Engines
get/engines
Response
JSON
{
"object": "string",
"data": [
{
"id": "string",
"object": "string",
"created": 0,
"ready": true
}
]
}
get/engines/{engine_id}
Path parameters
- Name
engine_id
- Type
- string
- Required
- Description
The ID of the engine to use for this request
Response
JSON
{
"id": "string",
"object": "string",
"created": 0,
"ready": true
}
post/engines/{engine_id}/search
Path parameters
- Name
engine_id
- Type
- string
- Required
- Description
The ID of the engine to use for this request. You can select one of
ada
,babbage
,curie
, ordavinci
.
Body params
- Name
query
- Type
- string
- Required
- Description
- Query to search against the documents.
- Name
documents
- Type
- array[string]
- Description
- Up to 200 documents to search over, provided as a list of strings. The maximum document length (in tokens) is 2034 minus the number of tokens in the query. You should specify either `documents` or a `file`, but not both.
- Name
file
- Type
- string
- Description
- The ID of an uploaded file that contains documents to search over. You should specify either `documents` or a `file`, but not both.
- Name
max_rerank
- Type
- integer
- Description
- The maximum number of documents to be re-ranked and returned by search. This flag only takes effect when `file` is set.
- Name
return_metadata
- Type
- boolean
- Description
- A special boolean flag for showing metadata. If set to `true`, each document entry in the returned JSON will contain a "metadata" field. This flag only takes effect when `file` is set.
- Name
user
- Type
- string
- Description
- A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](/docs/guides/safety-best-practices/end-user-ids).
Response
JSON
{
"object": "string",
"model": "string",
"data": [
{
"object": "string",
"document": 0,
"score": 0
}
]
}