Generate Message Completions

POST

Generate completions for a list of messages.

This endpoint uses the language model to generate completions for the provided messages. The generation process can be customized using the generation_config parameter.

The messages list should contain alternating user and assistant messages, with an optional system message at the start. Each message should have a ‘role’ and ‘content’.

Query parameters

response_modelstringRequired

Request

This endpoint expects an object.

messageslist of objectsRequired

List of messages to generate completion for

generation_configobjectOptional

Configuration for text generation

Response

Successful Response

Errors

Built with

1	from r2r import R2RClient
2
3	client = R2RClient("http://localhost:7272")
4	# when using auth, do client.login(...)
5
6	response =client.completion(
7	messages=[
8	{"role": "system", "content": "You are a helpful assistant."},
9	{"role": "user", "content": "What is the capital of France?"},
10	{"role": "assistant", "content": "The capital of France is Paris."},
11	{"role": "user", "content": "What about Italy?"}
12	],
13	generation_config={
14	"model": "gpt-4o-mini",
15	"temperature": 0.7,
16	"max_tokens": 150,
17	"stream": False
18	}
19	)