PUT /v2/gen-ai/agents/{uuid}
To update an agent, send a PUT request to /v2/gen-ai/agents/{uuid}
. The response body is a JSON object containing the agent.
Servers
- https://api.digitalocean.com
Path parameters
Name | Type | Required | Description |
---|---|---|---|
uuid |
String | Yes |
Unique agent id |
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 |
---|---|---|---|
k |
Integer | No |
How many results should be considered from an attached knowledge base |
project_id |
String | No |
The id of the DigitalOcean project this agent will belong to |
provide_citations |
Boolean | No | |
description |
String | No |
Agent description |
temperature |
Number | No |
Controls the model’s creativity, specified as a number between 0 and 1. Lower values produce more predictable and conservative responses, while higher values encourage creativity and variation. |
uuid |
String | No |
Unique agent id |
anthropic_key_uuid |
String | No |
Optional anthropic key uuid for use with anthropic models |
top_p |
Number | No |
Defines the cumulative probability threshold for word selection, specified as a number between 0 and 1. Higher values allow for more diverse outputs, while lower values ensure focused and coherent responses. |
open_ai_key_uuid |
String | No |
Optional OpenAI key uuid for use with OpenAI models |
name |
String | No |
Agent name |
retrieval_method |
String | No |
Possible values:
Default value: "RETRIEVAL_METHOD_UNKNOWN" |
tags[] |
Array | No |
A set of abitrary tags to organize your agent |
max_tokens |
Integer | No |
Specifies the maximum number of tokens the model can process in a single input or output, set as a number between 1 and 512. This determines the length of each response. |
instruction |
String | No |
Agent instruction. Instructions help your agent to perform its job effectively. See Write Effective Agent Instructions for best practices. |
model_uuid |
String | No |
Identifier for the foundation model. |
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.