Skip to main content

​
Overview

Streams an AI-generated answer to a natural language question, grounded in your project’s content. Uses SSE (Server-Sent Events) to deliver tokens incrementally. Returns source citations once the stream completes. For integration guidance, see Ask Content.

​
Usage Example

import { useAskContent } from "@replyke/react-js";

function AskUI() {
  const { answer, sources, streaming, loading, error, ask, reset } = useAskContent();

  return (
    <div>
      <button onClick={() => ask({ query: "How do I reset my password?" })} disabled={loading || streaming}>
        Ask
      </button>
      {answer && <p>{answer}{streaming && " ▋"}</p>}
      {sources.map((s) => <div key={s.record.id}>[{s.sourceType}] {s.record.id}</div>)}
    </div>
  );
}

​
Parameters

Call ask with:
​
query
string
required
The natural language question.
​
sourceTypes
("entity" | "comment" | "message")[]
Limit the content types searched for context.
​
spaceId
string
Scope context lookup to a specific space.
​
conversationId
string
Scope context lookup to a specific conversation.
​
limit
number
Maximum number of source records to use as context.

​
Returns

​
answer
string
The AI-generated answer. Grows token by token while streaming is true.
​
sources
ContentSearchResult[]
Source records used as context. Populated after streaming ends.
​
streaming
boolean
true while the SSE stream is open and tokens are arriving.
​
loading
boolean
true from ask() call until the first token arrives.
​
error
string | null
Error message if the request failed.
​
ask
(props) => void
Starts a new question. Aborts any in-flight stream first.
​
reset
() => void
Aborts in-flight stream and clears all state.
In React Native, SSE streaming requires polyfills. Install react-native-fetch-api, web-streams-polyfill, and react-native-polyfill-globals, then call polyfillGlobals() at app startup before using this hook.