Evaluation Samples: add multi-turn conversation evaluation samples S1-S4#47034
Open
kseager wants to merge 3 commits into
Open
Evaluation Samples: add multi-turn conversation evaluation samples S1-S4#47034kseager wants to merge 3 commits into
kseager wants to merge 3 commits into
Conversation
Add sample_multiturn_conversation_evaluation.py demonstrating: - Custom data source config with messages/tool_definitions schema - Conversation-level evaluators (customer_satisfaction, task_completion, coherence, groundedness) - Dataset upload and evaluation run with evaluation_level=conversation - Polling for results Includes sample JSONL with 3 conversations: basic multi-turn, tool-calling, and extended support dialog. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
kseager
requested review from
bobogogo1990,
dargilco,
glharper,
howieleung,
kingernupur,
nick863,
trangevi and
trrwilson
as code owners
- S2: sample_multiturn_trace_evaluation_by_id.py Evaluate traces by conversation_id or trace_id - S3: sample_multiturn_trace_evaluation_agent_filter.py Evaluate traces by agent name/version/id with optional smart filtering - S4: sample_multiturn_conversation_simulation.py Simulate multi-turn conversations against an agent and evaluate - Data: sample_data_simulation_scenarios.jsonl (3 seed scenarios for S4) All samples use 4 conversation-level evaluators: customer_satisfaction, task_completion, coherence, groundedness. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
kseager
changed the title
The .id property on upload_file() returns Optional[str], which pyright flags when passed to SourceFileID(id=...) which expects str. Split the chain and add an assert to narrow the type. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
howieleung
reviewed
May 21, 2026
|
|
||
| Before running the sample: | ||
|
|
||
| pip install "azure-ai-projects>=2.0.0" python-dotenv |
Member
There was a problem hiding this comment.
I believe 2.0.0 is OK. Please confirm.
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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.
Add sample_multiturn_conversation_evaluation.py demonstrating:
Includes sample JSONL with 3 conversations: basic multi-turn, tool-calling, and extended support dialog.
Description
Please add an informative description that covers that changes made by the pull request and link all relevant issues.
If an SDK is being regenerated based on a new API spec, a link to the pull request containing these API spec changes should be included above.
All SDK Contribution checklist:
General Guidelines and Best Practices
Testing Guidelines