Spaces:
Runtime error
Runtime error
import google.generativeai as genai | |
from pathlib import Path | |
import gradio as gr | |
from dotenv import load_dotenv | |
import os | |
# Load environment variables from a .env file | |
load_dotenv() | |
# Configure the GenerativeAI API key using the loaded environment variable | |
genai.configure(api_key=os.getenv("AIzaSyDGsO9HM1KDZ0BdZ1RGWP8lC2XR4A_Oz5w")) | |
# Set up the model configuration for text generation | |
generation_config = { | |
"temperature": 0.4, | |
"top_p": 1, | |
"top_k": 32, | |
"max_output_tokens": 4096, | |
} | |
# Define safety settings for content generation | |
safety_settings = [ | |
{"category": f"HARM_CATEGORY_{category}", | |
"threshold": "BLOCK_MEDIUM_AND_ABOVE"} | |
for category in ["HARASSMENT", "HATE_SPEECH", "SEXUALLY_EXPLICIT", "DANGEROUS_CONTENT"] | |
] | |
# Initialize the GenerativeModel with the specified model name, configuration, and safety settings | |
model = genai.GenerativeModel( | |
model_name="gemini-pro-vision", | |
generation_config=generation_config, | |
safety_settings=safety_settings, | |
) | |
# Function to read image data from a file path | |
def read_image_data(file_path): | |
image_path = Path(file_path) | |
if not image_path.exists(): | |
raise FileNotFoundError(f"Could not find image: {image_path}") | |
return {"mime_type": "image/jpeg", "data": image_path.read_bytes()} | |
# Function to generate a response based on a prompt and an image path | |
def generate_gemini_response(prompt, image_path): | |
image_data = read_image_data(image_path) | |
response = model.generate_content([prompt, image_data]) | |
return response.text | |
# Initial input prompt for the plant pathologist | |
input_prompt = """ | |
As a highly skilled dermatologist, your expertise is indispensable. You will be provided with information or samples related to Skin diseases, and your role involves conducting a detailed analysis to identify the specific issues, propose solutions, and offer recommendations. | |
**Analysis Guidelines:** | |
1. **Disease Identification:** Examine the provided information or samples to identify and characterize Skin diseases accurately. | |
2. **Detailed Findings:** Provide in-depth findings on the nature and extent of the identified Skin diseases, including affected parts, symptoms, and potential causes. | |
3. **Next Steps:** Outline the recommended course of action for managing and controlling the identified diseases. This may involve treatment options, preventive measures, or further investigations. | |
4. **Recommendations:** Offer informed recommendations for maintaining plant health, preventing disease spread, and optimizing overall plant well-being. | |
5. **Important Note:** As a dermatologist, your insights are vital for informed decision-making. Your response should be thorough, concise, and focused on Skin health. | |
**Disclaimer:** | |
*"Please note that the information provided is based on human Skin analysis and should not replace professional dermatologist advice. Consult with qualified dermatologist experts before implementing any strategies or treatments."* | |
Your role is pivotal in ensuring the health and productivity of humans. Proceed to analyze the provided information or samples, adhering to the structured | |
""" | |
# Function to process uploaded files and generate a response | |
def process_uploaded_files(files): | |
file_path = files[0].name if files else None | |
response = generate_gemini_response( | |
input_prompt, file_path) if file_path else None | |
return file_path, response | |
# Gradio interface setup | |
with gr.Blocks() as demo: | |
file_output = gr.Textbox() | |
image_output = gr.Image() | |
combined_output = [image_output, file_output] | |
# Upload button for user to provide images | |
upload_button = gr.UploadButton( | |
"Click to Upload an Image", | |
file_types=["image"], | |
file_count="multiple", | |
) | |
# Set up the upload button to trigger the processing function | |
upload_button.upload(process_uploaded_files, | |
upload_button, combined_output) | |
# Launch the Gradio interface with debug mode enabled | |
demo.launch(debug=True) | |