Skip to main content
POST
/
api
/
v1
/
search
/
pgvector
Semantic search — pgvector
curl --request POST \
  --url http://localhost:8080/api/v1/search/pgvector \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: <api-key>' \
  --data '
{
  "query": "<string>",
  "table": "documents",
  "schema": "public",
  "embeddingSecretName": "<string>",
  "postgresSecretName": "<string>",
  "topK": 5
}
'
{
  "results": [
    {
      "text": "<string>",
      "chunk_index": 123,
      "source_pipeline": "<string>",
      "filename": "<string>",
      "_score": 123
    }
  ],
  "count": 123
}

Authorizations

​
x-api-key
string
header
required

Optional API key for authentication (enabled via application.yaml)

Body

application/json
​
query
string
required

Natural language search query

​
table
string
default:documents

PostgreSQL table name

​
schema
string
default:public

PostgreSQL schema

​
embeddingSecretName
string

Optional override of the embedding Vault secret. Defaults to the server-level ai.embedding.secretName (oss/embedding), which is seeded automatically by vault-init.sh. The secret is self-describing — provider, endpoint, model, apiKey, and (optionally) version.

​
postgresSecretName
string

Vault secret name for PostgreSQL/pgvector connection

​
topK
integer
default:5

Response

Search results

​
results
object[]
​
count
integer