Update app.py

app.py

@@ -5,6 +5,7 @@ import cv2
 import boto3
 import os
 import json
+import requests
 from fastapi import FastAPI, UploadFile, File, HTTPException
 from rapidocr_onnxruntime import RapidOCR
 from openai import OpenAI
@@ -24,6 +25,9 @@ if not OPENAI_API_KEY:
 
 client = OpenAI(api_key=OPENAI_API_KEY)
 
+# Category API URL
+CATEGORY_API_URL = "https://logicgoinfotechspaces-auto-expense-categorization.hf.space/api/labels"
+
 # S3 client
 s3 = boto3.client(
     "s3",
@@ -82,14 +86,12 @@ async def generate(image_id: str):
     if not result:
         raise HTTPException(status_code=500, detail="OCR returned empty result")
 
-    # Full extracted text
     full_text = "\n".join([text for _, text, _ in result])
 
     # -------- CONFIDENCE SCORE --------
     confidences = [conf for _, _, conf in result if isinstance(conf, (int, float))]
     avg_confidence = sum(confidences) / len(confidences) if confidences else 0
 
-    # If confidence is low → return early
     if avg_confidence < 0.70:
         return {
             "image_id": image_id,
@@ -98,7 +100,7 @@ async def generate(image_id: str):
             "message": "Upload image with more clarity or enter manually."
         }
 
-    # -------- NEW FUNCTION CALLING FORMAT --------
+    # -------- JSON SCHEMA FOR GPT --------
     schema = {
         "name": "extract_expense_details",
         "schema": {
@@ -118,7 +120,7 @@ async def generate(image_id: str):
         }
     }
 
-    # -------- AI PROMPT --------
+    # -------- PROMPT --------
     prompt = f"""
 You are an expense extraction AI.
 
@@ -144,29 +146,21 @@ Extract expense details from the OCR text below:
 Always generate notes EXACTLY in this format:
 "Spent <total_amount> on <label> on <date>."
 
-- If <total_amount> is unknown → use "unknown"
-- If <label> is unknown → use "unknown"
-- If <date> is unknown → use "unknown"
-
 ### Required Output:
 Return structured JSON (via schema) with:
-- total_amount     (if missing → "unknown")
-- label            (if missing → "unknown")
-- date             (if missing → "unknown")
-- time             (if missing → "unknown")
-- payment_type     (if missing → "unknown")
-- notes            (follow the provided format)
-
-Fill **every** field ONLY with information found in the extracted text or "unknown".
+- total_amount
+- label
+- date
+- time
+- payment_type
+- notes
 """
 
+    # -------- CALL GPT --------
     try:
         response = client.chat.completions.create(
             model="gpt-4o-mini",
-            response_format={
-                "type": "json_schema",
-                "json_schema": schema
-            },
+            response_format={"type": "json_schema", "json_schema": schema},
             messages=[
                 {"role": "system", "content": "You are an expert in receipt parsing."},
                 {"role": "user", "content": prompt}
@@ -179,6 +173,26 @@ Fill **every** field ONLY with information found in the extracted text or "unkno
     except Exception as e:
         raise HTTPException(status_code=500, detail=f"OpenAI Error: {str(e)}")
 
+    # -------- CATEGORY API CALL --------
+    extracted_label = parsed.get("label", "unknown")
+
+    try:
+        cat_response = requests.post(
+            CATEGORY_API_URL,
+            json={"label": extracted_label},
+            timeout=10
+        )
+
+        if cat_response.status_code == 200:
+            cat_data = cat_response.json()
+            parsed["category"] = cat_data.get("category", "unknown")
+        else:
+            parsed["category"] = "unknown"
+
+    except Exception:
+        parsed["category"] = "unknown"
+
+    # -------- FINAL RESPONSE --------
     return {
         "image_id": image_id,
         "raw_text": full_text,