Update app.py

app.py

@@ -1,89 +1,118 @@
-import os
-from fastapi import FastAPI, UploadFile, File, HTTPException
-from transformers import pipeline
-import logging
-from PIL import Image
-import io
-from docx import Document
-import fitz  # PyMuPDF
-
-# Configure logging
-logging.basicConfig(level=logging.INFO)
-logger = logging.getLogger(__name__)
-
-app = FastAPI()
-
-# Load a multimodal model for image captioning and visual question answering
-multimodal_pipeline = pipeline("image-to-text", model="Salesforce/blip-image-captioning-base")
-
-# Load a text-based model for summarization and text question answering
-text_pipeline = pipeline("text2text-generation", model="t5-small")
-
-@app.get("/")
-def read_root():
-    return {"message": "Welcome to the AI-Powered Web Application!"}
-
-@app.post("/analyze")
-async def analyze(file: UploadFile = File(...)):
-    logger.info(f"Received file for analysis: {file.filename}")
-    try:
-        if file.filename.endswith((".pdf", ".docx")):
-            # Summarize document
-            text = await extract_text_from_file(file)
-            summary = text_pipeline(f"summarize: {text}", max_length=100)
-            return {"summary": summary[0]['generated_text']}
-        elif file.filename.endswith((".jpg", ".jpeg", ".png")):
-            # Caption image
-            image = Image.open(io.BytesIO(await file.read()))
-            caption = multimodal_pipeline(image)
-            return {"caption": caption[0]['generated_text']}
-        else:
-            raise HTTPException(status_code=400, detail="Unsupported file format")
-    except Exception as e:
-        logger.error(f"Error during analysis: {e}")
-        raise HTTPException(status_code=500, detail=str(e))
-
-@app.post("/ask")
-async def ask(file: UploadFile = File(...), question: str = ""):
-    logger.info(f"Received file for question answering: {file.filename}")
-    logger.info(f"Received question: {question}")
-    try:
-        if file.filename.endswith((".pdf", ".docx")):
-            # Answer question from document
-            text = await extract_text_from_file(file)
-            answer = text_pipeline(f"question: {question} context: {text}")
-            return {"answer": answer[0]['generated_text']}
-        elif file.filename.endswith((".jpg", ".jpeg", ".png")):
-            # Answer question about image
-            image = Image.open(io.BytesIO(await file.read()))
-            answer = multimodal_pipeline(image, question=question)
-            return {"answer": answer[0]['generated_text']}
-        else:
-            raise HTTPException(status_code=400, detail="Unsupported file format")
-    except Exception as e:
-        logger.error(f"Error during question answering: {e}")
-        raise HTTPException(status_code=500, detail=str(e))
-
-# Helper function to extract text from files
-async def extract_text_from_file(file: UploadFile):
-    try:
-        if file.filename.endswith(".pdf"):
-            doc = fitz.open(stream=await file.read(), filetype="pdf")
-            text = ""
-            for page in doc:
-                text += page.get_text()
-            return text
-        elif file.filename.endswith(".docx"):
-            doc = Document(io.BytesIO(await file.read()))
-            text = "\n".join([para.text for para in doc.paragraphs])
-            return text
-        else:
-            raise ValueError("Unsupported file format. Please upload a PDF or DOCX file.")
-    except Exception as e:
-        logger.error(f"Error extracting text from file: {e}")
-        raise HTTPException(status_code=400, detail=str(e))
-
-# Hugging Face Spaces expects the app to be served on port 7860
-if __name__ == "__main__":
-    import uvicorn
+import os
+from fastapi import FastAPI, UploadFile, File, HTTPException
+from fastapi.staticfiles import StaticFiles
+from fastapi.responses import RedirectResponse
+from transformers import pipeline
+import logging
+from PIL import Image
+import io
+from docx import Document
+import fitz  # PyMuPDF
+
+# Configure logging
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+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_pipeline = pipeline("image-to-text", model="Salesforce/blip-image-captioning-base")
+
+# Load a text-based model for summarization and text question answering
+text_pipeline = pipeline("text2text-generation", model="t5-small")
+
+@app.get("/")
+def read_root():
+    # Redirect to the static HTML file
+    return RedirectResponse(url="/static/index.html")
+
+@app.post("/summarize")
+async def summarize_text(file: UploadFile = File(...)):
+    logger.info(f"Received document for summarization: {file.filename}")
+    try:
+        # Extract text from the document
+        text = await extract_text_from_file(file)
+        
+        # Use the text pipeline to summarize the text
+        summary = text_pipeline(f"summarize: {text}", max_length=100)
+        logger.info(f"Generated summary: {summary[0]['generated_text']}")
+        return {"summary": summary[0]['generated_text']}
+    except Exception as e:
+        logger.error(f"Error during summarization: {e}")
+        raise HTTPException(status_code=500, detail=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 multimodal pipeline to generate a caption for the image
+        caption = multimodal_pipeline(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}")
+        raise HTTPException(status_code=500, detail=str(e))
+
+@app.post("/answer")
+async def answer_question(file: UploadFile = File(...), question: str = ""):
+    logger.info(f"Received document for question answering: {file.filename}")
+    logger.info(f"Received question: {question}")
+    try:
+        # Extract text from the document
+        text = await extract_text_from_file(file)
+        
+        # Use the text pipeline to answer the question
+        answer = text_pipeline(f"question: {question} context: {text}")
+        logger.info(f"Generated answer: {answer[0]['generated_text']}")
+        return {"answer": answer[0]['generated_text']}
+    except Exception as e:
+        logger.error(f"Error during question answering: {e}")
+        raise HTTPException(status_code=500, detail=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 multimodal pipeline to answer the question about the image
+        answer = multimodal_pipeline(image, question=question)
+        logger.info(f"Generated answer: {answer[0]['generated_text']}")
+        return {"answer": answer[0]['generated_text']}
+    except Exception as e:
+        logger.error(f"Error during visual question answering: {e}")
+        raise HTTPException(status_code=500, detail=str(e))
+
+# Helper function to extract text from files
+async def extract_text_from_file(file: UploadFile):
+    try:
+        if file.filename.endswith(".pdf"):
+            doc = fitz.open(stream=await file.read(), filetype="pdf")
+            text = ""
+            for page in doc:
+                text += page.get_text()
+            return text
+        elif file.filename.endswith(".docx"):
+            doc = Document(io.BytesIO(await file.read()))
+            text = "\n".join([para.text for para in doc.paragraphs])
+            return text
+        else:
+            raise ValueError("Unsupported file format. Please upload a PDF or DOCX file.")
+    except Exception as e:
+        logger.error(f"Error extracting text from file: {e}")
+        raise HTTPException(status_code=400, detail=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)