Overview
Searches for memories and experiences in the current space and uses reciprocal rank fusion (RRF) to combine vector search and full-text search (FTS) results. The data.memories[].metadata field in the response contains scoring details such as _vector_similarity and _fusion_info.
API details
Constraints
- You must have an API key. For more information, see Manage AI API keys.
Request path
POST {BASE_URL}/api/v1/memory/spaces/{spaceId}/memories/search
Request headers
Name |
Required |
Example value |
Description |
|---|---|---|---|
| Authorization | Yes | Bearer {token} | Authentication information. |
| Content-Type | No | application/json | Request body format. |
| X-OB-Project-ID | Yes | - | Project ID |
Request parameters
Path parameters
Name |
Type |
Required |
Example value |
Description |
|---|---|---|---|---|
| spaceId | string | Yes | space-123 | Memory space ID. |
Body parameters
Name |
Type |
Required |
Example value |
Description |
|---|---|---|---|---|
| query | string | Yes | How do I optimize slow SQL queries? | Natural language query. |
Response
Response parameters
Name |
Type |
Description |
|---|---|---|
| success | boolean | Whether the request was successful |
| code | string | Response code. |
| message | string | Response message. |
| data | object | Response data. |
Data fields
Name |
Type |
Description |
|---|---|---|
| memories | array | List of retrieved memories. The metadata field of each item contains scoring details such as _vector_similarity and _fusion_info. |
Request example
curl --request POST '{BASE_URL}/api/v1/memory/spaces/{spaceId}/memories/search' \
--header 'Authorization: Bearer {token}' \
--header 'X-OB-Project-ID: {projectId}' \
--header 'Content-Type: application/json' \
--data '{
"query": "Search content"
}'
Response example
{
"success": true,
"code": "200",
"message": "successful",
"data": {
"memories": [
{
"id": "mem-123",
"content": "Related memory content",
"metadata": {
"_vector_similarity": 0.95,
"_fusion_info": "..."
}
}
]
}
}