> ## 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. # Search Content > Semantic search over entities, comments, and messages 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>. ; }; Performs vector-similarity search over project content (entities, comments, and chat messages) using AI embeddings. Returns the most semantically relevant results for the given query. **Requires a paid plan with semantic search enabled.** **Authentication required.** Send a user's access token as `Authorization: Bearer ` — missing token → `401`, invalid/expired token → `403` (refresh and retry). A service or master key is accepted too; such a request has no signed-in user, so the per-user filtering under [What's left out](#whats-left-out) doesn't apply to it. ## Body Parameters The natural language search query. Content types to search. Any combination of `entity`, `comment`, `message`. Restrict search to a specific space. Only applies with a `spaceId`. When `true`, the search also includes every space nested under it — children, grandchildren, the whole subtree at any depth — not just the named space. Ignored without a `spaceId`. Restrict message search to a specific conversation. Maximum number of results to return. A whole number from `1` to `50`, sent as a JSON number. A value outside that range is rejected with `400 search/invalid-body` — a `limit` above `50` isn't lowered to `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 result 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 Returns an array of result objects ordered by similarity (highest first): ```json theme={null} [ { "sourceType": "entity", "similarity": 0.87, "record": { ...Entity | Comment | ChatMessage... } } ] ``` Each result includes: * `sourceType` — one of `"entity"`, `"comment"`, or `"message"`, indicating which type of record was matched. * `similarity` — cosine similarity score between the query and the matched content. * `record` — the fully populated entity, comment, or chat message object. Entity records carry `commentsCount`. A record's `user` is the author's public [User](/v8/data-models/user) — no email or other private fields. ### What's left out Comments their author deleted are never returned. Comments a moderator removed are never returned either — to anyone, including the removed comment's author and requests made with a service or master key. Results are also filtered for the signed-in user (with the `moderation` bundle installed): * Content by users they are block-edged with, in either direction, is left out. * Comments on an entity whose author has blocked them are left out — their own comments there included. ## Error Responses The endpoint requires a user token or a service or master key. A missing token returns a bare `401`; an invalid or expired token returns a bare `403` — refresh the access token and retry. Returned when the body fails validation: `query` is missing or empty, `limit` isn't a whole number from `1` to `50`, `sourceTypes` contains a value other than `entity`, `comment` or `message`, `spaceId` or `conversationId` isn't a UUID, or `includeChildSpaces` isn't a boolean. ```json theme={null} { "error": "limit: Too big: expected number to be <=50", "code": "search/invalid-body" } ``` ```json theme={null} { "error": "Semantic search requires a paid plan", "code": "project/plan-required" } ``` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.