@aj-archipelago/cortex 1.3.67 → 1.4.0

package/helper-apps/cortex-doc-to-pdf/examples/package-lock.json

@@ -0,0 +1,297 @@
+{
+    "name": "doc-to-pdf-client-examples",
+    "version": "1.0.0",
+    "lockfileVersion": 3,
+    "requires": true,
+    "packages": {
+        "": {
+            "name": "doc-to-pdf-client-examples",
+            "version": "1.0.0",
+            "license": "ISC",
+            "dependencies": {
+                "axios": "^1.6.0",
+                "form-data": "^4.0.0"
+            },
+            "devDependencies": {}
+        },
+        "node_modules/asynckit": {
+            "version": "0.4.0",
+            "resolved": "https://registry.npmjs.org/asynckit/-/asynckit-0.4.0.tgz",
+            "integrity": "sha512-Oei9OH4tRh0YqU3GxhX79dM/mwVgvbZJaSNaRk+bshkj0S5cfHcgYakreBjrHwatXKbz+IoIdYLxrKim2MjW0Q==",
+            "license": "MIT"
+        },
+        "node_modules/axios": {
+            "version": "1.12.2",
+            "resolved": "https://registry.npmjs.org/axios/-/axios-1.12.2.tgz",
+            "integrity": "sha512-vMJzPewAlRyOgxV2dU0Cuz2O8zzzx9VYtbJOaBgXFeLc4IV/Eg50n4LowmehOOR61S8ZMpc2K5Sa7g6A4jfkUw==",
+            "license": "MIT",
+            "dependencies": {
+                "follow-redirects": "^1.15.6",
+                "form-data": "^4.0.4",
+                "proxy-from-env": "^1.1.0"
+            }
+        },
+        "node_modules/call-bind-apply-helpers": {
+            "version": "1.0.2",
+            "resolved": "https://registry.npmjs.org/call-bind-apply-helpers/-/call-bind-apply-helpers-1.0.2.tgz",
+            "integrity": "sha512-Sp1ablJ0ivDkSzjcaJdxEunN5/XvksFJ2sMBFfq6x0ryhQV/2b/KwFe21cMpmHtPOSij8K99/wSfoEuTObmuMQ==",
+            "license": "MIT",
+            "dependencies": {
+                "es-errors": "^1.3.0",
+                "function-bind": "^1.1.2"
+            },
+            "engines": {
+                "node": ">= 0.4"
+            }
+        },
+        "node_modules/combined-stream": {
+            "version": "1.0.8",
+            "resolved": "https://registry.npmjs.org/combined-stream/-/combined-stream-1.0.8.tgz",
+            "integrity": "sha512-FQN4MRfuJeHf7cBbBMJFXhKSDq+2kAArBlmRBvcvFE5BB1HZKXtSFASDhdlz9zOYwxh8lDdnvmMOe/+5cdoEdg==",
+            "license": "MIT",
+            "dependencies": {
+                "delayed-stream": "~1.0.0"
+            },
+            "engines": {
+                "node": ">= 0.8"
+            }
+        },
+        "node_modules/delayed-stream": {
+            "version": "1.0.0",
+            "resolved": "https://registry.npmjs.org/delayed-stream/-/delayed-stream-1.0.0.tgz",
+            "integrity": "sha512-ZySD7Nf91aLB0RxL4KGrKHBXl7Eds1DAmEdcoVawXnLD7SDhpNgtuII2aAkg7a7QS41jxPSZ17p4VdGnMHk3MQ==",
+            "license": "MIT",
+            "engines": {
+                "node": ">=0.4.0"
+            }
+        },
+        "node_modules/dunder-proto": {
+            "version": "1.0.1",
+            "resolved": "https://registry.npmjs.org/dunder-proto/-/dunder-proto-1.0.1.tgz",
+            "integrity": "sha512-KIN/nDJBQRcXw0MLVhZE9iQHmG68qAVIBg9CqmUYjmQIhgij9U5MFvrqkUL5FbtyyzZuOeOt0zdeRe4UY7ct+A==",
+            "license": "MIT",
+            "dependencies": {
+                "call-bind-apply-helpers": "^1.0.1",
+                "es-errors": "^1.3.0",
+                "gopd": "^1.2.0"
+            },
+            "engines": {
+                "node": ">= 0.4"
+            }
+        },
+        "node_modules/es-define-property": {
+            "version": "1.0.1",
+            "resolved": "https://registry.npmjs.org/es-define-property/-/es-define-property-1.0.1.tgz",
+            "integrity": "sha512-e3nRfgfUZ4rNGL232gUgX06QNyyez04KdjFrF+LTRoOXmrOgFKDg4BCdsjW8EnT69eqdYGmRpJwiPVYNrCaW3g==",
+            "license": "MIT",
+            "engines": {
+                "node": ">= 0.4"
+            }
+        },
+        "node_modules/es-errors": {
+            "version": "1.3.0",
+            "resolved": "https://registry.npmjs.org/es-errors/-/es-errors-1.3.0.tgz",
+            "integrity": "sha512-Zf5H2Kxt2xjTvbJvP2ZWLEICxA6j+hAmMzIlypy4xcBg1vKVnx89Wy0GbS+kf5cwCVFFzdCFh2XSCFNULS6csw==",
+            "license": "MIT",
+            "engines": {
+                "node": ">= 0.4"
+            }
+        },
+        "node_modules/es-object-atoms": {
+            "version": "1.1.1",
+            "resolved": "https://registry.npmjs.org/es-object-atoms/-/es-object-atoms-1.1.1.tgz",
+            "integrity": "sha512-FGgH2h8zKNim9ljj7dankFPcICIK9Cp5bm+c2gQSYePhpaG5+esrLODihIorn+Pe6FGJzWhXQotPv73jTaldXA==",
+            "license": "MIT",
+            "dependencies": {
+                "es-errors": "^1.3.0"
+            },
+            "engines": {
+                "node": ">= 0.4"
+            }
+        },
+        "node_modules/es-set-tostringtag": {
+            "version": "2.1.0",
+            "resolved": "https://registry.npmjs.org/es-set-tostringtag/-/es-set-tostringtag-2.1.0.tgz",
+            "integrity": "sha512-j6vWzfrGVfyXxge+O0x5sh6cvxAog0a/4Rdd2K36zCMV5eJ+/+tOAngRO8cODMNWbVRdVlmGZQL2YS3yR8bIUA==",
+            "license": "MIT",
+            "dependencies": {
+                "es-errors": "^1.3.0",
+                "get-intrinsic": "^1.2.6",
+                "has-tostringtag": "^1.0.2",
+                "hasown": "^2.0.2"
+            },
+            "engines": {
+                "node": ">= 0.4"
+            }
+        },
+        "node_modules/follow-redirects": {
+            "version": "1.15.11",
+            "resolved": "https://registry.npmjs.org/follow-redirects/-/follow-redirects-1.15.11.tgz",
+            "integrity": "sha512-deG2P0JfjrTxl50XGCDyfI97ZGVCxIpfKYmfyrQ54n5FO/0gfIES8C/Psl6kWVDolizcaaxZJnTS0QSMxvnsBQ==",
+            "funding": [
+                {
+                    "type": "individual",
+                    "url": "https://github.com/sponsors/RubenVerborgh"
+                }
+            ],
+            "license": "MIT",
+            "engines": {
+                "node": ">=4.0"
+            },
+            "peerDependenciesMeta": {
+                "debug": {
+                    "optional": true
+                }
+            }
+        },
+        "node_modules/form-data": {
+            "version": "4.0.4",
+            "resolved": "https://registry.npmjs.org/form-data/-/form-data-4.0.4.tgz",
+            "integrity": "sha512-KrGhL9Q4zjj0kiUt5OO4Mr/A/jlI2jDYs5eHBpYHPcBEVSiipAvn2Ko2HnPe20rmcuuvMHNdZFp+4IlGTMF0Ow==",
+            "license": "MIT",
+            "dependencies": {
+                "asynckit": "^0.4.0",
+                "combined-stream": "^1.0.8",
+                "es-set-tostringtag": "^2.1.0",
+                "hasown": "^2.0.2",
+                "mime-types": "^2.1.12"
+            },
+            "engines": {
+                "node": ">= 6"
+            }
+        },
+        "node_modules/function-bind": {
+            "version": "1.1.2",
+            "resolved": "https://registry.npmjs.org/function-bind/-/function-bind-1.1.2.tgz",
+            "integrity": "sha512-7XHNxH7qX9xG5mIwxkhumTox/MIRNcOgDrxWsMt2pAr23WHp6MrRlN7FBSFpCpr+oVO0F744iUgR82nJMfG2SA==",
+            "license": "MIT",
+            "funding": {
+                "url": "https://github.com/sponsors/ljharb"
+            }
+        },
+        "node_modules/get-intrinsic": {
+            "version": "1.3.0",
+            "resolved": "https://registry.npmjs.org/get-intrinsic/-/get-intrinsic-1.3.0.tgz",
+            "integrity": "sha512-9fSjSaos/fRIVIp+xSJlE6lfwhES7LNtKaCBIamHsjr2na1BiABJPo0mOjjz8GJDURarmCPGqaiVg5mfjb98CQ==",
+            "license": "MIT",
+            "dependencies": {
+                "call-bind-apply-helpers": "^1.0.2",
+                "es-define-property": "^1.0.1",
+                "es-errors": "^1.3.0",
+                "es-object-atoms": "^1.1.1",
+                "function-bind": "^1.1.2",
+                "get-proto": "^1.0.1",
+                "gopd": "^1.2.0",
+                "has-symbols": "^1.1.0",
+                "hasown": "^2.0.2",
+                "math-intrinsics": "^1.1.0"
+            },
+            "engines": {
+                "node": ">= 0.4"
+            },
+            "funding": {
+                "url": "https://github.com/sponsors/ljharb"
+            }
+        },
+        "node_modules/get-proto": {
+            "version": "1.0.1",
+            "resolved": "https://registry.npmjs.org/get-proto/-/get-proto-1.0.1.tgz",
+            "integrity": "sha512-sTSfBjoXBp89JvIKIefqw7U2CCebsc74kiY6awiGogKtoSGbgjYE/G/+l9sF3MWFPNc9IcoOC4ODfKHfxFmp0g==",
+            "license": "MIT",
+            "dependencies": {
+                "dunder-proto": "^1.0.1",
+                "es-object-atoms": "^1.0.0"
+            },
+            "engines": {
+                "node": ">= 0.4"
+            }
+        },
+        "node_modules/gopd": {
+            "version": "1.2.0",
+            "resolved": "https://registry.npmjs.org/gopd/-/gopd-1.2.0.tgz",
+            "integrity": "sha512-ZUKRh6/kUFoAiTAtTYPZJ3hw9wNxx+BIBOijnlG9PnrJsCcSjs1wyyD6vJpaYtgnzDrKYRSqf3OO6Rfa93xsRg==",
+            "license": "MIT",
+            "engines": {
+                "node": ">= 0.4"
+            },
+            "funding": {
+                "url": "https://github.com/sponsors/ljharb"
+            }
+        },
+        "node_modules/has-symbols": {
+            "version": "1.1.0",
+            "resolved": "https://registry.npmjs.org/has-symbols/-/has-symbols-1.1.0.tgz",
+            "integrity": "sha512-1cDNdwJ2Jaohmb3sg4OmKaMBwuC48sYni5HUw2DvsC8LjGTLK9h+eb1X6RyuOHe4hT0ULCW68iomhjUoKUqlPQ==",
+            "license": "MIT",
+            "engines": {
+                "node": ">= 0.4"
+            },
+            "funding": {
+                "url": "https://github.com/sponsors/ljharb"
+            }
+        },
+        "node_modules/has-tostringtag": {
+            "version": "1.0.2",
+            "resolved": "https://registry.npmjs.org/has-tostringtag/-/has-tostringtag-1.0.2.tgz",
+            "integrity": "sha512-NqADB8VjPFLM2V0VvHUewwwsw0ZWBaIdgo+ieHtK3hasLz4qeCRjYcqfB6AQrBggRKppKF8L52/VqdVsO47Dlw==",
+            "license": "MIT",
+            "dependencies": {
+                "has-symbols": "^1.0.3"
+            },
+            "engines": {
+                "node": ">= 0.4"
+            },
+            "funding": {
+                "url": "https://github.com/sponsors/ljharb"
+            }
+        },
+        "node_modules/hasown": {
+            "version": "2.0.2",
+            "resolved": "https://registry.npmjs.org/hasown/-/hasown-2.0.2.tgz",
+            "integrity": "sha512-0hJU9SCPvmMzIBdZFqNPXWa6dqh7WdH0cII9y+CyS8rG3nL48Bclra9HmKhVVUHyPWNH5Y7xDwAB7bfgSjkUMQ==",
+            "license": "MIT",
+            "dependencies": {
+                "function-bind": "^1.1.2"
+            },
+            "engines": {
+                "node": ">= 0.4"
+            }
+        },
+        "node_modules/math-intrinsics": {
+            "version": "1.1.0",
+            "resolved": "https://registry.npmjs.org/math-intrinsics/-/math-intrinsics-1.1.0.tgz",
+            "integrity": "sha512-/IXtbwEk5HTPyEwyKX6hGkYXxM9nbj64B+ilVJnC/R6B0pH5G4V3b0pVbL7DBj4tkhBAppbQUlf6F6Xl9LHu1g==",
+            "license": "MIT",
+            "engines": {
+                "node": ">= 0.4"
+            }
+        },
+        "node_modules/mime-db": {
+            "version": "1.52.0",
+            "resolved": "https://registry.npmjs.org/mime-db/-/mime-db-1.52.0.tgz",
+            "integrity": "sha512-sPU4uV7dYlvtWJxwwxHD0PuihVNiE7TyAbQ5SWxDCB9mUYvOgroQOwYQQOKPJ8CIbE+1ETVlOoK1UC2nU3gYvg==",
+            "license": "MIT",
+            "engines": {
+                "node": ">= 0.6"
+            }
+        },
+        "node_modules/mime-types": {
+            "version": "2.1.35",
+            "resolved": "https://registry.npmjs.org/mime-types/-/mime-types-2.1.35.tgz",
+            "integrity": "sha512-ZDY+bPm5zTTF+YpCrAU9nK0UgICYPT0QtT1NZWFv4s++TNkcgVaT0g6+4R2uI4MjQjzysHB1zxuWL50hzaeXiw==",
+            "license": "MIT",
+            "dependencies": {
+                "mime-db": "1.52.0"
+            },
+            "engines": {
+                "node": ">= 0.6"
+            }
+        },
+        "node_modules/proxy-from-env": {
+            "version": "1.1.0",
+            "resolved": "https://registry.npmjs.org/proxy-from-env/-/proxy-from-env-1.1.0.tgz",
+            "integrity": "sha512-D+zkORCbA9f1tdWRK0RaCR3GPv50cMxcrz4X8k5LTSUD1Dkw47mKJEZQNunItRTkWwgtaUSo1RVFRIG9ZXiFYg==",
+            "license": "MIT"
+        }
+    }
+}

package/helper-apps/cortex-doc-to-pdf/examples/package.json

@@ -0,0 +1,23 @@
+{
+    "name": "doc-to-pdf-client-examples",
+    "version": "1.0.0",
+    "description": "Client examples for Document to PDF Converter service",
+    "main": "nodejs-client.js",
+    "scripts": {
+        "example": "node nodejs-client.js",
+        "test": "node nodejs-client.js"
+    },
+    "dependencies": {
+        "axios": "^1.6.0",
+        "form-data": "^4.0.0"
+    },
+    "devDependencies": {},
+    "keywords": [
+        "pdf",
+        "converter",
+        "document",
+        "streaming"
+    ],
+    "author": "",
+    "license": "ISC"
+}

package/helper-apps/cortex-doc-to-pdf/function_app.py

@@ -0,0 +1,85 @@
+"""Main application entry point for Azure Functions and standalone server."""
+
+import azure.functions as func
+import logging
+import asyncio
+from aiohttp import web
+import os
+from request_handlers import handle_azure_function_request, handle_aiohttp_request
+
+# Azure Functions app
+app = func.FunctionApp(http_auth_level=func.AuthLevel.FUNCTION)
+
+
+@app.route(route="convert")
+async def http_convert_trigger(req: func.HttpRequest) -> func.HttpResponse:
+    """
+    Azure Function HTTP trigger for document to PDF conversion.
+    
+    Note: For GET requests with URLs containing special characters (like Azure SAS tokens),
+    the URI should be URL-encoded, or use POST with JSON body instead.
+    """
+    return await handle_azure_function_request(req)
+
+
+# ============================================================================
+# Standalone aiohttp server for container deployment
+# ============================================================================
+
+async def main_server():
+    """Main function to run the standalone aiohttp server."""
+    logging.basicConfig(
+        level=logging.INFO,
+        format='%(asctime)s - %(levelname)s - %(message)s'
+    )
+    
+    port_str = os.environ.get("PORT", "8080")
+    try:
+        port = int(port_str)
+    except ValueError:
+        logging.warning(f"Invalid PORT environment variable '{port_str}'. Defaulting to 8080.")
+        port = 8080
+    
+    aiohttp_app = web.Application()
+    
+    # Conversion endpoints (both /convert and / root)
+    aiohttp_app.router.add_post('/convert', handle_aiohttp_request)
+    aiohttp_app.router.add_get('/convert', handle_aiohttp_request)
+    aiohttp_app.router.add_post('/', handle_aiohttp_request)  # Root path also works
+    
+    # Health check endpoint
+    async def health_check(request):
+        return web.json_response({"status": "healthy", "service": "doc-to-pdf-converter"})
+    
+    aiohttp_app.router.add_get('/health', health_check)
+    aiohttp_app.router.add_get('/', health_check)  # GET / returns health check
+
+    runner = web.AppRunner(aiohttp_app)
+    await runner.setup()
+    site = web.TCPSite(runner, '0.0.0.0', port)
+    await site.start()
+    
+    logging.info(f"🚀 Document to PDF Converter server started on http://0.0.0.0:{port}")
+    print(f"======== Running on http://0.0.0.0:{port} ========")
+    print(f"======== Convert: POST http://0.0.0.0:{port}/ or /convert ========")
+    print(f"======== Health: GET http://0.0.0.0:{port}/health ========")
+    print("(Press CTRL+C to quit)")
+    
+    try:
+        while True:
+            await asyncio.sleep(3600)
+    except KeyboardInterrupt:
+        logging.info("Server shutting down...")
+    finally:
+        await runner.cleanup()
+        logging.info("Server stopped.")
+
+
+if __name__ == "__main__":
+    """Run as standalone server when executed directly."""
+    try:
+        asyncio.run(main_server())
+    except KeyboardInterrupt:
+        logging.info("Application shut down by user.")
+    except Exception as e:
+        logging.critical(f"Application failed to start or crashed: {e}")

package/helper-apps/cortex-doc-to-pdf/host.json

@@ -0,0 +1,16 @@
+{
+    "version": "2.0",
+    "logging": {
+        "applicationInsights": {
+            "samplingSettings": {
+                "isEnabled": true,
+                "maxTelemetryItemsPerSecond": 20
+            }
+        }
+    },
+    "extensionBundle": {
+        "id": "Microsoft.Azure.Functions.ExtensionBundle",
+        "version": "[4.*, 5.0.0)"
+    },
+    "functionTimeout": "00:10:00"
+}

package/helper-apps/cortex-doc-to-pdf/request_handlers.py

@@ -0,0 +1,193 @@
+"""HTTP request handlers for both Azure Functions and standalone server."""
+
+import logging
+import json
+import urllib.parse
+from aiohttp import web
+import azure.functions as func
+from document_converter import convert_from_uri, convert_from_stream
+
+
+async def handle_azure_function_request(req: func.HttpRequest) -> func.HttpResponse:
+    """
+    Azure Function HTTP trigger handler.
+    
+    Supports GET and POST methods.
+    Accepts 'uri' parameter (query string or JSON body) or file upload.
+    Returns PDF as binary data with appropriate headers.
+    """
+    logging.info('Azure Function triggered')
+
+    # Get URI parameter from query string or request body
+    uri = req.params.get('uri')
+    if not uri:
+        try:
+            req_body = await req.get_json()
+            uri = req_body.get('uri')
+        except ValueError:
+            pass
+
+    if not uri:
+        return func.HttpResponse(
+            json.dumps({
+                "error": "Missing 'uri' parameter",
+                "message": "Please provide a 'uri' parameter with the document URL to convert. For URLs with special characters (like SAS tokens), use POST with JSON body or URL-encode the URI parameter."
+            }),
+            status_code=400,
+            mimetype="application/json"
+        )
+    
+    # URL decode if it looks encoded (contains %XX patterns)
+    if '%' in uri:
+        try:
+            uri = urllib.parse.unquote(uri)
+            logging.info(f"URL-decoded URI to: {uri[:100]}...")
+        except Exception as e:
+            logging.warning(f"Failed to URL-decode URI: {e}")
+
+    # Process the conversion
+    result = await convert_from_uri(uri)
+    
+    if result.get("success"):
+        # Return PDF as binary data
+        return func.HttpResponse(
+            body=result["data"],
+            status_code=200,
+            mimetype="application/pdf",
+            headers={
+                "Content-Disposition": f'attachment; filename="{result["filename"]}"',
+                "Content-Type": "application/pdf"
+            }
+        )
+    else:
+        # Return error as JSON
+        error_response = {k: v for k, v in result.items() if k != "success"}
+        return func.HttpResponse(
+            json.dumps(error_response),
+            status_code=400 if "Unsupported" in str(result.get("error")) or "download" in str(result.get("error")) else 500,
+            mimetype="application/json"
+        )
+
+
+async def handle_aiohttp_request(request: web.Request) -> web.Response:
+    """
+    aiohttp standalone server request handler.
+    
+    Supports file upload (multipart/form-data) and URI-based conversion.
+    Returns streaming PDF response to avoid RAM bloat.
+    """
+    logging.info(f'Request received. Content-Type: {request.content_type}')
+    
+    result = None
+    
+    # Check if this is a multipart file upload (streaming upload)
+    if request.content_type and 'multipart/form-data' in request.content_type:
+        logging.info("Processing multipart file upload")
+        try:
+            reader = await request.multipart()
+            file_data = None
+            filename = None
+            
+            # Stream the file data
+            async for part in reader:
+                if part.name == 'file':
+                    filename = part.filename or 'document'
+                    # Read file in chunks to avoid RAM bloat
+                    chunks = []
+                    chunk_count = 0
+                    while True:
+                        chunk = await part.read_chunk(8192)  # 8KB chunks
+                        if not chunk:
+                            break
+                        chunks.append(chunk)
+                        chunk_count += 1
+                    
+                    file_data = b''.join(chunks)
+                    logging.info(f"Received file: {filename}, size: {len(file_data)} bytes ({chunk_count} chunks)")
+                    break
+            
+            if not file_data:
+                return web.json_response(
+                    {"error": "No file provided in multipart upload"},
+                    status=400
+                )
+            
+            # Convert from uploaded file
+            result = await convert_from_stream(file_data, filename)
+            
+        except Exception as e:
+            logging.error(f"Error processing multipart upload: {e}", exc_info=True)
+            return web.json_response(
+                {"error": "Failed to process file upload", "details": str(e)},
+                status=400
+            )
+    else:
+        # Try URI-based conversion
+        uri = None
+        
+        # Try to get URI from query parameters
+        uri = request.query.get('uri')
+        if uri:
+            logging.info(f"Found URI in query parameters: {uri[:100]}...")
+            # URL decode if it looks encoded
+            if '%' in uri:
+                try:
+                    decoded_uri = urllib.parse.unquote(uri)
+                    logging.info(f"URL-decoded URI to: {decoded_uri[:100]}...")
+                    uri = decoded_uri
+                except Exception as e:
+                    logging.warning(f"Failed to URL-decode URI: {e}")
+        else:
+            # Try to get from JSON body
+            logging.info("URI not found in query parameters. Checking JSON body.")
+            try:
+                req_body = await request.json()
+                if req_body:
+                    uri = req_body.get('uri')
+                    if uri:
+                        logging.info(f"Found URI in JSON body: {uri[:100]}...")
+            except json.JSONDecodeError:
+                logging.info("Request body is not valid JSON.")
+            except Exception as e:
+                logging.warning(f"Error reading JSON body: {e}")
+
+        if not uri:
+            logging.warning("Neither file upload nor URI provided")
+            return web.json_response(
+                {
+                    "error": "Please provide either a file upload or a 'uri' parameter",
+                    "supported_methods": {
+                        "file_upload": "POST with multipart/form-data and 'file' field",
+                        "uri": "POST with JSON body containing 'uri' field, or GET with 'uri' query parameter"
+                    }
+                },
+                status=400
+            )
+
+        # Validate URI format
+        if not uri.startswith(('http://', 'https://')):
+            logging.error(f"Invalid URI format: {uri}")
+            return web.json_response(
+                {"error": "Invalid URI format. Must start with http:// or https://"},
+                status=400
+            )
+
+        # Process the conversion from URI
+        result = await convert_from_uri(uri)
+    
+    # Return streaming response
+    if result.get("success"):
+        # Stream PDF response to avoid loading entire file in RAM
+        return web.Response(
+            body=result["data"],
+            status=200,
+            content_type="application/pdf",
+            headers={
+                "Content-Disposition": f'attachment; filename="{result["filename"]}"'
+            }
+        )
+    else:
+        # Return error as JSON
+        error_response = {k: v for k, v in result.items() if k != "success"}
+        status_code = 400 if "Unsupported" in str(result.get("error")) or "download" in str(result.get("error")) else 500
+        return web.json_response(error_response, status=status_code)

package/helper-apps/cortex-doc-to-pdf/requirements.txt

@@ -0,0 +1,3 @@
+azure-functions==1.18.0
+aiohttp==3.9.1
+PyPDF2==3.0.1

package/helper-apps/cortex-doc-to-pdf/tests/run_tests.sh

@@ -0,0 +1,26 @@
+#!/bin/bash
+# Run end-to-end conversion tests
+
+echo "🧪 Running Document to PDF Conversion Tests"
+echo "============================================="
+echo ""
+
+# Check if LibreOffice is installed
+if ! command -v soffice &> /dev/null && ! command -v libreoffice &> /dev/null; then
+    echo "❌ Error: LibreOffice not found!"
+    echo "Please install LibreOffice:"
+    echo "  - macOS: brew install --cask libreoffice"
+    echo "  - Ubuntu/Debian: sudo apt-get install libreoffice"
+    exit 1
+fi
+
+# Check if Python requirements are installed
+if ! python3 -c "import PyPDF2" 2>/dev/null; then
+    echo "📦 Installing Python dependencies..."
+    pip3 install -r requirements.txt
+fi
+
+# Run tests
+python3 test_conversion.py
+
+exit $?