Gemini Video

from openai import OpenAI

client = OpenAI(
    api_key="sk-mai-this_a_test_string_please_use_your_generated_key_during_testing",
    base_url="https://mavi-backend.memories.ai/serve/api/v2/vu"
)

def call_my_vlm():
    resp = client.chat.completions.create(
        model="gemini:gemini-2.5-flash",  # e.g. gemini:gemini-3-flash-preview or gemini:gemini-2.5-flash
        messages=[
            {"role": "system", "content": "You are a multimodal assistant. Keep your answers concise."},
            {
                "role": "user",
                "content": [
                    {
                        "type": "text",
                        "text": "Please summarize the content of this video and image"
                    },
                    {
                        "type": "input_file",
                        "file_uri": "https://storage.googleapis.com/memories-test-data/gun5.png",  # base64 or url, video does not support base64
                        "mime_type": "image/jpeg"
                    },
                    {
                        "type": "input_file",
                        "file_uri": "https://storage.googleapis.com/memories-test-data/test_1min.mp4",  # base64 or url, video does not support base64
                        "mime_type": "video/mp4"
                    }
                ]
            }
        ],
        temperature=0.7,  # Controls randomness: 0.0-2.0, higher = more random
        max_tokens=1000,  # Maximum number of tokens to generate
        top_p=1.0,  # Nucleus sampling: 0.0-1.0, consider tokens with top_p probability mass
        frequency_penalty=0.0,  # -2.0 to 2.0, reduces repetition of frequent tokens
        presence_penalty=0.0,  # -2.0 to 2.0, increases likelihood of new topics
        n=1,  # Number of completions to generate
        stream=False,  # Whether to stream the response
        stop=None,  # Stop sequences (list of strings)
        extra_body={
            "metadata": {
                "thinking_config": {
                    "thinking_budget": 1024
                },
                "response_mime_type": "application/json",  # application/json, json_schema
                "responseSchema": {
                    "type": "OBJECT",
                    "properties": {
                        "video_summary": {
                            "type": "STRING",
                            "description": "Summary of the video content from 1 second to 8 seconds."
                        },
                        "image_summary": {
                            "type": "STRING",
                            "description": "Summary of the image content."
                        }
                    },
                    "required": [
                        "video_summary",
                        "image_summary"
                    ]
                }
            }
        }
    )
    return resp

# Usage example
result = call_my_vlm()
print(result)