🤖 Agentic AI Chatbot
Multi-Tool AI Assistant

A production-ready Flask-based AI chatbot backend that leverages LangChain, LangGraph, and Groq LLM to orchestrate multiple external tools for comprehensive information retrieval and intelligent responses.

🎯 Business Applications:

✓ Enterprise knowledge management systems
✓ Customer support automation with real-time data
✓ Financial analysis chatbots for market research
✓ Academic research assistants for universities
✓ Business intelligence tools with live web search

Live Demo (Render) Streamlit Version GitHub

Tech Stack: Flask • LangChain • LangGraph • Groq • Arxiv API • Wikipedia API • Tavily Search • yfinance

🚀 Core Capabilities

Intelligent tool orchestration powered by LangGraph and Groq's LLM

Intelligent Tool Selection

AI automatically chooses the right tool for each query

LangGraph orchestrates tool calls based on context. The AI determines whether to search academic papers, check stock prices, or query Wikipedia - all autonomously.

Academic Research

Access to 2M+ papers via Arxiv API

Leverages ArxivAPIWrapper to pull academic research papers, summaries, and citations. Perfect for research assistants and educational platforms.

Knowledge Base

Wikipedia integration for factual information

WikipediaAPIWrapper provides encyclopedic knowledge and fact-checking capabilities, ensuring well-sourced, accurate responses.

Real-Time Web Search

Live internet search via Tavily API

For current events and latest information, Tavily Search API browses the web and delivers up-to-date results with source citations.

Financial Data

Live stock prices from Yahoo Finance

Integrated yfinance library retrieves real-time stock prices, market data, and financial metrics for any ticker symbol.

Conversation Memory

Context-aware multi-turn conversations

Maintains conversation history and context across multiple queries, enabling natural follow-up questions and coherent dialogue.

Technology Stack

The tools and technologies that power the AI Chatbot.

Python

F

Flask

LangChain

LangGraph

Groq

Interactive Setup Guide

Follow this step-by-step guide to get the chatbot running locally.

Check Your Tools

Before you begin, ensure you have Python installed on your system. The backend is built entirely on Python.

Python 3.8 or newer

Install Dependencies

Open your terminal in the project directory and run the following command to install all the necessary Python packages.

pip install Flask Flask-CORS langchain-community langchain-groq langgraph yfinance python-dotenv

Configure API Keys & Run Server

Create a file named .env in your project root and add your API keys.

GROQ_API_KEY="your_groq_api_key_here"
TAVILY_API_KEY="your_tavily_api_key_here"

Finally, run the Flask server. It will be accessible at `http://127.0.0.1:5000`.

python app.py

Usage Demo

See examples of questions you can ask the chatbot.

Click a button below to see an example interaction.

Troubleshooting FAQ

Common questions and solutions to get you back on track.

Why am I getting a "Connection Error" on the frontend?

Ensure your Flask backend (`app.py`) is running in your terminal. You should see output indicating the server has started.
Verify that your browser is not blocking requests from the page to `127.0.0.1:5000` due to CORS. The backend is configured with Flask-CORS, but browser plugins can sometimes interfere.

Why are there no AI responses or tool outputs?

Double-check that your `GROQ_API_KEY` and `TAVILY_API_KEY` in the `.env` file are correct and active.
Check your internet connection, as the app needs to reach external APIs.
Review the Flask backend console for any API-related error messages from Groq, Tavily, or other services.

🤖 Agentic AI Chatbot Multi-Tool AI Assistant