README.md

🔍Search engine using SAM & CLIP

🎫 Enhance RAG: Integrate Contextual Compression and Filtering for Precision.

Follow the Colab Notebook for full code.

Interface 🌟

1. Load the Model from Huggingface.
2. Instantiate Contextual Compressor from Langchain.
3. Create a pipeline with different retrieving filters.
4. Get the answer using QA chain.