Skip to main content
POST
/
v1alpha1
/
public
/
knowledge-base
/
document
Create document
curl --request POST \
  --url https://realtime-api.voiceflow.com/v1alpha1/public/knowledge-base/document \
  --header 'Content-Type: multipart/form-data' \
  --header 'authorization: <api-key>' \
  --form 'data={
  "type": "url",
  "url": "<string>",
  "metadata": {},
  "name": "<string>",
  "refreshRate": "daily",
  "lastSuccessUpdate": "<string>",
  "accessTokenID": 123,
  "integrationExternalID": "<string>",
  "source": "zendesk"
}'
{
  "data": {
    "documentID": "<string>",
    "data": {
      "type": "csv",
      "name": "<string>",
      "rowsCount": 123
    },
    "updatedAt": "2023-11-07T05:31:56Z",
    "status": {
      "type": "ERROR",
      "data": "<unknown>"
    }
  }
}

Authorizations

​
authorization
string
header
required

Voiceflow Dialog Manager API key (VF.DM) or Workspace API key (VF.WS)

Headers

​
content-type
string

Query Parameters

​
maxChunkSize
any

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.

​
overwrite

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

​
markdownConversion

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

​
llmBasedChunks
​
llmGeneratedQ

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.

​
llmContentSummarization

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.

​
llmPrependContext

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.

​
llmVision

Body

multipart/form-data
​
data
object
required

Response

201 - application/json

The document was created successfully.

​
data
object
required