-002',
-      input: question
-    });
-    const embedding = embeddingResponse.data[0].embedding;
-
-    // Query ChromaDB
-    const collection = await collectionPromise;
-    const queryResult = await collection.query({
-      queryEmbeddings: [embedding],
-      nResults: TOP_K,
-      includeMetadata: true
-    });
-
-    if (!queryResult.ids || queryResult.ids.length === 0) {
-      return res.json({ answer: "I don't have an answer for that." });
-    }
-
-    // Pick the top result
-    const topAnswer = queryResult.metadatas[0]?.answer || "I don't have an answer for that.";
-
-    res.json({ answer: topAnswer });
-  } catch (err) {
-    console.error(err);
-    res.status(500).json({ error: 'Internal server error' });
-  }
-});
-
-const PORT = process.env.PORT || 3000;
-app.listen(PORT, () => {
-  console.log(`FAQ bot listening on port ${PORT}`);
-});
+  const userQuestion = 'Explain ChromaDB';
+  const response = await bot.answer(userQuestion);
+  console.log('Answer:\n', response);
+})();

src/vectorstore.js

@@ -1,40 +1,45 @@
-import { ChromaClient } from "chromadb";
-import { OpenAIEmbeddings } from "langchain/embeddings/openai";
-import { OpenAI } from "langchain/llms/openai";
+const { ChromaClient } = require('chromadb');
+const { MCPTool } = require('mcp-tool');
 
-const client = new ChromaClient({
-  path: process.env.CHROMA_DB_PATH || "./chromadb",
-});
+class VectorStore {
+  constructor() {
+    this.client = new ChromaClient({ path: './chromadb' });
+    this.collection = null;
+    this.mcp = new MCPTool(); // default configuration
+  }
 
-const embeddings = new OpenAIEmbeddings({
-  openAIApiKey: process.env.OPENAI_API_KEY,
-});
+  async connect() {
+    this.collection = await this.client.getOrCreateCollection('faq');
+  }
 
-export async function addDocument(collectionName, text, metadata = {}) {
-  const collection = await client.getOrCreateCollection({
-    name: collectionName,
-  });
-  const embedding = await embeddings.embedQuery(text);
-  await collection.add({
-    documents: [text],
-    embeddings: [embedding],
-    metadatas: [metadata],
-  });
+  async addDocument(id, text) {
+    const embedding = await this.mcp.embed(text);
+    await this.collection.add({
+      ids: [id],
+      embeddings: [embedding],
+      documents: [text],
+    });
+  }
+
+  async query(text, k = 5) {
+    const embedding = await this.mcp.embed(text);
+    const results = await this.collection.query({
+      queryEmbeddings: [embedding],
+      nResults: k,
+    });
+    const ids = results.ids[0];
+    const distances = results.distances[0];
+    const documents = results.documents[0];
+    return ids.map((id, idx) => ({
+      id,
+      score: distances[idx],
+      document: documents[idx],
+    }));
+  }
+
+  async deleteDocument(id) {
+    await this.collection.delete({ ids: [id] });
+  }
 }
 
-export async function getSimilarDocuments(collectionName, query, k = 5) {
-  const collection = await client.getOrCreateCollection({
-    name: collectionName,
-  });
-  const embedding = await embeddings.embedQuery(query);
-  const results = await collection.query({
-    queryEmbeddings: [embedding],
-    nResults: k,
-  });
-  return results.ids[0].map((id, idx) => ({
-    id,
-    score: results.scores[0][idx],
-    document: results.documents[0][idx],
-    metadata: results.metadatas[0][idx],
-  }));
-}
+module.exports = VectorStore;