Gemini.Client.HTTP (GeminiEx v0.8.2)
View SourceUnified HTTP client for both Gemini and Vertex AI APIs using Req.
Supports multiple authentication strategies and provides both regular and streaming request capabilities.
Rate Limiting
All requests are automatically routed through the rate limiter unless
disable_rate_limiter: true is passed in options. The rate limiter:
- Enforces concurrency limits per model
- Honors 429 RetryInfo delays from the API
- Retries transient failures with backoff
- Tracks token usage for budget estimation
See Gemini.RateLimiter for configuration options.
Summary
Functions
Make a DELETE request using the configured authentication.
Make a GET request using the configured authentication.
Make a PATCH request using the configured authentication.
Make a POST request using the configured authentication.
Make an authenticated HTTP request.
Stream a POST request for Server-Sent Events using configured authentication.
Raw streaming POST with full URL (used by streaming manager).
Stream a POST request with specific authentication configuration.
Functions
Make a DELETE request using the configured authentication.
Make a GET request using the configured authentication.
Make a PATCH request using the configured authentication.
Make a POST request using the configured authentication.
Make an authenticated HTTP request.
Options
In addition to standard request options, supports rate limiter options:
:disable_rate_limiter- Bypass rate limiting (default: false):non_blocking- Return immediately if rate limited (default: false):max_concurrency_per_model- Override concurrency limit
Stream a POST request for Server-Sent Events using configured authentication.
Raw streaming POST with full URL (used by streaming manager).
Stream a POST request with specific authentication configuration.