This project explores the capabilities of Haystack, an open-source framework for building search systems. We dive into various components and use cases to understand its potential in creating powerful, AI-driven search solutions.
- Document retrieval
- Question answering
- Semantic search
- And more!
- Clone the repository:
git clone https://github.com/90barricade93/haystack-explore
- Navigate to the project directory:
cd haystack-explore
Set up a virtual environment:
python3 -m venv haystack_env
source haystack_env/bin/activate
Install dependencies:
pip install -r requirements.txt
Set up API keys:
Create a `.env` file in the project root and add your API keys for any services you plan to use (e.g., OpenAI, Elasticsearch).
Run any of the Python scripts to explore different Haystack features:
python3 first_rag_pipeline.py
python3 embedding_metadata_for_improved_retrieval.py
python3 extractive_qa_pipeline.py
python3 metadata_filtering.py
python3 file_type_preprocessing_index_pipeline.py
python3 serializing_pipelines.py
Contributions are welcome! Please feel free to submit a Pull Request.
If you encounter any issues, please check The haystack tutorial or open an issue.
This project is licensed under the MIT License - see the LICENSE file for details.