feat: Add support for langchain-anthropic in LLMEndpoint completes CORE-144 #2991
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
This commit adds support for the langchain-anthropic language model in the LLMEndpoint class. The function has been updated to include the new model names. Now, when configuring the LLMEndpoint, if the model name starts with claude, the ChatAnthropic class from langchain-anthropic will be used instead of ChatOpenAI from langchain-openai.
|
The latest updates on your projects. Learn more about Vercel for Git ↗︎
|
dosubot
bot
added
size:L
fix core-142 --------- Co-authored-by: Stan Girard <girard.stanislas@gmail.com> Co-authored-by: aminediro <aminedirhoussi1@gmail.com>
# Description - Complete rewrite of Syncutils - Eager processing Syncs on Create and Update Sync. - Simplified a LOT of filtering logic on files - Fixed notifier async knowledge
dosubot
bot
added
size:XXL
dosubot
bot
added
size:L
I have made changes to the knowledge table schema and models to improve functionality and data organization. This includes adding new columns, modifying existing columns, and updating relationships. These changes will enhance the overall performance and usability of the application. --------- Co-authored-by: Stan Girard <girard.stanislas@gmail.com> Co-authored-by: aminediro <aminedirhoussi1@gmail.com>
Needs export UV_INDEX_STRATEGY=unsafe-first-match to work Completes CORE-153
This commit adds the langchain-anthropic dependency to the project's pyproject.toml file. The version specified is 0.1.23.
AmineDiro
reviewed
Aug 22, 2024
| @@ -13,7 +13,8 @@ dependencies = [ | |||
| "rich>=13.7.1", | |||
| "tiktoken>=0.7.0", | |||
| "aiofiles>=24.1.0", | |||
| "langchain-community>=0.2.12" | |||
| "langchain-community>=0.2.12", | |||
| "langchain-anthropic>=0.1.23", | |||
There was a problem hiding this comment.
anthropic is present in the core/base environment ?
backend/core/tests/test_quivr_rag.py
Outdated
There was a problem hiding this comment.
The quivrqa tests depends n a fixture generated from openai endpoint. Maybe we can generate fixture file for claude so that the mock response closely matches the api endpoint 👍🏼
| api_key=SecretStr(config.llm_api_key) if config.llm_api_key else None, | ||
| base_url=config.llm_base_url, | ||
| ) | ||
| if config.model.startswith("claude"): |
There was a problem hiding this comment.
Just to reduce code boilerplate. if and only if the class have the exact params:
Suggested change
| if config.model.startswith("claude"): | |
| if config.model.startswith("claude"): | |
| from langchain_anthropic import ChatAnthropic | |
| cls = ChatAnthropic | |
| else: | |
| cls = ChaatOpenAI |
dosubot
bot
added
size:XXL
|
Thanks for your contributions, we'll be closing this PR as it has gone stale. Feel free to reopen if you'd like to continue the discussion. |
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.
This commit adds support for the langchain-anthropic language model in the LLMEndpoint class. The function has been updated to include the new model names. Now, when configuring the LLMEndpoint, if the model name starts with claude, the ChatAnthropic class from langchain-anthropic will be used instead of ChatOpenAI from langchain-openai.
Description
Please include a summary of the changes and the related issue. Please also include relevant motivation and context.
Checklist before requesting a review
Please delete options that are not relevant.
Screenshots (if appropriate):