> ## Documentation Index > Fetch the complete documentation index at: https://docs.sublay.io/llms.txt > Use this file to discover all available pages before exploring further. # Ask Content > AI-powered Q&A grounded in your project's content export const SpaceReputationParams = ({variant = "context", field = "path"}) => { const isUser = variant === "user"; return <> Opt-in. Adds a spaceReputation number to each returned user, scoped to a single space. Requires the reputation bundle. The reputation total is always present regardless;{" "} spaceReputation is purely additive and only appears when you pass this object. This object is the primary form — it replaces the deprecated flat props below. See the{" "} Reputation data model for the full contract. {isUser ? Which bucket to read. A space <uuid> reads that space's bucket; "none" reads the project-general (space-less) bucket.{" "} "context" is rejected (400) on this endpoint — there is no space context to derive. The empty string and the legacy general / null aliases are also rejected. Missing buckets read as 0. : Which bucket to read. One of: a space <uuid>{" "} (that space's bucket), "none" (the project-general, space-less bucket), or{" "} "context" (the space derived from the request context — resolved per-row on lists, or the single space on member/team/conversation surfaces). The empty string and the legacy{" "} general / null aliases are rejected (400). Missing buckets read as 0. } Only honored when spaceId is an explicit space <uuid>. When true, spaceReputation is the{" "} subtree sum — the named space plus all of its descendant spaces (the root space's own bucket included). Ignored for{" "} "none"; not allowed with "context". {isUser ? Deprecated — use the spaceReputation{" "} object instead. The flat form of spaceReputation.spaceId. Still accepted (the object wins if both are passed); removal is a later major version. Accepts a space <uuid> or "none" only —{" "} "context" is rejected (400) on this endpoint. : Deprecated — use the spaceReputation{" "} object instead. The flat form of spaceReputation.spaceId. Still accepted (the object wins if both are passed); removal is a later major version. Accepts a space <uuid>, "none", or{" "} "context". } Deprecated — use{" "} spaceReputation.includeDescendants instead. The flat form, only honored alongside an explicit spaceReputationId <uuid>. ; }; Answers a natural language question using content from your project as context. The endpoint first performs semantic retrieval to find relevant content, then sends the context to an LLM to generate a grounded answer. Responds via **Server-Sent Events (SSE)** for streaming output. **Requires a paid plan with semantic search enabled.** **Requires an authenticated user.** Send the user's access token as `Authorization: Bearer `. Requests without a valid token are rejected before any work is done — missing token → `401`, invalid/expired token → `403` (refresh the access token and retry). ## Body Parameters The question to answer. Typos and ambiguous phrasing are handled gracefully. Content types to use as context. Any combination of `entity`, `comment`, `message`. Restrict the context lookup to a specific space. Only applies with a `spaceId`. When `true`, the context lookup also includes every space nested under it — children, grandchildren, the whole subtree at any depth — not just the named space. Use it to ask across a community and all of its channels at once. Ignored without a `spaceId`. Restrict message context lookup to a specific conversation. Maximum number of content chunks to retrieve for context. Maximum `50`. ## Query Parameters ### Space-scoped reputation This endpoint has a space in context, so it accepts the opt-in reputation params. They add a `spaceReputation` field to each source record's populated `user`, alongside the always-present `reputation` total. Requires the `reputation` bundle. See the [Reputation data model](/v8/data-models/reputation) for the full contract. ## Response The response is a **Server-Sent Events** stream with `Content-Type: text/event-stream`. Three event types are emitted: **`token`** — streamed LLM answer tokens: ``` event: token data: {"content": "Based on"} event: token data: {"content": " the discussion..."} ``` **`sources`** — the content records used as context, sent after the answer is complete: ``` event: sources data: [{"sourceType": "entity", "similarity": 0.87, "record": {...}}, ...] ``` Each source object follows the same shape as the [Search Content](/v8/api-reference/search/search-content) response — `sourceType`, `similarity`, and a fully populated `record`. An empty array is sent when no relevant context was found. The answer is generated only from content the signed-in user can see: content by users they are block-edged with (in either direction), comments on an entity whose author has blocked them, and comments their author deleted, are never used as context or returned as sources. **`done`** — signals the stream is finished: ``` event: done data: {} ``` If no relevant content is found above the similarity threshold, the LLM response is skipped and the answer event immediately says "I couldn't find any relevant content to answer your question." ## Error Responses The endpoint requires an authenticated user. A missing token returns a bare `401`; an invalid or expired token returns a bare `403` — refresh the access token and retry. These are returned before streaming starts. ```json theme={null} { "error": "Semantic search requires a paid plan", "code": "project/plan-required" } ``` Only returned when headers have not yet been sent (i.e., before streaming starts). If an error occurs after streaming starts: ``` event: error data: {"error": "Internal server error"} ``` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.