chore(fix): Removed Python Custom Error Handler & Fixed Python Bug in ReportingByComment (#45)

* chore(fix):
Removed Python custom error handler and replaced with HTTPException.
Removed all files and instances related to custom Python error handler
Fixed Python bug in ReportingByComment
* Adding docstring
* chore: corrected tests
* (fix): implementing feedback changes & testing cli pipeline
* (fix): increase wait time for integration tests
* bug fix
* bug fix - Devnull
* Update run-python-tests.yml
* Update run-python-tests.yml
Remove tmate for debugging
* Update run-python-tests.yml
direction connection change
* Update run-python-tests.yml
Adding index creation
* Update run-python-tests.yml
* Update run-python-tests.yml
* Update run-python-tests.yml
* Update run-python-tests.yml

Author: tmcneil-mdb

.github/workflows/run-python-tests.yml

@@ -38,9 +38,58 @@ jobs:
       - name: Download sample data
         run: curl https://atlas-education.s3.amazonaws.com/sampledata.archive -o sampledata.archive
 
-      - name: Add sample data to database
-        run: mongorestore --archive=sampledata.archive --port=27017
+      - name: Setup Database (Data & Indexes)
+        run: |
+          # 1. Restore the data
+          mongorestore --archive=sampledata.archive --port=27017
+
+          # 2. Prepare the Search Index Definition
+          echo '{
+            "name": "movieSearchIndex",
+            "database": "sample_mflix",
+            "collectionName": "movies",
+            "mappings": {
+              "dynamic": false,
+              "fields": {
+                "plot": {"type": "string", "analyzer": "lucene.standard"},
+                "fullplot": {"type": "string", "analyzer": "lucene.standard"},
+                "directors": {"type": "string", "analyzer": "lucene.standard"},
+                "writers": {"type": "string", "analyzer": "lucene.standard"},
+                "cast": {"type": "string", "analyzer": "lucene.standard"}
+              }
+            }
+          }' > search_index.json
+
+          # 3. Create the Search Index
+          atlas deployments search indexes create \
+            --deploymentName myLocalRs1 \
+            --file search_index.json
+
+          # 4. Prepare the Vector Index Definition
+          echo '{
+            "name": "vector_index",
+            "database": "sample_mflix",
+            "collectionName": "embedded_movies",
+            "type": "vectorSearch",
+            "fields": [
+              {
+                "type": "vector",
+                "path": "plot_embedding_voyage_3_large",
+                "numDimensions": 2048,
+                "similarity": "cosine"
+              }
+            ]
+          }' > vector_index.json
 
+          # 5. Create the Vector Index
+          atlas deployments search indexes create \
+            --deploymentName myLocalRs1 \
+            --file vector_index.json
+
+          # 6. Wait for indexes to build
+          echo "Waiting for indexes to build..."
+          sleep 20
+          
       - name: Set up Python
         uses: actions/setup-python@v5
         with:
@@ -63,10 +112,10 @@ jobs:
 
       - name: Run integration tests
         working-directory: mflix/server/python-fastapi
-        run: pytest -m integration --verbose --tb=short --junit-xml=test-results-integration.xml || true
+        run: pytest -m integration --verbose --tb=short --junit-xml=test-results-integration.xml
         env:
-          MONGO_URI: mongodb://localhost:27017
-          MONGO_DB: sample_mflix
+          MONGO_URI: mongodb://localhost:27017/?directConnection=true
+          MONGO_DB: sample_mflix   
 
       - name: Upload test results
         uses: actions/upload-artifact@v4

mflix/server/python-fastapi/main.py

@@ -2,7 +2,6 @@
 from fastapi import FastAPI
 from fastapi.middleware.cors import CORSMiddleware
 from src.routers import movies
-from src.utils.errorHandler import register_error_handlers
 from src.database.mongo_client import db, get_collection
 
 import os
@@ -15,8 +14,9 @@
 @asynccontextmanager
 async def lifespan(app: FastAPI):
     # Startup: Create search indexes
-    await ensure_search_index()
-    await vector_search_index()
+    await ensure_mongodb_search_index()
+    await ensure_vector_search_index()
+    await ensure_standard_index()
 
     # Print server information
     print(f"\n{'='*60}")
@@ -30,10 +30,9 @@ async def lifespan(app: FastAPI):
     # Add any cleanup code here
 
 
-async def ensure_search_index():
+async def ensure_mongodb_search_index():
     try:
         movies_collection = db.get_collection("movies")
-        comments_collection = db.get_collection("comments")
 
         # Check and create search index for movies collection
         result = await movies_collection.list_search_indexes()
@@ -71,7 +70,7 @@ async def ensure_search_index():
         )
 
 
-async def vector_search_index():
+async def ensure_vector_search_index():
     """
     Creates vector search index on application startup if it doesn't already exist.
     This ensures the index is ready before any vector search requests are made.
@@ -114,6 +113,26 @@ async def vector_search_index():
             f"and verify the 'embedded_movies' collection exists with the required embedding field."
         )
 
+async def ensure_standard_index():
+    """
+    Creates a standard MongoDB index on the comments collection on application startup.
+    This improves performance for queries filtering by movie_id such as ReportingByComments().
+    """
+
+    try:
+        comments_collection = db.get_collection("comments")
+
+        existing_indexes_cursor = await comments_collection.list_indexes()
+        existing_indexes = [index async for index in existing_indexes_cursor]
+        index_names = [index.get("name") for index in existing_indexes]
+        standard_index_name = "movie_id_index"
+        if standard_index_name not in index_names:
+            await comments_collection.create_index([("movie_id", 1)], name=standard_index_name)
+
+    except Exception as e:
+        print(f"Failed to create standard index on 'comments' collection: {str(e)}. ")
+        print(f"Performance may be degraded. Please check your MongoDB configuration.")
+
 
 app = FastAPI(lifespan=lifespan)
 
@@ -127,6 +146,5 @@ async def vector_search_index():
     allow_headers=["*"],
 )
 
-register_error_handlers(app)
 app.include_router(movies.router, prefix="/api/movies", tags=["movies"])
 

mflix/server/python-fastapi/src/database/mongo_client.py

@@ -18,4 +18,6 @@ def get_collection(name:str):
 def voyage_ai_available():
     """Check if Voyage API Key is available and valid."""
     api_key = os.getenv("VOYAGE_API_KEY")
+    if api_key is None or api_key =="your_voyage_api_key":
+        return None
     return api_key is not None and api_key.strip() != ""

mflix/server/python-fastapi/src/models/models.py

@@ -127,22 +127,9 @@ class SuccessResponse(BaseModel, Generic[T]):
     timestamp: str
     pagination: Optional[Pagination] = None
 
-
-class ErrorDetails(BaseModel):
-    message: str
-    code: Optional[str]
-    details: Optional[Any] = None
-
 class BatchUpdateRequest(BaseModel):
     filter: MovieFilter
     update: UpdateMovieRequest
 
 class BatchDeleteRequest(BaseModel):
     filter: MovieFilter
-
-class ErrorResponse(BaseModel):
-    success: bool = False
-    message: str
-    error: ErrorDetails
-    timestamp: str
-