Update appImage.py

appImage.py

@@ -1,134 +1,5 @@
-"""import gradio as gr
-from transformers import AutoProcessor, AutoModelForCausalLM
-from PIL import Image
-import torch
-from fastapi import FastAPI
-from fastapi.responses import RedirectResponse
-
-# Initialize FastAPI
-app = FastAPI()
-
-# Load models - Using microsoft/git-large-coco
-try:
-    # Load the better model
-    processor = AutoProcessor.from_pretrained("microsoft/git-large-coco")
-    git_model = AutoModelForCausalLM.from_pretrained("microsoft/git-large-coco")
-    print("Successfully loaded microsoft/git-large-coco model")
-    USE_GIT = True
-except Exception as e:
-    print(f"Failed to load GIT model: {e}. Falling back to smaller model")
-    captioner = pipeline("image-to-text", model="nlpconnect/vit-gpt2-image-captioning")
-    USE_GIT = False
-
-def generate_caption(image_path):
-    "Generate caption using the best available model""
-    try:
-        if USE_GIT:
-            image = Image.open(image_path)
-            inputs = processor(images=image, return_tensors="pt")
-            outputs = git_model.generate(**inputs, max_length=50)
-            return processor.batch_decode(outputs, skip_special_tokens=True)[0]
-        else:
-            result = captioner(image_path)
-            return result[0]['generated_text']
-    except Exception as e:
-        print(f"Caption generation error: {e}")
-        return "Could not generate caption"
-
-def process_image(file_path: str):
-    "Handle image processing for Gradio interface"
-    if not file_path:
-        return "Please upload an image first"
-    
-    try:
-        caption = generate_caption(file_path)
-        return f"📷 Image Caption:\n{caption}"
-    except Exception as e:
-        return f"Error processing image: {str(e)}"
-
-# Gradio Interface
-with gr.Blocks(title="Image Captioning Service", theme=gr.themes.Soft()) as demo:
-    gr.Markdown("# 🖼️ Image Captioning Service")
-    gr.Markdown("Upload an image to get automatic captioning")
-    
-    with gr.Row():
-        with gr.Column():
-            image_input = gr.Image(label="Upload Image", type="filepath")
-            analyze_btn = gr.Button("Generate Caption", variant="primary")
-        
-        with gr.Column():
-            output = gr.Textbox(label="Caption Result", lines=5)
-    
-    analyze_btn.click(
-        fn=process_image,
-        inputs=[image_input],
-        outputs=[output]
-    )
-
-# Mount Gradio app to FastAPI
-app = gr.mount_gradio_app(app, demo, path="/")
-
-@app.get("/")
-def redirect_to_interface():
-    return RedirectResponse(url="/")
-"""
-import gradio as gr
-from transformers import AutoProcessor, AutoModelForCausalLM, pipeline
-from PIL import Image
-import torch
-from fastapi import FastAPI, UploadFile, Form
-from fastapi.responses import RedirectResponse, JSONResponse, FileResponse
-from fastapi.middleware.cors import CORSMiddleware
-import os
-import tempfile
-
-# ✅ Initialize FastAPI
-app = FastAPI()
-
-# ✅ Enable CORS (so frontend JS can call backend)
-app.add_middleware(
-    CORSMiddleware,
-    allow_origins=["*"],
-    allow_credentials=True,
-    allow_methods=["*"],
-    allow_headers=["*"],
-)
-
-# ✅ Load caption model
-USE_GIT = False
-try:
-    processor = AutoProcessor.from_pretrained("microsoft/git-large-coco")
-    git_model = AutoModelForCausalLM.from_pretrained("microsoft/git-large-coco")
-    git_model.eval()
-    USE_GIT = True
-except Exception as e:
-    print(f"[INFO] Falling back to ViT: {e}")
-    captioner = pipeline("image-to-text", model="nlpconnect/vit-gpt2-image-captioning")
-
-# ✅ Image captioning logic
-def generate_caption(image_path: str) -> str:
-    try:
-        if USE_GIT:
-            image = Image.open(image_path).convert("RGB")
-            inputs = processor(images=image, return_tensors="pt")
-            outputs = git_model.generate(**inputs, max_length=50)
-            caption = processor.batch_decode(outputs, skip_special_tokens=True)[0]
-        else:
-            result = captioner(image_path)
-            caption = result[0]['generated_text']
-        return caption
-    except Exception as e:
-        return f"Error: {str(e)}"
-
-# ✅ For Gradio demo
-def process_image(file_path: str):
-    if not file_path:
-        return "Please upload an image."
-    return f"📷 Image Caption:\n{generate_caption(file_path)}"
-
-# ✅ FastAPI endpoint for frontend POSTs
 @app.post("/imagecaption/")
-async def caption_from_frontend(file: UploadFile, question: str = Form("")):
+async def caption_from_frontend(file: UploadFile):
     try:
         # Save temp image
         contents = await file.read()
@@ -138,39 +9,15 @@ async def caption_from_frontend(file: UploadFile, question: str = Form("")):
 
         caption = generate_caption(tmp_path)
 
-        # Optionally generate audio
-        from gtts import gTTS
+        # Generate audio
         audio_path = os.path.join(tempfile.gettempdir(), file.filename + ".mp3")
         tts = gTTS(text=caption)
         tts.save(audio_path)
 
-        return {
+        return JSONResponse({
             "answer": caption,
             "audio": f"/files/{os.path.basename(audio_path)}"
-        }
+        })
 
     except Exception as e:
-        return JSONResponse({"error": str(e)}, status_code=500)
-
-# ✅ Serve static files
-@app.get("/files/{file_name}")
-async def serve_file(file_name: str):
-    path = os.path.join(tempfile.gettempdir(), file_name)
-    if os.path.exists(path):
-        return FileResponse(path)
-    return JSONResponse({"error": "File not found"}, status_code=404)
-
-# ✅ Mount Gradio demo for test
-with gr.Blocks(title="🖼️ Image Captioning") as demo:
-    gr.Markdown("# 🖼️ Image Captioning Demo")
-    image_input = gr.Image(type="filepath", label="Upload Image")
-    result_box = gr.Textbox(label="Caption")
-    btn = gr.Button("Generate Caption")
-    btn.click(fn=process_image, inputs=[image_input], outputs=[result_box])
-
-app = gr.mount_gradio_app(app, demo, path="/")
-
-# ✅ Optional root redirect to frontend
-@app.get("/")
-def redirect_to_frontend():
-    return RedirectResponse(url="/templates/home.html")
+        return JSONResponse({"error": str(e)}, status_code=500)