Skip to main content
POST
/
api
/
claims
/
search
Search claims
curl --request POST \
  --url https://api.example.com/api/claims/search \
  --header 'Content-Type: application/json' \
  --data '
{
  "query_text": "<string>",
  "top_k": 123,
  "min_similarity": 123
}
'

Documentation Index

Fetch the complete documentation index at: https://docs.minns.ai/llms.txt

Use this file to discover all available pages before exploring further.

Use this endpoint for fuzzy, concept-based queries like “What are the user’s favorite genres?” or “Has the user complained before?”

​
Request body

​
query_text
string
required
Natural language query. Keep it conversational — don’t include IDs.
​
top_k
integer
default:"10"
Number of results to return.
​
min_similarity
number
default:"0.7"
Minimum similarity threshold (0.0–1.0).

​
Example request

{
  "query_text": "What are the user's favorite genres?",
  "top_k": 3,
  "min_similarity": 0.7
}

​
Response

Returns an array of ClaimResponse objects with the similarity field populated. 
[
  {
    "claim_id": 42,
    "claim_text": "User prefers Sci-Fi movies",
    "confidence": 0.92,
    "source_event_id": 123456789012345678901234567890,
    "similarity": 0.89,
    "evidence_spans": [
      {
        "start_offset": 15,
        "end_offset": 45,
        "text_snippet": "I really love Sci-Fi movies"
      }
    ],
    "support_count": 3,
    "status": "Active",
    "created_at": 1738425600000000000,
    "last_accessed": 1738512000000000000
  }
]
Keep the query_text natural. Don’t include IDs in the string — filter the results in your application code instead.