Skip to content

README.md

Latest commit

 

History

History
92 lines (70 loc) · 2.17 KB

README.md

File metadata and controls

92 lines (70 loc) · 2.17 KB
Raw

🔎 Search-Engine-LLM

An AI-powered search assistant built with LangChain, Streamlit, and GROQ LLM. This project lets you ask natural language questions and get intelligent answers by combining multiple knowledge sources like DuckDuckGo, Wikipedia, and Arxiv.

It’s like having your own research assistant that can search the web, academic papers, and encyclopedic knowledge — all in one chat interface.

🚀 Features

  • 🌐 DuckDuckGo Search – fetch real-time web results
  • 📚 Wikipedia – retrieve concise encyclopedic knowledge
  • 📄 Arxiv – query research papers and summaries
  • 🤖 LLM-powered reasoning with Llama3-8b-8192 (via GROQ API)
  • 🎛️ Streamlit UI with interactive chat experience
  • 🧠 Multi-tool agent that decides the best source for each query

🧰 Tech Stack

  • Python
  • Streamlit (UI)
  • LangChain (Agent + Tools)
  • GROQ LLM (ChatGroq)
  • DuckDuckGo API
  • Wikipedia API
  • Arxiv API
  • dotenv

📦 Installation

  1. Clone the Repo bash

    git clone https://github.com/jasoncobra3/Search-Engine-LLM.git
cd Search-Engine-LLM

  2. Create Virtual Environment

     python -m venv venv

  3. Activate the Virtual Environment

     # Windows:
 venv\Scripts\activate
 # macOS/Linux:
 venv/bin/activate

  4. Install Dependencies

    pip install -r requirements.txt

🔐 Setup

  1. Create a .env file in root folder with 
     GROQ_API_KEY=your_groq_api_key_here
  2. Or enter your API key in the Streamlit sidebar when running the app.

🚀Run the App

Run the Script in Terminal

  streamlit run app.py

📁 Project Structure

├── app.py               # Main Streamlit app
├── requirements.txt     # Dependencies
├── .env                 # API key (not committed)
├── .gitignore
└── README.md

🤝 Contributing

Pull requests are welcome! If you’d like to add more tools (e.g., Google Search, PubMed, News APIs), feel free to fork and contribute.

⭐ Show Your Support

If you like this project, give it a ⭐ on GitHub — it helps others discover it!