Update app.py

app.py

@@ -1,17 +1,23 @@
 import uvicorn
 from fastapi.staticfiles import StaticFiles
 import hashlib
+from enum import Enum
 from fastapi import FastAPI, Header, Query, Depends, HTTPException
+from PIL import Image
+import io
+import fitz  # PyMuPDF for PDF handling
+import logging
 from pymongo import MongoClient
+
 import boto3
 import openai
 import os
-import traceback  
+import traceback  # For detailed traceback of errors
+import re
 import json
 from dotenv import load_dotenv
 import base64
 from bson.objectid import ObjectId
-import logging
 
 db_client = None
 load_dotenv()
@@ -20,26 +26,26 @@ load_dotenv()
 logging.basicConfig(level=logging.INFO)
 logger = logging.getLogger(__name__)
 
-# Validate and Load Environment Variables
+# MongoDB Configuration
 MONGODB_URI = os.getenv("MONGODB_URI")
 DATABASE_NAME = os.getenv("DATABASE_NAME")
 COLLECTION_NAME = os.getenv("COLLECTION_NAME", "invoice_collection")
-AWS_ACCESS_KEY = os.getenv("AWS_ACCESS_KEY")
-AWS_SECRET_KEY = os.getenv("AWS_SECRET_KEY")
-S3_BUCKET_NAME = os.getenv("S3_BUCKET_NAME")
-OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
-API_KEY = os.getenv("API_KEY")
 
-if not all([MONGODB_URI, DATABASE_NAME, AWS_ACCESS_KEY, AWS_SECRET_KEY, S3_BUCKET_NAME, OPENAI_API_KEY, API_KEY]):
-    raise ValueError("One or more required environment variables are missing.")
+# use_gpu = False
+# output_dir = 'output'
+
+# Check if environment variables are set
+if not MONGODB_URI:
+    raise ValueError("MONGODB_URL is not set. Please add it to Hugging Face secrets.")
 
 # Initialize MongoDB Connection
 db_client = MongoClient(MONGODB_URI)
 db = db_client[DATABASE_NAME]
 invoice_collection = db[COLLECTION_NAME]
-openai.api_key = OPENAI_API_KEY
 
 app = FastAPI(docs_url='/')
+use_gpu = False
+output_dir = 'output'
 
 @app.on_event("startup")
 def startup_db():
@@ -49,6 +55,15 @@ def startup_db():
     except Exception as e:
         logger.error(f"MongoDB connection failed: {str(e)}")
 
+# AWS S3 Configuration
+API_KEY = os.getenv("API_KEY")
+AWS_ACCESS_KEY = os.getenv("AWS_ACCESS_KEY")
+AWS_SECRET_KEY = os.getenv("AWS_SECRET_KEY")
+S3_BUCKET_NAME = os.getenv("S3_BUCKET_NAME")
+
+# OpenAI Configuration
+openai.api_key = os.getenv("OPENAI_API_KEY")
+
 # S3 Client
 s3_client = boto3.client(
     's3',
@@ -56,13 +71,164 @@ s3_client = boto3.client(
     aws_secret_access_key=AWS_SECRET_KEY
 )
 
+# Function to fetch file from S3
 def fetch_file_from_s3(file_key):
     try:
         response = s3_client.get_object(Bucket=S3_BUCKET_NAME, Key=file_key)
-        return response['Body'].read(), response['ContentType']
+        content_type = response['ContentType']  # Retrieve MIME type
+        file_data = response['Body'].read()
+        return file_data, content_type  # Return file data as BytesIO
+    except Exception as e:
+        raise Exception(f"Failed to fetch file from S3: {str(e)}")
+
+# Function to summarize text using OpenAI GPT
+def extract_invoice_data(file_data, content_type):
+    system_prompt = "You are an expert in document data extraction."
+
+    # Convert file to Base64
+    base64_encoded = base64.b64encode(file_data).decode('utf-8')
+
+    # Determine the correct MIME type for OpenAI
+    if content_type.startswith("image/"):
+        mime_type = content_type  # e.g., image/png, image/jpeg
+    elif content_type == "application/pdf":
+        mime_type = "application/pdf"
+    else:
+        raise ValueError(f"Unsupported content type: {content_type}")
+
+    try:
+        response = openai.ChatCompletion.create(
+            model="gpt-4o-mini",
+            messages=[
+                {"role": "system", "content": system_prompt},
+                {
+                    "role": "user",
+                    "content": [
+                        {
+                            "type": "image_url",
+                            "image_url": {
+                                "url": f"data:{mime_type};base64,{base64_encoded}"
+                            }
+                        }
+                    ]
+                }
+            ],
+            response_format={
+                "type": "json_schema",
+                "json_schema": {
+                    "name": "invoice",
+                    "strict": True,
+                    "schema": {
+                        "type": "object",
+                        "title": "Invoice Information Extractor",
+                        "$schema": "http://json-schema.org/draft-07/schema#",
+                        "properties": {
+                            "LineItems": {
+                                "type": "array",
+                                "items": {
+                                    "type": "object",
+                                    "required": [
+                                        "ProductCode",
+                                        "Description",
+                                        "Amount"
+                                    ],
+                                    "properties": {
+                                        "ProductCode": {
+                                            "type": "string",
+                                            "title": "Product Code",
+                                            "description": "The code of the product"
+                                        },
+                                        "Description": {
+                                            "type": "string",
+                                            "title": "Description",
+                                            "description": "Description of the product"
+                                        },
+                                        "Amount": {
+                                            "type": "number",
+                                            "title": "Amount",
+                                            "description": "The amount of the product"
+                                        }
+                                    },
+                                    "additionalProperties": False
+                                },
+                                "title": "Line Items",
+                                "description": "List of line items on the invoice"
+                            },
+                            "TaxAmount": {
+                                "type": "number",
+                                "title": "Tax Amount",
+                                "description": "The tax amount on the invoice"
+                            },
+                            "VendorGST": {
+                                "type": "string",
+                                "title": "Vendor GST",
+                                "description": "The GST number of the vendor"
+                            },
+                            "VendorName": {
+                                "type": "string",
+                                "title": "Vendor Name",
+                                "description": "The name of the vendor"
+                            },
+                            "InvoiceDate": {
+                                "type": "string",
+                                "title": "Invoice Date",
+                                "description": "The date of the invoice (format: dd-MMM-yyyy)"
+                            },
+                            "TotalAmount": {
+                                "type": "number",
+                                "title": "Total Amount",
+                                "description": "The total amount on the invoice"
+                            },
+                            "InvoiceNumber": {
+                                "type": "string",
+                                "title": "Invoice Number",
+                                "description": "The number of the invoice"
+                            },
+                            "VendorAddress": {
+                                "type": "string",
+                                "title": "Vendor Address",
+                                "description": "The address of the vendor"
+                            },
+                            "InvoiceCurrency": {
+                                "type": "string",
+                                "title": "Invoice Currency",
+                                "description": "The currency used in the invoice (e.g., USD, INR, AUD)"
+                            }
+                        },
+                        "required": [
+                            "LineItems",
+                            "TaxAmount",
+                            "VendorGST",
+                            "VendorName",
+                            "InvoiceDate",
+                            "TotalAmount",
+                            "InvoiceNumber",
+                            "VendorAddress",
+                            "InvoiceCurrency"
+                        ],
+                        "additionalProperties": False,
+                        "description": "Schema for extracting structured invoice data"
+                    }
+                }
+            },
+            temperature=0.5,
+            max_tokens=16384
+        )
+
+        # Clean and parse JSON output
+        content = response.choices[0].message.content.strip()
+        cleaned_content = content.strip().strip('```json').strip('```')
+
+        try:
+            parsed_content = json.loads(cleaned_content)
+            return parsed_content
+        except json.JSONDecodeError as e:
+            logger.error(f"JSON Parse Error: {e}")
+            return None
+
     except Exception as e:
-        logger.error(f"Failed to fetch file from S3: {e}")
-        raise HTTPException(status_code=500, detail=f"S3 fetch error: {str(e)}")
+        logger.error(f"Error in data extraction: {e}")
+        return {"error": str(e)}
 
 def extract_text_from_s3(file_key, content_type):
     return "Extracted text from file", 1  # Placeholder for real extraction logic
@@ -73,42 +239,88 @@ def convert_to_base64(file_key):
 def generate_summary(extracted_text):
     return "Summarized text"  # Placeholder
 
+def get_content_type_from_s3(file_key):
+    """Fetch the content type (MIME type) of a file stored in S3."""
+    try:
+        response = s3_client.head_object(Bucket=S3_BUCKET_NAME, Key=file_key)
+        return response.get('ContentType', 'application/octet-stream')  # Default to binary if not found
+    except Exception as e:
+        raise Exception(f"Failed to get content type from S3: {str(e)}")
+
+
+# Dependency to check API Key
 def verify_api_key(api_key: str = Header(...)):
     if api_key != API_KEY:
         raise HTTPException(status_code=401, detail="Invalid API Key")
 
+@app.get("/")
+def read_root():
+    return {"message": "Welcome to the Invoice Summarization API!"}
+
 @app.get("/ocr/extraction")
 def extract_text_from_file(
     api_key: str = Depends(verify_api_key), 
-    file_key: str = Query(..., description="S3 file key"),
-    document_type: str = Query(..., description="Document type"),
+    file_key: str = Query(..., description="S3 file key for the file"),
+    document_type: str = Query(..., description="Type of document"),
     entity_ref_key: str = Query(..., description="Entity Reference Key")
 ):
+    """Extract text from a PDF or Image stored in S3 and process it based on document size."""
     try:
         existing_document = invoice_collection.find_one({"entityrefkey": entity_ref_key})
+
         if existing_document:
             existing_document["_id"] = str(existing_document["_id"])
-            return {"message": "Document Retrieved from MongoDB.", "document": existing_document}
-        
-        file_data, content_type = fetch_file_from_s3(file_key)
+            return {
+                "message": "Document Retrieved from MongoDB.",
+                "document": existing_document
+            }
+            
+        # Retrieve file from S3 and determine content type (Ensure this step is implemented)
+        content_type = get_content_type_from_s3(file_key)  # Implement this function
+
+        # Extract text (Ensure Extraction function is implemented)
         extracted_text, num_pages = extract_text_from_s3(file_key, content_type)
+
+        # Define values for small/large files
         base64DataResp = None
         summary = None
         if num_pages <= 2:
-            base64DataResp = convert_to_base64(file_key)
-            summary = generate_summary(extracted_text)
-        
+            base64DataResp = convert_to_base64(file_key)  # Implement this function
+            summary = generate_summary(extracted_text)  # Implement this function
+
+        # Store extracted data in MongoDB
         document = {
             "file_key": file_key,
             "file_type": content_type,
             "document_type": document_type,
             "entityrefkey": entity_ref_key,
             "num_pages": num_pages,
-            "base64DataResp": base64DataResp,
-            "extracted_text": extracted_text if num_pages <= 2 else "Skipped",
-            "summary": summary,
+            "base64DataResp": base64DataResp,  # Only for small files
+            "extracted_text": extracted_text,
+            "summary": summary,  # Only for small files
         }
+
         inserted_doc = invoice_collection.insert_one(document)
-        return {"message": "Document stored in MongoDB", "document_id": str(inserted_doc.inserted_id)}
+        document_id = str(inserted_doc.inserted_id)
+
+        return {
+            "message": "Document successfully stored in MongoDB",
+            "document_id": document_id,
+            "file_key": file_key,
+            "num_pages": num_pages,
+            "summary": summary if summary else "Skipped for large documents"
+        }
+
     except Exception as e:
-        return {"error": {"type": type(e).__name__, "message": str(e), "traceback": traceback.format_exc()}}
+        error_details = {
+            "error_type": type(e).__name__,
+            "error_message": str(e),
+            "traceback": traceback.format_exc()
+        }
+        return {"error": error_details}
+     
+# Serve the output folder as static files
+app.mount("/output", StaticFiles(directory="output", follow_symlink=True, html=True), name="output")
+
+if __name__ == '__main__':
+    uvicorn.run(app=app)