Skip to content

john-adeojo/graph_websearch_agent

Repository files navigation

Custom WebSearch Agent with LangGraph

Watch the Tutorial:

Watch this video on YouTube

Agent Schema:

Agent Schema

Prerequisites

Environment Setup

  1. Install Anaconda:
    Download Anaconda from https://www.anaconda.com/.

  2. Create a Virtual Environment:

    conda create -n agent_env python=3.11 pip
  3. Activate the Virtual Environment:

    conda activate agent_env

Clone and Navigate to the Repository

  1. Clone the Repo:

    git clone https://github.com/john-adeojo/graph_websearch_agent.git
  2. Navigate to the Repo:

    cd /path/to/your-repo/graph_websearch_agent
  3. Install Requirements:

    pip install -r requirements.txt

Configure API Keys

  1. Open the config.yaml:

    nano config.yaml
  2. Enter API Keys:

Run the front end

If you want to run the front end

For Windows, run:

run_windows.ps1

For Linux/macOS, run:

chmod +x run_linux.sh
run_linux.sh

Run Your Query In Shell

python -m app.app

Then enter your query.

If you want to work with Ollama

Setup Ollama Server

  1. Download Ollama: Download https://ollama.com/download

  2. Download an Ollama Model:

    curl http://localhost:11434/api/pull -d "{\"name\": \"llama3\"}"

Ollama API documentation

Video on how I integrated the Ollama Server:

Watch the video

About

Websearch agent built on the LangGraph framework

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages