DataSciencePilot is an innovative chat-based interface designed to interact with custom PDF files. It leverages the power of Pinecone for efficient vector database management and LLaMA-2 for advanced query response capabilities. This combination allows users to easily extract and analyze information from PDF documents through a conversational interface.
- Chat Interface: Interact with your PDF files through a user-friendly chat interface.
- Pinecone Integration: Utilizes Pinecone's vector database for efficient data handling and retrieval.
- LLaMA-2 Powered: Harnesses the advanced natural language processing capabilities of LLaMA-2 for accurate and relevant responses.
- PDF Support: Seamlessly works with custom PDF files for data extraction and analysis.
To get started with DataSciencePilot, follow these simple steps:
-
Clone the Repository: Clone this repository to your local machine.
git clone https://github.com/kowshik24/DataSciencePilot.git
-
Download the model: Download the model from huggingface from here: https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGML/blob/main/llama-2-7b-chat.ggmlv3.q4_0.bin then place it in the
model
folder. And on theapp.py
file change the model path to the path of the model you just downloaded.llm=CTransformers(model="model/llama-2-7b-chat.ggmlv3.q4_0.bin")
-
Create a Virtual Environment: Create a virtual environment using the following command:
python3 -m venv env
-
Activate the Virtual Environment: Activate the virtual environment using the following command:
source env/bin/activate
-
Install Dependencies: Install the required dependencies using the following command:
pip install -r requirements.txt
-
.env File: Create a
.env
file in the root directory of the project and add the following environment variables:PINECONE_API_KEY=<your-pinecone-api-key> PINECONE_API_ENV=<your-pinecone-api-env> PINECONE_INDEX_NAME=<your-pinecone-index-name>
-
Run the Application: Run the application using the following command:
python app.py
-
Open the Application: Open the application in your browser using the following URL:
http://localhost:5120/
πΈ Screenshots
Sample Visualization 1 | Sample Visualization 2 |
π Contact Information For support, feedback, or contributions, please reach out to:
- π§ Email: [email protected]
- π± Phone: 01706 896161
- π Website: https://kowshik24.github.io/kowshik.github.io/
- π GitHub: Kowshik Deb Nath
- π€ LinkedIn: Kowshik Deb Nath