Update space

app.py

@@ -2,34 +2,69 @@ import keras
 from keras.models import load_model
 import gradio as gr
 import cv2
+import numpy as np
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
 
-my_model = load_model('Final_Chicken_disease_model.h5', compile=True)
-auth_model = load_model('auth_model.h5', compile=True)
+# Load models
+my_model = load_model('models/Final_Chicken_disease_model.h5', compile=True)
+auth_model = load_model('models/auth_model.h5', compile=True)
+llama_tokenizer = AutoTokenizer.from_pretrained('huggingface/llama3')
+llama_model = AutoModelForCausalLM.from_pretrained('huggingface/llama3')
+
+# Dictionaries for disease names, results, and recommendations
 name_disease = {0: 'Coccidiosis', 1: 'Healthy', 2: 'New Castle Disease', 3: 'Salmonella'}
 result = {0: 'Critical', 1: 'No issue', 2: 'Critical', 3: 'Critical'}
-recommend = {0: 'Panadol', 1: 'You have no need of Medicine', 2: 'Percetamol', 3: 'Ponston'}
+recommend = {0: 'Panadol', 1: 'You have no need of Medicine', 2: 'Paracetamol', 3: 'Ponston'}
 
 
 def predict(image):
+    # Preprocess the image for the authentication model
     image_check = cv2.resize(image, (224, 224))
-    indx = auth_model.predict(image_check.reshape(1, 224, 224, 3)).argmax()
-    if indx == 0:
+    image_check = np.expand_dims(image_check, axis=0)  # Add batch dimension
+    indx = auth_model.predict(image_check).argmax()
+
+    if indx == 0:  # If the image is recognized as a chicken disease image
+        # Preprocess the image for the disease prediction model
         image = cv2.resize(image, (224, 224))
-        indx = my_model.predict(image.reshape(1, 224, 224, 3)).argmax()
+        image = np.expand_dims(image, axis=0)  # Add batch dimension
+        indx = my_model.predict(image).argmax()
+
         name = name_disease.get(indx)
         status = result.get(indx)
         recom = recommend.get(indx)
-        return name, status, recom
-    else:
+    else:  # If the image is not recognized as a chicken disease image
         name = 'Unknown Image'
         status = 'N/A'
         recom = 'N/A'
-        return name, status, recom
 
+    return f"Chicken is {status}, the disease it has is {name}, the recommended medication is {recom}"
+
+
+def chat_response(user_input):
+    inputs = llama_tokenizer(user_input, return_tensors='pt')
+    outputs = llama_model.generate(inputs['input_ids'], max_length=500, do_sample=True)
+    response = llama_tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return response
+
+
+def combined_interface(image, text):
+    if image is not None:
+        return predict(image)
+    elif text:
+        return chat_response(text)
+    else:
+        return "Please provide an image or ask a question."
+
+
+# Create Gradio interface
+interface = gr.Interface(
+    fn=combined_interface,
+    inputs=[gr.inputs.Image(label='Upload Image', optional=True),
+            gr.inputs.Textbox(label='Ask a question', optional=True)],
+    outputs=gr.Textbox(label="Response"),
+    examples=[['disease.jpg', ''], ['', 'What should I do if my chicken is sick?']]
+)
 
-interface = gr.Interface(fn=predict, inputs=[gr.Image(label='upload Image')],
-                         outputs=[gr.components.Textbox(label="Disease Name"),
-                                  gr.components.Textbox(label="result"),
-                                  gr.components.Textbox(label='Medicine Recommend')],
-                         examples=[['disease.jpg'], ['ncd.jpg']])
+# Launch the interface
 interface.launch(debug=True)

requirements.txt

@@ -2,4 +2,5 @@ huggingface_hub==0.22.2
 keras
 gradio
 opencv-python
-tensorflow==2.12.0
+tensorflow==2.12.0
+transformers