OpenAI Classification Action
Provided by: "Apache Software Foundation"
Support Level for this Kamelet is: "Preview"
Classifies a sentence using the OpenAI API.
It requires an OpenAI account (beta accounts available at https://beta.openai.com/).
Training data for classification can be provided in advance by uploading a file with purpose="classifications", see: https://beta.openai.com/docs/api-reference/files/upload.
The Kamelet accepts data in:
-
text/plain
format (default) -
application/json
format: see reference at https://beta.openai.com/docs/api-reference/classifications/create
Configuration Options
The following table summarizes the configuration options available for the openai-classification-action
Kamelet:
Property | Name | Description | Type | Default | Example |
---|---|---|---|---|---|
Authorization Token |
Required The authorization token to use to contact the openAI API. |
string |
|||
Engine |
The OpenAI engine to use. |
string |
davinci |
||
Examples File |
The ID of an uploaded file containing examples for classification. |
string |
file-9HbeJXxtG7pg1YTXRx1v1fmn |
||
Format |
The response format ('text/plain' or 'application/json' are supported). |
string |
text/plain |
Dependencies
At runtime, the openai-classification-action
Kamelet relies upon the presence of the following dependencies:
-
mvn:org.apache.camel.kamelets:camel-kamelets-utils:0.6.0
-
camel:jackson
-
camel:jsonpath
-
camel:core
-
camel:kamelet
-
camel:http
Usage
This section describes how you can use the openai-classification-action
.
Knative action
You can use the openai-classification-action
Kamelet as an intermediate step in a Knative binding.
apiVersion: camel.apache.org/v1alpha1
kind: KameletBinding
metadata:
name: openai-classification-action-binding
spec:
source:
ref:
kind: Kamelet
apiVersion: camel.apache.org/v1alpha1
name: timer-source
properties:
message: Hello
steps:
- ref:
kind: Kamelet
apiVersion: camel.apache.org/v1alpha1
name: openai-classification-action
properties:
authorizationToken: The Authorization Token
sink:
ref:
kind: Channel
apiVersion: messaging.knative.dev/v1
name: mychannel
Prerequisite
You have Camel K installed on the cluster.
Kafka action
You can use the openai-classification-action
Kamelet as an intermediate step in a Kafka binding.
apiVersion: camel.apache.org/v1alpha1
kind: KameletBinding
metadata:
name: openai-classification-action-binding
spec:
source:
ref:
kind: Kamelet
apiVersion: camel.apache.org/v1alpha1
name: timer-source
properties:
message: Hello
steps:
- ref:
kind: Kamelet
apiVersion: camel.apache.org/v1alpha1
name: openai-classification-action
properties:
authorizationToken: The Authorization Token
sink:
ref:
kind: KafkaTopic
apiVersion: kafka.strimzi.io/v1beta1
name: my-topic
Prerequisites
-
You’ve installed Strimzi.
-
You’ve created a topic named
my-topic
in the current namespace. -
You have Camel K installed on the cluster.
Procedure for using the cluster CLI
-
Save the
openai-classification-action-binding.yaml
file to your local drive, and then edit it as needed for your configuration. -
Run the action by using the following command:
kubectl apply -f openai-classification-action-binding.yaml
Procedure for using the Kamel CLI
Configure and run the action by using the following command:
kamel bind openai-classification-action -p "step-0.authorizationToken=The Authorization Token" kafka.strimzi.io/v1beta1:KafkaTopic:my-topic
This command creates the KameletBinding in the current namespace on the cluster.