code cleaning

Author: Rafi-Microsoft

infra/scripts/index_scripts/03_cu_process_data_text.py

@@ -79,10 +79,7 @@ def get_secrets_from_kv(kv_name, secret_name):
 ANALYZER_ID = "ckm-json"
 print("Content Understanding client initialized.")
 
-# ---------- Azure AI Foundry (Inference) clients (Managed Identity) ----------
-# Project endpoint has the form: https://your-ai-services-account-name.services.ai.azure.com/api/projects/your-project-name
-# Inference endpoint has the form: https://your-ai-services-account-name.services.ai.azure.com/models
-# Strip the "/api/projects/your-project-name" part and replace with "/models":
+# Azure AI Foundry (Inference) clients (Managed Identity)
 inference_endpoint = f"https://{urlparse(ai_project_endpoint).netloc}/models"
 
 chat_client = ChatCompletionsClient(
@@ -96,11 +93,9 @@ def get_secrets_from_kv(kv_name, secret_name):
     credential=credential,
     credential_scopes=["https://ai.azure.com/.default"],
 )
-# -----------------------------------------------------------------------------
 
 # Utility functions
 def get_embeddings(text: str):
-    # Uses Azure AI Inference EmbeddingsClient with the AI Foundry project inference endpoint.
     try:
         resp = embeddings_client.embed(model=embedding_deployment, input=[text])
         return resp.data[0].embedding
@@ -296,7 +291,7 @@ def call_gpt4(topics_str1, client):
         Return the topics and their labels in JSON format.Always add 'topics' node and 'label', 'description' attributes in json.
         Do not return anything else.
         """
-    # Inference client: Chat completions with model deployment name
+    
     response = client.complete(
         model=deployment,
         messages=[
@@ -308,7 +303,6 @@ def call_gpt4(topics_str1, client):
     res = response.choices[0].message.content
     return json.loads(res.replace("```json", '').replace("```", ''))
 
-# --- REPLACED: AzureOpenAI(...) with ChatCompletionsClient (already created as `chat_client`) ---
 max_tokens = 3096
 
 res = call_gpt4(topics_str, chat_client)

infra/scripts/index_scripts/03_cu_process_data_text_manual.py

@@ -82,11 +82,7 @@ def get_secrets_from_kv(kv_name, secret_name):
 ANALYZER_ID = "ckm-json"
 print("Content Understanding client initialized.")
 
-
-# ---------- Azure AI Foundry (Inference) clients (Managed Identity) ----------
-# Project endpoint has the form: https://your-ai-services-account-name.services.ai.azure.com/api/projects/your-project-name
-# Inference endpoint has the form: https://your-ai-services-account-name.services.ai.azure.com/models
-# Strip the "/api/projects/your-project-name" part and replace with "/models":
+# Azure AI Foundry (Inference) clients (Managed Identity)
 inference_endpoint = f"https://{urlparse(ai_project_endpoint).netloc}/models"
 
 chat_client = ChatCompletionsClient(
@@ -100,12 +96,9 @@ def get_secrets_from_kv(kv_name, secret_name):
     credential=credential,
     credential_scopes=["https://ai.azure.com/.default"],
 )
-# -----------------------------------------------------------------------------
-
 
 # Utility functions
 def get_embeddings(text: str):
-    # Uses Azure AI Inference EmbeddingsClient with the AI Foundry project inference endpoint.
     try:
         resp = embeddings_client.embed(model=embedding_deployment, input=[text])
         return resp.data[0].embedding
@@ -301,7 +294,6 @@ def call_gpt4(topics_str1, client):
         Return the topics and their labels in JSON format.Always add 'topics' node and 'label', 'description' attributes in json.
         Do not return anything else.
         """
-    # Inference client: Chat completions with model deployment name
     response = client.complete(
         model=deployment,
         messages=[

infra/scripts/index_scripts/04_cu_process_data_new_data.py

@@ -70,10 +70,7 @@ def get_secrets_from_kv(kv_name, secret_name):
 index_client = SearchIndexClient(endpoint=search_endpoint, credential=search_credential)
 print("Azure Search setup complete.")
 
-# ---------- Azure AI Foundry (Inference) clients (Managed Identity) ----------
-# Project endpoint has the form: https://your-ai-services-account-name.services.ai.azure.com/api/projects/your-project-name
-# Inference endpoint has the form: https://your-ai-services-account-name.services.ai.azure.com/models
-# Strip the "/api/projects/your-project-name" part and replace with "/models":
+# Azure AI Foundry (Inference) clients (Managed Identity)
 inference_endpoint = f"https://{urlparse(ai_project_endpoint).netloc}/models"
 
 chat_client = ChatCompletionsClient(
@@ -187,7 +184,6 @@ def create_search_index():
 
 # Utility functions
 def get_embeddings(text: str):
-    # Uses Azure AI Inference EmbeddingsClient with the AI Foundry project inference endpoint.
     try:
         resp = embeddings_client.embed(model=embedding_model, input=[text])
         return resp.data[0].embedding