Spaces:
Sleeping
Sleeping
| title: Lightweight Chatbot | |
| emoji: 🚀 | |
| colorFrom: purple | |
| colorTo: yellow | |
| sdk: docker | |
| app_port: 8501 | |
| pinned: false | |
| license: mit | |
| # 🤖 Ollama AI Assistant | |
| This project hosts a lightweight AI assistant powered by **Ollama**, **FastAPI**, and **Streamlit**, all bundled in a single Docker environment. | |
| ## 🚀 Overview | |
| - **Ollama** – Runs and serves the LLM model. | |
| - **FastAPI** – Handles backend API requests to interact with the model. | |
| - **Streamlit** – Provides a user-friendly web UI. | |
| - **Docker** – Runs everything in isolated and reproducible containers. | |
| --- | |
| ## 🧠 How It Works | |
| 1. **Ollama** loads the LLM model: `krishna_choudhary/lightweight_chatbot`. | |
| 2. **FastAPI** provides an API backend (running on internal port `7860`) for prompt-response communication. | |
| 3. **Streamlit UI** (exposed on port `8501`) lets users enter prompts and receive responses. | |
| 4. The UI interacts with FastAPI, which in turn queries the LLM via Ollama. | |
| --- | |
| ## 🖥️ User Interface | |
| By default, the **Streamlit UI** is the primary interface and launches at: | |