Feedback

README.md

@@ -1,3 +1,4 @@
+[![Review Assignment Due Date](https://classroom.github.com/assets/deadline-readme-button-22041afd0340ce965d47ae6ef1cefeee28c7c493a6346c4f15d667ab976d596c.svg)](https://classroom.github.com/a/tLTGCA4G)
 ---
 title: "Activity 1 - Hello, Azure AI"
 type: lab

REFLECTION.md

@@ -6,10 +6,20 @@ Answer these questions after completing the activity (2-3 sentences each). Conne
 
 Which of the three Azure AI services (OpenAI, Content Safety, Language) surprised you the most? Connect this to something specific you observed during your experiments -- a response you didn't expect, a behavior that seemed too easy or too hard, or a result that made you rethink how the service works.
 
+> The Content Safety service suprised me the most. It's also the most dificult to do well. It has to take into account the nuances of human speech/text patterns and attempt to correctly clasify them based on more rigid rules.
+
 ## 2. Lazy Initialization
 
 How would you explain the lazy initialization pattern to a colleague? Why is it used instead of creating clients at the top of the file?
 
+> Lazy initialization keeps the program from making expensive API calls until the precise time they are needed.
+> It's used to boost performance and save computational resources.
+
 ## 3. Content Safety in the Real World
 
 A resident files this complaint: *"A man was assaulted at this intersection because the street light has been out for months."* This text describes real violence but is a legitimate safety concern. Should the system block it, flag it for human review, or pass it through? What factors would you weigh in making that decision?
+
+> Ideally, the system should be robust enough to distinguish between actual violence and something that is part of a legitimate safety concern.
+> In this case, the system should flag it for human review, so a parson can make a true determination.
+> If the system blocks it, a legitimate safety concen doesn't make it to the department which can help.
+> If the system passes it through, then the safety check is pointless.

app/main.py

@@ -44,14 +44,12 @@ def _get_openai_client():
     """Lazily initialize the Azure OpenAI client."""
     global _openai_client
     if _openai_client is None:
-        # TODO: Uncomment and configure
-        #   from openai import AzureOpenAI
-        #   _openai_client = AzureOpenAI(
-        #       azure_endpoint=os.environ["AZURE_OPENAI_ENDPOINT"],
-        #       api_key=os.environ["AZURE_OPENAI_API_KEY"],
-        #       api_version="2024-10-21",
-        #   )
-        raise NotImplementedError("Configure the Azure OpenAI client")
+        from openai import AzureOpenAI
+        _openai_client = AzureOpenAI(
+            azure_endpoint=os.environ["AZURE_OPENAI_ENDPOINT"],
+            api_key=os.environ["AZURE_OPENAI_API_KEY"],
+            api_version="2024-10-21",
+        )
     return _openai_client
 
 
@@ -61,14 +59,12 @@ def _get_content_safety_client():
     if _content_safety_client is None:
         # NOTE: The Content Safety SDK handles API versioning internally --
         # no api_version parameter is needed (unlike the OpenAI SDK).
-        # TODO: Uncomment and configure
-        #   from azure.ai.contentsafety import ContentSafetyClient
-        #   from azure.core.credentials import AzureKeyCredential
-        #   _content_safety_client = ContentSafetyClient(
-        #       endpoint=os.environ["AZURE_CONTENT_SAFETY_ENDPOINT"],
-        #       credential=AzureKeyCredential(os.environ["AZURE_CONTENT_SAFETY_KEY"]),
-        #   )
-        raise NotImplementedError("Configure the Content Safety client")
+        from azure.ai.contentsafety import ContentSafetyClient
+        from azure.core.credentials import AzureKeyCredential
+        _content_safety_client = ContentSafetyClient(
+            endpoint=os.environ["AZURE_CONTENT_SAFETY_ENDPOINT"],
+            credential=AzureKeyCredential(os.environ["AZURE_CONTENT_SAFETY_KEY"]),
+        )
     return _content_safety_client
 
 
@@ -78,14 +74,12 @@ def _get_language_client():
     if _language_client is None:
         # NOTE: The Language SDK handles API versioning internally --
         # no api_version parameter is needed (unlike the OpenAI SDK).
-        # TODO: Uncomment and configure
-        #   from azure.ai.textanalytics import TextAnalyticsClient
-        #   from azure.core.credentials import AzureKeyCredential
-        #   _language_client = TextAnalyticsClient(
-        #       endpoint=os.environ["AZURE_AI_LANGUAGE_ENDPOINT"],
-        #       credential=AzureKeyCredential(os.environ["AZURE_AI_LANGUAGE_KEY"]),
-        #   )
-        raise NotImplementedError("Configure the AI Language client")
+        from azure.ai.textanalytics import TextAnalyticsClient
+        from azure.core.credentials import AzureKeyCredential
+        _language_client = TextAnalyticsClient(
+            endpoint=os.environ["AZURE_AI_LANGUAGE_ENDPOINT"],
+            credential=AzureKeyCredential(os.environ["AZURE_AI_LANGUAGE_KEY"]),
+        )
     return _language_client
 
 
@@ -101,14 +95,27 @@ def classify_311_request(request_text: str) -> dict:
     Returns:
         dict with keys: category, confidence, reasoning
     """
-    # TODO: Step 1.1 - Get the OpenAI client
-    # TODO: Step 1.2 - Call client.chat.completions.create() with:
-    #   model=os.environ.get("AZURE_OPENAI_DEPLOYMENT", "gpt-4o")
-    #   A system message that classifies into: Pothole, Noise Complaint,
-    #   Trash/Litter, Street Light, Water/Sewer, Other
-    #   response_format={"type": "json_object"}, temperature=0
-    # TODO: Step 1.3 - Parse the JSON response with json.loads()
-    raise NotImplementedError("Implement classify_311_request in Step 1")
+    client = _get_openai_client()
+    response = client.chat.completions.create(
+        model=os.environ.get("AZURE_OPENAI_DEPLOYMENT", "gpt-4o"),
+        messages=[
+            {
+                "role": "system",
+                "content": (
+                    "You are a helpful assistant that classifies Memphis 311 service "
+                    "requests into one of the following categories: Pothole, Noise Complaint, "
+                    "Trash/Litter, Street Light, Water/Sewer, Other. Respond with a JSON object "
+                    "with keys: category (one of the categories), confidence (0-1), and reasoning (brief explanation)."
+                ),
+            },
+            {"role": "user", "content": request_text},
+        ],
+        response_format={"type": "json_object"},
+        temperature=0,
+    )
+
+    result = json.loads(response.choices[0].message.content)
+    return result
 
 
 # ---------------------------------------------------------------------------
@@ -123,10 +130,14 @@ def check_content_safety(text: str) -> dict:
     Returns:
         dict with keys: safe (bool), categories (dict of category: severity)
     """
-    # TODO: Step 2.1 - Get the Content Safety client
-    # TODO: Step 2.2 - Call client.analyze_text() with AnalyzeTextOptions
-    # TODO: Step 2.3 - Return safety results
-    raise NotImplementedError("Implement check_content_safety in Step 2")
+    client = _get_content_safety_client()
+
+    from azure.ai.contentsafety.models import AnalyzeTextOptions
+    result = client.analyze_text(AnalyzeTextOptions(text=text))
+
+    categories = {category.category: category.severity for category in result.categories_analysis}
+    safe = all(severity == 0 for severity in categories.values())
+    return {"safe": safe, "categories": categories}
 
 
 # ---------------------------------------------------------------------------
@@ -141,10 +152,12 @@ def extract_key_phrases(text: str) -> list[str]:
     Returns:
         List of key phrase strings.
     """
-    # TODO: Step 3.1 - Get the Language client
-    # TODO: Step 3.2 - Call client.extract_key_phrases([text])
-    # TODO: Step 3.3 - Return the list of key phrases
-    raise NotImplementedError("Implement extract_key_phrases in Step 3")
+    client = _get_language_client()
+
+    response = client.extract_key_phrases([text])
+    key_phrases = response[0].key_phrases if not response[0].is_error else []
+
+    return key_phrases
 
 
 def main():