Google Gemini
Requirements
Section titled “Requirements”Server-side:
GOOGLE_API_KEY=<your-ai-studio-key># or, for Vertex AI:GOOGLE_APPLICATION_CREDENTIALS=/path/to/sa.jsonVERTEX_PROJECT=your-gcp-projectVERTEX_LOCATION=europe-west4Option A — SDK
Section titled “Option A — SDK”from tappass import Agent
agent = Agent("https://tappass.example.com", "tp_...")response = agent.chat("Hello", model="google/gemini-1.5-pro")Option B — OpenAI SDK, zero-code
Section titled “Option B — OpenAI SDK, zero-code”export OPENAI_BASE_URL=https://tappass.example.com/v1export OPENAI_API_KEY=tp_...from openai import OpenAI
client = OpenAI()response = client.chat.completions.create( model="google/gemini-1.5-pro", messages=[{"role": "user", "content": "Hello"}],)What’s supported
Section titled “What’s supported”- Gemini 1.5 Pro, Flash, Flash-8B
- Streaming + non-streaming
- Tool calls (function calling)
- Vision (image + video content)
- JSON mode / schema-typed outputs
Data residency
Section titled “Data residency”For EU residency, use Vertex AI with VERTEX_LOCATION=europe-west4 (Netherlands) or europe-west1 (Belgium). AI Studio (the GOOGLE_API_KEY path) is US-routed and should be disabled when TAPPASS_EU_DATA_RESIDENCY=true.