[NOTICKET]: add comments to flag that file type lists must stay in sync

src/api/v1/document.py

@@ -24,20 +24,25 @@ class DocumentResponse(BaseModel):
     created_at: str
  
  
-@router.get("/documents/doctypes")
+# NOTE: Keep in sync with SUPPORTED_FILE_TYPES in src/pipeline/document_pipeline/document_pipeline.py
+_DOC_TYPES = [
+    {"doc_type": "pdf", "max_size": 10, "status": "active", "message": None},
+    {"doc_type": "docx", "max_size": 10, "status": "active", "message": None},
+    {"doc_type": "txt", "max_size": 10, "status": "active", "message": None},
+    {"doc_type": "csv", "max_size": 10, "status": "active", "message": None},
+    {"doc_type": "xlsx", "max_size": 10, "status": "active", "message": None},
+]
+
+
+@router.get(
+    "/documents/doctypes",
+    summary="List supported document types",
+    response_description="All document types supported by DataEyond with their size limits and status.",
+)
 @log_execution(logger)
 async def get_document_types():
-    """List supported document types with max file size and status."""
-    return {
-        "status": "success",
-        "data": [
-            {"doc_type": "pdf", "max_size": 10, "status": "active", "message": None},
-            {"doc_type": "docx", "max_size": 10, "status": "active", "message": None},
-            {"doc_type": "txt", "max_size": 10, "status": "active", "message": None},
-            {"doc_type": "csv", "max_size": 10, "status": "active", "message": None},
-            {"doc_type": "xlsx", "max_size": 10, "status": "active", "message": None},
-        ]
-    }
+    """Return every document type DataEyond can process, with max file size and active/inactive status."""
+    return {"status": "success", "data": _DOC_TYPES}
 
 
 @router.get("/documents/{user_id}", response_model=List[DocumentResponse])

src/pipeline/document_pipeline/document_pipeline.py

@@ -10,7 +10,9 @@ from src.storage.az_blob.az_blob import blob_storage
 
 logger = get_logger("document_pipeline")
 
+# NOTE: Keep in sync with _DOC_TYPES in src/api/v1/document.py
 SUPPORTED_FILE_TYPES = ["pdf", "docx", "txt", "csv", "xlsx"]
+MAX_FILE_SIZE_BYTES = 10 * 1024 * 1024  # 10 MB
 
 
 class DocumentPipeline:
@@ -21,7 +23,6 @@ class DocumentPipeline:
         content = await file.read()
         file_type = file.filename.split(".")[-1].lower() if "." in file.filename else "txt"
 
-        MAX_FILE_SIZE_BYTES = 10 * 1024 * 1024  # 10 MB
         if len(content) > MAX_FILE_SIZE_BYTES:
             raise HTTPException(
                 status_code=400,