Repository Issue Activity (beta)

#626 Feature: Prompt compression to reduce LLM token costs in chat history

#572 Bug: ttl_seconds parameter ignored in in-memory RedisCache set() method

#533 fix(docs_tools): filter stale URLs before returning search results

#503 EU AI Act: Document model provenance & user data handling requirements

#27 why no data display in your demo

#26 Error when running ingest.py

#22 The web ui hangs after chat input, and console print message of 405 Method Not Allowed

#24 any followup to update text-davinci-003 to GPT-3.5-turbo?

#20 Why can't my chat generate code

#19 Running into error ERROR:root:type object 'Completion' has no attribute 'acreate'

#17 'NoneType' object has no attribute 'search'

#16 What does the archive folder contain exactly?

#15 Oops! There seems to be an error. Please try again.

#10 chat.langchain.dev demo broken

#13 First request hangs and it never completes

#8 A bit more insight on the thought process of the prompt chain

#7 Missing license

#4 KeyError: 'data` after the first successful answer

#2 Keeps asking for API key, even once I have entered one.

#1 Return example code from the docs

#75 Outdated

#72 Implement agent

#69 cannot import name 'AsyncCallbackManager' from 'langchain.callbacks.base' (/Users/friahi/Library/Python/3.9/lib/python/site-packages/langchain/callbacks/base.py)

#68 IndexError: list index out of range in index = faiss.IndexFlatL2(len(embeddings[0]))

#63 Add ContextualCompressionRetriever