Alignement with new promptflow packages (#2642)

# Description

Please add an informative description that covers that changes made by
the pull request and link all relevant issues.

# All Promptflow Contribution checklist:
- [ ] **The pull request does not introduce [breaking changes].**
- [ ] **CHANGELOG is updated for new features, bug fixes or other
significant changes.**
- [ ] **I have read the [contribution guidelines](../CONTRIBUTING.md).**
- [ ] **Create an issue and link to the pull request to get dedicated
review from promptflow team. Learn more: [suggested
workflow](../CONTRIBUTING.md#suggested-workflow).**

## General Guidelines and Best Practices
- [ ] Title of the pull request is clear and informative.
- [ ] There are a small number of commits, each of which have an
informative message. This means that previously merged commits do not
appear in the history of the PR. For more information on cleaning up the
commits in your PR, [see this
page](https://github.com/Azure/azure-powershell/blob/master/documentation/development-docs/cleaning-up-commits.md).

### Testing Guidelines
- [ ] Pull request includes test coverage for the included changes.

---------

Co-authored-by: Nagkumar Arkalgud <nagkumar91@users.noreply.github.com>

.github/workflows/promptflow-evals-unit-test.yml

@@ -50,9 +50,15 @@ jobs:
         with:
           name: promptflow-evals
           path: ${{ env.WORKING_DIRECTORY }}
+      - name: install promptflow packages in editable mode
+        run: |
+          poetry run pip install -e ../promptflow-core
+          poetry run pip install -e ../promptflow-devkit
+          poetry run pip install -e ../promptflow-tools
+        working-directory: ${{ env.WORKING_DIRECTORY }}
       - name: install promptflow-evals from wheel
         # wildcard expansion (*) does not work in Windows, so leverage python to find and install
-        run: poetry run pip install $(python -c "import glob; print(glob.glob('promptflow_evals-*.whl')[0])")
+        run: poetry run pip install --pre $(python -c "import glob; print(glob.glob('promptflow_evals-*.whl')[0])")
         working-directory: ${{ env.WORKING_DIRECTORY }}
       - name: install test dependency group
         run: poetry install --only test

scripts/dev-setup/main.py

@@ -19,6 +19,7 @@
     "promptflow-azure",
     "promptflow[azure]",
     "promptflow-tools",
+    "promptflow-evals",
 ]
 
 

src/promptflow-evals/promptflow/evals/evaluate/_evaluate.py

@@ -4,7 +4,7 @@
 from typing import Optional, Dict, Callable
 import pandas as pd
 from ._flow_run_wrapper import FlowRunWrapper
-from promptflow import PFClient
+from promptflow.client import PFClient
 
 
 def _calculate_mean(df) -> Dict[str, float]:

src/promptflow-evals/promptflow/evals/evaluate/_flow_run_wrapper.py

@@ -2,7 +2,7 @@
 # Copyright (c) Microsoft Corporation. All rights reserved.
 # ---------------------------------------------------------
 import time
-from promptflow import PFClient
+from promptflow.client import PFClient
 
 
 class FlowRunWrapper(object):

src/promptflow-evals/promptflow/evals/evaluators/chat/__init__.py

@@ -4,7 +4,7 @@
 
 __path__ = __import__("pkgutil").extend_path(__path__, __name__)  # type: ignore
 
-from promptflow.entities import AzureOpenAIConnection
+from promptflow.connections import AzureOpenAIConnection
 from promptflow.evals.evaluators import GroundednessEvaluator, RelevanceEvaluator, CoherenceEvaluator, FluencyEvaluator
 from typing import List, Dict
 from concurrent.futures import ThreadPoolExecutor, as_completed

src/promptflow-evals/promptflow/evals/evaluators/coherence/__init__.py

@@ -4,8 +4,8 @@
 
 __path__ = __import__("pkgutil").extend_path(__path__, __name__)  # type: ignore
 
-from promptflow import load_flow
-from promptflow.entities import AzureOpenAIConnection
+from promptflow.client import load_flow
+from promptflow.connections import AzureOpenAIConnection
 from pathlib import Path
 
 

src/promptflow-evals/promptflow/evals/evaluators/coherence/flow/parse_score.py

@@ -1,4 +1,4 @@
-from promptflow import tool
+from promptflow.core import tool
 import numpy as np
 import re
 

src/promptflow-evals/promptflow/evals/evaluators/coherence/flow/validate_inputs.py

@@ -1,4 +1,4 @@
-from promptflow import tool
+from promptflow.core import tool
 
 
 @tool

src/promptflow-evals/promptflow/evals/evaluators/content_safety/flow/evaluate_with_rai_service.py

@@ -1,4 +1,4 @@
-from promptflow import tool
+from promptflow.core import tool
 import time
 from constants import RAIService, Tasks
 from typing import List

src/promptflow-evals/promptflow/evals/evaluators/content_safety/flow/validate_inputs.py

@@ -1,4 +1,4 @@
-from promptflow import tool
+from promptflow.core import tool
 
 
 @tool

src/promptflow-evals/promptflow/evals/evaluators/content_safety/hate_unfairness.py

@@ -1,4 +1,4 @@
-from promptflow import load_flow
+from promptflow.client import load_flow
 from pathlib import Path
 from azure.core.credentials import TokenCredential
 from promptflow.evals._constants import EvaluationMetrics

src/promptflow-evals/promptflow/evals/evaluators/content_safety/self_harm.py

@@ -1,4 +1,4 @@
-from promptflow import load_flow
+from promptflow.client import load_flow
 from pathlib import Path
 from azure.core.credentials import TokenCredential
 from promptflow.evals._constants import EvaluationMetrics

src/promptflow-evals/promptflow/evals/evaluators/content_safety/sexual.py

@@ -1,4 +1,4 @@
-from promptflow import load_flow
+from promptflow.client import load_flow
 from pathlib import Path
 from azure.core.credentials import TokenCredential
 from promptflow.evals._constants import EvaluationMetrics

src/promptflow-evals/promptflow/evals/evaluators/content_safety/violence.py

@@ -1,4 +1,4 @@
-from promptflow import load_flow
+from promptflow.client import load_flow
 from pathlib import Path
 from azure.core.credentials import TokenCredential
 from promptflow.evals._constants import EvaluationMetrics

src/promptflow-evals/promptflow/evals/evaluators/f1_score/__init__.py

@@ -4,7 +4,7 @@
 
 __path__ = __import__("pkgutil").extend_path(__path__, __name__)  # type: ignore
 
-from promptflow import load_flow
+from promptflow.client import load_flow
 from pathlib import Path
 
 

src/promptflow-evals/promptflow/evals/evaluators/f1_score/flow/f1_score.py

@@ -1,4 +1,4 @@
-from promptflow import tool
+from promptflow.core import tool
 from collections import Counter
 
 

src/promptflow-evals/promptflow/evals/evaluators/f1_score/flow/validate_inputs.py

@@ -1,4 +1,4 @@
-from promptflow import tool
+from promptflow.core import tool
 
 
 @tool

src/promptflow-evals/promptflow/evals/evaluators/fluency/__init__.py

@@ -4,7 +4,7 @@
 
 __path__ = __import__("pkgutil").extend_path(__path__, __name__)  # type: ignore
 
-from promptflow import load_flow
+from promptflow.client import load_flow
 from promptflow.entities import AzureOpenAIConnection
 from pathlib import Path
 

src/promptflow-evals/promptflow/evals/evaluators/fluency/flow/parse_score.py

@@ -1,4 +1,4 @@
-from promptflow import tool
+from promptflow.core import tool
 import numpy as np
 import re
 

src/promptflow-evals/promptflow/evals/evaluators/fluency/flow/validate_inputs.py

@@ -1,4 +1,4 @@
-from promptflow import tool
+from promptflow.core import tool
 
 
 @tool

src/promptflow-evals/promptflow/evals/evaluators/groundedness/__init__.py

@@ -4,7 +4,7 @@
 
 __path__ = __import__("pkgutil").extend_path(__path__, __name__)  # type: ignore
 
-from promptflow import load_flow
+from promptflow.client import load_flow
 from promptflow.entities import AzureOpenAIConnection
 from pathlib import Path
 

src/promptflow-evals/promptflow/evals/evaluators/groundedness/flow/parse_score.py

@@ -1,4 +1,4 @@
-from promptflow import tool
+from promptflow.core import tool
 import numpy as np
 import re
 

src/promptflow-evals/promptflow/evals/evaluators/groundedness/flow/validate_inputs.py

@@ -1,4 +1,4 @@
-from promptflow import tool
+from promptflow.core import tool
 
 
 @tool

src/promptflow-evals/promptflow/evals/evaluators/relevance/__init__.py

@@ -4,7 +4,7 @@
 
 __path__ = __import__("pkgutil").extend_path(__path__, __name__)  # type: ignore
 
-from promptflow import load_flow
+from promptflow.client import load_flow
 from promptflow.entities import AzureOpenAIConnection
 from pathlib import Path
 

src/promptflow-evals/promptflow/evals/evaluators/relevance/flow/parse_score.py

@@ -1,4 +1,4 @@
-from promptflow import tool
+from promptflow.core import tool
 import numpy as np
 import re
 

src/promptflow-evals/promptflow/evals/evaluators/relevance/flow/validate_inputs.py

@@ -1,4 +1,4 @@
-from promptflow import tool
+from promptflow.core import tool
 
 
 @tool

src/promptflow-evals/promptflow/evals/evaluators/similarity/__init__.py

@@ -4,7 +4,7 @@
 
 __path__ = __import__("pkgutil").extend_path(__path__, __name__)  # type: ignore
 
-from promptflow import load_flow
+from promptflow.client import load_flow
 from promptflow.entities import AzureOpenAIConnection
 from pathlib import Path
 

src/promptflow-evals/promptflow/evals/evaluators/similarity/flow/parse_score.py

@@ -1,4 +1,4 @@
-from promptflow import tool
+from promptflow.core import tool
 import numpy as np
 import re
 

src/promptflow-evals/promptflow/evals/evaluators/similarity/flow/validate_inputs.py

@@ -1,4 +1,4 @@
-from promptflow import tool
+from promptflow.core import tool
 
 
 @tool

src/promptflow-evals/pyproject.toml

@@ -37,7 +37,8 @@ packages = [
 [tool.poetry.dependencies]
 python = "<4.0,>=3.8"
 azure-ai-ml = ">=1.14.0"
-promptflow = "<2.0.0"
+promptflow-devkit = "<2.0.0"
+promptflow-core = "<2.0.0"
 promptflow-tools = "<2.0.0"
 
 [tool.poetry.group.dev.dependencies]

src/promptflow-evals/samples/built_in_evaluators.py

@@ -13,12 +13,13 @@
     api_type="azure",
 )
 
-deployment_name = "gpt-4"
+deployment_name = "GPT-4-Prod"
 
 project_scope = {
-    "subscription_id": "2d385bf4-0756-4a76-aa95-28bf9ed3b625",
-    "resource_group_name": "rg-name",
-    "project_name": "project-name",
+    "subscription_id": "e0fd569c-e34a-4249-8c24-e8d723c7f054",
+    "resource_group_name": "resource-group",
+    "project_name": "project-name"
+
 }
 
 
@@ -114,7 +115,7 @@ def run_safety_evaluators():
 
 
 def run_qa_evaluator():
-    qa_eval = QAEvaluator(model_config=model_config, deployment_name="gpt-4")
+    qa_eval = QAEvaluator(model_config=model_config, deployment_name=deployment_name)
 
     score = qa_eval(
         question="Tokyo is the capital of which country?",
@@ -128,7 +129,7 @@ def run_qa_evaluator():
 
 
 def run_chat_evaluator():
-    chat_eval = ChatEvaluator(model_config=model_config, deployment_name="gpt-4")
+    chat_eval = ChatEvaluator(model_config=model_config, deployment_name=deployment_name)
 
     conversation = [
         {"role": "user", "content": "What is the value of 2 + 2?"},

src/promptflow-evals/tests/unittests/test_chat_evaluator.py

@@ -1,6 +1,6 @@
 import pytest
 from promptflow.evals.evaluators import ChatEvaluator
-from promptflow.entities import AzureOpenAIConnection
+from promptflow.connections import AzureOpenAIConnection
 
 
 @pytest.mark.unittest