The Retrieval Augmented Engine (RAG) is a powerful tool for document retrieval, summarization, and interactive question-answering. This project utilizes LangChain, Streamlit, and Pinecone to provide a seamless web application for users to perform these tasks. With RAG, you can easily upload multiple PDF documents, generate vector embeddings for text within these documents, and perform conversational interactions with the documents. The chat history is also remembered for a more interactive experience.
Before running the project, make sure you have the following prerequisites:
Clone the repository to your local machine:
git clone https://github.com/wsxqaza12/RAG_LangChain_streamlit.git
cd RAG_LangChain_streamlit
Install the required dependencies by running:
pip install -r requirements.txt
Run the Streamlit app:
streamlit run rag_engine.py
Access the app by opening a web browser and navigating to the provided URL.
Input your LLM URL or OpenAI API key,
Upload the PDF documents you want to analyze.
Click the "Submit Documents" button to process the documents and generate vector embeddings.
Engage in interactive conversations with the documents by typing your questions in the chat input box.