Spaces:
Sleeping
Sleeping
| title: "RAG Chatbot" | |
| colorFrom: blue | |
| colorTo: purple | |
| sdk: streamlit | |
| sdk_version: "1.28.1" | |
| app_file: app.py | |
| pinned: false | |
| # Hybrid Search Chatbot | |
| A Streamlit app for hybrid search: SQL (Sakila DB) and semantic (RAG, AG News/ChromaDB). | |
| ## Features | |
| - **SQL Mode**: Natural language queries on Sakila movie database | |
| - **RAG Mode**: Semantic search on AG News articles with ChromaDB | |
| ## Quick Start | |
| 1. Install dependencies: | |
| ```bash | |
| pip install -r requirements.txt | |
| ``` | |
| 2. Initialize data: | |
| ```bash | |
| python setup_data.py | |
| ``` | |
| 3. Run the app: | |
| ```bash | |
| streamlit run app.py | |
| ``` | |
| ## Configuration | |
| - Edit `.env` for API keys: | |
| ``` | |
| GOOGLE_API_KEY=your-google-api-key-here | |
| ``` | |
| ## Dependencies | |
| See `requirements.txt` for full list: | |
| - streamlit | |
| - chromadb | |
| - langchain | |
| - langchain-google-genai | |
| - sentence-transformers | |
| - datasets | |
| ## Usage | |
| 1. Select mode from sidebar (SQL or RAG) | |
| 2. Ask questions in natural language | |
| 3. Get AI-powered answers | |
| ### Example Questions | |
| **SQL Mode:** | |
| - How many films are there? | |
| - Show me the top 5 longest films | |
| - Which actors have the most films? | |
| **RAG Mode:** | |
| - What's happening with oil prices? | |
| - Tell me about technology news | |
| - Any sports updates? | |
| --- | |
| Created by Bharath Gajula | Powered by Gemini & LangChain | |