A node that accumulates Text based events and creates a 2-3 sentence long summary in the given Language at the end of operation.
Parameters
name |
description | default |
|---|---|---|
| IgnoreSslErrors | Ignore any SSL certificate errors for the Http calls | false |
| Credential | API Key Credential for the OpenAI service | empty |
| Language | Language of the expected event output. | tr-TR |
| Model | Model code of the OpenAI Version | gpt-3.5-turbo |
Inputs
Audio
none
Events
| name | description | known nodes that generate this event |
|---|---|---|
Every Event that has Data.Text field. |
i.e SR Milestone events. Translation events, Custom events. | SR Http, SR WebSocket, Translation |
| Language Change | Language Change event changes the outputted event's language. | Language Identifier, Text Language Identifier |
Outputs
Audio
none
Events
name |
description |
|---|---|
| Summarize | Contains a 1-2 sentence summary of all the inputted text containing fields in the Data.Summary field. |
Remarks
Requirements
The node needs an OpenAI Api key to perform. To learn more about getting an API Key and finding it, you can refer to the OpenAI Api page .
After getting your API Key, you can learn about finding and securely using your key following the instructions on this page .
You can also see which models are available through the OpenAI Models page.
Project Structure
The node expects events from the SR Http or SR WebSocket node.
A minimum viable project that utilizes the Summarize node can be built as such:
Taking this a step further, we can create a project that identifies the spoken language, and summarizes it in the end :
Note that the Language Identifier output is connected to summarization, changing its outputted language.
Detailed Workflow
Summarize node accumulates all the Text Based events it receives and waits for a Flush call. (eg. If the client is a Call Recorder application, Flush is typically sent at the end of a call.) When Summarize node receives a Flush, it summarizes all the text it had received so far with the help of OpenAI and raises a Summarize event.
Supported flow types
Stream, Batch