kmafutah / custom_websearch_agent

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

Custom Agent

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

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:**
```bash
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:

   • Serper API Key: Get it from https://serper.dev/
   • OpenAI API Key: Get it from https://openai.com/

Run Your Query

python app.py "YOUR QUERY"