New Research: Supply Chain Attack on Axios Pulls Malicious Dependency from npm.Details →
Socket
Book a DemoSign in
Socket

research_agent

Package Overview
Dependencies
Maintainers
1
Versions
5
Alerts
File Explorer

Advanced tools

Socket logo

Install Socket

Detect and block malicious and high-risk dependencies

Install

research_agent

A research agent that uses AI to research the web and summarize and create reports

latest
Source
npmnpm
Version
1.3.0
Version published
Weekly downloads
1
Maintainers
1
Weekly downloads
 
Created
Source

research_agent

Build states Coverage

Description

research_agent leverages AI to automate the research process. It can: Analyze websites and extract relevant information. Generate summaries of findings. Create detailed reports in markdown format. The library supports multiple AI models

  • OpenAI
  • Mistral AI (partial)

Getting Started

Install

pnpm add research_agent

Usage

import { writeFileSync } from 'fs';
import { ResearchManager } from 'research_agent';

const writeToFile = async (fileName, data) => {
  writeFileSync(fileName, data);
};

const main = async () => {
  const manager = new ResearchManager(); // You can customize the LLM model here
  const result = await manager.search('Who is this person in that website "www.youssefhany.dev"?');

  // Write the report to a markdown file
  await writeToFile('output.md', result);
};

void main();

Example with Mistral AI

import { WebPageLoaderWithSummary, QuestionGeneratorAgent, ResearchManager, NotificationManager } from 'research_agent';
import { ChatMistralAI } from '@langchain/mistralai';

const main = async (): Promise<void> => {
  const chatgpt = createOpenAIChatModel({
    modelName: 'gpt-3.5-turbo',
  });
  const mistralai = new ChatMistralAI({
    apiKey: process.env.MISTRAL_API_KEY,
    modelName: 'mistral-large-latest',
  });

  NotificationManager.addListener(console.log);

  const questionGeneratorAgent = new QuestionGeneratorAgent(mistralai); // still not stable with mistral ai
  const researchManager = new ResearchManager(mistralai, questionGeneratorAgent, {
    maxIterations: 2,
    researchWorkerConfig: {
      llmModel: chatgpt,
      tools: {
        webLoader: new WebPageLoaderWithSummary(mistralai),
      },
    },
  });
  const query = 'Write a report about ramadan and its importance';
  await researchManager.search(query);
};

await main();

This code snippet creates a ResearchManager instance and uses it to search for information about a person on a specific website. The search results are then written to a markdown file.

Features

  • Multiple AI model support: Choose from OpenAI, Mistral AI, and potentially others.
  • Question generation: Automatically generates questions to guide the research process.
  • Web search and analysis: Utilizes tools like Tavily Search and Puppeteer to gather information from the web.
  • Report generation: Creates comprehensive reports in markdown format.

Contributing

Contributions are welcome!

License

This project is licensed under the MIT license.

API Reference

For detailed information about the library's API, please refer to the exported classes and functions: ResearchManager: Manages the research process and generates reports. QuestionGeneratorAgent: Generates questions to guide research. SearchWorker: Performs web searches and analyzes websites.

Keywords

research

FAQs

Package last updated on 14 Mar 2024

Did you know?

Socket

Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.

Install

Related posts