POST /vector_stores/{vector_store_id}/search
Servers
- https://api.openai.com/v1
Path parameters
| Name | Type | Required | Description |
|---|---|---|---|
vector_store_id |
String | Yes |
The ID of the vector store to search. |
Request headers
| Name | Type | Required | Description |
|---|---|---|---|
Content-Type |
String | Yes |
The media type of the request body.
Default value: "application/json" |
Request body fields
| Name | Type | Required | Description |
|---|---|---|---|
filters |
No |
A filter to apply based on file attributes. |
|
query |
Yes |
A query string for a search |
|
rewrite_query |
Boolean | No |
Whether to rewrite the natural language query for vector search. Default value: false |
max_num_results |
Integer | No |
The maximum number of results to return. This number should be between 1 and 50 inclusive. Default value: 10 |
ranking_options |
Object | No |
Ranking options for search. |
ranking_options.ranker |
String | No |
Possible values:
Default value: "auto" |
ranking_options.score_threshold |
Number | No |
Default value: 0 |
How to start integrating
- Add HTTP Task to your workflow definition.
- Search for the API you want to integrate with and click on the name.
- This loads the API reference documentation and prepares the Http request settings.
- Click Test request to test run your request to the API and see the API's response.