📌 Ollama API (localhost)

Number of APIs: 1

Prerequisites

• Qodex

• Ollama Account: https://ollama.com/

Usage

1. Create a fork

2. Send requests

Documentation

• Models: https://ollama.com/library

Models

Models include Gemma (by Google, open-weight), Llama & CodeLlama (by Meta AI, open-weight), Mixtral (by Mistral AI, open-weight), Phi (by Microsoft), and more.

About Ollama

Ollama is a tool (similar to Docker) to run Large Language Models locally. It can be used via REST API, Python SDK, or CLI.

1. Generate - qwen2 POST http://localhost:11434/api/generate