curl --request POST \ --url https://realtime-api.voiceflow.com/v1/stable/document/table \ --header 'Authorization: Bearer <token>' --header 'Content-Type: application/json' \ --data '{ "url": "<string>", "name": "<string>", "items": [ {} ], "schema": { "metadataFields": [], "searchableFields": [ "<string>" ] }, "metadata": [] }'

{ "document": { "id": "<string>", "data": "<KBDocumentUrlData>", "status": { "type": "ERROR", "data": null }, "smartChunking": { "markdownConversion": true, "llmBasedChunks": true, "llmGeneratedQ": true, "llmContentSummarization": true, "llmPrependContext": true } } }

Authorizations

Authorization

string

header

required

Voiceflow bearer token

Query Parameters

projectID

string

required

The ID of the project to operate on.

environmentAlias

string

required

The alias of the environment to operate on (e.g. main).

maxChunkSize

object

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.

Show child attributes

Option 1

string

Option 2

number

overwrite

object

If set to true, the existing table with the same name will be overwritten.

Show child attributes

Option 1

boolean

Option 2

enum<string>

markdownConversion

object

When enabled, HTML is automatically converted to markdown to generate better chunks.

Show child attributes

Option 1

boolean

Option 2

enum<string>

llmBasedChunks

object

Show child attributes

Option 1

boolean

Option 2

enum<string>

llmGeneratedQ

object

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.

Show child attributes

Option 1

boolean

Option 2

enum<string>

llmContentSummarization

object

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.

Show child attributes

Option 1

boolean

Option 2

enum<string>

llmPrependContext

object

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.

Show child attributes

Option 1

boolean

Option 2

enum<string>

Body

url

string

An optional source URL to associate with the table document.

name

string

required

items

object[]

required

The table rows to ingest; each row is a flat object and becomes its own chunk.

schema

object

required

Declares which top-level keys of each row are full-text searchable versus row-level metadata.

Show child attributes

metadataFields

string[]

Per-row metadata, returned with results.

searchableFields

string[]

required

Full-text indexed; what semantic search matches against.

metadata

object[]

Metadata tags attached to the document, used to filter knowledge base retrieval at runtime.

Show child attributes

key

string

required

The name of the metadata field.

values

string[]

required

The values assigned to this metadata field.

Response

201 - application/json

Returns the document created from the structured data, with its assigned ID and status. The chunks it was split into are not in this response.

document

object

required

Show child attributes

string

required

data

object

required

Show child attributes

status

object

required

Show child attributes

type

object

required

Available options: ERROR, PENDING, SUCCESS, INITIALIZED

data

any

smartChunking

object

required

Show child attributes

markdownConversion

object

When enabled, HTML is automatically converted to markdown to generate better chunks.

Show child attributes

Option 1

boolean

Option 2

enum<string>

llmBasedChunks

object

Show child attributes

Option 1

boolean

Option 2

enum<string>

llmGeneratedQ

object

Show child attributes

Option 1

boolean

Option 2

enum<string>

llmContentSummarization

object

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.

Show child attributes

Option 1

boolean

Option 2

enum<string>

llmPrependContext

object

Show child attributes

Option 1

boolean

Option 2

enum<string>

Getting started

Running agents

Build

Manage

Publishing

Observe

Insights

QA

Analytics

Webhooks

Create table document

Authorizations

Query Parameters

Body

Response

Getting started

Running agents

Build

Manage

Publishing

Observe

Insights

QA

Analytics

Webhooks