Update app.py

app.py

@@ -1,81 +1,90 @@
 import os
-import gradio as gr
 import openai
-import torch
-from torchvision import transforms
+import gradio as gr
 from PIL import Image
-import requests
-from io import BytesIO
+import io
+import base64
 
 # Set your OpenAI API key here or use environment variables
 openai.api_key = "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"
 
-# Load a pre-trained model for leaf disease detection
-# For demonstration, we'll use a generic ResNet model fine-tuned for classification
-# Replace the model path with your specific model trained for leaf diseases
-model = torch.hub.load('pytorch/vision:v0.10.0', 'resnet50', pretrained=True)
-model.eval()
-
-# Define image transformations
-preprocess = transforms.Compose([
-    transforms.Resize(256),
-    transforms.CenterCrop(224),
-    transforms.ToTensor(),
-    transforms.Normalize(
-        mean=[0.485, 0.456, 0.406],  # Standard ImageNet means
-        std=[0.229, 0.224, 0.225]    # Standard ImageNet stds
-    )
-])
-
-# Load class labels (You should replace this with your specific disease classes)
-# For demonstration, we'll use ImageNet labels
-LABELS_URL = "https://s3.amazonaws.com/outcome-blog/imagenet/labels.json"
-response = requests.get(LABELS_URL)
-labels = {int(key): value for key, value in response.json().items()}
-
-def detect_disease(image):
-    # Preprocess the image
-    img = preprocess(image).unsqueeze(0)  # Add batch dimension
-
-    # Perform inference
-    with torch.no_grad():
-        outputs = model(img)
-        _, predicted = torch.max(outputs, 1)
-        class_id = predicted.item()
-        disease = labels.get(class_id, "Unknown Disease")
-
-    if disease == "Unknown Disease":
-        return disease, "Sorry, the disease could not be identified. Please consult a local agricultural extension office."
-
-    # Generate remedies using OpenAI's ChatGPT
-    prompt = f"The following disease has been detected on a plant leaf: {disease}. Please provide detailed remedies and treatment options for this disease."
+def detect_disease_and_get_remedies(image):
+    """
+    Detects leaf disease from the uploaded image and provides remedies.
+
+    Args:
+        image (PIL.Image): Uploaded leaf image.
 
+    Returns:
+        Tuple[str, str]: Detected disease and corresponding remedies.
+    """
     try:
-        completion = openai.ChatCompletion.create(
+        # Convert PIL Image to bytes
+        buffered = io.BytesIO()
+        image.save(buffered, format="JPEG")
+        img_bytes = buffered.getvalue()
+
+        # Encode image to base64
+        img_base64 = base64.b64encode(img_bytes).decode('utf-8')
+
+        # Create a system prompt to guide the model
+        system_prompt = "You are an agricultural expert specializing in plant diseases."
+
+        # Step 1: Detect Disease
+        disease_prompt = (
+            "Analyze the following image of a plant leaf and identify any diseases present. "
+            "Provide only the name of the disease without additional explanation.\n\n"
+            "Image (base64 encoded): {}\n\nDisease:".format(img_base64)
+        )
+
+        # Send the image to OpenAI's ChatCompletion API for disease detection
+        response = openai.ChatCompletion.create(
+            model="gpt-4-vision",  # Assuming GPT-4 with vision capabilities
+            messages=[
+                {"role": "system", "content": system_prompt},
+                {"role": "user", "content": disease_prompt}
+            ],
+            temperature=0
+        )
+
+        disease = response.choices[0].message['content'].strip()
+
+        if not disease or disease.lower() in ["no disease detected", "healthy"]:
+            return "No Disease Detected", "The leaf appears to be healthy. Maintain regular plant care to prevent future issues."
+
+        # Step 2: Get Remedies for the Detected Disease
+        remedy_prompt = (
+            "Provide detailed remedies and treatment options for the following plant leaf disease: {}. "
+            "Include both chemical and organic treatment methods if applicable.".format(disease)
+        )
+
+        remedy_response = openai.ChatCompletion.create(
             model="gpt-4",
             messages=[
-                {"role": "system", "content": "You are a helpful agricultural expert."},
-                {"role": "user", "content": prompt}
+                {"role": "system", "content": "You are a knowledgeable agricultural advisor."},
+                {"role": "user", "content": remedy_prompt}
             ],
             temperature=0.7,
             max_tokens=500
         )
-        remedies = completion.choices[0].message.content.strip()
-    except Exception as e:
-        remedies = "An error occurred while fetching remedies. Please try again later."
 
-    return disease, remedies
+        remedies = remedy_response.choices[0].message['content'].strip()
+
+        return disease, remedies
+
+    except Exception as e:
+        return "Error", f"An error occurred: {str(e)}"
 
 # Define the Gradio interface
 iface = gr.Interface(
-    fn=detect_disease,
-    inputs=gr.inputs.Image(type="pil", label="Upload Leaf Image"),
+    fn=detect_disease_and_get_remedies,
+    inputs=gr.Image(type="pil", label="Upload Leaf Image"),
     outputs=[
-        gr.outputs.Textbox(label="Detected Disease"),
-        gr.outputs.Textbox(label="Remedies")
+        gr.Textbox(label="Detected Disease"),
+        gr.Textbox(label="Remedies")
     ],
     title="Leaf Disease Detector",
-    description="Upload an image of a leaf, and the system will detect the disease and provide remedies."
+    description="Upload an image of a leaf, and the system will detect any diseases present and provide remedies."
 )
 
 if __name__ == "__main__":