Skip to content

Python: Add parallel_tool_calls attribute to OpenAI chat prompt execution settings - #9479

Merged
Evan Mattson (moonbox3) merged 3 commits into
microsoft:mainfrom
moonbox3:auto-func-calling-attribute
Oct 30, 2024
Merged

Python: Add parallel_tool_calls attribute to OpenAI chat prompt execution settings#9479
Evan Mattson (moonbox3) merged 3 commits into
microsoft:mainfrom
moonbox3:auto-func-calling-attribute

Conversation

@moonbox3

@moonbox3 Evan Mattson (moonbox3) commented Oct 30, 2024

Copy link
Copy Markdown
Collaborator

Motivation and Context

OpenAI / Azure OpenAI released the ability to specify the parallel_tool_calls = True | False boolean attribute on the prompt execution settings in July. This was never brought into SK Python.

Further, there appears to be a pesky bug related to function calling where enabling parallel tool calls can cause 500s. The only way to get around this is to disable parallel function calling. This has been both tested on the Azure Chat Completion and OpenAI Chat Completion code and works well -- the chat history shows the synchronous function calls if multiple tool calls are required.

Description

Add the parallel_tool_calls attribute on the OpenAIChatPromptExecutionExecution settings, which are also used by the AzureChatCompletionClass.

Contribution Checklist

@moonbox3
Evan Mattson (moonbox3) requested a review from a team as a code owner October 30, 2024 19:29
@markwallace-microsoft Mark Wallace (markwallace-microsoft) added the python Pull requests for the Python Semantic Kernel label Oct 30, 2024
@moonbox3 Evan Mattson (moonbox3) added the ai connector Anything related to AI connectors label Oct 30, 2024
@markwallace-microsoft

Mark Wallace (markwallace-microsoft) commented Oct 30, 2024 •
edited
Loading

Copy link
Copy Markdown
Contributor

Python Test Coverage

Python Test Coverage Report
FileStmtsMissCoverMissing
semantic_kernel
   kernel.py1994776%148, 159, 163, 313–316, 423, 437–480
semantic_kernel/agents/group_chat
   agent_chat.py124298%78, 171
   agent_group_chat.py100298%151, 201
   broadcast_queue.py72199%35
semantic_kernel/agents/open_ai
   assistant_content_generation.py141994%97–98, 329–337, 379, 381
   azure_assistant_agent.py106298%285, 305
   open_ai_assistant_agent.py105298%252, 272
   open_ai_assistant_base.py467898%260, 338–339, 747, 868, 871, 945, 1007
semantic_kernel/connectors/ai
   chat_completion_client_base.py116298%382, 392
   completion_usage.py8188%17
semantic_kernel/connectors/ai/anthropic/services
   anthropic_chat_completion.py176597%147, 165, 169, 223, 419
semantic_kernel/connectors/ai/azure_ai_inference/services
   azure_ai_inference_chat_completion.py119794%120, 146–149, 159, 180, 202
   azure_ai_inference_text_embedding.py41198%87
semantic_kernel/connectors/ai/bedrock/services
   bedrock_chat_completion.py1361490%117, 138, 163, 167–170, 228, 246–265, 324
   bedrock_text_completion.py57296%95, 118
   bedrock_text_embedding.py45198%94
semantic_kernel/connectors/ai/bedrock/services/model_provider
   bedrock_ai21_labs.py13192%67
   bedrock_anthropic_claude.py12192%54
   bedrock_cohere.py20195%75
   utils.py802075%68, 71, 102, 106–115, 132–150, 171–174
semantic_kernel/connectors/ai/embeddings
   embedding_generator_base.py8188%50
semantic_kernel/connectors/ai/google/google_ai/services
   google_ai_chat_completion.py119497%126, 152, 175, 177
   google_ai_text_completion.py63297%98, 121
   utils.py65395%139, 159–164
semantic_kernel/connectors/ai/google/vertex_ai/services
   utils.py66395%140, 160–165
   vertex_ai_chat_completion.py119497%121, 147, 170, 172
   vertex_ai_text_completion.py62297%95, 116
semantic_kernel/connectors/ai/hugging_face/services
   hf_text_completion.py60395%103, 112, 127
   hf_text_embedding.py32584%79–83
semantic_kernel/connectors/ai/mistral_ai/services
   mistral_ai_chat_completion.py118794%118–121, 307–310
semantic_kernel/connectors/ai/ollama/services
   ollama_chat_completion.py1071190%114, 139, 143–144, 154, 187, 224, 234–235, 257, 284
   ollama_text_completion.py57395%93, 103, 131
   utils.py462546%29, 44–52, 64–86, 98–102, 119–122
semantic_kernel/connectors/ai/onnx
   utils.py53394%50–51, 112
semantic_kernel/connectors/ai/onnx/services
   onnx_gen_ai_chat_completion.py72790%67–68, 98, 122, 167, 173, 179
   onnx_gen_ai_completion_base.py582164%59–71, 79–90
   onnx_gen_ai_text_completion.py46589%54–55, 87, 117, 133
semantic_kernel/connectors/ai/open_ai/prompt_execution_settings
   open_ai_prompt_execution_settings.py95199%113
semantic_kernel/connectors/ai/open_ai/services
   azure_chat_completion.py107595%118, 123, 157, 166, 169
   azure_text_completion.py28293%82, 87
   azure_text_embedding.py30293%84, 89
   open_ai_chat_completion_base.py127596%71, 121, 141, 177, 287
   open_ai_handler.py63395%86, 95–96
   open_ai_text_completion_base.py80298%56, 161
semantic_kernel/connectors/ai/open_ai/settings
   azure_open_ai_settings.py22195%99
semantic_kernel/connectors/memory/azure_ai_search
   azure_ai_search_collection.py87298%150, 152
semantic_kernel/connectors/memory/redis
   redis_collection.py160299%146, 316
   utils.py451176%145–146, 164, 166, 173–188
semantic_kernel/connectors/memory/weaviate
   utils.py60493%78, 82, 110, 249
   weaviate_collection.py1152578%144–153, 157–177, 181–186
   weaviate_store.py44980%106–114, 118–123
semantic_kernel/connectors/openapi_plugin
   openapi_manager.py58297%110–111
   openapi_parser.py88298%71, 128
   openapi_runner.py105298%181–182
semantic_kernel/connectors/openapi_plugin/models
   rest_api_operation.py129199%242
semantic_kernel/contents
   function_call_content.py100298%185, 213
   streaming_chat_message_content.py68199%210
   streaming_content_mixin.py39295%37, 64
semantic_kernel/core_plugins/sessions_python_tool
   sessions_python_plugin.py134894%69, 82–91, 99
   sessions_python_settings.py39490%84–87
semantic_kernel/data
   vector_store_record_collection.py2491992%408, 468–472, 480–484, 524–527, 534–537
   vector_store_record_utils.py26292%50, 52
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_function_log_messages.py36683%37–43
   kernel_plugin.py187299%472, 475
semantic_kernel/planners
   plan.py2344581%54, 163–165, 197, 214–227, 264, 269, 277–278, 288–291, 308, 313, 329, 332–337, 355, 360, 363, 365, 372, 386–388, 393–397
semantic_kernel/planners/function_calling_stepwise_planner
   function_calling_stepwise_planner.py116497%145, 189–190, 198
semantic_kernel/planners/sequential_planner
   sequential_planner.py64691%71, 75, 109, 125, 134–135
   sequential_planner_extensions.py50982%31–32, 56, 110–124
   sequential_planner_parser.py771284%66–74, 93, 117–120
semantic_kernel/processes
   process_builder.py683943%43–52, 56–58, 64–74, 78–85, 89–92, 96–100, 105, 109–114
   process_end_step.py19289%37, 41
   process_function_target_builder.py25388%37–40
   process_step_builder.py1052477%44, 89, 103, 110–123, 135–142, 151, 160–169, 178, 192, 209
   process_step_edge_builder.py34391%31, 46, 56
   process_types.py25196%35
semantic_kernel/processes/kernel_process
   kernel_process_step_context.py17194%37
semantic_kernel/processes/local_runtime
   local_kernel_process.py20290%23, 30
   local_kernel_process_context.py32294%66–67
   local_process.py1345261%92, 102, 120–130, 163–190, 194–199, 203, 207–213, 217–227, 231–232
   local_step.py17811436%61, 72, 81–169, 173, 177, 181–182, 187–249, 253–270, 274–277, 281–284, 288–297, 303–306, 310–312
semantic_kernel/schema
   kernel_json_schema_builder.py129993%53, 90, 186, 194, 205, 213, 228, 232–233
semantic_kernel/services
   ai_service_client_base.py22195%64
semantic_kernel/template_engine/blocks
   code_block.py77199%119
   named_arg_block.py43198%98
semantic_kernel/utils/authentication
   entra_id_authentication.py15287%26, 38
semantic_kernel/utils/telemetry
   user_agent.py16288%18–19
semantic_kernel/utils/telemetry/model_diagnostics
   decorators.py171498%372–375
TOTAL1341671395% 

Python Unit Test Overview

Tests Skipped Failures Errors Time
2771 4 💤 0 ❌ 0 🔥 1m 7s ⏱️

@moonbox3
Evan Mattson (moonbox3) added this pull request to the merge queue Oct 30, 2024
@github-merge-queue
github-merge-queue Bot removed this pull request from the merge queue due to failed status checks Oct 30, 2024
@moonbox3
Evan Mattson (moonbox3) added this pull request to the merge queue Oct 30, 2024
Merged via the queue into microsoft:main with commit 5e632fd Oct 30, 2024
@moonbox3
Evan Mattson (moonbox3) deleted the auto-func-calling-attribute branch October 30, 2024 22:45
@moonbox3 Evan Mattson (moonbox3) mentioned this pull request Oct 31, 2024
Closed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@alliscode Ben Thomas (alliscode) alliscode approved these changes
+1 more reviewer
@esttenorio Estefanía Tenorio (esttenorio) esttenorio approved these changes
Reviewers whose approvals may not affect merge requirements

Assignees

@moonbox3 Evan Mattson (moonbox3)

Labels

ai connector Anything related to AI connectors python Pull requests for the Python Semantic Kernel

Projects

Semantic Kernel
Archived in project

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

Python: Bug: How do I disable parallel function calling in Semantic Kernel (Python)?

4 participants

@moonbox3 @markwallace-microsoft @esttenorio @alliscode