uumerrr684 commited on
Commit
ff1c93a
Β·
verified Β·
1 Parent(s): 8f69236

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +49 -12
README.md CHANGED
@@ -1,19 +1,56 @@
1
  ---
2
  title: RAG Chat Flow
3
- emoji: πŸš€
4
- colorFrom: red
5
- colorTo: red
6
- sdk: docker
7
- app_port: 8501
8
- tags:
9
- - streamlit
10
  pinned: false
11
- short_description: Streamlit template space
12
  ---
13
 
14
- # Welcome to Streamlit!
15
 
16
- Edit `/src/streamlit_app.py` to customize this app to your heart's desire. :heart:
17
 
18
- If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
19
- forums](https://discuss.streamlit.io).
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  title: RAG Chat Flow
3
+ emoji: πŸ“š
4
+ colorFrom: blue
5
+ colorTo: purple
6
+ sdk: streamlit
7
+ sdk_version: 1.29.0
8
+ app_file: app.py
 
9
  pinned: false
10
+ license: mit
11
  ---
12
 
13
+ # RAG Chat Flow πŸ“š
14
 
15
+ An intelligent document Q&A chatbot powered by Retrieval-Augmented Generation (RAG). Upload your documents and ask questions to get accurate, context-aware answers.
16
 
17
+ ## Features
18
+
19
+ - πŸ” **Smart Document Search**: Uses semantic search to find relevant information
20
+ - πŸ€– **AI-Enhanced Answers**: Combines document retrieval with AI processing for natural responses
21
+ - πŸ“ **Multi-Document Support**: Upload multiple text files for comprehensive knowledge base
22
+ - πŸ’¬ **Chat History**: Persistent chat sessions with automatic saving
23
+ - πŸ‘₯ **Multi-User Support**: Real-time user tracking and session management
24
+ - 🎯 **Confidence Scoring**: Shows how confident the system is in its answers
25
+ - πŸ“Š **Source Attribution**: Always shows which documents answers come from
26
+
27
+ ## How to Use
28
+
29
+ 1. **Upload Documents**: Use the sidebar to upload .txt files containing your knowledge base
30
+ 2. **Index Documents**: Click "Re-index Documents" to process your files
31
+ 3. **Ask Questions**: Start chatting! Ask specific questions about your uploaded documents
32
+ 4. **Get Answers**: Receive both AI-enhanced and extracted answers with source citations
33
+
34
+ ## Technical Details
35
+
36
+ - **Embedding Model**: all-mpnet-base-v2 for semantic understanding
37
+ - **Vector Database**: ChromaDB for efficient similarity search
38
+ - **Text Splitting**: Intelligent chunking that preserves context
39
+ - **AI Enhancement**: Optional OpenRouter API integration for natural language responses
40
+
41
+ ## Environment Variables
42
+
43
+ Set `OPENROUTER_API_KEY` for AI-enhanced responses (optional - works without it too).
44
+
45
+ ## Example Use Cases
46
+
47
+ - Corporate policy documents
48
+ - Technical documentation
49
+ - Research papers
50
+ - Product manuals
51
+ - Legal documents
52
+ - Knowledge bases
53
+
54
+ ## Setup
55
+
56
+ The app automatically handles document processing and indexing. Simply upload your text files and start asking questions!