POST
/
v1
/
tools
/
semantic-search
{
"content": [
{
"type": "source",
"sources": [
{
"object": "context.chunk",
"id": "d3ab07fe-b7ab-4fda-8524-1cb41b01200a",
"score": 0.83,
"document": {
"object": "ingest.document",
"artifact": "0196ee69-666a-7bcd-800b-b01fa9b2f24c",
"doc_metadata": {
"file_name": "dense_x_retrieval.pdf"
}
},
"text": "Wenhao Yu et al. 2023. Chain-ofnote: Enhancing robustness in retrieval-augmented LMs.",
"content_type": "text/markdown",
"metadata": {
"page": 13,
"shorter_id": "GONG"
},
"previous_texts": [],
"next_texts": []
}
]
},
{
"type": "text",
"text": "**Context Information**:\nCitation identifier [GONG]\n---\nContent:\nWenhao Yu, Hongming Zhang... Chain-ofnote: Enhancing robustness in retrieval-augmented language models."
}
],
"is_error": false
}

Body

application/json

Request body for semantic search. Includes the query, optional filters, and response formatting preferences.

Request body for semantic search.

query
string
required

The natural language query to search for relevant content.

Examples:

"What were the Q4 revenue trends?"

context_filter
object
required

Filters to narrow the search context (collections, artifacts, metadata).

format
enum<string>
default:default

Format of the result content. 'default' returns standard content blocks. 'citations' returns blocks annotated for citation formatting.

Available options:
default,
citations
Examples:

"default"

Response

Semantic search completed successfully.

Response returned from tool-based operations.

content
Content · array
required

List of content blocks generated by the tool. Blocks can include plain text, citations, source attributions, or images.

is_error
boolean
default:false

True if the tool encountered an error during execution.