@rayu-dev/rayu-cli 1.2.13 → 1.2.14
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +5 -2
- package/dist/rayu.js +131962 -130529
- package/package.json +3 -1
package/README.md
CHANGED
|
@@ -67,11 +67,14 @@ Inside a session:
|
|
|
67
67
|
|
|
68
68
|
## Providers
|
|
69
69
|
|
|
70
|
-
Rayu supports
|
|
70
|
+
Rayu supports four provider types:
|
|
71
71
|
|
|
72
72
|
- **`anthropic`** — Anthropic API (`ANTHROPIC_API_KEY`)
|
|
73
|
-
- **`openai-compatible`** — Any OpenAI-style endpoint (NVIDIA, DeepSeek, Kimi, OpenRouter, Ollama, LM Studio, etc.)
|
|
73
|
+
- **`openai-compatible`** — Any OpenAI-style endpoint (NVIDIA, DeepSeek, Kimi, OpenRouter, Google Gemini API, Ollama, LM Studio, etc.)
|
|
74
74
|
- **`bedrock`** — AWS Bedrock API (`AWS_BEARER_TOKEN_BEDROCK` or default AWS credentials)
|
|
75
|
+
- **`vertex`** — Google Gemini on Vertex AI (Google OAuth / Application Default Credentials)
|
|
76
|
+
|
|
77
|
+
Google Gemini is available three ways: a **Gemini API key** (`GEMINI_API_KEY`, via the OpenAI-compatible endpoint), **Vertex AI with OAuth/ADC** (project + region scoped), or **Login with Gemini** (interactive Google sign-in — free, no GCP project, via the Gemini Code Assist backend like the Gemini CLI). The Vertex/OAuth credentials also power Imagen 4 image generation and Veo 3.1 video generation. Pick the image/video model with `/model_image_generation` and `/model_video_generation` (default: NVIDIA).
|
|
75
78
|
|
|
76
79
|
Example — NVIDIA NIM headless run:
|
|
77
80
|
|