Upload 3 files

Dockerfile

@@ -0,0 +1,13 @@
+FROM python:3.9
+
+RUN useradd -m -u 1000 user
+USER user
+ENV PATH="/home/user/.local/bin:$PATH"
+
+WORKDIR /app
+
+COPY --chown=user ./requirements.txt requirements.txt
+RUN pip install --no-cache-dir --upgrade -r requirements.txt
+
+COPY --chown=user . /app
+CMD ["python", "app.py"]

app.py

@@ -0,0 +1,89 @@
+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
+    uvicorn.run(app, host="0.0.0.0", port=7860)

requirements.txt

@@ -0,0 +1,10 @@
+fastapi==0.74.*
+requests==2.31.*
+uvicorn
+sentencepiece
+torch
+transformers
+pillow
+python-multipart
+pymupdf
+python-docx