Async Support for LLMChainExtractor #3587
Closed
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
fixed the formatting... |
vowelparrot
reviewed
Apr 26, 2023
|
Reverted the Sync changes and just added async without the use of |
hwchase17
pushed a commit
that referenced
this pull request
May 2, 2023
@vowelparrot @hwchase17 Here a new implementation of `acompress_documents` for `LLMChainExtractor ` without changes to the sync-version, as you suggested in #3587 / [Async Support for LLMChainExtractor](#3587) . I created a new PR to avoid cluttering history with reverted commits, hope that is the right way. Happy for any improvements/suggestions. (PS: I also tried an alternative implementation with a nested helper function like ``` python async def acompress_documents_old( self, documents: Sequence[Document], query: str ) -> Sequence[Document]: """Compress page content of raw documents.""" async def _compress_concurrently(doc): _input = self.get_input(query, doc) output = await self.llm_chain.apredict_and_parse(**_input) return Document(page_content=output, metadata=doc.metadata) outputs=await asyncio.gather(*[_compress_concurrently(doc) for doc in documents]) compressed_docs=list(filter(lambda x: len(x.page_content)>0,outputs)) return compressed_docs ``` But in the end I found the commited version to be better readable and more "canonical" - hope you agree.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Implemented
acompress_documentsand changed syntax forcompress_documentsslightly to make sync/async functions consistent.LLMChainExtractoras implemented in #2915 for use in theContextualCompressionRetrieverlacked an async method. As compression of retrieved documents is a highly parallelizable task, this was a major performance bottleneck in my tests.This implementation is consistent to the implementation in the somewhat similar
MapReduceDocumentsChainchain, see https://github.com/hwchase17/langchain/blob/85dae78548ed0c11db06e9154c7eb4236a1ee246/langchain/chains/combine_documents/map_reduce.py#L131 .In my own tests (standalone as well as in a compression pipeline) inputs/outputs are unchanged and the async-speedup is significant.