> ## Documentation Index > Fetch the complete documentation index at: https://docs.voiceflow.com/llms.txt > Use this file to discover all available pages before exploring further. # Create document > Upload or provide a URL to scrape and import as a knowledge base document. Supports both `application/json` and `multipart/form-data` content types. ## OpenAPI ````yaml /specs/realtime/openapi.public.json post /v1alpha1/public/knowledge-base/document openapi: 3.0.0 info: title: Realtime description: Realtime gateway API service version: 1.0.0 contact: {} servers: - url: https://realtime-api.voiceflow.com security: [] paths: /v1alpha1/public/knowledge-base/document: post: tags: - KBPublicApiDocument - Public-Docs summary: Create document description: >- Upload or provide a URL to scrape and import as a knowledge base document. Supports both `application/json` and `multipart/form-data` content types. operationId: KnowledgeBaseDocumentApiPublicHTTPController_publicCreateOne parameters: - name: maxChunkSize required: false in: query schema: description: >- Determines how granularly each document is broken up. Range available is 500-1500 tokens, default is 1000. Smaller chunk size means narrower context, faster response, less tokens consumed, and greater risk of less accurate answers. Max chunk size affects the total amount of chunks parsed from a document - i.e., larger chunks means less chunks retrieved. - name: overwrite required: false in: query schema: description: >- If set to true, the existing table with the same name will be overwritten. oneOf: - type: boolean - type: string enum: - 'true' - 'false' - name: markdownConversion required: false in: query schema: description: >- When enabled, HTML is automatically converted to markdown to generate better chunks. oneOf: - type: boolean - type: string enum: - 'true' - 'false' - name: llmBasedChunks required: false in: query schema: oneOf: - type: boolean - type: string enum: - 'true' - 'false' - name: llmGeneratedQ required: false in: query schema: description: >- When enabled, an LLM will be used to generate a question based on the document context and specific chunk, then prepend it to the chunk. This enhances retrieval by aligning chunks with potential user queries. oneOf: - type: boolean - type: string enum: - 'true' - 'false' - name: llmContentSummarization required: false in: query schema: description: >- When enabled, an LLM summarizes and rewrites the content, removing unnecessary information and focusing on important parts to optimize for retrieval. Limited to 15 rows per table upload. oneOf: - type: boolean - type: string enum: - 'true' - 'false' - name: llmPrependContext required: false in: query schema: description: >- When enabled, an LLM generates a context summary based on the document and chunk context, and prepends it to each chunk. This improves retrieval by providing additional context to each chunk. Note: If both llmGeneratedQ and llmPrependContext are set to true, llmGeneratedQ takes precedence, and the context summarization will not be applied. oneOf: - type: boolean - type: string enum: - 'true' - 'false' - name: llmVision required: false in: query schema: oneOf: - type: boolean - type: string enum: - 'true' - 'false' - name: content-type in: header schema: type: string requestBody: content: application/json: schema: type: object properties: data: type: object properties: type: type: string enum: - url url: type: string name: type: string refreshRate: type: string enum: - daily - weekly - monthly - never x-enumNames: - DAILY - WEEKLY - MONTHLY - NEVER folderID: type: string documentMetadata: description: >- An array of document metadata fields. > **💡 Tip:** This metadata can be used in agent KB metadata filter conditions. [Learn more about metadata filtering](/documentation/build/querying-the-knowledge-base#meta-data-filtering). type: array items: type: object properties: key: type: string maxLength: 255 values: type: array items: type: string required: - key - values metadata: description: >- Chunk-level metadata that can be used in a KB API query request. > **⚠️ Warning:** This metadata can't be used in agent KB metadata filter conditions. Use `documentMetadata` instead if you need agent-level metadata filtering. type: object additionalProperties: {} projectEnvironmentIDOrAlias: description: >- The alias of the environment to target (ie. `main`). You can find this in the environments page of your agent. > **💡 Tip:** [Learn more about Environments](/documentation/deploy/environments). type: string required: - type - url required: - data multipart/form-data: schema: type: object properties: file: type: string format: binary description: The file to upload (max 10 MB). folderID: type: string description: The folder ID to place the document in. documentMetadata: type: string description: >- JSON string of document metadata fields. > **💡 Tip:** This metadata can be used in agent KB metadata filter conditions. [Learn more about metadata filtering](/documentation/build/querying-the-knowledge-base#meta-data-filtering). metadata: type: string description: >- JSON string of chunk metadata key-value pairs. Can be used in a KB API query request. > **⚠️ Note:** This metadata can't be used in agent KB metadata filter conditions. Use `documentMetadata` instead if you need agent-level metadata filtering. url: type: string description: The source URL of the document. projectEnvironmentIDOrAlias: description: >- The alias of the environment to target (ie. `main`). You can find this in the environments page of your agent. > **💡 Tip:** [Learn more about Environments](/documentation/deploy/environments). type: string required: - file responses: '201': description: The document was created successfully. content: application/json: schema: type: object properties: data: type: object properties: documentID: type: string data: type: object properties: type: type: string enum: - url name: type: string url: type: string refreshRate: type: string enum: - daily - weekly - monthly - never x-enumNames: - DAILY - WEEKLY - MONTHLY - NEVER lastSuccessUpdate: type: string accessTokenID: type: number integrationExternalID: type: string source: type: string enum: - zendesk - shopify x-enumNames: - ZENDESK - SHOPIFY required: - type - name - url nullable: true updatedAt: type: string format: date-time status: type: object properties: type: type: string enum: - ERROR - PENDING - SUCCESS - INITIALIZED x-enumNames: - ERROR - PENDING - SUCCESS - INITIALIZED data: {} required: - type required: - documentID - data - updatedAt - status required: - data multipart/form-data: schema: type: object properties: data: type: object properties: documentID: type: string data: oneOf: - type: object properties: type: type: string enum: - docx name: type: string url: type: string nullable: true required: - type - name - type: object properties: type: type: string enum: - pdf name: type: string url: type: string nullable: true required: - type - name - type: object properties: type: type: string enum: - text name: type: string canEdit: type: boolean url: type: string nullable: true required: - type - name - type: object properties: type: type: string enum: - csv name: type: string rowsCount: type: number url: type: string nullable: true required: - type - name - type: object properties: type: type: string enum: - xlsx name: type: string rowsCount: type: number url: type: string nullable: true required: - type - name nullable: true updatedAt: type: string format: date-time status: type: object properties: type: type: string enum: - ERROR - PENDING - SUCCESS - INITIALIZED x-enumNames: - ERROR - PENDING - SUCCESS - INITIALIZED data: {} required: - type required: - documentID - data - updatedAt - status required: - data security: - auth: [] components: securitySchemes: auth: type: apiKey in: header name: authorization description: Voiceflow API key ````