GET
/
v1
/
files
/
search
curl --request GET \
  --url https://api.botpress.cloud/v1/files/search
{
  "passages": [
    {
      "content": "<string>",
      "score": 123,
      "meta": {
        "type": "chunk",
        "subtype": "title",
        "pageNumber": 123,
        "position": 123,
        "sourceUrl": "<string>"
      },
      "file": {
        "id": "<string>",
        "key": "<string>",
        "contentType": "<string>",
        "tags": {},
        "createdAt": "<string>",
        "updatedAt": "<string>"
      }
    }
  ]
}

Query Parameters

tags
any

Filter files by tags. Tags should be passed as a URL-encoded JSON object of key-value pairs that must be present in the tags of a file. An array of multiple string values for the same key are treated as an OR condition. To exclude a value, express it as an object with a nested not key with the string or string-array value(s) to exclude.

query
string
required

Query expressed in natural language to retrieve matching text passages within all indexed files in the bot using semantical search.

contextDepth
integer

The number of neighbor passages to prepend and append as surrounding context to the content of each returned passage (default: 1, minimum: 0, maximum: 10).

limit
integer

The maximum number of passages to return.

consolidate
boolean

Consolidate the results by merging matching passages from the same file into a single passage per file. The consolidated passage will include the matching passages ordered by their original position in the file (rather than by relevance score) and include hierarchical context such as the title/subtitle to which they belong.

includeBreadcrumb
boolean

Prepend a breadcrumb to each passage, containing the title and subtitle(s) the passage belongs to in the file. This option is ignored when the consolidate option is set to true.

Response

200
application/json
Returns the text passages within all indexed files that matched the query.
passages
object[]
required