search | SignalWire

Perform a semantic search across all documents in the Datasphere.

Request

query_stringstringRequired

Search term.

tagslist of stringsOptional

Document tags.

document_idstringOptionalformat: "uuid"

Unique ID of a Document.

distancedoubleOptional0-78.3836717690617

Specifies how closely related the query is to the document. Low distance means high relevance and similarity. High distance means low relevance and similarity.

countintegerOptional>=1Defaults to 5

Specifies number of returned Chunks.

languagestringOptionalDefaults to en

Language of the Document.

pos_to_expandlist of stringsOptionalDefaults to ["NOUN","VERB","ADJ","ADV"]

Part of Speech considered for expansion or analysis.

max_synonymsintegerOptional>=1Defaults to 10

Maximum number of synonyms to consider.

Response

chunkslist of objectsRequired

A list of search result chunks.

Response Example

Response

{
  "chunks": [
    {
      "text": "Cristiano Ronaldo is the highest-paid football player in the world in 2024",
      "document_id": "acaa5c49-be5e-4477-bce0-48f4b23b7720"
    }
  ]
}

Example

from signalwire.rest import RestClient
client = RestClient(
    project="your-project-id",
    token="your-api-token",
    host="your-space.signalwire.com",
)
results = client.datasphere.documents.search(
    query_string="How do I reset my password?",
    count=5,
)
for chunk in results.get("chunks", []):
    print(chunk.get("text"), "score:", chunk.get("score"))