Update summarizer_service.py

summarizer_service.py

@@ -1,10 +1,12 @@
 from transformers import T5ForConditionalGeneration, T5Tokenizer
 from flask import Flask, request, jsonify
+from dotenv import load_dotenv
 import pytesseract
 from pdf2image import convert_from_path
 import docx
+import pandas as pd
+from PIL import Image
 import os
-from dotenv import load_dotenv
 
 load_dotenv()
 app = Flask(__name__)
@@ -14,14 +16,27 @@ model = T5ForConditionalGeneration.from_pretrained(MODEL_PATH)
 tokenizer = T5Tokenizer.from_pretrained(MODEL_PATH)
 
 def extract_text(file_path, file_type):
+    file_type = file_type.lower()
+
     if file_type == 'pdf':
         images = convert_from_path(file_path)
-        text = ''.join(pytesseract.image_to_string(image) for image in images)
+        text = ''.join(pytesseract.image_to_string(img) for img in images)
+
+    elif file_type in ['jpg', 'jpeg', 'png']:
+        image = Image.open(file_path)
+        text = pytesseract.image_to_string(image)
+
     elif file_type == 'docx':
         doc = docx.Document(file_path)
-        text = '\n'.join(p.text for p in doc.paragraphs)
+        text = '\n'.join([p.text for p in doc.paragraphs])
+
+    elif file_type in ['csv', 'xls', 'xlsx']:
+        df = pd.read_excel(file_path) if file_type in ['xls', 'xlsx'] else pd.read_csv(file_path)
+        text = df.to_string(index=False)
+
     else:
         raise ValueError('Unsupported file type')
+
     return text
 
 def summarize_contract(text, aspect=None):