Update app.py

app.py

@@ -1,87 +1,87 @@
-import os
-from crewai import Agent, Task, Crew
-from langchain_groq import ChatGroq
-from PIL import Image
-import streamlit as st
-
-# Initialize the LLM (assuming it can also handle image processing)
-llm = ChatGroq(
-    groq_api_key="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",
-    model_name="llama-3.1-70b-versatile",
-)
-
-# Define the agent for medical image analysis
-medical_image_agent = Agent(
-    role='Medical Image Captioning Agent',
-    goal='Analyze medical images and provide a title, description, and reasons for detected issues.',
-    backstory=(
-        "You are a Medical Image Captioning Agent. Your role is to analyze medical-related images "
-        "Figure out whether the image is  X-rays, skin blemishes, or accident pictures, and then generate a relevant title, description, "
-        "and reasons why issues might have occurred."
-    ),
-    verbose=True,
-    llm=llm,
-)
-
-def process_image_with_agent(image_path, agent):
-    """Process the uploaded image using the AI agent."""
-    try:
-        image = Image.open(image_path)
-    except Exception as e:
-        return f"Error opening image: {e}"
-
-    # Define the task for the agent
-    task_description = f"Analyze the medical image and provide a title, description, and reasons for detected issues. Image path: {image_path}"
-
-    # Define the task
-    medical_image_task = Task(
-        description=task_description,
-        agent=agent,
-        human_input=False,
-        expected_output="Title, description, and reasons for detected issues",
-    )
-
-    # Instantiate the crew with the defined agent and task
-    crew = Crew(
-        agents=[agent],
-        tasks=[medical_image_task],
-        verbose=2,
-    )
-
-    # Execute the task and return the result
-    result = crew.kickoff()
-    return result
-
-# Streamlit App
-def main():
-    st.title("Medical Image Analysis and Captioning")
-    st.write(
-        "Upload a medical-related image (e.g., X-ray, skin blemish, accident photo), "
-        "and the AI agent will analyze it to provide relevant insights."
-    )
-
-    # File uploader
-    uploaded_file = st.file_uploader("Upload an image", type=["jpg", "jpeg", "png", "bmp"])
-
-    if uploaded_file:
-        # Save the uploaded file locally
-        temp_file_path = f"temp_{uploaded_file.name}"
-        with open(temp_file_path, "wb") as f:
-            f.write(uploaded_file.getbuffer())
-
-        # Display the uploaded image
-        st.image(temp_file_path, caption="Uploaded Image", use_column_width=True)
-
-        # Process the image
-        with st.spinner("Analyzing the image..."):
-            result = process_image_with_agent(temp_file_path, medical_image_agent)
-
-        # Display the result
-        st.write("### Analysis Result:")
-        st.write(result)
-
-        # Remove the temporary file
-        os.remove(temp_file_path)
-
-if __name__ == "__main__":
-    main()
+import os
+from crewai import Agent, Task, Crew
+from langchain_groq import ChatGroq
+from PIL import Image
+import streamlit as st
+
+# Initialize the LLM (assuming it can also handle image processing)
+llm = ChatGroq(
+    groq_api_key="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",
+    model_name="llama-3.1-70b-versatile",
+)
+
+# Define the agent for medical image analysis
+medical_image_agent = Agent(
+    role='Medical Image Captioning Agent',
+    goal='Analyze medical images and provide a title, description, and reasons for detected issues.',
+    backstory=(
+        "You are a Medical Image Captioning Agent. Your role is to analyze medical-related images "
+        "Figure out issues from the image of X-rays, skin blemishes, or accident pictures, and then generate a relevant title, description, "
+        "and reasons why issues might have occurred."
+    ),
+    verbose=True,
+    llm=llm,
+)
+
+def process_image_with_agent(image_path, agent):
+    """Process the uploaded image using the AI agent."""
+    try:
+        image = Image.open(image_path)
+    except Exception as e:
+        return f"Error opening image: {e}"
+
+    # Define the task for the agent
+    task_description = f"Analyze the medical image and provide a title, description, and reasons for detected issues. Image path: {image_path}"
+
+    # Define the task
+    medical_image_task = Task(
+        description=task_description,
+        agent=agent,
+        human_input=False,
+        expected_output="Title, description, and reasons for detected issues",
+    )
+
+    # Instantiate the crew with the defined agent and task
+    crew = Crew(
+        agents=[agent],
+        tasks=[medical_image_task],
+        verbose=2,
+    )
+
+    # Execute the task and return the result
+    result = crew.kickoff()
+    return result
+
+# Streamlit App
+def main():
+    st.title("Medical Image Analysis and Captioning")
+    st.write(
+        "Upload a medical-related image (e.g., X-ray, skin blemish, accident photo), "
+        "and the AI agent will analyze it to provide relevant insights."
+    )
+
+    # File uploader
+    uploaded_file = st.file_uploader("Upload an image", type=["jpg", "jpeg", "png", "bmp"])
+
+    if uploaded_file:
+        # Save the uploaded file locally
+        temp_file_path = f"temp_{uploaded_file.name}"
+        with open(temp_file_path, "wb") as f:
+            f.write(uploaded_file.getbuffer())
+
+        # Display the uploaded image
+        st.image(temp_file_path, caption="Uploaded Image", use_column_width=True)
+
+        # Process the image
+        with st.spinner("Analyzing the image..."):
+            result = process_image_with_agent(temp_file_path, medical_image_agent)
+
+        # Display the result
+        st.write("### Analysis Result:")
+        st.write(result)
+
+        # Remove the temporary file
+        os.remove(temp_file_path)
+
+if __name__ == "__main__":
+    main()