https://github.com/leodeveloper/qasimilaritysearch
Question and Answer Similarity Search Application using pinecone vector database
https://github.com/leodeveloper/qasimilaritysearch
Last synced: about 1 year ago
JSON representation
Question and Answer Similarity Search Application using pinecone vector database
- Host: GitHub
- URL: https://github.com/leodeveloper/qasimilaritysearch
- Owner: leodeveloper
- Created: 2024-05-04T15:29:15.000Z (almost 2 years ago)
- Default Branch: main
- Last Pushed: 2024-05-04T16:08:11.000Z (almost 2 years ago)
- Last Synced: 2024-05-05T16:39:24.071Z (almost 2 years ago)
- Language: Jupyter Notebook
- Size: 1.09 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Question and Answer Similarity Search Application
This project aims to create a Question and Answer (QA) similarity search application using Python. It leverages various libraries and tools including Jupyter Notebook, Pinecone, Vector Database, LangChain, RetrievalQA, ChatGPT, OpenAIEmbeddings, PineconeVectorStore, PyPDFDirectoryLoader, and RecursiveCharacterTextSplitter.
## Features
- **Question-Answer Similarity Search**: Allows users to input a question and retrieves similar questions or answers from a dataset.
- **Integration with Large Language Models**: Integrates with ChatGPT and other large language models for improved understanding and retrieval.
- **Efficient Vector Database**: Utilizes Pinecone as a vector database for fast and scalable similarity search.
- **Support for Various Data Formats**: Supports PDF documents through PyPDFDirectoryLoader and text processing with RecursiveCharacterTextSplitter.
## Installation
1. Clone the repository:
```bash
git clone https://github.com/your_username/your_project.git
```
2. Install the required dependencies:
```bash
pip install -r requirements.txt
```
3. Set up Pinecone:
Visit [Pinecone](https://www.pinecone.io/) and follow the instructions to create an account and obtain an API key. Replace `YOUR_API_KEY` in `config.py` with your actual API key.
## Usage
1. Start Jupyter Notebook:
```bash
jupyter notebook
```
2. Open `QASimilaritySearch.ipynb` and follow the instructions to run the application.
## Contributors
- Muhammad Suleman (@skylinestorytel)
## License
This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.