Update README.md

README.md

@@ -1,19 +1,73 @@
 ---
-title: Application Test 1
-emoji: 🚀
-colorFrom: red
-colorTo: red
-sdk: docker
-app_port: 8501
-tags:
-- streamlit
+title: RAG Chatbot
+emoji: 🤖
+colorFrom: blue
+colorTo: purple
+sdk: streamlit
+sdk_version: 1.28.0
+app_file: app.py
 pinned: false
-short_description: Streamlit template space
+license: apache-2.0
 ---
 
-# Welcome to Streamlit!
+# 🤖 RAG Chatbot
 
-Edit `/src/streamlit_app.py` to customize this app to your heart's desire. :heart:
+An intelligent chatbot powered by Retrieval Augmented Generation (RAG) that answers questions based on your custom knowledge base.
 
-If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
-forums](https://discuss.streamlit.io).
+## ✨ Features
+
+- 📚 **Custom Knowledge Base**: Upload your own documents (.txt files)
+- 🔍 **Smart Retrieval**: Uses FAISS for efficient similarity search
+- 🤖 **Multiple LLM Options**: Choose from various open-source models
+- 💬 **Chat Interface**: Interactive conversation with context
+- 📄 **Source Citations**: See which documents were used for answers
+- 🚀 **100% Free**: Uses HuggingFace's free inference API
+
+## 🚀 How to Use
+
+1. **Get a HuggingFace Token** (free):
+   - Visit [HuggingFace Settings](https://huggingface.co/settings/tokens)
+   - Create a **Fine-grained** token
+   - ✅ Enable **'Make calls to Inference Providers'**
+   - Copy the token
+
+2. **Enter Your Token**:
+   - Paste it in the sidebar
+
+3. **Ask Questions**:
+   - The chatbot will answer based on the knowledge base documents
+   - View source documents for each answer
+
+## 📋 Knowledge Base
+
+The knowledge base contains documents that the chatbot uses to answer questions. You can customize it by:
+
+1. Adding .txt files to the `knowledge_base/` folder
+2. Clicking "🔄 Reload Knowledge Base" in the sidebar
+
+## 🛠️ Configuration Options
+
+- **Embedding Model**: Choose how text is converted to vectors
+- **LLM Model**: Select the language model for generating answers
+- **Chunk Size**: Control how documents are split
+- **Number of Results**: How many document chunks to retrieve
+
+## 🔒 Privacy
+
+- Your token is only used to call HuggingFace APIs
+- Conversations are not stored
+- Documents remain private to your session
+
+## 🐛 Troubleshooting
+
+**Model is loading**: Wait 20-30 seconds and try again  
+**Token error**: Make sure 'Make calls to Inference Providers' is enabled  
+**No documents found**: Add .txt files to the knowledge_base folder
+
+## 📝 License
+
+Apache 2.0
+
+---
+
+Built with ❤️ using Streamlit, LangChain, and HuggingFace