> ## Documentation Index > Fetch the complete documentation index at: https://developers.datagrid.com/llms.txt > Use this file to discover all available pages before exploring further. # List summaries > Returns a list of AI-generated summary records for a knowledge table. Use `record_type=row` (the default) for per-row summaries, or `record_type=table` for the single table-level summary. This endpoint reflects the current index state and does not consume AI credits. ## OpenAPI ````yaml get /tables/{table_id}/summaries openapi: 3.0.3 info: version: 0.1.1 title: Datagrid API description: Datagrid API servers: - url: https://api.datagrid.com/v1 security: - BearerAuth: [] paths: /tables/{table_id}/summaries: get: tags: - Tables summary: List summaries description: >- Returns a list of AI-generated summary records for a knowledge table. Use `record_type=row` (the default) for per-row summaries, or `record_type=table` for the single table-level summary. This endpoint reflects the current index state and does not consume AI credits. operationId: Tables.listSummaries parameters: - name: table_id in: path required: true schema: type: string description: The id of the table to retrieve summaries from. - name: limit in: query schema: type: integer default: 500 minimum: 1 maximum: 1000 required: false description: >- The limit on the number of objects to return, ranging between 1 and 1000. - $ref: '#/components/parameters/next' - name: record_type in: query required: false schema: type: string enum: - row - table default: row description: >- Which summary variant to return. `row` (default) returns one summary per source row. `table` returns the single table-level summary. Matches `record_type` on each Summary in the response. responses: '200': description: List of summaries content: application/json: schema: type: object required: - object - data properties: object: type: string enum: - list data: type: array items: $ref: '#/components/schemas/Summary' description: >- An array containing the actual response elements, paginated by any request parameters. cursor: type: string description: >- The stable cursor to use to get the next page of summaries. x-stainless-pagination-property: purpose: next_cursor_field has_more: type: boolean description: >- Whether or not there are more elements available after this set. If false, this set comprises the end of the list. '400': description: >- Bad request. The teamspace does not support summary listing (non-Turbopuffer vector store), or `next` is not a valid summary cursor. '404': description: >- Not found. The requested table does not exist, or the authenticated user does not have permission to access it. '429': description: >- Rate limit exceeded. The request has been throttled because the rate limit for this endpoint has been reached. Check the `Retry-After` response header and retry after the specified number of seconds. content: application/json: schema: $ref: '#/components/schemas/RateLimitError' components: parameters: next: name: next in: query schema: type: string required: false description: >- A cursor to use in pagination to continue a query from the previous request. This is automatically added when the request has more results to fetch. schemas: Summary: type: object description: >- The `summary` object represents an AI-generated summary record produced during knowledge indexing. A row summary describes a single source row; a table summary describes the entire table. required: - object - id - table_id - record_type - summary - is_vectorized - created_at - updated_at properties: object: type: string enum: - summary description: The object type, which is always `summary`. id: type: string description: The summary identifier. table_id: type: string description: The id of the table this summary belongs to. record_type: type: string enum: - row - table description: >- The kind of summary. `row` is per source row; `table` is the single table-level summary. primary_key: type: string nullable: true description: >- The primary key of the source row for a row summary. `null` for table summaries. title: type: string nullable: true description: The generated title, when available. summary: type: string nullable: true description: >- The AI-generated summary, as markdown. `null` for records that have not finished indexing. source_data: type: object additionalProperties: true nullable: true description: >- The source row data used to generate the summary. `null` when unavailable or not applicable. is_vectorized: type: boolean description: >- Whether the summary has been embedded and is available for retrieval. created_at: type: string format: date-time nullable: true description: >- The ISO string for when the summary was created. `null` for records that have not finished indexing. updated_at: type: string format: date-time nullable: true description: >- The ISO string for when the summary was last updated. `null` for records that have not finished indexing. RateLimitError: type: object description: >- Returned when the rate limit is exceeded. Rate limits are enforced per teamspace, endpoint path, and HTTP method over a 60-second sliding window. Each endpoint may have its own limit — check the X-RateLimit-Limit response header for the effective value. required: - error - message - retryable - status_code properties: status_code: type: integer description: The HTTP status code (429). statusCode: type: integer deprecated: true description: Deprecated. Use status_code instead. error: type: string enum: - rate_limit_exceeded description: The error code identifying this as a rate limit error. message: type: string description: A human-readable error message. mitigation: type: string description: Suggested action to resolve the error. retryable: type: boolean description: Whether the request can be retried after a delay. details: type: object properties: reason: type: string description: A detailed explanation of why the rate limit was exceeded. securitySchemes: BearerAuth: type: http scheme: bearer ````