Follow the Colab Notebook for full code.
- Load the Model from Huggingface.
- Instantiate Contextual Compressor from Langchain.
- Create a pipeline with different retrieving filters.
- Get the answer using QA chain.
Contextual-Compression-with-RAG
Folders and files
| Name | Name | Last commit date | ||
|---|---|---|---|---|
parent directory.. | ||||