mirror of
https://github.com/hwchase17/langchain
synced 2024-11-06 03:20:49 +00:00
aaac7071a3
Improvements to Deep Lake Vector Store - much faster view loading of embeddings after filters with `fetch_chunks=True` - 2x faster ingestion - use np.float32 for embeddings to save 2x storage, LZ4 compression for text and metadata storage (saves up to 4x storage for text data) - user defined functions as filters Docs - Added retriever full example for analyzing twitter the-algorithm source code with GPT4 - Added a use case for code analysis (please let us know your thoughts how we can improve it) --------- Co-authored-by: Davit Buniatyan <d@activeloop.ai> |
||
|---|---|---|
| .. | ||
| evaluation | ||
| apis.md | ||
| chatbots.md | ||
| code.md | ||
| evaluation.rst | ||
| extraction.md | ||
| personal_assistants.md | ||
| question_answering.md | ||
| summarization.md | ||
| tabular.md | ||