google-genai-sdk-python

Use this skill to write high-quality, idiomatic Python code for the Gemini API.

Reference Materials

Identify the user's task and refer to the relevant file:

• Setup & Client: Installation, auth, client initialization.
• Models: Recommended models (Flash, Pro, Lite, Imagen, Veo).
• Text Generation: Basic inference, streaming, system instructions, safety.
• Chat: Multi-turn conversations and history.
• Reasoning: Thinking config (thinking_level / thinking_budget), thought signatures.
• Structured Output: JSON schemas, Pydantic models, Enums.
• Multimodal Inputs: Images, audio, video, PDFs, media resolution.
• Tools: Function calling, code execution, Google Search grounding.
• Media Generation: Image generation/editing (Imagen), video generation (Veo).
• Source Code: Raw SDK source code for deep inspection.

Core Principles

1. Unified SDK: Always use google-genai.
2. Stateless Models: Use client.models for single requests.
3. Stateful Chats: Use client.chats for conversations.
4. Types: Import from google.genai.types.