Added stop sequence support to replicate #8107
Merged
+152
−61
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
|
The latest updates on your projects. Learn more about Vercel for Git ↗︎
|
dosubot
bot
added
the
🤖:improvement
|
Hi @baskaryan I've resolved the earlier merge conflicts and have been using this diff for the last few days with no issues... let me know if any questions. |
|
this is great, thank you @tjaffri! |
bdonkey
added a commit
to bdonkey/langchain
that referenced
this pull request
Jul 26, 2023
* master: (496 commits) New enterprise support form (langchain-ai#8254) Add LLMChain example of memory with chat models (langchain-ai#8250) Update Broken Links (langchain-ai#8247) Remove operator overloading for BaseMessage (langchain-ai#8245) Update references (langchain-ai#8243) Bug Fix langchain-ai#6462 (langchain-ai#8241) bump 242 (langchain-ai#8238) Add/faiss test score threshold (langchain-ai#8224) use logger instead of logging (langchain-ai#8225) Refactored `requests` (langchain-ai#8203) Update Integrations links (langchain-ai#8206) Update base chain type hints (langchain-ai#7680) feat: temp fixed Could not parse LLM output on agents folder (langchain-ai#7746) add Hybrid retriever that not require any external service (langchain-ai#8108) Fixed grammar in LLM models documentation (langchain-ai#8210) Update supabase.py, add filter to query (matches latest supabase docs & js) (langchain-ai#7721) Fixed sparql SELECT and UPDATE query function (langchain-ai#7758) Add async support for transform chain (langchain-ai#8205) Added stop sequence support to replicate (langchain-ai#8107) Add etherscan document loader (langchain-ai#7943) ...
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.
Stop sequences are useful if you are doing long-running completions and need to early-out rather than running for the full max_length... not only does this save inference cost on Replicate, it is also much faster if you are going to truncate the output later anyway.
Other LLMs support stop sequences natively (e.g. OpenAI) but I didn't see this for Replicate so adding this via their prediction cancel method.
Housekeeping: I ran
make formatandmake lint, no issues reported in the files I touched.I did update the replicate integration test and ran
poetry run pytest tests/integration_tests/llms/test_replicate.pysuccessfully.Finally, I am @tjaffri https://twitter.com/tjaffri for feature announcement tweets... or if you could please tag @docugami https://twitter.com/docugami we would really appreciate that :-)
Tagging model maintainers @hwchase17 @baskaryan
Thank for all the awesome work you folks are doing.