Update app.py

app.py

@@ -1,26 +1,40 @@
 import gradio as gr
 from transformers import AutoModelForSequenceClassification, AutoTokenizer
+from PIL import Image
+import pytesseract  # Install using `pip install pytesseract` and ensure Tesseract is installed
 
 # Load your fine-tuned model and tokenizer
 model_name = "quadranttechnologies/Receipt_Image_Analyzer"
 model = AutoModelForSequenceClassification.from_pretrained(model_name)
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 
-# Define a prediction function
-def analyze_receipt(receipt_text):
-    inputs = tokenizer(receipt_text, return_tensors="pt", truncation=True, padding=True)
+# Define a function to preprocess the image and predict
+def analyze_receipt(image):
+    # Perform OCR to extract text from the image
+    extracted_text = pytesseract.image_to_string(image)
+    
+    # Tokenize the extracted text
+    inputs = tokenizer(extracted_text, return_tensors="pt", truncation=True, padding=True)
+    
+    # Get model predictions
     outputs = model(**inputs)
     logits = outputs.logits
     predicted_class = logits.argmax(-1).item()
-    return f"Predicted Class: {predicted_class}"
+    
+    # Optionally return extracted text and prediction as JSON
+    result = {
+        "extracted_text": extracted_text,
+        "predicted_class": predicted_class
+    }
+    return result
 
 # Create a Gradio interface
 interface = gr.Interface(
     fn=analyze_receipt,
-    inputs="text",
-    outputs="text",
+    inputs=gr.inputs.Image(type="pil"),  # Accept image input
+    outputs="json",  # Return JSON output
     title="Receipt Image Analyzer",
-    description="Analyze receipts for relevant information using a fine-tuned LLM model.",
+    description="Upload a receipt image to analyze and classify its contents.",
 )
 
 # Launch the Gradio app