langchain-python

mirror of https://github.com/Mintplex-Labs/langchain-python.git synced 2026-08-26 16:55:38 -04:00

Files

T

Rafal Wojdyla 37ed6f2177 Handle length safe embedding only if needed (#3723 )

Re: https://github.com/hwchase17/langchain/issues/3722

Copy pasting context from the issue:


https://github.com/hwchase17/langchain/blob/1bf1c37c0cccb7c8c73d87ace27cf742f814dbe5/langchain/embeddings/openai.py#L210-L211

Means that the length safe embedding method is "always" used, initial
implementation https://github.com/hwchase17/langchain/pull/991 has the
`embedding_ctx_length` set to -1 (meaning you had to opt-in for the
length safe method), https://github.com/hwchase17/langchain/pull/2330
changed that to max length of OpenAI embeddings v2, meaning the length
safe method is used at all times.

How about changing that if branch to use length safe method only when
needed, meaning when the text is longer than the max context length?

2023-04-28 20:10:04 -07:00

__init__.py

Add Sentence Transformers Embeddings (#3409 )

2023-04-23 18:25:20 -07:00

aleph_alpha.py

Minor: Remove duplicated word in error message (#2706 )

2023-04-11 13:10:33 -07:00

base.py

FAISS and embedding support (#48 )

2022-11-01 21:29:39 -07:00

cohere.py

Minor: Remove duplicated word in error message (#2706 )