ai

# Butterbase AI Gateway Every app has an LLM gateway with chat, embeddings, model listing, configuration, and usage reporting. One umbrella tool: **`manage_ai`**. | Action | What it does | Returns | |---|---|---| | `chat` | Synchronous chat completion (no streaming) | OpenAI-shaped `{ choices: [...] }` | | `embed` | Vector embeddings for string or string[] | OpenAI-shaped `{ data: [{ embedding: [...] }] }` | | `list_models` | Available models with capabilities | `{ models: AiModel[] }` | | `get_config` | Current AI config (default model, BYOK key flag, etc.) | `AiConfig` | | `update_config` | Set defaults, allowed models, max tokens, BYOK | `AiConfig` | | `get_usage` | Token + cost aggregate over a window | usage record | --- ## 1. Chat ``` manage_ai({ action: "chat", app_id, messages: [ { role: "system", content: "You are a helpful assistant." }, { role: "user", content: "What's RAG?" } ], model: "openai/gpt-4o-mini", // optional — falls back to app's default temperature: 0.2, // optional max_tokens: 500 // optional }) ``` This action sets `stream: false` deliberately — agent tools don't stream. If you need partial-token deltas, drive the SDK's `ai.chatStream(…)` from inside a function or DO instead. `messages[].content` can be a string or an array of content parts (`{ type: "text", text }`, `{ type: "image_url", image_url: {...} }`, `{ type: "video_url", video_url: {...} }`). --- ## 2. Embed ``` manage_ai...