feat(llm): add Anthropic LLM client #31
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
|
Trivy scanning results. |
|
Code Coverage SummaryDiff against mainResults for commit: 030c8f5 Minimum allowed coverage is ♻️ This comment has been updated with latest results |
mhordynski
reviewed
May 15, 2024
ludwiktrammer
approved these changes
May 16, 2024
|
|
||
| Args: | ||
| prompt: Prompt as an Anthropic client style list. | ||
| response_format: Optional argument used in the OpenAI API - used to force the json output. |
There was a problem hiding this comment.
Not really a comment to this PR, but having an argument in AnthropicClient that is specific to OpenAI clearly illustrates that we should refactor this option away (both here and in the prompt object itself). In a separate PR/ticket of course.
Maybe for example we could have a expect_json as a general boolen flag that each LLM client could implement in a way that makes sense for the particular model/API (by passing the appropriate option for the particular API or even by using post-processing).
There was a problem hiding this comment.
You're right. I was also thinking of moving response_format argument to LLMOptions, which would make the interface cleaner. What do you think?
cc @mhordynski
There was a problem hiding this comment.
I think response_format (or its non-OpenAI specific equivalent) should remain coupled with the prompt (i.e., be part of the PromptTemplate class), because whether we expect json fully depend on the prompt itself.
|
Closing this PR, we decided to use the litellm API to integrate with Anthropic. |
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Outdated suggestions cannot be applied.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 PR adds support for Anthropic's Claude models.