Proposal : Add RAG-Based LLM PromptBot (OpenRouter + Files)

[VathareVinayak]

Streamlit RAG PromptBot

@Shubhamsaboo , This PR adds a full working example of a Retrieval-Augmented Chatbot using Streamlit and OpenRouter API. The app reads PDF files as a knowledge base and answers user queries intelligently without storing any data in a database — all chat is kept in session memory.

Features

• RAG-based responses using PDF context.
• Upload your own PDF knowledge files.
• Streamlit interactive UI with chat interface.
• Session-only memory; no database required.
• OpenRouter API integration for LLM responses.
• Error handling for API issues.

Tech Stack

• Streamlit (Frontend UI)
• OpenRouter API (gpt-3.5-turbo) for LLM
• Python 3.10+
• PyPDF2 for PDF text extraction
• python-dotenv for environment variables

Project Folder

rag_tutorials/openrouter_rag_based_chatbot/
├── app.py
├── utils/pdf_reader.py
├── requirements.txt
├── .gitignore
├── .env.example
├── README.md
└── snaps/
├── OpenrouterResting.png
└── testSnaps.png

Installation & Running

1. Clone the repo or fork.
2. Create a Python virtual environment and activate it.
3. Install dependencies: pip install -r requirements.txt.
4. Add your OpenRouter API key in .env.
5. Run: streamlit run app.py.

Performance & Notes

• Response time: ~1-2.038 seconds (also depending on PDF contains tables , imagnes or not and also API)
• Best performance with PDFs < 20 MB.
• Lightweight, no database used.

Screenshots

Screenshots

Upload PDF Interface:

Chat Interface:

This PR adds a ready-to-run, self-contained example project for users to try RAG with Streamlit + OpenRouter API.