
openai invoke
Use the OpenAI invoke policy to invoke OpenAI operations.
Gateway support
Gateway | Policy version |
---|---|
DataPower® API Gateway | 2.0.0 |
This topic describes how to configure the policy in the assembly user interface; for details on how to configure the policy in your OpenAPI source, see openai-invoke.
About
POST /chat/completions
POST /embeddings
GET /models
GET /models/[model-id]
The OpenAI invoke policy supports the properties shown in Table 2.
Properties
The following table lists the policy properties, indicates whether a property is required, specifies the valid and default values for input, and specifies the data type of the values.
Property label | Required | Description | Data type |
---|---|---|---|
Title | No | OpenAI invoke chat completions |
string |
Description | No | A description of the policy. | string |
OpenAI Operation | Yes | The OpenAI operation to invoke; must be one of the following operations:
|
string |
OpenAI API Key | Yes | The API key, or a variable reference to the variable that contains an API key. The API key is used to authenticate OpenAI requests. | string |
OpenAI Organization Id | No | An optional property where you can specify the organization identifier associated with your OpenAI account that will be associated with the requests sent by this policy. Policy requests specifying this property will count as usage by the organization specified. | string |
OpenAI Project Id | No | An optional property where you can specify the project identifier associated with your OpenAI account that will be associated with the requests sent by this policy. Policy request specifying this property will count as usage by the project specified. | string |
Enable response caching | No | Response caching is enabled by default to optimize API performance; however, you can disable
it if needed for your API. When response caching is enabled, then when a request is sent to the OpenAI service, the response cache is inspected to determine if the request payload has an associated cached response. If so, that cached response and its associated HTTP response headers are placed into the DataPower API Gateway context message specified by the Output Message property. If there is no cached response, the request is passed to the OpenAI service, and the response is cached for subsequent operations using the time-to-live specified in the Response Cache Expiration property. |
boolean |
Response Cache Expiration | No | The duration of the cache (the time-to-live). The minimum duration is 60 seconds and the maximum duration is 86400 seconds (1 day) -- any value outside of that range will fail validation when the API is published, even if the value is accepted in this field. | integer |
Cache Scope | No | A string that adds uniqueness to the key used to store a cached response. Adding a cache scope enables the same request to be saved in multiple cache entries. | string |
OpenAI Operation Path Parameters | No | For operations that have a path parameter designated with a path parameter name in square
brackets in the operation, specify the name of the parameter and the value separated by a colon. If
the operation has more that one path parameter, each path parameter designation should be separated
with a comma. For example, for operation GET models/[model] , the path parameter
property would be specified as model:somename .Note: If a path parameter is required
for the operation selected but was not provided, the invoke operation will fail. However, for
operations that don't require a path parameter, any provided path parameter will be
ignored.
|
string |
OpenAI Operation Query Parameters | No | For operations that support query parameters, specify a query parameter string that specifies the name of the parameter and value separated with an equal sign character. If more than one query parameter is supported, each query parameter would be separated with an ampersand character. The supported operations at this time do not support query parameters, although operations that could be supported in the future would support query parameters. | string |
Output Message | No | The name of the DataPower API Gateway context message that receives the OpenAI response. By default, this property uses message as the value, which enables the
response to be accessible by subsequent API policies in message.body and
message.headers . |
string |