gpt-researcher

What is gpt-researcher

GPT Researcher is an innovative open-source deep research agent designed to facilitate comprehensive web and local research tasks. Its primary purpose is to generate detailed, factual, and unbiased research reports, addressing the challenges of misinformation and inefficiency in traditional research methods. Targeted at researchers, students, and organizations, GPT Researcher leverages advanced AI techniques to produce reliable results quickly. Built using Python, it incorporates technologies such as FastAPI for backend services, JavaScript for web scraping, and supports various document formats for input and output.

How to Use

To get started with GPT Researcher, follow these installation instructions:

1. Install Python 3.11 or later. Refer to this guide for assistance.
2. Clone the repository and navigate to the project directory:

   git clone https://github.com/assafelovic/gpt-researcher.git
   cd gpt-researcher
   

3. Set up API keys by exporting them or creating a .env file:

   export OPENAI_API_KEY={Your OpenAI API Key here}
   export TAVILY_API_KEY={Your Tavily API Key here}
   

4. Install dependencies and start the server:

   pip install -r requirements.txt
   python -m uvicorn main:app --reload
   

5. Visit http://localhost:8000 to access the application.

For additional setups, such as using Docker or the PIP package, refer to the Getting Started page.

Example Usage:

from gpt_researcher import GPTResearcher

query = "why is Nvidia stock going up?"
researcher = GPTResearcher(query=query)
research_result = await researcher.conduct_research()
report = await researcher.write_report()

Key Features

• Comprehensive Research Reports: Generate detailed reports using both web and local documents, exceeding 2,000 words.
• Multi-Source Aggregation: Aggregate information from over 20 sources to ensure objective conclusions.
• Smart Image Scraping: Automatically scrape and filter relevant images for inclusion in reports.
• Frontend Options: Choose between a lightweight HTML/CSS/JS frontend or a production-ready NextJS application.
• MCP Integration: Connect with specialized data sources like GitHub and custom APIs for hybrid research capabilities.
• Deep Research Workflow: Utilize a recursive research approach that explores topics in-depth with configurable parameters.
• Export Formats: Export reports in multiple formats, including PDF, Word, and Markdown.
• Community and Enterprise Features: Engage with a community-driven project that supports extensibility and customization for various research needs.

This comprehensive overview of GPT Researcher highlights its capabilities, making it a valuable tool for anyone engaged in research activities.