> ## Documentation Index > Fetch the complete documentation index at: https://dify-6c0370d8-fix-template-upload-size-guidance.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. # Create Chunks > Create one or more chunks within a document. ## OpenAPI ````yaml /en/api-reference/openapi_service.json post /datasets/{dataset_id}/documents/{document_id}/segments openapi: 3.0.1 info: description: >- REST API for Dify applications and knowledge bases. Application endpoints authenticate with an app API key; knowledge endpoints authenticate with a dataset API key. title: Dify Service API version: 1.0.0 servers: - description: >- Base URL of the Dify Service API. For self-hosted deployments, replace it with your own API base URL. url: https://{api_base_url} variables: api_base_url: default: api.dify.ai/v1 description: Host and path of the API base URL, without the `https://` prefix. security: - ApiKeyAuth: [] tags: - description: Operations related to chat messages and interactions. name: Chat Messages - description: File upload and preview operations. name: Files - description: Operations related to end user information. name: End Users - description: User feedback operations. name: Feedback - description: Operations related to managing conversations. name: Conversations - description: Text-to-Speech and Speech-to-Text operations. name: Audio - description: Operations to retrieve application settings and information. name: Applications - description: Operations related to managing annotations for direct replies. name: Annotations - description: Endpoints for resuming paused workflows that require human input. name: Human Input - description: Operations for executing and managing workflows. name: Workflow Runs - description: Operations related to text generation and completion. name: Completion Messages - description: >- Operations for managing knowledge bases, including creation, configuration, and retrieval. name: Knowledge Bases - description: >- Operations for creating, updating, and managing documents within a knowledge base. name: Documents - description: Operations for managing document chunks and child chunks. name: Chunks - description: >- Operations for managing knowledge base metadata fields and document metadata values. name: Metadata - description: Operations for managing knowledge base tags and tag bindings. name: Tags - description: Operations for retrieving available models. name: Models - description: >- Operations for managing and running knowledge pipelines, including datasource plugins and pipeline execution. name: Knowledge Pipeline paths: /datasets/{dataset_id}/documents/{document_id}/segments: post: tags: - Chunks summary: Create Chunks description: Create one or more chunks within a document. operationId: createSegments parameters: - description: >- Knowledge base ID. Obtain it from [List Knowledge Bases](/en/api-reference/knowledge-bases/list-knowledge-bases). in: path name: dataset_id required: true schema: format: uuid type: string - description: >- Document ID. Obtain it from [List Documents](/en/api-reference/documents/list-documents). in: path name: document_id required: true schema: format: uuid type: string requestBody: content: application/json: schema: properties: segments: description: Array of chunk objects to create. items: properties: answer: description: >- Answer text. Required for Q&A-mode (`qa_model`) documents. type: string attachment_ids: description: Attachment file IDs. items: type: string type: array content: description: Chunk text content. minLength: 1 type: string keywords: description: Keywords for the chunk. items: type: string type: array required: - content type: object minItems: 1 type: array required: - segments type: object required: true responses: '200': content: application/json: examples: success: summary: Response Example value: data: - answer: '' attachments: [] child_chunks: [] completed_at: 1741267200 content: Dify is an open-source LLM app development platform. created_at: 1741267200 created_by: ad313dd6-ef04-4dd1-a5b0-c0f0b9e2e7e4 disabled_at: null disabled_by: null document_id: a8e0e5b5-78c6-4130-a5ce-25feb0e0b4ac enabled: true error: null hit_count: 0 id: f3d1c7be-9f3a-40d8-8eb8-3a1ef9c3f2c1 index_node_hash: abc123def456 index_node_id: a1b2c3d4-e5f6-7890-abcd-000000000001 indexing_at: 1741267200 keywords: - dify - platform - llm position: 1 sign_content: '' status: completed stopped_at: null summary: null tokens: 12 updated_at: 1741267200 updated_by: ad313dd6-ef04-4dd1-a5b0-c0f0b9e2e7e4 word_count: 9 doc_form: text_model schema: properties: data: description: List of created chunks. items: $ref: '#/components/schemas/Segment' type: array doc_form: description: Document chunking mode used by this document. type: string type: object description: Chunks created successfully. '400': content: application/json: examples: invalid_param_limit: summary: invalid_param (segments limit) value: code: invalid_param message: Exceeded maximum segments limit of 1000. status: 400 provider_not_initialize: summary: provider_not_initialize value: code: provider_not_initialize message: >- No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider. status: 400 validation_error: summary: schema validation (non-standard body) value: error: |- 1 validation error for SegmentCreatePayload segments.0.content String should have at least 1 character [type=string_too_short, input_value='', input_type=str] description: >- - `provider_not_initialize` : The knowledge base uses high-quality indexing but its embedding model is missing or misconfigured. - `invalid_param` : A chunk field is invalid (for example, `answer` is required for Q&A-mode documents) or the number of chunks exceeds the per-request limit. - Request-body schema validation (such as empty `content`) returns a non-standard body `{"error": ""}` with no `code` or `status` field. '403': content: application/json: examples: forbidden_1: summary: forbidden (api access) value: code: forbidden message: Dataset api access is not enabled. status: 403 forbidden_2: summary: forbidden (vector space) value: code: forbidden message: >- The capacity of the vector space has reached the limit of your subscription. status: 403 forbidden_3: summary: forbidden (rate limit) value: code: forbidden message: >- Sorry, you have reached the knowledge base request rate limit of your subscription. status: 403 forbidden_4: summary: forbidden (upgrade plan) value: code: forbidden message: >- To unlock this feature and elevate your Dify experience, please upgrade to a paid plan. status: 403 description: >- - `forbidden` : Dataset api access is not enabled. - `forbidden` : The capacity of the vector space has reached the limit of your subscription. - `forbidden` : Sorry, you have reached the knowledge base request rate limit of your subscription. - `forbidden` : To unlock this feature and elevate your Dify experience, please upgrade to a paid plan. '404': content: application/json: examples: not_found_1: summary: not_found value: code: not_found message: Dataset not found. status: 404 not_found_2: summary: not_found value: code: not_found message: Document not found. status: 404 not_found_3: summary: not_found value: code: not_found message: Document is not completed. status: 404 not_found_4: summary: not_found value: code: not_found message: Document is disabled. status: 404 description: |- - `not_found` : Dataset not found. - `not_found` : Document not found. - `not_found` : Document is not completed. - `not_found` : Document is disabled. '503': content: application/json: examples: service_unavailable: summary: service_unavailable value: code: service_unavailable message: >- Unable to verify vector space usage right now. Please try again later. status: 503 description: >- `service_unavailable` : Vector space usage could not be verified. Returned on the Dify Cloud Sandbox plan only; retry the request later. components: schemas: Segment: properties: answer: description: Answer content, used in Q&A mode documents. type: string attachments: description: Files attached to this chunk. items: properties: extension: description: File extension. type: string id: description: Attachment file identifier. type: string mime_type: description: MIME type of the file. type: string name: description: Original file name. type: string size: description: File size in bytes. type: integer source_url: description: URL to access the attachment. type: string type: object type: array child_chunks: description: >- Child chunks belonging to this chunk. Only present for hierarchical mode documents. items: $ref: '#/components/schemas/ChildChunk' type: array completed_at: description: Timestamp when indexing completed. `null` if not yet completed. nullable: true type: number content: description: Text content of the chunk. type: string created_at: description: Creation timestamp (Unix epoch in seconds). type: number created_by: description: ID of the user who created the chunk. type: string disabled_at: description: Timestamp when the chunk was disabled. `null` if enabled. nullable: true type: number disabled_by: description: ID of the user who disabled the chunk. `null` if enabled. nullable: true type: string document_id: description: ID of the document this chunk belongs to. type: string enabled: description: Whether the chunk is enabled for retrieval. type: boolean error: description: Error message if indexing failed. `null` when no error. nullable: true type: string hit_count: description: Number of times this chunk has been matched in retrieval queries. type: integer id: description: Unique identifier of the chunk. type: string index_node_hash: description: Hash of the indexed content, used to detect changes. type: string index_node_id: description: ID of the index node in the vector store. type: string indexing_at: description: Timestamp when indexing started. `null` if not yet started. nullable: true type: number keywords: description: Keywords associated with this chunk for keyword-based retrieval. items: type: string type: array position: description: Position of the chunk within the document. type: integer sign_content: description: Signed content hash for integrity verification. type: string status: description: >- Current indexing status of the chunk, e.g. `completed`, `indexing`, `error`. type: string stopped_at: description: Timestamp when indexing was stopped. `null` if not stopped. nullable: true type: number summary: description: >- AI-generated summary of the chunk content. `null` if summary indexing is not enabled. nullable: true type: string tokens: description: Token count of the chunk content. type: integer updated_at: description: Last update timestamp (Unix epoch in seconds). type: number updated_by: description: ID of the user who last updated the chunk. type: string word_count: description: Word count of the chunk content. type: integer type: object ChildChunk: properties: content: description: Text content of the child chunk. type: string created_at: description: Creation timestamp (Unix epoch in seconds). type: number id: description: Unique identifier of the child chunk. type: string position: description: Position of the child chunk within the parent chunk. type: integer segment_id: description: ID of the parent chunk this child chunk belongs to. type: string type: description: >- How the child chunk was created. Child chunks created or updated through the API are always `customized`. System-generated child chunks are `automatic`. type: string updated_at: description: Last update timestamp (Unix epoch in seconds). type: number word_count: description: Word count of the child chunk content. type: integer type: object securitySchemes: ApiKeyAuth: bearerFormat: API_KEY description: >- Every request authenticates with an API key: `Authorization: Bearer {API_KEY}`. App endpoints take an app API key; knowledge endpoints take a knowledge base API key ([Get Started](/en/api-reference/guides/get-started)). Keep keys server-side; never embed them in client code. Requests with a missing or invalid key fail with HTTP `401` (`unauthorized`). scheme: bearer type: http ````