Skip to content

Python: Update chat history channel to produce the correct messages with a visibility bool #7619

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 9 commits into from
Aug 5, 2024

Conversation

moonbox3
Copy link
Contributor

@moonbox3 moonbox3 commented Aug 2, 2024

Motivation and Context

To align with the dotnet ChatHistoryChannel, there needs to be an update to the Python ChatHistoryChannel that properly handles the invoked message via a queue. This allows the final messages to be produced (as they sometimes may contain function call content or function result content). The messages are also produced with an is_visibile bool.

Description

This PR:

  • updates the chat history channel to implement the queue that handles ChatMessageContent types and the is_visible bool to the caller.
    • This change requires the use of a set and thus an implementation of a __hash__ method for some content types so we know we're not adding/handling duplicate messages.
  • Upgrades OpenAI package to 1.37.1 (supersedes a previous Dependabot PR doing the same)
  • Updates unit tests for ChatHistoryChannel based on the new code to maintain 100% coverage.
  • Adds a missing parallel_tool_calls bool in the Run object of agent unit tests related to the upgrade to OpenAI 1.37.1.

Contribution Checklist

@moonbox3 moonbox3 requested a review from a team as a code owner August 2, 2024 14:16
@markwallace-microsoft markwallace-microsoft added the python Pull requests for the Python Semantic Kernel label Aug 2, 2024
@markwallace-microsoft
Copy link
Member

markwallace-microsoft commented Aug 2, 2024

Python Test Coverage

Python Test Coverage Report
FileStmtsMissCoverMissing
semantic_kernel
   kernel.py157796%145, 156, 160, 310–313, 422
semantic_kernel/connectors/ai/azure_ai_inference/services
   azure_ai_inference_chat_completion.py149497%169, 312, 416, 430
semantic_kernel/connectors/ai/embeddings
   embedding_generator_base.py8188%50
semantic_kernel/connectors/ai/google
   shared_utils.py39295%100, 122
semantic_kernel/connectors/ai/google/google_ai/services
   google_ai_chat_completion.py145398%149, 251, 287
   utils.py62395%138, 156–161
semantic_kernel/connectors/ai/google/vertex_ai/services
   utils.py64395%140, 158–163
   vertex_ai_chat_completion.py145398%143, 244, 280
semantic_kernel/connectors/ai/hugging_face/services
   hf_text_completion.py54394%95, 103, 134
   hf_text_embedding.py32584%77–81
semantic_kernel/connectors/openapi_plugin
   openapi_manager.py58297%110–111
   openapi_parser.py88199%127
   openapi_runner.py105298%181–182
semantic_kernel/connectors/openapi_plugin/models
   rest_api_operation.py129199%240
semantic_kernel/contents
   function_call_content.py97199%201
semantic_kernel/functions
   kernel_function_decorator.py98199%102
   kernel_function_from_method.py96199%153
   kernel_function_from_prompt.py154795%165–166, 180, 201, 219, 239, 322
   kernel_plugin.py187299%472, 475
semantic_kernel/planners
   plan.py2344581%52, 161–163, 195, 212–225, 262, 267, 275–276, 286–289, 306, 311, 327, 330–335, 353, 358, 361, 363, 370, 384–386, 391–395
semantic_kernel/planners/function_calling_stepwise_planner
   function_calling_stepwise_planner.py116497%143, 187–188, 196
semantic_kernel/planners/sequential_planner
   sequential_planner.py64691%69, 73, 107, 123, 132–133
   sequential_planner_extensions.py50982%29–30, 52, 106–120
   sequential_planner_parser.py771284%64–72, 91, 115–118
semantic_kernel/schema
   kernel_json_schema_builder.py119596%48, 82, 204, 208–209
semantic_kernel/template_engine/blocks
   code_block.py77199%119
   named_arg_block.py43198%98
semantic_kernel/utils/telemetry
   decorators.py113496%232, 240, 243, 252
   user_agent.py16288%18–19
TOTAL862714198% 

Python Unit Test Overview

Tests Skipped Failures Errors Time
2102 1 💤 0 ❌ 0 🔥 51.369s ⏱️

@moonbox3 moonbox3 enabled auto-merge August 5, 2024 15:14
@moonbox3 moonbox3 added this pull request to the merge queue Aug 5, 2024
@github-merge-queue github-merge-queue bot removed this pull request from the merge queue due to failed status checks Aug 5, 2024
@moonbox3 moonbox3 enabled auto-merge August 5, 2024 16:17
@moonbox3 moonbox3 added this pull request to the merge queue Aug 5, 2024
Merged via the queue into microsoft:main with commit 91090f8 Aug 5, 2024
25 checks passed
@moonbox3 moonbox3 deleted the agent_chat_history_channel_update branch August 5, 2024 16:34
LudoCorporateShark pushed a commit to LudoCorporateShark/semantic-kernel that referenced this pull request Aug 25, 2024
…ith a visibility bool (microsoft#7619)

### Motivation and Context

To align with the dotnet ChatHistoryChannel, there needs to be an update
to the Python ChatHistoryChannel that properly handles the invoked
message via a queue. This allows the final messages to be produced (as
they sometimes may contain function call content or function result
content). The messages are also produced with an `is_visibile` bool.

<!-- 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.
-->

### Description

This PR:
- updates the chat history channel to implement the queue that handles
ChatMessageContent types and the `is_visible` bool to the caller.
- This change requires the use of a set and thus an implementation of a
`__hash__` method for some content types so we know we're not
adding/handling duplicate messages.
- Upgrades OpenAI package to 1.37.1 (supersedes a previous Dependabot PR
doing the same)
- Updates unit tests for ChatHistoryChannel based on the new code to
maintain 100% coverage.
- Adds a missing `parallel_tool_calls` bool in the Run object of agent
unit tests related to the upgrade to OpenAI 1.37.1.

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->

### 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
- [ ] I didn't break anyone 😄

---------

Co-authored-by: Chris <66376200+crickman@users.noreply.github.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
python Pull requests for the Python Semantic Kernel
Projects
Archived in project
Development

Successfully merging this pull request may close these issues.

6 participants