Files
langchain-python/langchain/chains
Nick 0874872dee add token reduction to ConversationalRetrievalChain (#2075)
This worked for me, but I'm not sure if its the right way to approach
something like this, so I'm open to suggestions.

Adds class properties `reduce_k_below_max_tokens: bool` and
`max_tokens_limit: int` to the `ConversationalRetrievalChain`. The code
is basically copied from
[`RetreivalQAWithSourcesChain`](https://github.com/nkov/langchain/blob/46d141c6cb6c0fdebb308336d8ae140d8368945a/langchain/chains/qa_with_sources/retrieval.py#L24)
2023-03-28 15:07:31 -07:00
..
2023-02-12 23:01:26 -08:00
2023-01-27 00:45:17 -08:00
2023-03-20 07:50:49 -07:00
2023-03-20 07:53:26 -07:00
2023-02-02 08:23:38 -08:00
2023-03-20 07:50:49 -07:00
2023-03-14 12:37:48 -07:00
2023-03-20 07:50:49 -07:00
2023-03-20 07:50:49 -07:00
2023-03-22 23:15:04 -07:00
2023-03-07 07:59:37 -08:00
2023-03-06 08:34:24 -08:00
2023-03-22 23:15:04 -07:00
2022-12-10 09:19:16 -08:00
2023-03-04 08:15:52 -08:00
2022-12-06 21:58:16 -08:00