Python: Anthropic function calling fixes #9938
Merged
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
TaoChenOSU
added
PR: in progress
github-actions
bot
changed the title
eavanvalkenburg
approved these changes
Dec 11, 2024
python/semantic_kernel/connectors/ai/anthropic/services/utils.py
Outdated
Show resolved
Hide resolved
moonbox3
approved these changes
Dec 11, 2024
TaoChenOSU
removed
the
PR: in progress
moonbox3
approved these changes
Dec 16, 2024
This was referenced Dec 17, 2024
github-merge-queue bot
pushed a commit
that referenced
this pull request
Dec 19, 2024
### Motivation and Context <!-- Thank you for your contribution to the semantic-kernel repo! Please help reviewers and future users, providing the following information: 1. Why is this change required? 2. What problem does it solve? 3. What scenario does it contribute to? 4. If it fixes an open issue, please link to the issue here. --> When using the Anthropic connector with function calling, it's possible that the model will request multiple functions in a single request. This is referred to as [`parallel tool use`](https://docs.anthropic.com/en/docs/build-with-claude/tool-use#disabling-parallel-tool-use) by Anthropic. When the model requests multiple functions, it expects the tool results to be included in a single user message to be passed back to the model. Right now, the Anthropic connector parses the tool results into multiple user messages, which causes the model to throw an error. This is a possible regression introduced by this PR: #9938 ### Description <!-- Describe your changes, the overall approach, the underlying design. These notes will help understanding how your code works. Thanks! --> 1. Fix the Anthropic connector to handle parallel tool calls. 2. Add unit tests to ensure that future changes don't break this functionality. 3. Enable integration test on Anthropic since we have a service endpoint now. 4. Refactoring. ### Contribution Checklist <!-- Before submitting this PR, please make sure: --> - [x] The code builds clean without any errors or warnings - [x] The PR follows the [SK Contribution Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md) and the [pre-submission formatting script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts) raises no violations - [x] All unit tests pass, and I have added new tests where possible - [x] I didn't break anyone 😄
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.
Motivation and Context
The current implementation of the Anthropic connector relies on the
inner_contents in chat messages to prepare the chat history for the Anthropic client. This will only work when the chat history is created by the Anthropic connector. This won't work if the chat history has been processed by other connectors, or if it is hardcoded as in testing.Description
Contribution Checklist