A simple Retrieval Augmented Generation (RAG) chatbot that allows users to upload multiple documents and chat with them. The application uses Gradio for the frontend interface and Pinecone as the vector database.

• Upload multiple documents (PDF, TXT, DOCX)
• Extract text from documents and store as vector embeddings
• Chat with your documents using natural language
• Responses include source information

• Docker installed on your machine
• OpenAI API key
• Pinecone API key

1. Clone this repository:

   git clone <repository-url>
   cd <repository-directory>
   

2. Create a .env file by copying the example:

   cp .env.example .env
   

3. Edit the .env file and fill in your API keys:

   OPENAI_API_KEY=your_openai_api_key_here
   PINECONE_API_KEY=your_pinecone_api_key_here
   PINECONE_ENVIRONMENT=your_pinecone_environment_here
   PINECONE_INDEX_NAME=your_pinecone_index_name_here
   

docker-compose up -d

This will build the image and start the container in the background. You can view the logs with:

docker-compose logs -f

1. Build the Docker image:

   docker build -t rag-document-chatbot .
   

2. Run the container:

   docker run -p 7860:7860 --env-file .env rag-document-chatbot
   

3. Access the application in your browser at:

   http://localhost:7860
   

1. Go to the "Upload Documents" tab.
2. Upload one or more documents (PDF, TXT, DOCX).
3. Click "Process Documents" and wait for confirmation.
4. Switch to the "Chat" tab.
5. Ask questions about your documents.

1. Document Processing: Uploaded documents are processed, chunked, and embedded.
2. Vector Storage: Document chunks are stored in Pinecone as vector embeddings.
3. Retrieval: When you ask a question, the system finds the most relevant document chunks.
4. Generation: The language model generates a response based on the retrieved context.

• Python
• Gradio (Frontend)
• LangChain (RAG framework)
• OpenAI (Embeddings and LLM)
• Pinecone (Vector Database)
• Docker (Containerization)

This project is licensed under the MIT License - see the LICENSE file for details.