README.md

metadata

title: Ollama AI Assistant
emoji: 🤖
colorFrom: purple
colorTo: blue
sdk: docker
app_port: 8501
pinned: false
license: mit

This Hugging Face Space hosts an AI assistant powered by Ollama, FastAPI, and Streamlit.

Ollama: The large language model (LLM) inference engine.

FastAPI: Provides a robust backend API for interacting with the LLM.

Streamlit: Offers an intuitive and interactive web-based user interface.

How it Works

The Docker container starts, running Ollama, FastAPI, and Streamlit concurrently.

Ollama pulls and serves the krishna_choudhary/AI_Assistant_Chatbot model.

The Streamlit UI (exposed on port 8501) communicates with the FastAPI backend (running internally on port 7860) to send user prompts and receive AI responses.

Get Started

Simply type your query into the text box and click "Get Response" to interact with the AI assistant.

Built with Docker, Ollama, FastAPI, and Streamlit.