Skip to content

Custom Websearch Agent Built with Local Models, vLLM, and OpenAI

License

Notifications You must be signed in to change notification settings

5uperfred/custom_websearch_agent

 
 

Repository files navigation

Custom Agent

A custom websearch agent useable with Ollama, OpenAI and vLLM.

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=3.10 pip
  3. Activate the Virtual Environment:

    conda activate agent_env

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[https://github.com/ollama/ollama/blob/main/docs/api.md#list-local-models](API documentionation)

Clone and Navigate to the Repository

  1. Clone the Repo:

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

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

    pip install -r requirements.txt

Configure API Keys

  1. Open the config.yaml:

    nano config.yaml
  2. Enter API Keys:

Run Your Query

python agent.py run

Then enter your query.

About

Custom Websearch Agent Built with Local Models, vLLM, and OpenAI

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%