Packages

gemini_ex

0.14.0
0.15.0 0.14.0 0.13.0 0.12.0 0.11.1 0.11.0 0.10.0 0.9.1 0.9.0 0.8.8 0.8.7 0.8.6 0.8.5 0.8.4 0.8.3 0.8.2 0.8.1 0.8.0 0.7.3 0.7.2 0.7.1 0.7.0 0.6.4 0.6.3 0.6.2 0.6.1 0.6.0 0.5.2 0.5.1 0.5.0 0.4.0 0.3.0 0.2.3 0.2.2 0.2.1 0.2.0 0.1.1 0.1.0 0.0.3 0.0.2 0.0.1

Comprehensive Elixir client for Google's Gemini AI API with dual authentication, embeddings with MRL, streaming, type safety, and built-in telemetry for production applications.

HexDocs

Current section

Files

Jump to
Readme
41 Versions
7 Dependencies
Dependants
Files
Activity
gemini_ex guides README.md
Raw

guides/README.md 

# GeminiEx Guides



This folder contains the primary guides for running GeminiEx in production:



- `interactions.md` – stateful interactions (CRUD), streaming, and resumption

- `rate_limiting.md` – atomic token reservations, jittered retry windows, and concurrency gating defaults

- `structured_outputs.md` – structured JSON responses

- `files.md`, `batches.md`, `operations.md` – working with Files, Batch jobs, and long-running operations



Rate limiting highlights (v0.7.1):

- Atomic budget reservation with safety multipliers and reconciliation after responses

- Shared retry windows with jittered release (`retry_window_set/hit/release` telemetry)

- Telemetry for budget reservations (`budget_reserved`/`budget_rejected`) and concurrency gate hardening



For model selection, use `Gemini.Config.model_for_use_case/2` to resolve the built-in use-case aliases (`:cache_context`, `:report_section`, `:fast_path`) to the registered model strings.