useAllemChat

Chat hook with streaming, message history, and provider context. Built on the Vercel AI SDK.

import { useAllemChat } from "@allem-sdk/ai";

Options

Prop	Type	Default	Description
api	string	—	Override API endpoint from provider
model	string	—	Model identifier (e.g. "gemini-2.0-flash")
provider	"google" \| "anthropic" \| "openai"	—	Provider name
systemPrompt	string	—	System prompt sent with requests
headers	Record<string, string>	—	Extra headers merged with provider headers
experimental_throttle	number	—	Throttle wait in ms for updates

Returns

Property	Type	Description
messages	UIMessage[]	Array of chat messages
sendMessage	({ text }): Promise	Send a message
status	"ready" \| "submitted" \| "streaming"	Current chat status
stop	() => void	Stop streaming
setMessages	(msgs) => void	Replace message history

Usage

const { messages, sendMessage, status } = useAllemChat({
  provider: "anthropic",
  model: "claude-sonnet-4-20250514",
  systemPrompt: "You are a helpful assistant.",
});

const isLoading = status === "submitted" || status === "streaming";

// Send a message
await sendMessage({ text: "Hello!" });

// Render messages
messages.map((m) => (
  <div key={m.id}>
    {m.parts?.filter((p) => p.type === "text").map((p) => p.text).join("")}
  </div>
));