Fix quality sample (#168)

* update promptflow-eval dependencies to azure-ai-evaluation

* clear local variables

* fix errors and remove 'question' col from data

* small fix in evaluator config

* Fix AI as Judge Quality Evaluators sample

Author: slister1001

scenarios/evaluate/Supported_Evaluation_Metrics/AI_Judge_Evaluators_Quality/AI_Judge_Evaluators_Quality.ipynb

@@ -39,7 +39,8 @@
    "source": [
     "%pip install azure-ai-evaluation\n",
     "%pip install promptflow-azure\n",
-    "%pip install azure-identity"
+    "%pip install azure-identity\n",
+    "%pip install --upgrade openai"
    ]
   },
   {
@@ -56,9 +57,8 @@
    "outputs": [],
    "source": [
     "from pprint import pprint\n",
-    "from openai import AzureOpenAI\n",
     "import pandas as pd\n",
-    "from azure.identity import DefaultAzureCredential, get_bearer_token_provider"
+    "from azure.identity import DefaultAzureCredential"
    ]
   },
   {
@@ -89,9 +89,9 @@
    "outputs": [],
    "source": [
     "azure_ai_project = {\n",
-    "    \"subscription_id\": \"<your-subscription-id>\",\n",
-    "    \"resource_group_name\": \"<your-resource-group-name>\",\n",
-    "    \"project_name\": \"<your-project-name>\",\n",
+    "    \"subscription_id\": \"<subscription_id>\",\n",
+    "    \"resource_group_name\": \"<resource_group_name>\",\n",
+    "    \"project_name\": \"<project_name>\",\n",
     "}"
    ]
   },
@@ -103,11 +103,10 @@
    "source": [
     "import os\n",
     "\n",
-    "# Use the following code to set the environment variables if not already set. If set, you can skip this step.\n",
+    "# Use the following code to set the environment variables if not already set. If set, you can skip this step. In addition, you should also set \"AZURE_OPENAI_ENDPOINT\" to the endpoint of your AzureOpenAI service.\n",
     "\n",
-    "os.environ[\"AZURE_OPENAI_API_VERSION\"] = \"<api version>\"\n",
-    "os.environ[\"AZURE_OPENAI_DEPLOYMENT\"] = \"<your-deployment>\"\n",
-    "os.environ[\"AZURE_OPENAI_ENDPOINT\"] = \"<your-endpoint>\""
+    "os.environ[\"AZURE_OPENAI_API_VERSION\"] = \"<openai_api_version>\"\n",
+    "os.environ[\"AZURE_OPENAI_DEPLOYMENT\"] = \"<openai_deployment>\""
    ]
   },
   {
@@ -143,63 +142,14 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "import os\n",
+    "\n",
     "model_config = {\n",
     "    \"azure_endpoint\": os.environ.get(\"AZURE_OPENAI_ENDPOINT\"),\n",
     "    \"azure_deployment\": os.environ.get(\"AZURE_OPENAI_DEPLOYMENT\"),\n",
     "}"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from typing_extensions import Self\n",
-    "from typing import TypedDict\n",
-    "from promptflow.tracing import trace\n",
-    "\n",
-    "\n",
-    "class ModelEndpoint:\n",
-    "    def __init__(self: Self, env: dict) -> str:\n",
-    "        self.env = env\n",
-    "\n",
-    "    class Response(TypedDict):\n",
-    "        query: str\n",
-    "        response: str\n",
-    "\n",
-    "    @trace\n",
-    "    def __call__(self: Self, query: str) -> Response:\n",
-    "        token_provider = get_bearer_token_provider(\n",
-    "            DefaultAzureCredential(), \"https://cognitiveservices.azure.com/.default\"\n",
-    "        )\n",
-    "\n",
-    "        client = AzureOpenAI(\n",
-    "            azure_endpoint=self.env[\"azure_endpoint\"],\n",
-    "            api_version=\"2024-06-01\",\n",
-    "            azure_ad_token_provider=token_provider,\n",
-    "        )\n",
-    "        # Call the model\n",
-    "        completion = client.chat.completions.create(\n",
-    "            model=self.env[\"azure_deployment\"],\n",
-    "            messages=[\n",
-    "                {\n",
-    "                    \"role\": \"user\",\n",
-    "                    \"content\": query,\n",
-    "                }\n",
-    "            ],\n",
-    "            max_tokens=800,\n",
-    "            temperature=0.7,\n",
-    "            top_p=0.95,\n",
-    "            frequency_penalty=0,\n",
-    "            presence_penalty=0,\n",
-    "            stop=None,\n",
-    "            stream=False,\n",
-    "        )\n",
-    "        output = completion.to_dict()\n",
-    "        return {\"query\": query, \"response\": output[\"choices\"][0][\"message\"][\"content\"]}"
-   ]
-  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -236,9 +186,12 @@
     "    FluencyEvaluator,\n",
     "    SimilarityEvaluator,\n",
     ")\n",
+    "from model_endpoint import ModelEndpoint\n",
     "\n",
     "\n",
-    "content_safety_evaluator = ContentSafetyEvaluator(azure_ai_project)\n",
+    "content_safety_evaluator = ContentSafetyEvaluator(\n",
+    "    azure_ai_project=azure_ai_project, credential=DefaultAzureCredential()\n",
+    ")\n",
     "relevance_evaluator = RelevanceEvaluator(model_config)\n",
     "coherence_evaluator = CoherenceEvaluator(model_config)\n",
     "groundedness_evaluator = GroundednessEvaluator(model_config)\n",
@@ -310,7 +263,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "venv-azureai-samples",
+   "display_name": ".venv",
    "language": "python",
    "name": "python3"
   },

scenarios/evaluate/Supported_Evaluation_Metrics/AI_Judge_Evaluators_Quality/model_endpoint.py

@@ -0,0 +1,45 @@
+from typing_extensions import Self
+from typing import TypedDict
+from azure.identity import DefaultAzureCredential, get_bearer_token_provider
+from openai import AzureOpenAI
+
+
+class ModelEndpoint:
+    def __init__(self: Self, env: dict) -> None:
+        self.env = env
+        print(self.env)
+
+    class Response(TypedDict):
+        query: str
+        response: str
+
+    # @trace
+    def __call__(self: Self, query: str) -> Response:
+        token_provider = get_bearer_token_provider(
+            DefaultAzureCredential(), "https://cognitiveservices.azure.com/.default"
+        )
+
+        client = AzureOpenAI(
+            azure_endpoint=self.env["azure_endpoint"],
+            api_version="2024-06-01",
+            azure_ad_token_provider=token_provider,
+        )
+        # Call the model
+        completion = client.chat.completions.create(
+            model=self.env["azure_deployment"],
+            messages=[
+                {
+                    "role": "user",
+                    "content": query,
+                }
+            ],
+            max_tokens=800,
+            temperature=0.7,
+            top_p=0.95,
+            frequency_penalty=0,
+            presence_penalty=0,
+            stop=None,
+            stream=False,
+        )
+        output = completion.to_dict()
+        return {"query": query, "response": output["choices"][0]["message"]["content"]}