> ## Documentation Index > Fetch the complete documentation index at: https://docs.prisme.ai/llms.txt > Use this file to discover all available pages before exploring further. # Retrieve a knowledge base ## OpenAPI ````yaml /api-reference/storage/swagger.yml get /v1/knowledge_bases/{knowledgeBaseId} openapi: 3.0.3 info: version: 1.0.0 title: Knowledges API description: > Public REST API for the Prisme.ai Knowledges (storage) workspace: knowledge bases, documents (uploaded files, web pages, remote files, connector documents), recurring web-crawl sources, semantic search, access control, per-knowledge-base API keys, and skills. Resource identifiers use the physical prefixes emitted by the implementation (`vs_` knowledge base, `vsf_` document, `seed_` web source, `kb-` API-key slug). This spec documents the public REST surface only. Internal helpers (private automations prefixed with `_`) and admin/GDPR lifecycle operations are not part of the public contract. contact: name: Prisme.ai url: https://prisme.ai servers: - url: https://{host}/v2/workspaces/slug:storage/webhooks description: Prisme.ai workspace webhooks variables: host: default: api.studio.prisme.ai description: API host (override for self-hosted or sandbox) security: - BearerAuth: [] - WorkspaceApiKeyAuth: [] tags: - name: Knowledge Bases description: >- Create, list, read, update, and delete knowledge bases (vector-backed document stores). - name: Documents description: >- Ingest and manage documents (uploaded files, web pages, remote files, connector documents) and their indexing. - name: Web Sources description: >- Recurring web crawl seeds that discover and index pages into a knowledge base. - name: Search description: Semantic search over a knowledge base. - name: Access description: Per-knowledge-base access bindings (user, group, org, agent principals). - name: API Keys description: Per-knowledge-base API keys for connector authentication. - name: Stats description: Aggregate dashboard statistics. - name: Skills description: Prompt/instruction registry entries. paths: /v1/knowledge_bases/{knowledgeBaseId}: parameters: - name: knowledgeBaseId in: path required: true schema: type: string pattern: ^vs_[A-Za-z0-9-]+$ maxLength: 128 description: >- Knowledge base id. Legacy physical prefix `vs_` (the `kb_` rename is deferred). get: tags: - Knowledge Bases summary: Retrieve a knowledge base operationId: getKnowledgeBase parameters: - name: include in: query required: false schema: type: string enum: - processing description: | `processing` triggers a live crawler round-trip that populates the `processing` object (`status`, `metrics`, `crawler_reachable`). Omitted → those live fields are `null`. - name: agent_id in: query required: false schema: type: string description: Agent context for agent-owned knowledge bases. responses: '200': description: The knowledge base. content: application/json: schema: $ref: '#/components/schemas/KnowledgeBase' '401': $ref: '#/components/responses/Error401' '403': $ref: '#/components/responses/Error403' '404': $ref: '#/components/responses/Error404' security: - BearerAuth: [] components: schemas: KnowledgeBase: type: object description: | Knowledge base metadata. PATCH is metadata-only; web-crawl configuration lives in `/web_sources`. required: - id - object - name - provider - index_name - embedding - status - owner - owner_org_slug - created_at properties: id: type: string pattern: ^vs_[A-Za-z0-9-]+$ maxLength: 128 object: type: string enum: - knowledge_base name: type: string maxLength: 256 description: type: string maxLength: 4096 provider: type: string enum: - mock - elasticsearch - opensearch - redis - pgvector - qdrant - pinecone index_name: type: string description: Physical index name on the provider. embedding: type: object required: - model - dimensions properties: model: type: string dimensions: type: integer minimum: 1 chunking_strategy: type: object additionalProperties: true description: Default chunking for documents; overridable per document. parser: type: string enum: - tika - tika-ocr - unstructured - unstructured-ocr - llm - null nullable: true file_parsing: type: object properties: image: type: string audio: type: string document: type: string nullable: true status: type: string enum: - creating - active - failed - deleting description: | `creating` before external resources are provisioned; `active` after metadata + physical setup + owner binding succeed; `failed` is a visible failed state with a cleanup-job hook; `deleting` is the transactional deletion window. document_counts: type: object description: | Per-status aggregate over this store's documents. Maintained with transitions guarded by each document's `index_generation` - duplicate or stale crawler callbacks cannot corrupt counters. properties: queued: type: integer minimum: 0 in_progress: type: integer minimum: 0 completed: type: integer minimum: 0 failed: type: integer minimum: 0 fetch_expired: type: integer minimum: 0 total: type: integer minimum: 0 owner: type: object required: - type - id description: | First-class owner principal (§F-6). For agent-owned (conversation-scope) stores `type: agent` and `id` is the agent id - represented as a `principalType: agent` binding in the platform-managed `product_bindings` store, NOT a blanked `owner_user_id`. `owner_user_id` / `agent_id` below mirror this for convenience and filtering. properties: type: type: string enum: - user - agent - org id: type: string maxLength: 128 owner_user_id: type: string description: '`owner.id` when `owner.type == user`; null for agent-owned stores.' nullable: true owner_org_slug: type: string description: Tenant scope. All knowledge-base lookups are scoped by this field. agent_id: type: string description: >- `owner.id` when `owner.type == agent`; null otherwise. Filterable on list. nullable: true role: type: string enum: - owner - admin - editor - reader - null description: | Caller's effective role, computed at read time from access bindings. Null on cross-workspace (`workspace_jwt`) reads. nullable: true access_reason: type: string enum: - owner - admin_binding - editor_binding - reader_binding - agent_binding - trusted_workspace - null nullable: true processing: $ref: '#/components/schemas/Processing' crawl_settings: type: object description: | Engine-global crawl settings - one Crawler instance per KB, so these are the single values the crawler honors (they are NOT per-seed). Read from the store-level columns; edited via the KB PATCH (added 2026-07-17, web-sources crawl-settings re-home). required: - webpages_limit - periodicity - paused properties: webpages_limit: type: integer minimum: 1 description: | Per-crawl page cap, governance-capped (Platform → Org hierarchy). nullable: true periodicity: type: integer description: | Seconds between crawls; null = manual-only (seconds integer rather than an enum for lossless crawler parity - deviation 06-A-1). nullable: true paused: type: boolean description: Whether the whole crawler is paused. max_webpages_limit: type: integer readOnly: true description: | Resolved governance cap (Platform → Org hierarchy) for `webpages_limit` - the "max allowed" hint surfaced on the KB detail response. Read-only; not accepted on PATCH (added 2026-07-20). nullable: true web_source_count: type: integer minimum: 0 description: | Number of registered web sources (crawl seeds). Summary metadata for list cards - the seed objects themselves stay on `/web_sources` (added 2026-07-15, SPA migration F1). last_active_at: type: integer description: Unix seconds. nullable: true created_at: type: integer updated_at: type: integer Processing: type: object description: | Knowledge-base processing / parser-backend health (§F-5). The crawler is the universal parse/fetch backend for EVERY document (uploads, single pages, web crawl), so this is present whenever the knowledge base has documents - even with zero web sources. Live fields come from the crawler; when it is unreachable `crawler_reachable` is false and the live `status`/`metrics` degrade to null rather than erroring (replacing the legacy overloaded `status:"unknown"` + `crawler_error`). DB-derived per-seed counts live on `/web_sources` and remain available regardless. properties: status: type: string enum: - idle - processing - paused - unknown - null nullable: true crawler_reachable: type: boolean description: | `null` by default - the live crawler round-trip only runs when the KB detail request passes `?include=processing`; `true`/ `false` otherwise. nullable: true health: type: object description: | The persisted crawler health - previously exposed by no endpoint, now surfaced here (powers OUT_OF_SPACE / PAUSED inline banners). properties: status: type: string enum: - HEALTHY - OUT_OF_SPACE - PAUSED - UNAUTHENTICATED - UNHEALTHY message: type: string nullable: true last_event_at: type: integer nullable: true metrics: type: object description: Live KB-wide item counts from the crawler; null when unreachable. properties: total_items: type: integer minimum: 0 indexed: type: integer minimum: 0 failed: type: integer minimum: 0 skipped: type: integer minimum: 0 nullable: true last_run_at: type: integer nullable: true Error: type: object description: | Single error envelope shared by every non-2xx response. `code` is the stable machine-readable identifier; `message` is the human-readable text; `details` is optional structured context. properties: error: type: object required: - code - message properties: code: type: string example: VALIDATION_ERROR message: type: string details: type: object additionalProperties: true required: - error responses: Error401: description: Authentication missing or invalid. content: application/json: schema: $ref: '#/components/schemas/Error' examples: unauthenticated: value: error: code: UNAUTHENTICATED message: Authentication required. Error403: description: Authentication present, authorization denied. content: application/json: schema: $ref: '#/components/schemas/Error' examples: forbidden: value: error: code: FORBIDDEN message: Caller is not allowed to access this resource. hook_rejected: summary: An external content hook blocked ingestion (sync) value: error: code: HOOK_REJECTED message: Content was rejected by a compliance hook. details: rejected_by: hook_pii_filter rejection_reason: detected_unmasked_pii Error404: description: Resource does not exist or is not visible to the caller. content: application/json: schema: $ref: '#/components/schemas/Error' examples: not_found: value: error: code: NOT_FOUND message: knowledge_base.document not found. details: resource: knowledge_base.document id: vsf_unknown securitySchemes: BearerAuth: type: http scheme: bearer bearerFormat: JWT description: >- User session JWT or instance API key (`iak_*`). Send as `Authorization: Bearer `. WorkspaceApiKeyAuth: type: apiKey in: header name: x-prismeai-api-key description: Workspace- or knowledge-base-scoped API key. ````