✨ WizSearch

Your intelligent ally for effortless data retrieval across documents and seamless browsing the web.

Demo 🎬

1. Get your API key groq
2. Checkout https://wizsearch.streamlit.app/

Checkout the features 💻 Quick start with Ollama in local 🦙✨

wizsearch-demo.mp4

How we built it 🛠️

We built Wiz Search using the following components:

• LLM/VLM: Open source models like llama3.1, mistral, LLaVA, etc are supported by platforms such as Ollama and Groq. Closed source models like gpt-4o, gpt-4 supported by OpenAI and Azure OpenAI for natural language understanding and generation. Litellm is used to support all the models.
• Embeddings: jina-embeddings-v3 and BM25 using fastembed to enhance search relevance.
• Intelligent Search: Tavily for advanced search capabilities.
• Data Extraction: MarkItDown for converting documents to text.
• Vector Databases: Qdrant for efficient data storage and retrieval.
• Observability: Langfuse for monitoring and observability.
• UI: Streamlit for creating an interactive and user-friendly interface.

Run The Application ⚙️

1. Clone the repo

git clone https://github.com/SSK-14/WizSearch.git

2. Install required libraries

• Create virtual environment

pip3 install virtualenv
python3 -m venv {your-venvname}
source {your-venvname}/bin/activate

• Install required libraries

pip3 install -r requirements.txt

• Activate your virtual environment

source {your-venvname}/bin/activate

3. Set up your config.yaml and .env file Update a config.yaml file in root folder Refer. Create a .env file in root folder Refer

4. Installation and setup

bash setup.sh

5. Running

streamlit run app.py 

Contributing 🤝

Contributions to this project are welcome! If you find any issues or have suggestions for improvement, please open an issue or submit a pull request on the project's GitHub repository.

License 📝

This project is licensed under the MIT License. Feel free to use, modify, and distribute the code as per the terms of the license.