Spaces:
Sleeping
Sleeping
| import os | |
| import base64 | |
| import requests | |
| import streamlit as st | |
| # OpenAI API Key | |
| # Access the secret API key | |
| # if the app is running locally, you can set the API key as an environment variable | |
| api_key = os.getenv("OPENAI_API_KEY") # Make sure this environment variable is set correctly | |
| headers = { | |
| "Content-Type": "application/json", | |
| "Authorization": f"Bearer {api_key}" | |
| } | |
| def main(): | |
| st.title("Multimodal using GPT-4 Turbo Model") | |
| text = """Prof. Louie F. Cervantes, M. Eng. (Information Engineering) | |
| CCS 229 - Intelligent Systems | |
| Department of Computer Science | |
| College of Information and Communications Technology | |
| West Visayas State University | |
| """ | |
| with st.expander("About"): | |
| st.text(text) | |
| st.write("Upload an image and select the image analysis task.") | |
| # File upload for image | |
| uploaded_image = st.file_uploader("Upload an Image", type=["jpg", "jpeg", "png"]) | |
| if uploaded_image is not None: | |
| # Encode the uploaded image to base64 | |
| base64_image = base64.b64encode(uploaded_image.getvalue()).decode('utf-8') | |
| # Display the uploaded image | |
| st.image(uploaded_image, caption="Uploaded Image", use_container_width=True) | |
| # List of image analysis tasks | |
| analysis_tasks = [ | |
| "Scene Analysis: Describe the scene depicted in the image. Identify the objects present, their spatial relationships, and any actions taking place.", | |
| "Object Detection and Classification: Identify and classify all objects present in the image. Provide detailed descriptions of each object, including its size, shape, color, and texture.", | |
| "Image Captioning: Generate a concise and accurate caption that describes the content of the image.", | |
| "Visual Question Answering: Answer specific questions about the image, such as 'What color is the car?' or 'How many people are in the image?'", | |
| "Image Similarity Search: Given a query image, find similar images from a large dataset based on visual features.", | |
| "Image Segmentation: Segment the image into different regions corresponding to objects or areas of interest.", | |
| "Optical Character Recognition (OCR): Extract text from the image, such as printed or handwritten text.", | |
| "Diagram Understanding: Analyze a diagram (e.g., flowchart, circuit diagram) and extract its structure and meaning.", | |
| "Art Analysis: Describe the artistic style, subject matter, and emotional impact of an image.", | |
| "Medical Image Analysis: Analyze medical images (e.g., X-rays, MRIs) to detect abnormalities or diagnose diseases.", | |
| "Obtaining text data: Extract text from the image, such as names, date, time, etc.", | |
| ] | |
| # Task selection dropdown | |
| selected_task = st.selectbox("Select an image analysis task:", analysis_tasks) | |
| # Button to generate response | |
| if st.button("Generate Response"): | |
| if uploaded_image is None or not selected_task: # Check if a task is selected | |
| st.error("Please upload an image and select a task.") | |
| else: | |
| # Prepare the multimodal prompt | |
| payload = { | |
| "model": "gpt-4-turbo", | |
| "messages": [ | |
| { | |
| "role": "user", | |
| "content": [ | |
| { | |
| "type": "text", | |
| "text": selected_task | |
| }, | |
| { | |
| "type": "image_url", | |
| "image_url": { | |
| "url": f"data:image/jpeg;base64,{base64_image}" | |
| } | |
| } | |
| ] | |
| } | |
| ], | |
| "max_tokens": 2048, | |
| } | |
| with st.spinner("Processing..."): | |
| # Generate response | |
| response = requests.post("https://api.openai.com/v1/chat/completions", headers=headers, json=payload) | |
| # Check for errors in the response | |
| if response.status_code != 200: | |
| st.error(f"Error: {response.status_code} - {response.text}") | |
| else: | |
| # Display the response | |
| content = response.json() | |
| # Show the response content | |
| st.success("Response generated!") | |
| # Extract the content of the response | |
| # Access the content correctly from the response JSON | |
| contentstring = content['choices'][0]['message']['content'] | |
| st.markdown(f"AI Response: {contentstring}") | |
| if __name__ == "__main__": | |
| main() |