Merge remote-tracking branch 'origin/dev' into PSL-US-40568

Author: AjitPadhi-Microsoft

.github/workflows/test.yml

@@ -31,6 +31,7 @@ on:
 permissions:
   contents: read
   actions: read
+  pull-requests: write
 
 jobs:
   #   frontend_tests:
@@ -106,7 +107,19 @@ jobs:
       - name: Run Backend Tests with Coverage
         if: env.skip_backend_tests == 'false'
         run: |
-          pytest --cov=. --cov-report=term-missing --cov-report=xml ./src/tests/api
+          pytest --cov=. --cov-report=term-missing --cov-report=xml --junitxml=pytest.xml ./src/tests/api
+
+      - name: Pytest Coverage Comment
+        if: |
+          always() &&
+          github.event_name == 'pull_request' &&
+          github.event.pull_request.head.repo.fork == false &&
+          env.skip_backend_tests == 'false'
+        uses: MishaKav/pytest-coverage-comment@26f986d2599c288bb62f623d29c2da98609e9cd4  # v1.6.0
+        with:
+          pytest-xml-coverage-path: coverage.xml
+          junitxml-path: pytest.xml
+          report-only-changed-files: true
 
       - name: Skip Backend Tests
         if: env.skip_backend_tests == 'true'

docs/workshop/docs/workshop/Challenge-5/python/utility.py

@@ -242,7 +242,7 @@ def schema_to_tool(schema: Any):
                 return json.loads(
                     assistant_message.tool_calls[0].function.arguments, strict=False
                 )
-            except:
+            except Exception:
                 return assistant_message.tool_calls[0].function.arguments
 
     def get_structured_output_answer(
@@ -348,7 +348,6 @@ def generate_scenes(
         scene_generation_prompt = Template(SCENE_GENERATION_PROMPT).substitute(
             descriptions=next_segment_content
         )
-        scence_response = VideoSceneResponse(scenes=[])
         scence_response = openai_assistant.get_structured_output_answer(
             "", scene_generation_prompt, VideoSceneResponse
         )
@@ -433,7 +432,6 @@ def generate_chapters(
     chapter_generation_prompt = Template(CHAPTER_GENERATION_PROMPT).substitute(
         descriptions=scene_descriptions
     )
-    chapter_response = VideoChapterResponse(chapters=[])
     chapter_response = openai_assistant.get_structured_output_answer(
         "", chapter_generation_prompt, VideoChapterResponse
     )
@@ -460,7 +458,6 @@ def aggregate_tags(
     tags_dedup = set(map(lambda x: re.sub(r'^ ', '', x), tags))
     tag_dedup_prompt = Template(DEDUP_PROMPT).substitute(tag_list=tags_dedup)
 
-    tag_response = VideoTagResponse(tags=[])
     tag_response = openai_assistant.get_structured_output_answer(
         "", tag_dedup_prompt, VideoTagResponse
     )

infra/scripts/fabric_scripts/create_fabric_items.py

@@ -1,8 +1,6 @@
-from azure.identity import ManagedIdentityCredential
 import base64
 import json
 import requests
-import pandas as pd
 import os
 from glob import iglob
 import zipfile
@@ -98,11 +96,11 @@
         # upload extracted folder
         file_names = [f for f in iglob(os.path.join(local_path, "**", "*"), recursive=True) if os.path.isfile(f)]
         # print('file_names ex', file_names)
-        for file_name in file_names:
-            upload_file_name = os.path.basename(file_name)
+        for extracted_file in file_names:
+            upload_file_name = os.path.basename(extracted_file)
             file_client = directory_client.get_file_client("cu_audio_files_all/" + upload_file_name)
-            # with open(file=os.path.join(extract_dir, file_name), mode="rb") as data:
-            with open(file=file_name, mode="rb") as data:
+            # with open(file=os.path.join(extract_dir, extracted_file), mode="rb") as data:
+            with open(file=extracted_file, mode="rb") as data:
                 # print('data', data)
                 file_client.upload_data(data, overwrite=True)
 
@@ -127,7 +125,7 @@
   env_res = requests.get(fabric_env_url, headers=fabric_headers)
   env_res_id = env_res.json()['value'][0]['id']
   # print(env_res.json())
-except:
+except Exception:  # Environments may not be provisioned yet
   env_res_id = ''
 
 #create notebook items
@@ -150,14 +148,14 @@
         notebook_json['metadata']['dependencies']['lakehouse']['default_lakehouse'] = lakehouse_res.json()['id']
         notebook_json['metadata']['dependencies']['lakehouse']['default_lakehouse_name'] = lakehouse_res.json()['displayName']
         notebook_json['metadata']['dependencies']['lakehouse']['default_lakehouse_workspace_id'] = lakehouse_res.json()['workspaceId']
-    except:
+    except Exception:  # Lakehouse metadata may not be available
         pass
 
     if env_res_id != '':
         try:
             notebook_json['metadata']['dependencies']['environment']['environmentId'] = env_res_id
             notebook_json['metadata']['dependencies']['environment']['workspaceId'] = lakehouse_res.json()['workspaceId']
-        except:
+        except Exception:  # Environment metadata may not be available
             pass
 
 
@@ -178,8 +176,7 @@
         }
     }
 
-    fabric_response = requests.post(fabric_items_url, headers=fabric_headers, json=notebook_data)
-    #print(fabric_response.json())
+    requests.post(fabric_items_url, headers=fabric_headers, json=notebook_data)
 
 time.sleep(120)
 

infra/scripts/index_scripts/02_create_cu_template_audio.py

@@ -36,7 +36,7 @@
     analyzer = client.get_analyzer_detail_by_id(ANALYZER_ID)
     if analyzer is not None:
         client.delete_analyzer(ANALYZER_ID)
-except Exception:
+except Exception:  # Analyzer may not exist yet, safe to ignore
     pass
 
 response = client.begin_create_analyzer(ANALYZER_ID, analyzer_template_path=ANALYZER_TEMPLATE_FILE)

infra/scripts/index_scripts/02_create_cu_template_text.py

@@ -31,7 +31,7 @@
     analyzer = client.get_analyzer_detail_by_id(ANALYZER_ID)
     if analyzer is not None:
         client.delete_analyzer(ANALYZER_ID)
-except Exception:
+except Exception:  # Analyzer may not exist yet, safe to ignore
     pass
 
 response = client.begin_create_analyzer(ANALYZER_ID, analyzer_template_path=ANALYZER_TEMPLATE_FILE)

infra/scripts/index_scripts/03_cu_process_data_text.py

@@ -381,10 +381,10 @@ async def process_files():
 
                 docs.extend(await prepare_search_doc(content, conversation_id, path.name, embeddings_client))
                 counter += 1
-            except Exception:
+            except Exception:  # Skip files that fail processing
                 pass
             if docs != [] and counter % 10 == 0:
-                result = search_client.upload_documents(documents=docs)
+                search_client.upload_documents(documents=docs)
                 docs = []
         if docs:
             search_client.upload_documents(documents=docs)
@@ -533,7 +533,6 @@ async def call_topic_mining_agent(topics_str1):
     column_names = [i[0] for i in cursor.description]
     df_topics = pd.DataFrame(rows, columns=column_names)
     mined_topics_list = df_topics['label'].tolist()
-    mined_topics = ", ".join(mined_topics_list)
     print(f"✓ Mined {len(mined_topics_list)} topics")
 
     async def call_topic_mapping_agent(agent, input_text, list_of_topics):

infra/scripts/index_scripts/04_cu_process_custom_data.py

@@ -190,7 +190,7 @@ def create_search_index():
     connection_string = f"DRIVER={driver};SERVER={SQL_SERVER};DATABASE={SQL_DATABASE};"
     conn = pyodbc.connect(connection_string, attrs_before={SQL_COPT_SS_ACCESS_TOKEN: token_struct})
     cursor = conn.cursor()
-except: 
+except Exception:  # Fall back to ODBC Driver 17
     driver = "{ODBC Driver 17 for SQL Server}"
     token_bytes = credential.get_token("https://database.windows.net/.default").token.encode("utf-16-LE")
     token_struct = struct.pack(f"<I{len(token_bytes)}s", len(token_bytes), token_bytes)
@@ -435,10 +435,10 @@ async def process_files():
 
                 docs.extend(await prepare_search_doc(content, conversation_id, path.name, embeddings_client))
                 counter += 1
-            except Exception:
+            except Exception:  # Skip files that fail processing
                 pass
             if docs != [] and counter % 10 == 0:
-                result = search_client.upload_documents(documents=docs)
+                search_client.upload_documents(documents=docs)
                 docs = []
         if docs:
             search_client.upload_documents(documents=docs)
@@ -469,7 +469,6 @@ async def process_files():
                 conversation_id = file_name.split('convo_', 1)[1].split('_')[0]
                 conversationIds.append(conversation_id)
 
-                duration = int(result['result']['contents'][0]['fields']['Duration']['valueString'])
                 fields = result['result']['contents'][0]['fields']
                 duration_str = get_field_value(fields, 'Duration', '0')
                 try:
@@ -507,9 +506,9 @@ async def process_files():
                 docs.extend(await prepare_search_doc(content, document_id, path.name, embeddings_client))
                 counter += 1
             except Exception:
-                pass
+                pass  # Skip files that fail to process
             if docs != [] and counter % 10 == 0:
-                result = search_client.upload_documents(documents=docs)
+                search_client.upload_documents(documents=docs)
                 docs = []
 
         # upload the last batch
@@ -620,8 +619,6 @@ async def call_topic_mining_agent(topics_str1):
             res = res.replace("```json", '').replace("```", '').strip()
             return json.loads(res)
 
-    MAX_TOKENS = 3096
-
     res = asyncio.run(call_topic_mining_agent(topics_str))
     for object1 in res['topics']:
         cursor.execute("INSERT INTO km_mined_topics (label, description) VALUES (?,?)", (object1['label'], object1['description']))
@@ -632,7 +629,6 @@ async def call_topic_mining_agent(topics_str1):
     column_names = [i[0] for i in cursor.description]
     df_topics = pd.DataFrame(rows, columns=column_names)
     mined_topics_list = df_topics['label'].tolist()
-    mined_topics = ", ".join(mined_topics_list)
     print(f"✓ Mined {len(mined_topics_list)} topics")
 
     async def call_topic_mapping_agent(agent, input_text, list_of_topics):

infra/scripts/validate_bicep_params.py

@@ -107,7 +107,7 @@ def parse_parameters_env_vars(json_path: Path) -> dict[str, list[str]]:
     try:
         data = json.loads(sanitized)
         params = data.get("parameters", {})
-    except json.JSONDecodeError:
+    except json.JSONDecodeError:  # Parameters file may have azd variable placeholders
         pass
 
     # Walk each top-level parameter and scan its entire serialized value

src/App/package-lock.json

@@ -28,6 +28,7 @@
     "react-d3-cloud": "^1.0.6",
     "react-dom": "^18.3.1",
     "react-markdown": "^10.1.0",
+    "react-redux": "^9.1.2",
     "react-scripts": "^5.0.1",
     "rehype-raw": "^7.0.0",
     "remark-gfm": "^4.0.1",