Update appImage.py

appImage.py

@@ -49,40 +49,26 @@ def answer_question_from_image(image, question):
     
     predicted_id = outputs.logits.argmax(-1).item()
     return vqa_model.config.id2label[predicted_id]"""
-from fastapi import FastAPI, Request, UploadFile, Form
-from fastapi.responses import RedirectResponse, FileResponse, HTMLResponse, JSONResponse
-from fastapi.staticfiles import StaticFiles
-from fastapi.templating import Jinja2Templates
+from fastapi import FastAPI, UploadFile, Form
+from fastapi.responses import RedirectResponse, JSONResponse, FileResponse
 import os
-import shutil
 from PIL import Image
 from transformers import ViltProcessor, ViltForQuestionAnswering, pipeline
 from gtts import gTTS
 import easyocr
 import torch
 import tempfile
-import gradio as gr
 import numpy as np
+from io import BytesIO
 
 app = FastAPI()
 
-# Setup templates and static
-app.mount("/static", StaticFiles(directory="static"), name="static")
-app.mount("/resources", StaticFiles(directory="resources"), name="resources")
-templates = Jinja2Templates(directory="templates")
-
-# Serve custom HTML at /
-@app.get("/", response_class=HTMLResponse)
-def serve_home(request: Request):
-    return templates.TemplateResponse("home.html", {"request": request})
-
-# Load Models
+# Load models
 vqa_processor = ViltProcessor.from_pretrained("dandelin/vilt-b32-finetuned-vqa")
 vqa_model = ViltForQuestionAnswering.from_pretrained("dandelin/vilt-b32-finetuned-vqa")
 captioner = pipeline("image-to-text", model="nlpconnect/vit-gpt2-image-captioning")
-reader = easyocr.Reader(['en'], gpu=False, download_enabled=True)
+reader = easyocr.Reader(['en', 'fr'])
 
-# Determine which feature to use
 def classify_question(question: str):
     question_lower = question.lower()
     if any(word in question_lower for word in ["text", "say", "written", "read"]):
@@ -92,7 +78,6 @@ def classify_question(question: str):
     else:
         return "vqa"
 
-# Answer logic
 def answer_question_from_image(image, question):
     if image is None or not question.strip():
         return "Please upload an image and ask a question.", None
@@ -106,11 +91,13 @@ def answer_question_from_image(image, question):
             answer = text.strip() or "No readable text found."
         except Exception as e:
             answer = f"OCR Error: {e}"
+
     elif mode == "caption":
         try:
             answer = captioner(image)[0]['generated_text']
         except Exception as e:
             answer = f"Captioning error: {e}"
+
     else:
         try:
             inputs = vqa_processor(image, question, return_tensors="pt")
@@ -131,25 +118,26 @@ def answer_question_from_image(image, question):
 
     return answer, audio_path
 
-# API Endpoint for frontend
 @app.post("/predict")
-async def predict(file: UploadFile = Form(...), question: str = Form(...)):
+async def predict(question: str = Form(...), file: UploadFile = Form(...)):
     try:
-        file_ext = file.filename.split(".")[-1].lower()
-        image = Image.open(file.file)
+        image_data = await file.read()
+        image = Image.open(BytesIO(image_data)).convert("RGB")
         answer, audio_path = answer_question_from_image(image, question)
 
-        return JSONResponse({
-            "answer": answer,
-            "audio": f"/audio/{os.path.basename(audio_path)}" if audio_path else None
-        })
+        if audio_path and os.path.exists(audio_path):
+            return JSONResponse({"answer": answer, "audio": f"/audio/{os.path.basename(audio_path)}"})
+        else:
+            return JSONResponse({"answer": answer})
+
     except Exception as e:
-        return JSONResponse({"error": f"Server error: {e}"}, status_code=500)
+        return JSONResponse({"error": str(e)})
 
-# Serve audio responses
 @app.get("/audio/{filename}")
-def serve_audio(filename: str):
-    audio_path = os.path.join(tempfile.gettempdir(), filename)
-    if os.path.exists(audio_path):
-        return FileResponse(audio_path, media_type="audio/mpeg")
-    return JSONResponse({"error": "File not found"}, status_code=404)
+async def get_audio(filename: str):
+    filepath = os.path.join(tempfile.gettempdir(), filename)
+    return FileResponse(filepath, media_type="audio/mpeg")
+
+@app.get("/")
+def home():
+    return RedirectResponse(url="/static/home.html")