gemini_multipart_image_upload_and_text_generation.py

1import google.generativeai as genai
2import os
3
4# Setup API Key (ensure GEMINI_API_KEY is set in your environment)
5genai.configure(api_key=os.environ["GEMINI_API_KEY"])
6
7# Upload the file to the File API
8# Note: You can also use PIL.Image for local images without uploading
9sample_file = genai.upload_file(path="input_file.003.jpeg", display_name="Sample Image")
10
11print(f"Uploaded file '{sample_file.display_name}' as: {sample_file.uri}")
12
13# Initialize the model
14model = genai.GenerativeModel(model_name="gemini-1.5-flash")
15
16# Generate content using both text and the uploaded file (multipart)
17response = model.generate_content([sample_file, "Summarize the content of this image."])
18
19print(response.text)