Delete app.py

app.py

@@ -1,97 +0,0 @@
-import os
-from fastapi import FastAPI, UploadFile, File
-from transformers import pipeline
-import logging
-from PIL import Image
-import io
-
-# Configure logging
-logging.basicConfig(level=logging.INFO)
-logger = logging.getLogger(__name__)
-
-app = FastAPI()
-
-# Create a pipeline object for summarization
-summarizer = pipeline("summarization", model="sysresearch101/t5-large-finetuned-xsum-cnn")
-
-# Create a pipeline object for image captioning
-image_captioner = pipeline("image-to-text", model="nlpconnect/vit-gpt2-image-captioning")
-
-# Create a pipeline object for text question answering
-qa_pipeline = pipeline("question-answering", model="deepset/roberta-base-squad2")
-
-# Create a pipeline object for visual question answering
-vqa_pipeline = pipeline("visual-question-answering", model="dandelin/vilt-b32-finetuned-vqa")
-
-@app.get("/")
-def read_root():
-    return {"message": "Welcome to the Summarization, Image Captioning, Question Answering, and Visual Question Answering API!"}
-
-@app.get("/summarize")
-def summarize_text(text: str):
-    logger.info(f"Received text for summarization: {text}")
-    try:
-        # Use the pipeline to summarize the input text
-        summary = summarizer(text, max_length=100, num_beams=4, early_stopping=True)
-        logger.info(f"Generated summary: {summary[0]['summary_text']}")
-        return {"summary": summary[0]['summary_text']}
-    except Exception as e:
-        logger.error(f"Error during summarization: {e}")
-        return {"error": str(e)}
-
-@app.post("/caption")
-async def caption_image(file: UploadFile = File(...)):
-    logger.info(f"Received image for captioning: {file.filename}")
-    try:
-        # Read the image file
-        image_data = await file.read()
-        image = Image.open(io.BytesIO(image_data))
-
-        # Use the pipeline to generate a caption for the image
-        caption = image_captioner(image)
-        logger.info(f"Generated caption: {caption[0]['generated_text']}")
-        return {"caption": caption[0]['generated_text']}
-    except Exception as e:
-        logger.error(f"Error during image captioning: {e}")
-        return {"error": str(e)}
-
-@app.get("/answer")
-def answer_question(question: str, context: str):
-    logger.info(f"Received question: {question}")
-    logger.info(f"Received context: {context}")
-    try:
-        # Use the pipeline to answer the question based on the context
-        result = qa_pipeline(question=question, context=context)
-        logger.info(f"Generated answer: {result['answer']}")
-        return {"answer": result['answer']}
-    except Exception as e:
-        logger.error(f"Error during question answering: {e}")
-        return {"error": str(e)}
-
-@app.post("/vqa")
-async def visual_question_answering(file: UploadFile = File(...), question: str = ""):
-    logger.info(f"Received image for visual question answering: {file.filename}")
-    logger.info(f"Received question: {question}")
-    try:
-        # Read the image file
-        image_data = await file.read()
-        image = Image.open(io.BytesIO(image_data))
-
-        # Use the pipeline to answer the question about the image
-        result = vqa_pipeline(image=image, question=question)
-        
-        # Check if the result is a list and has at least one element
-        if isinstance(result, list) and len(result) > 0:
-            logger.info(f"Generated answer: {result[0]['answer']}")
-            return {"answer": result[0]['answer']}
-        else:
-            logger.error("No answer found in the result.")
-            return {"error": "No answer found in the result."}
-    except Exception as e:
-        logger.error(f"Error during visual question answering: {e}")
-        return {"error": str(e)}
-
-# Hugging Face Spaces expects the app to be served on port 7860
-if __name__ == "__main__":
-    import uvicorn
-    uvicorn.run(app, host="0.0.0.0", port=7860)