> ## Documentation Index > Fetch the complete documentation index at: https://docs.roark.ai/llms.txt > Use this file to discover all available pages before exploring further. # Create a knowledge base > Creates a knowledge base. TEXT and JSON sources accept inline `content`. FILE sources require `filename`, `mimeType`, and base64-encoded `contentBase64` — the file is decoded server-side, stored in S3, and (for PDFs) text-extracted inline before the response returns. ## OpenAPI ````yaml /api-reference/openapi.documented.json post /v1/knowledge-base openapi: 3.1.0 info: title: Roark Analytics API description: >- The Roark Analytics API gives you access to the same API that powers the award winning Roark Analytics platform. version: 1.0.0 servers: - description: Production url: https://api.roark.ai security: - Bearer: [] tags: - name: Agent - name: Agent Endpoint - name: Call - name: Chat - name: Metric - name: Metric Policy - name: Metric Collection Job - name: Simulation Persona - name: Simulation Scenario - name: Simulation Run Plan - name: Simulation Run Plan Job - name: Simulation Job - name: HTTP Request Definition - name: Webhook - name: Issue - name: Knowledge Base - name: Call Analysis - name: Health paths: /v1/knowledge-base: post: tags: - Knowledge Base summary: Create a knowledge base description: >- Creates a knowledge base. TEXT and JSON sources accept inline `content`. FILE sources require `filename`, `mimeType`, and base64-encoded `contentBase64` — the file is decoded server-side, stored in S3, and (for PDFs) text-extracted inline before the response returns. operationId: postV1Knowledge-base requestBody: content: application/json: schema: type: object properties: name: type: string minLength: 1 maxLength: 120 description: Customer-facing name. Unique within the project. Required. description: type: - string - 'null' maxLength: 500 description: Optional short blurb shown in pickers. sourceType: type: string enum: - TEXT - FILE - JSON description: >- Source types accepted via the public create endpoint. URL ingestion is currently only available in the platform UI. content: type: - string - 'null' description: >- For TEXT: raw markdown/text. For JSON: a JSON string (validated server-side and re-formatted with stable whitespace). Required for TEXT and JSON; omit for FILE. filename: type: - string - 'null' minLength: 1 maxLength: 255 description: >- For FILE: customer-supplied filename (informational only — used for download links). mimeType: type: - string - 'null' enum: - application/pdf - text/plain - text/markdown description: >- For FILE: mime type of the uploaded file. Only `application/pdf`, `text/plain`, and `text/markdown` are accepted. contentBase64: type: - string - 'null' description: >- For FILE: base64-encoded file bytes. Required for FILE. Max 10 MB after decoding. PDFs are text-extracted server-side; image-only PDFs are rejected. required: - name - sourceType title: CreateKnowledgeBaseInput description: >- Input for creating a knowledge base. See `sourceType` for which fields are required. responses: '201': description: The created knowledge base. content: application/json: schema: type: object properties: data: type: object properties: id: type: string format: uuid description: Unique identifier of the knowledge base. name: type: string description: Customer-supplied name. Unique within the project. description: type: - string - 'null' description: Optional customer-supplied description. sourceType: type: string enum: - TEXT - FILE - JSON - URL description: >- How the knowledge base content was provided. TEXT/JSON are stored as-is; FILE was uploaded and its text content extracted (PDF → text); URL was scraped from a webpage into markdown. status: type: string enum: - READY - PROCESSING - PENDING_UPLOAD - FAILED description: >- Lifecycle of the knowledge base. READY means the content is available to metrics. PROCESSING is set during PDF text extraction. FAILED means extraction errored — see `errorMessage`. originalFilename: type: - string - 'null' description: >- For FILE source: the customer-supplied filename. Null for TEXT/JSON/URL. mimeType: type: - string - 'null' description: >- For FILE source: the mime type of the uploaded file. Null for TEXT/JSON/URL. sourceUrl: type: - string - 'null' description: >- For URL source: the page that was scraped into markdown. Null for TEXT/JSON/FILE. byteSize: type: integer minimum: 0 description: >- Size of the content the model will read at evaluation time. For FILE this is the EXTRACTED text size, not the original PDF size. contentHash: type: - string - 'null' description: >- SHA-256 of the content. Stable across whitespace-equivalent edits for JSON (pretty-printed before hashing). Use it to detect change without diffing the content. errorMessage: type: - string - 'null' description: When `status` is FAILED, the reason. Null otherwise. createdAt: type: string description: Creation timestamp in ISO 8601 format. updatedAt: type: string description: Last update timestamp in ISO 8601 format. required: - id - name - description - sourceType - status - originalFilename - mimeType - sourceUrl - byteSize - contentHash - errorMessage - createdAt - updatedAt title: KnowledgeBase description: >- A customer-uploaded reference document attached to custom metrics as ground truth at evaluation time. required: - data '400': content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' description: Validation error example: type: validation code: invalid_parameter message: The request was invalid param: email description: Bad Request '401': content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' description: Authentication error example: type: authentication code: unauthorized message: Authentication required description: Unauthorized '500': content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' description: Server error example: type: internal code: internal_error message: Internal server error description: Internal Server Error components: schemas: ErrorResponse: type: object properties: type: type: string enum: - validation - authentication - forbidden - not_found - conflict - rate_limit - internal description: The error type category examples: - validation - authentication code: type: string description: Machine-readable error code identifier examples: - invalid_parameter - missing_required_field - unauthorized message: type: string description: Human-readable error message examples: - The request was invalid - Authentication required param: type: string description: The parameter that caused the error (if applicable) examples: - email - user_id details: description: Additional error context information required: - type - code - message securitySchemes: Bearer: type: http scheme: bearer bearerFormat: JWT ````