Evaluation Sample Fix (#178)

* Add files via upload

* Update model_endpoints.py

* Running nb clean

Author: singankit

scenarios/evaluate/Supported_Evaluation_Targets/Evaluate_Base_Model_Endpoint/Evaluate_Base_Model_Endpoint.ipynb

@@ -2,9 +2,7 @@
  "cells": [
   {
    "cell_type": "markdown",
-   "metadata": {
-    "tags": []
-   },
+   "metadata": {},
    "source": [
     "# Evaluate Base Model Endpoints using Azure AI Evaluation APIs\n",
     "\n",
@@ -39,9 +37,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%pip install azure-ai-evaluation\n",
-    "%pip install promptflow-azure\n",
-    "%pip install promptflow-tracing"
+    "%pip install -U azure-ai-evaluation"
    ]
   },
   {
@@ -65,9 +61,7 @@
   },
   {
    "cell_type": "markdown",
-   "metadata": {
-    "tags": []
-   },
+   "metadata": {},
    "source": [
     "## Target Application\n",
     "\n",
@@ -86,7 +80,7 @@
    "source": [
     "env_var = {\n",
     "    \"gpt4-0613\": {\n",
-    "        \"endpoint\": \"https://ai-***.**.azure.com/openai/deployments/gpt-4/chat/completions?api-version=2023-03-15-preview\",\n",
+    "        \"endpoint\": \"https://ai-**.openai.azure.com/openai/deployments/gpt-4o-mini/chat/completions?api-version=2024-08-01-preview\",\n",
     "        \"key\": \"***\",\n",
     "    },\n",
     "    \"gpt35-turbo\": {\n",
@@ -143,9 +137,10 @@
     "\n",
     "# Use the following code to set the environment variables if not already set. If set, you can skip this step.\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\"] = \"<api-version>\"\n",
+    "os.environ[\"AZURE_OPENAI_DEPLOYMENT\"] = \"<deployment-name>\"\n",
+    "os.environ[\"AZURE_OPENAI_ENDPOINT\"] = \"<endpoint>\"\n",
+    "os.environ[\"AZURE_OPENAI_KEY\"] = \"<key>\""
    ]
   },
   {
@@ -198,10 +193,14 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "model_config = {\n",
-    "    \"azure_endpoint\": os.environ.get(\"AZURE_OPENAI_ENDPOINT\"),\n",
-    "    \"azure_deployment\": os.environ.get(\"AZURE_OPENAI_DEPLOYMENT\"),\n",
-    "}"
+    "from azure.ai.evaluation import AzureOpenAIModelConfiguration\n",
+    "\n",
+    "model_config = AzureOpenAIModelConfiguration(\n",
+    "    azure_endpoint=os.environ.get(\"AZURE_OPENAI_ENDPOINT\"),\n",
+    "    azure_deployment=os.environ.get(\"AZURE_OPENAI_DEPLOYMENT\"),\n",
+    "    api_key=os.environ.get(\"AZURE_OPENAI_KEY\"),\n",
+    "    api_version=os.environ.get(\"AZURE_OPENAI_API_VERSION\"),\n",
+    ")"
    ]
   },
   {
@@ -259,6 +258,7 @@
     "        evaluators={\n",
     "            \"relevance\": relevance_evaluator,\n",
     "        },\n",
+    "        azure_ai_project=azure_ai_project,\n",
     "        evaluator_config={\n",
     "            \"relevance\": {\n",
     "                \"column_mapping\": {\n",

scenarios/evaluate/Supported_Evaluation_Targets/Evaluate_Base_Model_Endpoint/model_endpoints.py

@@ -15,7 +15,7 @@ class Response(TypedDict):
 
     @trace
     def __call__(self: Self, query: str) -> Response:
-        if self.model_type == "gpt4-0821":
+        if self.model_type == "gpt4-0613":
             output = self.call_gpt4_endpoint(query)
         elif self.model_type == "gpt35-turbo":
             output = self.call_gpt35_turbo_endpoint(query)
@@ -37,8 +37,8 @@ def query(self: Self, endpoint: str, headers: str, payload: str) -> str:
         return response.json()
 
     def call_gpt4_endpoint(self: Self, query: str) -> Response:
-        endpoint = self.env["gpt4-0821"]["endpoint"]
-        key = self.env["gpt4-0821"]["key"]
+        endpoint = self.env["gpt4-0613"]["endpoint"]
+        key = self.env["gpt4-0613"]["key"]
 
         headers = {"Content-Type": "application/json", "api-key": key}
 
@@ -115,5 +115,5 @@ def call_mistral_endpoint(self: Self, query: str) -> Response:
         response = output["choices"][0]["message"]["content"]
         return {"query": query, "response": response}
 
-    def call_default_endpoint(query: str) -> Response:
-        return {"query": "What is the capital of France?", "response": "Paris"}
+    def call_default_endpoint(self: Self, query: str) -> Response:
+        return {"query": query, "response": "Paris"}