Muokkaa

Evaluate conversation datasets with Microsoft Foundry SDK (preview)

Assess complete conversations from datasets at the turn or conversation level.

Prerequisites

The examples use the SDK client configured in Set up the SDK client.

Evaluate conversation datasets

Evaluate complete conversations to assess agent quality across entire user interactions - not just individual responses. Use conversation-level evaluation to identify quality problems like incomplete task resolution, user frustration, and tool-call regressions that turn-level evaluation misses.

For example, consider a support agent where the user grows frustrated over multiple turns:

Turn 1 — User: "I need to reset my password." Agent: "I found your account. I'll send a reset link."

Turn 2 — User: "I didn't get the email." Agent: "I've resent the link. Please check spam."

Turn 3 — User: "Still nothing. Can you just reset it directly?" Agent: "I've sent another reset link."

A turn-level evaluator scores only the last response - which is polite and takes action - so it scores well. A conversation-level evaluator grading customer satisfaction across the conversation flags that the agent repeated the same failing action three times without trying an alternative, leaving the user's problem unresolved.

Conversation-level evaluation differs from turn-level evaluation in several ways:

Aspect Turn-level Conversation-level
Scope Individual query-response pairs Complete conversations with multiple exchanges
Metrics Per-response quality and safety Conversation-level outcomes and user satisfaction
Data format JSONL with query and response fields JSONL with messages array containing the full conversation
Use case Testing individual model responses Testing end-to-end agent experiences

Choose the conversation workflow that matches your data source:

Workflow When to use Data source type
From dataset or inline You have local conversation traces or test data jsonl with file_id or file_content
Deployed conversations You want to evaluate specific conversations or sampled production traffic from Application Insights azure_ai_trace_data_source_preview with trace_source
Simulated conversations You want to generate synthetic test conversations azure_ai_target_completions with conversation_gen_preview

Choose an evaluation level

The evaluation_level parameter on the run determines whether evaluators score individual turns or complete conversations:

Value Behavior
"turn" Evaluators score each turn independently.
"conversation" Evaluators score the entire conversation as a whole.
(omitted) Defaults to "turn".

Important

Evaluator compatibility: Each evaluator supports specific evaluation levels. Check the evaluator's supported_evaluation_levels field in the evaluator catalog.

  • Turn-only evaluators (for example, fluency, relevance) can't be used with evaluation_level="conversation".
  • Currently, all conversation-level evaluators support both "turn" and "conversation" levels.

Common errors

Error Cause Solution
Incompatible evaluation level Using evaluation_level="conversation" with a turn-only evaluator Remove the turn-only evaluator or change to evaluation_level="turn"

Prepare conversation data

Create a JSONL file where each line contains a complete conversation in the messages field. Each message should include a role (user, assistant, or system) and content. For a complete example, see the conversation evaluation samples in the SDK.

 {"messages": [{"role": "user", "content": "What's my account balance?"}, {"role": "assistant", "content": "Your current balance is $1,234.56."}, {"role": "user", "content": "Thanks!"}, {"role": "assistant", "content": "You're welcome! Is there anything else?"}]}

You can also include tool definitions and tool calls if your agent uses tools:

{"messages": [{"role": "user", "content": "What is the capital/major city of France?"}, {"role": "assistant", "content": "Paris"}]}
{"messages": [{"role": "user", "content": "How do I reverse a string in Python?"}, {"role": "assistant", "content": "You can reverse a string in Python by using slicing: string[::-1]"}]}
{"messages": [{"role": "user", "content": "What are the main causes of climate change?"}, {"role": "assistant", "content": "The main causes of climate change are the increase in greenhouse gases in the atmosphere, primarily due to human activities such as burning fossil fuels and deforestation."}]}
{"messages": [{"role": "user", "content": "What's my account balance?"}, {"role": "assistant", "content": null, "tool_calls": [{"id": "call_abc123", "type": "function", "function": {"name": "get_account_balance", "arguments": "{\"account_id\": \"ACCT-7890\"}"}}]}, {"role": "tool", "tool_call_id": "call_abc123", "content": "{ \"balance\": 1234.56, \"currency\": \"USD\" }"}, {"role": "assistant", "content": "Your current balance is 1,234.56."}, {"role": "user", "content": "Thanks!"}, {"role": "assistant", "content": "You're welcome! Is there anything else?"}], "tool_definitions": [{"name": "get_account_balance", "description": "Retrieves the current balance for a customer account", "parameters": {"type": "object", "properties": {"account_id": {"type": "string"}}, "required": ["account_id"]}}]}
{"messages": [{"role": "user", "content": "Explain the theory of relativity in simple terms."}, {"role": "assistant", "content": "Einstein's theory of relativity shows that space and time are interconnected and relative to the observer's frame of reference."}]}
{"messages": [{"role": "user", "content": "What's the weather in Seattle?"}, {"role": "assistant", "content": null, "tool_calls": [{"id": "call_002", "type": "function", "function": {"name": "get_weather", "arguments": "{\"location\": \"Seattle, WA\"}"}}]}, {"role": "tool", "tool_call_id": "call_002", "content": "{ \"temperature\": 55, \"condition\": \"Cloudy\" }"}, {"role": "assistant", "content": "It's currently 55F and cloudy in Seattle."}], "tool_definitions": [{"name": "get_weather", "description": "Get the current weather for a location", "parameters": {"type": "object", "properties": {"location": {"type": "string"}}, "required": ["location"]}}]}
{"messages": [{"role": "user", "content": "What is the tallest mountain in the world?"}, {"role": "assistant", "content": "Mount Everest is the tallest mountain in the world."}]}
{"messages": [{"role": "user", "content": "Is 4 x 2 = 16?"}, {"role": "assistant", "content": "No, 4 x 2 = 8."}]}
{"messages": [{"role": "user", "content": "What is the best Italian desert?"}, {"role": "assistant", "content": "Tiramisu is a popular Italian dessert."}]}
{"messages": [{"role": "user", "content": "What is the chemical formula for water?"}, {"role": "assistant", "content": "The chemical formula for water is H2O."}]}

Define the data schema and evaluators

Specify the schema for your conversation data, "messages", and select evaluators designed for conversation-level evaluation. Conversation-level evaluators assess the entire interaction rather than individual turns.

pip install "azure-ai-projects>=2.2.0"

import os
from openai.types.eval_create_params import DataSourceConfigCustom
from azure.identity import DefaultAzureCredential
from azure.ai.projects import AIProjectClient
from azure.ai.projects.models import TestingCriterionAzureAIEvaluator

endpoint = os.environ["AZURE_AI_PROJECT_ENDPOINT"]
model_deployment_name = os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"]

with (
    DefaultAzureCredential() as credential,
    AIProjectClient(endpoint=endpoint, credential=credential) as project_client,
    project_client.get_openai_client() as openai_client,
):
    data_source_config = DataSourceConfigCustom(
        type="custom",
        item_schema={
            "type": "object",
            "properties": {
                "messages": {"type": "array"},
                "tool_definitions": {"type": "array"},
            },
            "required": ["messages"],
        },
        include_sample_schema=False,
    )

    testing_criteria = [
        TestingCriterionAzureAIEvaluator(
            type="azure_ai_evaluator",
            name="conversation_coherence",
            evaluator_name="builtin.coherence",
            initialization_parameters={"model": model_deployment_name},
            data_mapping={"messages": "{{item.messages}}"},
        ),
        TestingCriterionAzureAIEvaluator(
            type="azure_ai_evaluator",
            name="groundedness",
            evaluator_name="builtin.groundedness",
            initialization_parameters={"model": model_deployment_name},
            data_mapping={"messages": "{{item.messages}}"},
        ),
    ]

Create evaluation and run

Prep: download sample_data_multiturn_conversations.jsonl

from openai.types.evals.create_eval_jsonl_run_data_source_param import (
    CreateEvalJSONLRunDataSourceParam,
    SourceFileID,
)

# Upload conversation data
data_id = project_client.datasets.upload_file(
    name="multiturn-conversation-data",
    version="1",
    file_path="./sample_data_multiturn_conversations.jsonl",
).id

# Create the evaluation
eval_object = openai_client.evals.create(
    name="Multi-turn Conversation Evaluation",
    data_source_config=data_source_config,
    testing_criteria=testing_criteria,
)

# Create a run with evaluation_level set to "conversation"
eval_run = openai_client.evals.runs.create(
    eval_id=eval_object.id,
    name="multiturn-conversation-run",
    data_source=CreateEvalJSONLRunDataSourceParam(
        type="jsonl",
        source=SourceFileID(
            type="file_id",
            id=data_id,
        ),
    ),
    extra_body={"evaluation_level": "conversation"},
)

To poll for completion and interpret results, see Get cloud evaluation results.

For a complete runnable example, see sample_multiturn_conversation_evaluation.py on GitHub.

Next steps

  • Last updated on