Update app.py

app.py

@@ -1,7 +1,7 @@
 import os
 from fastapi import FastAPI, UploadFile, File, HTTPException, Form
 from fastapi.staticfiles import StaticFiles
-from fastapi.responses import RedirectResponse
+from fastapi.responses import RedirectResponse, JSONResponse
 from transformers import pipeline
 import logging
 from PIL import Image
@@ -23,5 +23,152 @@ app = FastAPI()
 # Serve static files (HTML, CSS, JS)
 app.mount("/static", StaticFiles(directory="static"), name="static")
 
-# Load a multimodal model for image captioning and visual question answering
-multimodal
+# Initialize models
+try:
+    # Image captioning and VQA
+    image_pipeline = pipeline("image-to-text", model="Salesforce/blip-image-captioning-base")
+    
+    # Text processing
+    text_pipeline = pipeline("text2text-generation", model="t5-small")
+    
+    # Translation models dictionary
+    translation_models = {
+        "fr": "Helsinki-NLP/opus-mt-en-fr",
+        "es": "Helsinki-NLP/opus-mt-en-es",
+        "de": "Helsinki-NLP/opus-mt-en-de"
+    }
+    
+    logger.info("All models loaded successfully")
+except Exception as e:
+    logger.error(f"Model loading failed: {str(e)}")
+    raise RuntimeError(f"Failed to initialize models: {str(e)}")
+
+@app.get("/")
+def read_root():
+    return RedirectResponse(url="/static/index.html")
+
+@app.get("/health")
+def health_check():
+    return {"status": "healthy", "models_loaded": True}
+
+@app.post("/summarize")
+async def summarize_text(
+    file: UploadFile = File(None),
+    text: str = Form(None)
+):
+    try:
+        if file:
+            text = await extract_text_from_file(file)
+        elif not text:
+            raise HTTPException(status_code=400, detail="No input provided")
+        
+        summary = text_pipeline(f"summarize: {text}", max_length=100)
+        return {"summary": summary[0]['generated_text']}
+    except Exception as e:
+        logger.error(f"Summarization error: {str(e)}")
+        raise HTTPException(status_code=500, detail=str(e))
+
+@app.post("/caption")
+async def caption_image(file: UploadFile = File(...)):
+    try:
+        image = Image.open(io.BytesIO(await file.read()))
+        caption = image_pipeline(image)
+        return {"caption": caption[0]['generated_text']}
+    except Exception as e:
+        logger.error(f"Captioning error: {str(e)}")
+        raise HTTPException(status_code=500, detail=str(e))
+
+@app.post("/answer")
+async def answer_question(
+    file: UploadFile = File(None),
+    text: str = Form(None),
+    question: str = Form(...)
+):
+    try:
+        if file:
+            text = await extract_text_from_file(file)
+        elif not text:
+            raise HTTPException(status_code=400, detail="No context provided")
+        
+        answer = text_pipeline(f"question: {question} context: {text}")
+        return {"answer": answer[0]['generated_text']}
+    except Exception as e:
+        logger.error(f"QA error: {str(e)}")
+        raise HTTPException(status_code=500, detail=str(e))
+
+@app.post("/vqa")
+async def visual_question_answering(
+    file: UploadFile = File(...),
+    question: str = Form(...)
+):
+    try:
+        image = Image.open(io.BytesIO(await file.read()))
+        answer = image_pipeline(image, question=question)
+        return {"answer": answer[0]['generated_text']}
+    except Exception as e:
+        logger.error(f"VQA error: {str(e)}")
+        raise HTTPException(status_code=500, detail=str(e))
+
+@app.post("/visualize")
+async def visualize_data(
+    file: UploadFile = File(...),
+    request: str = Form(...)
+):
+    try:
+        df = pd.read_excel(io.BytesIO(await file.read()))
+        
+        if "bar" in request.lower():
+            code = f"""import matplotlib.pyplot as plt
+plt.bar(df['{df.columns[0]}'], df['{df.columns[1]}'])
+plt.show()"""
+        else:
+            code = f"""import seaborn as sns
+sns.pairplot(df)
+plt.show()"""
+            
+        return {"code": code}
+    except Exception as e:
+        logger.error(f"Visualization error: {str(e)}")
+        raise HTTPException(status_code=500, detail=str(e))
+
+@app.post("/translate")
+async def translate_document(
+    file: UploadFile = File(...),
+    target_language: str = Form(...)
+):
+    try:
+        text = await extract_text_from_file(file)
+        
+        if target_language not in translation_models:
+            raise HTTPException(status_code=400, detail="Unsupported language")
+            
+        tokenizer = MarianTokenizer.from_pretrained(translation_models[target_language])
+        model = MarianMTModel.from_pretrained(translation_models[target_language])
+        
+        translated = model.generate(**tokenizer(text, return_tensors="pt", truncation=True))
+        translated_text = tokenizer.decode(translated[0], skip_special_tokens=True)
+        
+        return {"translated_text": translated_text}
+    except Exception as e:
+        logger.error(f"Translation error: {str(e)}")
+        raise HTTPException(status_code=500, detail=str(e))
+
+async def extract_text_from_file(file: UploadFile):
+    try:
+        content = await file.read()
+        
+        if file.filename.endswith(".pdf"):
+            doc = fitz.open(stream=content, filetype="pdf")
+            return " ".join([page.get_text() for page in doc])
+        elif file.filename.endswith(".docx"):
+            doc = Document(io.BytesIO(content))
+            return "\n".join([para.text for para in doc.paragraphs])
+        else:
+            raise ValueError("Unsupported file format")
+    except Exception as e:
+        logger.error(f"File extraction error: {str(e)}")
+        raise HTTPException(status_code=400, detail=str(e))
+
+if __name__ == "__main__":
+    import uvicorn
+    uvicorn.run(app, host="0.0.0.0", port=7860)