azure-ai-evaluation 1.0.0b3__py3-none-any.whl → 1.0.0b5__py3-none-any.whl

azure/ai/evaluation/_evaluate/_telemetry/__init__.py

@@ -6,7 +6,7 @@ import functools
 import inspect
 import json
 import logging
-from typing import Callable, Dict, TypeVar
+from typing import Callable, Dict, Literal, Optional, Union, cast
 
 import pandas as pd
 from promptflow._sdk.entities._flows import FlexFlow as flex_flow
@@ -16,31 +16,30 @@ from promptflow.client import PFClient
 from promptflow.core import Prompty as prompty_core
 from typing_extensions import ParamSpec
 
+from azure.ai.evaluation._model_configurations import AzureAIProject, EvaluationResult
+
 from ..._user_agent import USER_AGENT
 from .._utils import _trace_destination_from_project_scope
 
 LOGGER = logging.getLogger(__name__)
 
 P = ParamSpec("P")
-R = TypeVar("R")
 
 
-def _get_evaluator_type(evaluator: Dict[str, Callable]):
+def _get_evaluator_type(evaluator: Dict[str, Callable]) -> Literal["content-safety", "built-in", "custom"]:
     """
     Get evaluator type for telemetry.
 
     :param evaluator: The evaluator object
     :type evaluator: Dict[str, Callable]
     :return: The evaluator type. Possible values are "built-in", "custom", and "content-safety".
-    :rtype: str
+    :rtype: Literal["content-safety", "built-in", "custom"]
     """
-    built_in = False
-    content_safety = False
-
     module = inspect.getmodule(evaluator)
-    built_in = module and module.__name__.startswith("azure.ai.evaluation._evaluators.")
-    if built_in:
-        content_safety = module.__name__.startswith("azure.ai.evaluation._evaluators._content_safety")
+    module_name = module.__name__ if module else ""
+
+    built_in = module_name.startswith("azure.ai.evaluation._evaluators.")
+    content_safety = built_in and module_name.startswith("azure.ai.evaluation._evaluators._content_safety")
 
     if content_safety:
         return "content-safety"
@@ -98,22 +97,22 @@ def _get_evaluator_properties(evaluator, evaluator_name):
 
 
 # cspell:ignore isna
-def log_evaluate_activity(func: Callable[P, R]) -> Callable[P, R]:
+def log_evaluate_activity(func: Callable[P, EvaluationResult]) -> Callable[P, EvaluationResult]:
     """Decorator to log evaluate activity
 
     :param func: The function to be decorated
     :type func: Callable
     :returns: The decorated function
-    :rtype: Callable[P, R]
+    :rtype: Callable[P, EvaluationResult]
     """
 
     @functools.wraps(func)
-    def wrapper(*args: P.args, **kwargs: P.kwargs) -> R:
+    def wrapper(*args: P.args, **kwargs: P.kwargs) -> EvaluationResult:
         from promptflow._sdk._telemetry import ActivityType, log_activity
         from promptflow._sdk._telemetry.telemetry import get_telemetry_logger
 
-        evaluators = kwargs.get("evaluators", [])
-        azure_ai_project = kwargs.get("azure_ai_project", None)
+        evaluators = cast(Optional[Dict[str, Callable]], kwargs.get("evaluators", {})) or {}
+        azure_ai_project = cast(Optional[AzureAIProject], kwargs.get("azure_ai_project", None))
 
         pf_client = PFClient(
             config=(
@@ -127,7 +126,7 @@ def log_evaluate_activity(func: Callable[P, R]) -> Callable[P, R]:
         track_in_cloud = bool(pf_client._config.get_trace_destination())  # pylint: disable=protected-access
         evaluate_target = bool(kwargs.get("target", None))
         evaluator_config = bool(kwargs.get("evaluator_config", None))
-        custom_dimensions = {
+        custom_dimensions: Dict[str, Union[str, bool]] = {
             "track_in_cloud": track_in_cloud,
             "evaluate_target": evaluate_target,
             "evaluator_config": evaluator_config,

azure/ai/evaluation/_evaluate/_utils.py

@@ -6,15 +6,24 @@ import logging
 import os
 import re
 import tempfile
-from collections import namedtuple
 from pathlib import Path
-from typing import Dict
+from typing import Any, Dict, NamedTuple, Optional, Tuple, Union
+import uuid
+import base64
 
 import pandas as pd
-
-from azure.ai.evaluation._constants import DEFAULT_EVALUATION_RESULTS_FILE_NAME, DefaultOpenEncoding, Prefixes
+from promptflow.client import PFClient
+from promptflow.entities import Run
+
+from azure.ai.evaluation._constants import (
+    DEFAULT_EVALUATION_RESULTS_FILE_NAME,
+    DefaultOpenEncoding,
+    EvaluationRunProperties,
+    Prefixes,
+)
 from azure.ai.evaluation._evaluate._eval_run import EvalRun
 from azure.ai.evaluation._exceptions import ErrorBlame, ErrorCategory, ErrorTarget, EvaluationException
+from azure.ai.evaluation._model_configurations import AzureAIProject
 
 LOGGER = logging.getLogger(__name__)
 
@@ -23,14 +32,20 @@ AZURE_WORKSPACE_REGEX_FORMAT = (
     "(/providers/Microsoft.MachineLearningServices)?/workspaces/([^/]+)$"
 )
 
-AzureMLWorkspaceTriad = namedtuple("AzureMLWorkspace", ["subscription_id", "resource_group_name", "workspace_name"])
+
+class AzureMLWorkspace(NamedTuple):
+    subscription_id: str
+    resource_group_name: str
+    workspace_name: str
 
 
-def is_none(value):
+def is_none(value) -> bool:
     return value is None or str(value).lower() == "none"
 
 
-def extract_workspace_triad_from_trace_provider(trace_provider: str):  # pylint: disable=name-too-long
+def extract_workspace_triad_from_trace_provider(  # pylint: disable=name-too-long
+    trace_provider: str,
+) -> AzureMLWorkspace:
     match = re.match(AZURE_WORKSPACE_REGEX_FORMAT, trace_provider)
     if not match or len(match.groups()) != 5:
         raise EvaluationException(
@@ -47,7 +62,7 @@ def extract_workspace_triad_from_trace_provider(trace_provider: str):  # pylint:
     subscription_id = match.group(1)
     resource_group_name = match.group(3)
     workspace_name = match.group(5)
-    return AzureMLWorkspaceTriad(subscription_id, resource_group_name, workspace_name)
+    return AzureMLWorkspace(subscription_id, resource_group_name, workspace_name)
 
 
 def load_jsonl(path):
@@ -55,7 +70,7 @@ def load_jsonl(path):
         return [json.loads(line) for line in f.readlines()]
 
 
-def _azure_pf_client_and_triad(trace_destination):
+def _azure_pf_client_and_triad(trace_destination) -> Tuple[PFClient, AzureMLWorkspace]:
     from promptflow.azure._cli._utils import _get_azure_pf_client
 
     ws_triad = extract_workspace_triad_from_trace_provider(trace_destination)
@@ -68,15 +83,43 @@ def _azure_pf_client_and_triad(trace_destination):
     return azure_pf_client, ws_triad
 
 
+def _store_multimodal_content(messages, tmpdir: str):
+    # verify if images folder exists
+    images_folder_path = os.path.join(tmpdir, "images")
+    os.makedirs(images_folder_path, exist_ok=True)
+
+    # traverse all messages and replace base64 image data with new file name.
+    for message in messages:
+        if isinstance(message.get("content", []), list):
+            for content in message.get("content", []):
+                if content.get("type") == "image_url":
+                    image_url = content.get("image_url")
+                    if image_url and "url" in image_url and image_url["url"].startswith("data:image/jpg;base64,"):
+                        # Extract the base64 string
+                        base64image = image_url["url"].replace("data:image/jpg;base64,", "")
+
+                        # Generate a unique filename
+                        image_file_name = f"{str(uuid.uuid4())}.jpg"
+                        image_url["url"] = f"images/{image_file_name}"  # Replace the base64 URL with the file path
+
+                        # Decode the base64 string to binary image data
+                        image_data_binary = base64.b64decode(base64image)
+
+                        # Write the binary image data to the file
+                        image_file_path = os.path.join(images_folder_path, image_file_name)
+                        with open(image_file_path, "wb") as f:
+                            f.write(image_data_binary)
+
+
 def _log_metrics_and_instance_results(
-    metrics,
-    instance_results,
-    trace_destination,
-    run,
-    evaluation_name,
-) -> str:
+    metrics: Dict[str, Any],
+    instance_results: pd.DataFrame,
+    trace_destination: Optional[str],
+    run: Run,
+    evaluation_name: Optional[str],
+) -> Optional[str]:
     if trace_destination is None:
-        LOGGER.error("Unable to log traces as trace destination was not defined.")
+        LOGGER.debug("Skip uploading evaluation results to AI Studio since no trace destination was provided.")
         return None
 
     azure_pf_client, ws_triad = _azure_pf_client_and_triad(trace_destination)
@@ -94,10 +137,18 @@ def _log_metrics_and_instance_results(
         ml_client=azure_pf_client.ml_client,
         promptflow_run=run,
     ) as ev_run:
-
         artifact_name = EvalRun.EVALUATION_ARTIFACT if run else EvalRun.EVALUATION_ARTIFACT_DUMMY_RUN
 
         with tempfile.TemporaryDirectory() as tmpdir:
+            # storing multi_modal images if exists
+            col_name = "inputs.conversation"
+            if col_name in instance_results.columns:
+                for item in instance_results[col_name].items():
+                    value = item[1]
+                    if "messages" in value:
+                        _store_multimodal_content(value["messages"], tmpdir)
+
+            # storing artifact result
             tmp_path = os.path.join(tmpdir, artifact_name)
 
             with open(tmp_path, "w", encoding=DefaultOpenEncoding.WRITE) as f:
@@ -112,7 +163,8 @@ def _log_metrics_and_instance_results(
             if run is None:
                 ev_run.write_properties_to_run_history(
                     properties={
-                        "_azureml.evaluation_run": "azure-ai-generative-parent",
+                        EvaluationRunProperties.RUN_TYPE: "eval_run",
+                        EvaluationRunProperties.EVALUATION_RUN: "azure-ai-generative-parent",
                         "_azureml.evaluate_artifacts": json.dumps([{"path": artifact_name, "type": "table"}]),
                         "isEvaluatorRun": "true",
                     }
@@ -138,7 +190,7 @@ def _get_ai_studio_url(trace_destination: str, evaluation_id: str) -> str:
     return studio_url
 
 
-def _trace_destination_from_project_scope(project_scope: dict) -> str:
+def _trace_destination_from_project_scope(project_scope: AzureAIProject) -> str:
     subscription_id = project_scope["subscription_id"]
     resource_group_name = project_scope["resource_group_name"]
     workspace_name = project_scope["project_name"]
@@ -151,9 +203,9 @@ def _trace_destination_from_project_scope(project_scope: dict) -> str:
     return trace_destination
 
 
-def _write_output(path, data_dict):
+def _write_output(path: Union[str, os.PathLike], data_dict: Any) -> None:
     p = Path(path)
-    if os.path.isdir(path):
+    if p.is_dir():
         p = p / DEFAULT_EVALUATION_RESULTS_FILE_NAME
 
     with open(p, "w", encoding=DefaultOpenEncoding.WRITE) as f:
@@ -161,7 +213,7 @@ def _write_output(path, data_dict):
 
 
 def _apply_column_mapping(
-    source_df: pd.DataFrame, mapping_config: Dict[str, str], inplace: bool = False
+    source_df: pd.DataFrame, mapping_config: Optional[Dict[str, str]], inplace: bool = False
 ) -> pd.DataFrame:
     """
     Apply column mapping to source_df based on mapping_config.
@@ -211,7 +263,7 @@ def _apply_column_mapping(
     return result_df
 
 
-def _has_aggregator(evaluator):
+def _has_aggregator(evaluator: object) -> bool:
     return hasattr(evaluator, "__aggregate__")
 
 
@@ -234,11 +286,11 @@ def get_int_env_var(env_var_name: str, default_value: int) -> int:
         return default_value
 
 
-def set_event_loop_policy():
+def set_event_loop_policy() -> None:
     import asyncio
     import platform
 
     if platform.system().lower() == "windows":
         # Reference: https://stackoverflow.com/questions/45600579/asyncio-event-loop-is-closed-when-getting-loop
         # On Windows seems to be a problem with EventLoopPolicy, use this snippet to work around it
-        asyncio.set_event_loop_policy(asyncio.WindowsSelectorEventLoopPolicy())
+        asyncio.set_event_loop_policy(asyncio.WindowsSelectorEventLoopPolicy())  # type: ignore[attr-defined]

azure/ai/evaluation/_evaluators/_bleu/_bleu.py

@@ -63,7 +63,7 @@ class BleuScoreEvaluator:
         :keyword ground_truth: The ground truth to be compared against.
         :paramtype ground_truth: str
         :return: The BLEU score.
-        :rtype: dict
+        :rtype: Dict[str, float]
         """
         return async_run_allowing_running_loop(
             self._async_evaluator, response=response, ground_truth=ground_truth, **kwargs

azure/ai/evaluation/_evaluators/_coherence/_coherence.py

@@ -3,6 +3,7 @@
 # ---------------------------------------------------------
 import os
 from typing import Optional
+
 from typing_extensions import override
 
 from azure.ai.evaluation._evaluators._common import PromptyEvaluatorBase
@@ -30,18 +31,23 @@ class CoherenceEvaluator(PromptyEvaluatorBase):
     .. code-block:: python
 
         {
-            "gpt_coherence": 1.0
+            "coherence": 1.0,
+            "gpt_coherence": 1.0,
         }
+
+    Note: To align with our support of a diverse set of models, a key without the `gpt_` prefix has been added.
+    To maintain backwards compatibility, the old key with the `gpt_` prefix is still be present in the output;
+    however, it is recommended to use the new key moving forward as the old key will be deprecated in the future.
     """
 
-    PROMPTY_FILE = "coherence.prompty"
-    RESULT_KEY = "gpt_coherence"
+    _PROMPTY_FILE = "coherence.prompty"
+    _RESULT_KEY = "coherence"
 
     @override
-    def __init__(self, model_config: dict):
+    def __init__(self, model_config):
         current_dir = os.path.dirname(__file__)
-        prompty_path = os.path.join(current_dir, self.PROMPTY_FILE)
-        super().__init__(model_config=model_config, prompty_file=prompty_path, result_key=self.RESULT_KEY)
+        prompty_path = os.path.join(current_dir, self._PROMPTY_FILE)
+        super().__init__(model_config=model_config, prompty_file=prompty_path, result_key=self._RESULT_KEY)
 
     @override
     def __call__(
@@ -49,8 +55,8 @@ class CoherenceEvaluator(PromptyEvaluatorBase):
         *,
         query: Optional[str] = None,
         response: Optional[str] = None,
-        conversation: Optional[dict] = None,
-        **kwargs
+        conversation=None,
+        **kwargs,
     ):
         """Evaluate coherence. Accepts either a query and response for a single evaluation,
         or a conversation for a potentially multi-turn evaluation. If the conversation has more than one pair of
@@ -63,8 +69,8 @@ class CoherenceEvaluator(PromptyEvaluatorBase):
         :keyword conversation: The conversation to evaluate. Expected to contain a list of conversation turns under the
             key "messages". Conversation turns are expected
             to be dictionaries with keys "content" and "role".
-        :paramtype conversation: Optional[Dict]
+        :paramtype conversation: Optional[~azure.ai.evaluation.Conversation]
         :return: The relevance score.
-        :rtype: dict
+        :rtype: Union[Dict[str, float], Dict[str, Union[float, Dict[str, List[float]]]]]
         """
         return super().__call__(query=query, response=response, conversation=conversation, **kwargs)

azure/ai/evaluation/_evaluators/_coherence/coherence.prompty

@@ -5,7 +5,7 @@ model:
   api: chat
   parameters:
     temperature: 0.0
-    max_tokens: 1
+    max_tokens: 800
     top_p: 1.0
     presence_penalty: 0
     frequency_penalty: 0
@@ -20,38 +20,80 @@ inputs:
 
 ---
 system:
-You are an AI assistant. You will be given the definition of an evaluation metric for assessing the quality of an answer in a question-answering task. Your job is to compute an accurate evaluation score using the provided evaluation metric. You should return a single integer value between 1 to 5 representing the evaluation metric. You will include no other text or information.
+# Instruction
+## Goal
+### You are an expert in evaluating the quality of a RESPONSE from an intelligent system based on provided definition and data. Your goal will involve answering the questions below using the information provided.
+- **Definition**: You are given a definition of the communication trait that is being evaluated to help guide your Score.
+- **Data**: Your input data include a QUERY and a RESPONSE.
+- **Tasks**: To complete your evaluation you will be asked to evaluate the Data in different ways.
 
 user:
-Coherence of an answer is measured by how well all the sentences fit together and sound naturally as a whole. Consider the overall quality of the answer when evaluating coherence. Given the question and answer, score the coherence of answer between one to five stars using the following rating scale:
-One star: the answer completely lacks coherence
-Two stars: the answer mostly lacks coherence
-Three stars: the answer is partially coherent
-Four stars: the answer is mostly coherent
-Five stars: the answer has perfect coherency
-
-This rating value should always be an integer between 1 and 5. So the rating produced should be 1 or 2 or 3 or 4 or 5.
-
-question: What is your favorite indoor activity and why do you enjoy it?
-answer: I like pizza. The sun is shining.
-stars: 1
-
-question: Can you describe your favorite movie without giving away any spoilers?
-answer: It is a science fiction movie. There are dinosaurs. The actors eat cake. People must stop the villain.
-stars: 2
-
-question: What are some benefits of regular exercise?
-answer: Regular exercise improves your mood. A good workout also helps you sleep better. Trees are green.
-stars: 3
-
-question: How do you cope with stress in your daily life?
-answer: I usually go for a walk to clear my head. Listening to music helps me relax as well. Stress is a part of life, but we can manage it through some activities.
-stars: 4
-
-question: What can you tell me about climate change and its effects on the environment?
-answer: Climate change has far-reaching effects on the environment. Rising temperatures result in the melting of polar ice caps, contributing to sea-level rise. Additionally, more frequent and severe weather events, such as hurricanes and heatwaves, can cause disruption to ecosystems and human societies alike.
-stars: 5
-
-question: {{query}}
-answer: {{response}}
-stars:
+# Definition
+**Coherence** refers to the logical and orderly presentation of ideas in a response, allowing the reader to easily follow and understand the writer's train of thought. A coherent answer directly addresses the question with clear connections between sentences and paragraphs, using appropriate transitions and a logical sequence of ideas.
+
+# Ratings
+## [Coherence: 1] (Incoherent Response)
+**Definition:** The response lacks coherence entirely. It consists of disjointed words or phrases that do not form complete or meaningful sentences. There is no logical connection to the question, making the response incomprehensible.
+
+**Examples:**
+  **Query:** What are the benefits of renewable energy?
+  **Response:** Wind sun green jump apple silence over.
+
+  **Query:** Explain the process of photosynthesis.
+  **Response:** Plants light water flying blue music.
+
+## [Coherence: 2] (Poorly Coherent Response)
+**Definition:** The response shows minimal coherence with fragmented sentences and limited connection to the question. It contains some relevant keywords but lacks logical structure and clear relationships between ideas, making the overall message difficult to understand.
+
+**Examples:**
+  **Query:** How does vaccination work?
+  **Response:** Vaccines protect disease. Immune system fight. Health better.
+
+  **Query:** Describe how a bill becomes a law.
+  **Response:** Idea proposed. Congress discuss vote. President signs.
+
+## [Coherence: 3] (Partially Coherent Response)
+**Definition:** The response partially addresses the question with some relevant information but exhibits issues in the logical flow and organization of ideas. Connections between sentences may be unclear or abrupt, requiring the reader to infer the links. The response may lack smooth transitions and may present ideas out of order.
+
+**Examples:**
+  **Query:** What causes earthquakes?
+  **Response:** Earthquakes happen when tectonic plates move suddenly. Energy builds up then releases. Ground shakes and can cause damage.
+
+  **Query:** Explain the importance of the water cycle.
+  **Response:** The water cycle moves water around Earth. Evaporation, then precipitation occurs. It supports life by distributing water.
+
+## [Coherence: 4] (Coherent Response)
+**Definition:** The response is coherent and effectively addresses the question. Ideas are logically organized with clear connections between sentences and paragraphs. Appropriate transitions are used to guide the reader through the response, which flows smoothly and is easy to follow.
+
+**Examples:**
+  **Query:** What is the water cycle and how does it work?
+  **Response:** The water cycle is the continuous movement of water on Earth through processes like evaporation, condensation, and precipitation. Water evaporates from bodies of water, forms clouds through condensation, and returns to the surface as precipitation. This cycle is essential for distributing water resources globally.
+
+  **Query:** Describe the role of mitochondria in cellular function.
+  **Response:** Mitochondria are organelles that produce energy for the cell. They convert nutrients into ATP through cellular respiration. This energy powers various cellular activities, making mitochondria vital for cell survival.
+
+## [Coherence: 5] (Highly Coherent Response)
+**Definition:** The response is exceptionally coherent, demonstrating sophisticated organization and flow. Ideas are presented in a logical and seamless manner, with excellent use of transitional phrases and cohesive devices. The connections between concepts are clear and enhance the reader's understanding. The response thoroughly addresses the question with clarity and precision.
+
+**Examples:**
+  **Query:** Analyze the economic impacts of climate change on coastal cities.
+  **Response:** Climate change significantly affects the economies of coastal cities through rising sea levels, increased flooding, and more intense storms. These environmental changes can damage infrastructure, disrupt businesses, and lead to costly repairs. For instance, frequent flooding can hinder transportation and commerce, while the threat of severe weather may deter investment and tourism. Consequently, cities may face increased expenses for disaster preparedness and mitigation efforts, straining municipal budgets and impacting economic growth.
+
+  **Query:** Discuss the significance of the Monroe Doctrine in shaping U.S. foreign policy.
+  **Response:** The Monroe Doctrine was a pivotal policy declared in 1823 that asserted U.S. opposition to European colonization in the Americas. By stating that any intervention by external powers in the Western Hemisphere would be viewed as a hostile act, it established the U.S. as a protector of the region. This doctrine shaped U.S. foreign policy by promoting isolation from European conflicts while justifying American influence and expansion in the hemisphere. Its long-term significance lies in its enduring influence on international relations and its role in defining the U.S. position in global affairs.
+
+
+# Data
+QUERY: {{query}}
+RESPONSE: {{response}}
+
+
+# Tasks
+## Please provide your assessment Score for the previous RESPONSE in relation to the QUERY based on the Definitions above. Your output should include the following information:
+- **ThoughtChain**: To improve the reasoning process, think step by step and include a step-by-step explanation of your thought process as you analyze the data based on the definitions. Keep it brief and start your ThoughtChain with "Let's think step by step:".
+- **Explanation**: a very short explanation of why you think the input Data should get that Score.
+- **Score**: based on your previous analysis, provide your Score. The Score you give MUST be a integer score (i.e., "1", "2"...) based on the levels of the definitions.
+
+
+## Please provide your answers between the tags: <S0>your chain of thoughts</S0>, <S1>your explanation</S1>, <S2>your Score</S2>.
+# Output