Semantic searchDeprecated

Required capabilities: filesAcl:READ

This endpoint lets you search for relevant parts (passages) of up to 100 PDF documents by using advanced filters and semantic search queries. For each query you have to specify a list of document ids using the in filter (see exmple).

This endpoint has been deprecated in favor of /documents/passages/search which is now in GA. Please consider moving over.

Securityoidc-token or oauth2-client-credentials or oauth2-open-industrial-data or oauth2-auth-code
Request
header Parameters
cdf-version
string

cdf version header. Use this to specify the requested CDF release.

Example: alpha
Request Body schema: application/json
required

Fields to be set for the search request.

required
bool filters (and (object)) or (leaf filters (equals (object) or in (object) or semanticSearch (object) or lexicalSearch (object))) (DocumentSemanticFilter)
required
DocumentSemanticSearchPassageExpansionSymmetric (object)

A expansion strategy to to increase the text view for each passage returned. Helpful to increase context for an LLM.

limit
integer <int32> [ 1 .. 10 ]
Default: 10

Maximum number of items.

Responses
200

List of most relevant document passages for a given query. The results are sorted by relevance, and contains metadata such as page numbers.

400

The response for a failed request.

post/documents/semantic/search
Request samples
application/json
{
  • "filter": {
    • "and": [
      ]
    },
  • "expansionStrategy": {
    • "strategy": "symmetric",
    • "chunk_count": 1
    },
  • "limit": 10
}
Response samples
application/json
{
  • "items": [
    • {
      }
    ]
}
➔ Next to Semantic search for passages