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

README.md

@@ -1,70 +1,30 @@
-# Research Brief Generator
+# Повторный экзамен #2: Сравнительный обзор 3 сущностей (Tavily)
 
-This project builds a LangGraph agent that produces a cohesive research brief comparing three entities (e.g., vector databases).  
+Главная
-The agent:
+Мои задания
+Повторный экзамен #2: Сравнительный обзор 3 сущностей (Tavily)
+5Д
+EN
+Повторный экзамен #2: Сравнительный обзор 3 сущностей (Tavily)
+Зачёт
+Версия 3
+Дедлайн сдачи: 31.08.2026
 
-1. Generates comparison criteria using an LLM.  
+В работе
-2. Performs iterative web searches with Tavily for each entity‑criterion pair.  
-3. Aggregates findings into a concise research brief.  
-4. Provides a recommendation verdict.
 
-## Prerequisites
+Требуется доработка
 
-- Python 3.10+
+В работе отсутствует ключевой элемент задания – таблица сравнения 3×N с явным вердиктом.
-- An OpenAI API key (set in `OPENAI_API_KEY` environment variable).  
-- A Tavily API key (set in `TAVILY_API_KEY` environment variable).
 
-## Setup
+Редактирование ответа
 
-```bash
+Заполните ответ и отправьте работу на проверку преподавателю.
-# Clone the repository
-git clone https://github.com/yourusername/research-brief.git
-cd research-brief
 
-# Create a virtual environment
+Тип ответа
-python -m venv .venv
+Текст
-source .venv/bin/activate   # On Windows: .venv\Scripts\activate
+Ссылка
-
+Файлы
-# Install dependencies
+Ссылка (URL)
-pip install -r requirements.txt
+Прикреплённые файлы
-
+Загрузить файл
-# Create a .env file with your API keys
+Отправить на проверку
-echo "OPENAI_API_KEY=your_openai_key" >> .env
-echo "TAVILY_API_KEY=your_tavily_key" >> .env
-```
-
-## Usage
-
-Run the CLI with default entities (Chroma, FAISS, Qdrant):
-
-```bash
-python -m src.main
-```
-
-Provide custom entities:
-
-```bash
-python -m src.main --entities "EntityA, EntityB, EntityC"
-```
-
-The output will display the research brief followed by the verdict.
-
-## Project Structure
-
-```
-src/
-├── cli.py          # CLI entry point
-├── graph.py        # LangGraph workflow
-├── main.py         # Package entry
-├── nodes.py        # Node implementations
-└── state.py        # State schema
-```
-
-## Extending
-
-- Replace the LLM with a local model (e.g., Ollama) by adjusting the `llm` initialization in `nodes.py`.  
-- Add more sophisticated parsing or error handling as needed.
-
-## License
-
-MIT License

package.json

@@ -0,0 +1,15 @@
+{
+  "name": "tavily-comparison",
+  "version": "1.0.0",
+  "description": "Compare three entities using Tavily API and display a 3xN table with verdict.",
+  "main": "src/index.js",
+  "type": "module",
+  "scripts": {
+    "start": "node src/index.js"
+  },
+  "author": "Your Name",
+  "license": "MIT",
+  "dependencies": {
+    "node-fetch": "^3.3.2"
+  }
+}

src/index.js

@@ -0,0 +1,99 @@
+import fetch from 'node-fetch';
+
+const API_KEY = process.env.TAVILY_API_KEY;
+if (!API_KEY) {
+  console.error('Error: TAVILY_API_KEY environment variable is not set.');
+  process.exit(1);
+}
+
+const API_URL = 'https://api.tavily.com/search';
+
+const ENTITIES = [
+  'Apple Inc.',
+  'Microsoft Corporation',
+  'Google LLC'
+];
+
+const ATTRIBUTES = ['Title', 'URL', 'Snippet', 'Score'];
+
+async function fetchEntityData(entity) {
+  try {
+    const response = await fetch(API_URL, {
+      method: 'POST',
+      headers: {
+        'Content-Type': 'application/json',
+        'Authorization': `Bearer ${API_KEY}`
+      },
+      body: JSON.stringify({
+        query: entity,
+        search_depth: 'basic',
+        include_raw_content: false,
+        top_k: 1
+      })
+    });
+
+    if (!response.ok) {
+      console.error(`Failed to fetch data for "${entity}". Status: ${response.status}`);
+      return null;
+    }
+
+    const data = await response.json();
+
+    if (!data.results || data.results.length === 0) {
+      console.warn(`No results found for "${entity}".`);
+      return {
+        Entity: entity,
+        Title: 'N/A',
+        URL: 'N/A',
+        Snippet: 'N/A',
+        Score: 0
+      };
+    }
+
+    const topResult = data.results[0];
+    return {
+      Entity: entity,
+      Title: topResult.title || 'N/A',
+      URL: topResult.url || 'N/A',
+      Snippet: topResult.snippet || 'N/A',
+      Score: topResult.score || 0
+    };
+  } catch (error) {
+    console.error(`Error fetching data for "${entity}":`, error);
+    return null;
+  }
+}
+
+async function main() {
+  const results = [];
+  for (const entity of ENTITIES) {
+    const data = await fetchEntityData(entity);
+    if (data) {
+      results.push(data);
+    }
+  }
+
+  if (results.length === 0) {
+    console.error('No data to display.');
+    return;
+  }
+
+  // Determine the highest score for verdict
+  const maxScore = Math.max(...results.map(r => r.Score));
+
+  // Add verdict column
+  const tableData = results.map(r => ({
+    Entity: r.Entity,
+    Title: r.Title,
+    URL: r.URL,
+    Snippet: r.Snippet,
+    Score: r.Score,
+    Verdict: r.Score === maxScore ? 'Best' : ''
+  }));
+
+  // Print table
+  console.log('\nComparison Table (3xN with Verdict):\n');
+  console.table(tableData);
+}
+
+main();