Skip to main content
POST
/
v1alpha1
/
public
/
knowledge-base
/
document
/
upload
/
table
Upload table document
curl --request POST \
  --url https://realtime-api.voiceflow.com/v1alpha1/public/knowledge-base/document/upload/table \
  --header 'Content-Type: application/json' \
  --header 'authorization: <api-key>' \
  --data '
{
  "data": {
    "name": "<string>",
    "items": [
      {}
    ],
    "schema": {
      "searchableFields": [
        "<string>"
      ],
      "metadataFields": [
        "<string>"
      ]
    }
  }
}
'
{
  "data": {
    "documentID": "<string>",
    "data": {
      "type": "csv",
      "name": "<string>",
      "rowsCount": 123
    },
    "updatedAt": "2023-11-07T05:31:56Z",
    "status": {
      "type": "ERROR",
      "data": "<unknown>"
    }
  },
  "chunks": [
    {
      "chunkID": "<string>",
      "content": "<string>",
      "metadata": {}
    }
  ],
  "metadata": [
    {
      "key": "<string>",
      "values": [
        "<string>"
      ]
    }
  ]
}

Authorizations

​
authorization
string
header
required

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

Query Parameters

​
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

application/json
​
data
object
required

Response

200 - application/json

The document was uploaded successfully.

​
data
object
required
​
chunks
object[]
​
metadata
object[]