shvuuuu / LLamaIndexPdfChat

Taking advantage of LlamaIndex's in-context learning paradigm, LlamaDoc empowers users to input PDF documents and pose any questions related to the content. The tool leverages the LLama Index's reasoning capabilities to provide intelligent responses based on the contextual understanding of the LLM.

LlamaDoc

LlamaDoc is a powerful web application that utilizes the LlamaIndex library and the reasoning capabilities of LLMs (Language Model Models) to provide accurate and insightful responses from PDF files. It enables users to upload PDF documents, search for specific information within them, and receive relevant answers generated by LLMs.

Features

• PDF Upload: Users can upload their PDF files through the web interface.
• In-Context Learning: LlamaDoc leverages the in-context learning approach of LLMs, allowing for more accurate and context-aware responses.
• Search Functionality: Users can input their queries in the search bar to retrieve relevant information from the uploaded PDFs.
• Interactive PDF Viewing: LlamaDoc provides an interactive PDF viewer that allows users to view the uploaded PDF files directly in the web application.

Installation

1. Clone the repository:

git clone https://github.com/yourusername/LlamaDoc.git
cd <repository>

2. Install the required dependencies:

pip install -r requirements.txt

3. Set up the environment variables:

• Create a .env file in the root directory.
• Add the following key-value pairs to the .env file:

OPENAI_API_KEY=your_openai_api_key

4. Start the LlamaDoc web application:

streamlit run app.py