Upload 3 files

Dockerfile

@@ -0,0 +1,30 @@
+# Use Python 3.10.12 as the base image
+FROM python:3.9.13
+
+# Set the working directory to /code
+WORKDIR /code
+
+# Copy the requirements file into the container at /code/requirements.txt
+COPY ./requirements.txt /code/requirements.txt
+
+# Upgrade pip and install the dependencies
+RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
+
+# Create a non-root user with UID 1000
+RUN useradd -m -u 1000 user
+
+# Switch to the non-root user
+USER user
+
+# Set environment variables for the user
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:$PATH
+
+# Set the working directory for the application
+WORKDIR $HOME/app
+
+# Copy the local code into the container at /home/user/app
+COPY --chown=user . $HOME/app
+
+# Specify the command to run on container start
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]

main.py

@@ -0,0 +1,42 @@
+from fastapi import FastAPI, UploadFile, HTTPException, Body
+from fastapi.responses import JSONResponse
+from fastapi.middleware.cors import CORSMiddleware
+from transformers import pipeline
+from PIL import Image
+import base64
+from io import BytesIO
+
+app = FastAPI()
+
+# Load the image classification pipeline
+classifier = pipeline(model="Diginsa/Plant-Disease-Detection-Project")
+
+# CORS configuration
+origins = [""]  # Replace "" with the actual list of allowed origins
+
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=origins,
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+# Endpoint to perform image classification
+@app.post("/classify")
+async def classify_image(encoded_image: str= Body(..., embed=True)):
+    try:
+        # Decode the base64 encoded image string
+        decoded_image = base64.b64decode(encoded_image)
+
+        # Create an Image object from the decoded content
+        image = Image.open(BytesIO(decoded_image))
+
+        # Use the classifier with the decoded image
+        result = classifier(images=image)
+
+        # Return the classification result as JSON
+        return JSONResponse(content=result, status_code=200)
+
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))

requirements.txt

@@ -0,0 +1,4 @@
+fastapi
+transformers
+pillow
+uvicorn