Briefly is an innovative application that allows you to chat with your documents using open-source Large Language Models (LLMs). Upload your PDFs, ask questions, and receive relevant answers in no time!
- Interactive Chat: Engage in a conversation with your documents.
- Easy Upload: Upload multiple PDF files effortlessly.
- Efficient Processing: Fast and accurate document processing.
- Open-Source LLMs: Powered by open-source language models.
To get started with Briefly, follow these steps:
make sure Ollama and llama3 is installed
-
Clone the repository:
git clone https://github.com/Mhijazi16/Briefly.git cd Briefly
-
Install the required dependencies:
pip install -r requirements.txt
-
Run the application:
streamlit run Briefly.py
- Upload Documents: Use the sidebar to upload your PDF documents.
- Ask Questions: Enter your questions in the text input field.
- Get Answers: Receive relevant answers extracted from your documents.
Here's a brief overview of the main components of the code:
- Document Reading: Uses PyPDF2 to read and extract text from PDF documents.
- Text Splitting: Utilizes RecursiveCharacterTextSplitter from Langchain to split text into manageable chunks.
- Embedding and Retrieval: Implements OllamaEmbeddingWrapper to embed documents and FAISS for efficient retrieval.
- Interactive Interface: Built with Streamlit to provide a user-friendly interface.