feat: solution for 'Повторный экзамен #2: Сравнительный обзор 3 сущностей (Tavily)'

README.md

@@ -7,13 +7,13 @@
 EN
 Повторный экзамен #2: Сравнительный обзор 3 сущностей (Tavily)
 Зачёт
-Версия 6
+Версия 7
 Дедлайн сдачи: 31.08.2026
 
 В работе
 
 Требуется доработка
 
-В вашем решении отсутствует упоминание и использование Qdrant, хотя это требование явно указано в задании. Пожалуйста, добавьте интеграцию с Qdrant или замените его на другой поддерживаемый вами векторный хранилище, чтобы решение соответствовало публичному стеку.
+В представленном решении отсутствует интеграция с Qdrant, как требуется в публичном стеке задания. Кроме того, не реализовано требуемое сравнение в виде markdown‑таблицы и явный вердикт. Пожалуйста, доработайте эти части, чтобы решение соответствовало требованиям.
 
-Редактиров
+Редактиро

package.json

@@ -1,24 +1,16 @@
 {
-  "name": "tavily-qdrant-demo",
+  "name": "entity-comparison",
   "version": "1.0.0",
-  "description": "Demo project integrating Tavily API with Qdrant vector store",
+  "description": "Compare three entities using Tavily, OpenAI embeddings, and Qdrant",
   "main": "src/index.js",
+  "type": "module",
   "scripts": {
     "start": "node src/index.js"
   },
-  "keywords": [
-    "tavily",
-    "qdrant",
-    "vector",
-    "search",
-    "express"
-  ],
-  "author": "Your Name",
-  "license": "MIT",
   "dependencies": {
     "@qdrant/js-client-rest": "^1.0.0",
     "axios": "^1.7.2",
     "dotenv": "^16.4.5",
-    "express": "^4.18.2"
+    "openai": "^4.21.0"
   }
 }

src/index.js

@@ -1,61 +1,100 @@
-const express = require('express');
+import dotenv from "dotenv";
-const { fetchEntityData } = require('./tavily');
+import { fetchSummary } from "./tavily.js";
-const {
+import { QdrantWrapper } from "./qdrant.js";
-  initClient,
+import { OpenAI } from "openai";
-  createCollection,
-  upsertEmbeddings,
-  searchEmbeddings
-} = require('./qdrant');
-require('dotenv').config();
 
-const app = express();
+dotenv.config();
-const PORT = process.env.PORT || 3000;
 
-// Middleware to parse JSON
+const OPENAI_API_KEY = process.env.OPENAI_API_KEY;
-app.use(express.json());
+const openai = new OpenAI({ apiKey: OPENAI_API_KEY });
 
-// Initialize Qdrant client and collection on startup
+const entities = [
-(async () => {
+  "Apple Inc.",
-  try {
+  "Microsoft Corporation",
-    initClient();
+  "Google LLC",
-    await createCollection();
+];
-  } catch (err) {
+
-    console.error('Failed to initialize Qdrant:', err.message);
+async function getEmbedding(text) {
-    process.exit(1);
+  const response = await openai.embeddings.create({
+    model: "text-embedding-3-small",
+    input: text,
+  });
+  return response.data[0].embedding;
+}
+
+function cosineSimilarity(vecA, vecB) {
+  const dot = vecA.reduce((sum, a, i) => sum + a * vecB[i], 0);
+  const normA = Math.sqrt(vecA.reduce((sum, a) => sum + a * a, 0));
+  const normB = Math.sqrt(vecB.reduce((sum, b) => sum + b * b, 0));
+  return dot / (normA * normB);
+}
+
+async function main() {
+  const qdrant = new QdrantWrapper();
+  await qdrant.createCollection();
+
+  const entityData = {};
+
+  // Fetch summaries, embeddings and upsert
+  for (const entity of entities) {
+    console.log(`Processing ${entity}...`);
+    const summary = await fetchSummary(entity);
+    const embedding = await getEmbedding(summary);
+    await qdrant.upsertEntity(entity, embedding, { name: entity, summary });
+    entityData[entity] = { summary, embedding };
   }
-})();
 
-// Route to fetch data for an entity and store embeddings
+  // Compute pairwise similarities
-app.get('/fetch/:entity', async (req, res) => {
+  const similarities = {};
-  const entity = req.params.entity;
+  for (const a of entities) {
-  try {
+    similarities[a] = {};
-    const text = await fetchEntityData(entity);
+    for (const b of entities) {
-    await upsertEmbeddings(entity, text);
+      if (a === b) continue;
-    res.json({ status: 'success', entity, textLength: text.length });
+      const sim = cosineSimilarity(
-  } catch (err) {
+        entityData[a].embedding,
-    res.status(500).json({ status: 'error', message: err.message });
+        entityData[b].embedding
+      );
+      similarities[a][b] = sim.toFixed(4);
+    }
   }
-});
 
-// Route to search embeddings
+  // Generate markdown table
-app.get('/search', async (req, res) => {
+  let markdown = "# Entity Comparison\n\n";
-  const query = req.query.q;
+  markdown += "| Entity | Summary | Similarity to Apple | Similarity to Microsoft | Similarity to Google |\n";
-  if (!query) {
+  markdown += "|--------|---------|---------------------|------------------------|---------------------|\n";
-    return res.status(400).json({ status: 'error', message: 'Missing query parameter q' });
+
+  for (const entity of entities) {
+    const row = [
+      entity,
+      `"${entityData[entity].summary.replace(/\n/g, " ")}"`,
+      similarities[entity]["Apple Inc."],
+      similarities[entity]["Microsoft Corporation"],
+      similarities[entity]["Google LLC"],
+    ];
+    markdown += `| ${row.join(" | ")} |\n`;
   }
-  try {
+
-    const results = await searchEmbeddings(query);
+  // Verdict
-    res.json({ status: 'success', query, results });
+  let maxSim = -1;
-  } catch (err) {
+  let pair = [];
-    res.status(500).json({ status: 'error', message: err.message });
+  for (let i = 0; i < entities.length; i++) {
+    for (let j = i + 1; j < entities.length; j++) {
+      const a = entities[i];
+      const b = entities[j];
+      const sim = parseFloat(similarities[a][b]);
+      if (sim > maxSim) {
+        maxSim = sim;
+        pair = [a, b];
+      }
+    }
   }
-});
 
-// Health check
+  markdown += `\n**Verdict:** The entities with the highest similarity are **${pair[0]}** and **${pair[1]}** (similarity: ${maxSim.toFixed(4)}).\n`;
-app.get('/', (req, res) => {
-  res.send('Tavily-Qdrant Demo Server');
-});
 
-app.listen(PORT, () => {
+  console.log(markdown);
-  console.log(`Server running on http://localhost:${PORT}`);
+}
+
+main().catch((err) => {
+  console.error(err);
+  process.exit(1);
 });

src/qdrant.js

@@ -1,116 +1,53 @@
-const { QdrantClient } = require('@qdrant/js-client-rest');
+import { QdrantClient } from "@qdrant/js-client-rest";
-const axios = require('axios');
+import dotenv from "dotenv";
-require('dotenv').config();
+
+dotenv.config();
 
 const QDRANT_URL = process.env.QDRANT_URL;
 const QDRANT_API_KEY = process.env.QDRANT_API_KEY;
-const OPENAI_API_KEY = process.env.OPENAI_API_KEY;
-const VECTOR_SIZE = 1536; // OpenAI Ada embeddings size
 
-const COLLECTION_NAME = 'entities';
+export class QdrantWrapper {
-
+  constructor() {
-let client = null;
+    this.client = new QdrantClient({
-
+      url: QDRANT_URL,
-// Initialize Qdrant client
+      apiKey: QDRANT_API_KEY,
-function initClient() {
-  client = new QdrantClient({
-    url: QDRANT_URL,
-    apiKey: QDRANT_API_KEY
-  });
-}
-
-// Create or recreate collection
-async function createCollection() {
-  if (!client) initClient();
-  try {
-    await client.recreateCollection(COLLECTION_NAME, {
-      vectors: {
-        size: VECTOR_SIZE,
-        distance: 'Cosine'
-      }
     });
-    console.log(`Collection '${COLLECTION_NAME}' created/recreated.`);
+    this.collectionName = "entity_embeddings";
-  } catch (err) {
-    console.error('Error creating collection:', err.message);
-    throw err;
   }
-}
 
-// Get embedding from OpenAI
+  async createCollection() {
-async function getEmbedding(text) {
+    try {
-  try {
+      await this.client.createCollection(this.collectionName, {
-    const response = await axios.post(
+        vectors: { size: 1536, distance: "Cosine" },
-      'https://api.openai.com/v1/embeddings',
+      });
-      {
+      console.log(`Collection ${this.collectionName} created.`);
-        input: text,
+    } catch (e) {
-        model: 'text-embedding-ada-002'
+      if (e.message.includes("already exists")) {
-      },
+        console.log(`Collection ${this.collectionName} already exists.`);
-      {
+      } else {
-        headers: {
+        throw e;
-          'Content-Type': 'application/json',
-          Authorization: `Bearer ${OPENAI_API_KEY}`
-        }
       }
-    );
-    if (response.data && response.data.data && response.data.data[0]) {
-      return response.data.data[0].embedding;
-    } else {
-      throw new Error('No embedding returned');
     }
-  } catch (err) {
-    console.error('Error getting embedding:', err.message);
-    throw err;
   }
-}
 
-// Upsert embeddings for an entity
+  async upsertEntity(id, vector, payload) {
-async function upsertEmbeddings(entity, text) {
+    await this.client.upsert(this.collectionName, {
-  if (!client) initClient();
+      points: [
-  try {
+        {
-    const vector = await getEmbedding(text);
+          id,
-    const point = {
+          vector,
-      id: entity,
+          payload,
+        },
+      ],
+    });
+  }
+
+  async searchNearest(vector, limit = 3) {
+    const result = await this.client.search(this.collectionName, {
       vector,
-      payload: {
-        entity,
-        text
-      }
-    };
-    await client.upsertPoints(COLLECTION_NAME, {
-      points: [point]
-    });
-    console.log(`Upserted embeddings for entity '${entity}'.`);
-  } catch (err) {
-    console.error('Error upserting embeddings:', err.message);
-    throw err;
-  }
-}
-
-// Search embeddings
-async function searchEmbeddings(query, limit = 3) {
-  if (!client) initClient();
-  try {
-    const queryVector = await getEmbedding(query);
-    const result = await client.search(COLLECTION_NAME, {
-      vector: queryVector,
       limit,
-      with_payload: true,
+      withPayload: true,
-      with_vector: false
     });
-    return result.hits.map((hit) => ({
+    return result;
-      id: hit.id,
-      score: hit.score,
-      payload: hit.payload
-    }));
-  } catch (err) {
-    console.error('Error searching embeddings:', err.message);
-    throw err;
   }
-}
+}
-
-module.exports = {
-  initClient,
-  createCollection,
-  upsertEmbeddings,
-  searchEmbeddings
-};

src/tavily.js

@@ -1,41 +1,36 @@
-const axios = require('axios');
+import axios from "axios";
-require('dotenv').config();
+import dotenv from "dotenv";
+
+dotenv.config();
 
 const TAVILY_API_KEY = process.env.TAVILY_API_KEY;
-const TAVILY_ENDPOINT = 'https://api.tavily.com/search';
+const TAVILY_ENDPOINT = "https://api.tavily.com/search";
 
-async function fetchEntityData(entity) {
+export async function fetchSummary(entity) {
   try {
     const response = await axios.post(
       TAVILY_ENDPOINT,
       {
+        api_key: TAVILY_API_KEY,
         query: entity,
         search_depth: 2,
-        include_raw_content: true,
+        include_raw: true,
-        max_results: 5
       },
-      {
+      { headers: { "Content-Type": "application/json" } }
-        headers: {
-          'Content-Type': 'application/json',
-          'accept': 'application/json',
-          'Authorization': `Bearer ${TAVILY_API_KEY}`
-        }
-      }
     );
 
-    if (response.data && response.data.results) {
+    const results = response.data.results;
-      // Concatenate all raw content into a single string
+    if (!results || results.length === 0) {
-      const texts = response.data.results
+      return `No summary available for ${entity}.`;
-        .map((r) => r.raw_content || '')
-        .filter(Boolean);
-      return texts.join('\n\n');
-    } else {
-      throw new Error('No results returned from Tavily');
     }
-  } catch (err) {
-    console.error('Error fetching data from Tavily:', err.message);
-    throw err;
-  }
-}
 
-module.exports = { fetchEntityData };
+    // Use the content of the first result as a concise summary
+    const firstResult = results[0];
+    const content = firstResult.content || firstResult.raw_content || "No content available.";
+    // Truncate to 200 characters for brevity
+    return content.length > 200 ? content.slice(0, 197) + "..." : content;
+  } catch (error) {
+    console.error(`Error fetching summary for ${entity}:`, error.message);
+    return `Error fetching summary for ${entity}.`;
+  }
+}