Skip to main content
POST
/
v1
/
chat
/
simple
Chat Simple
curl --request POST \
  --url https://www.api.threesigma.ai/v1/chat/simple \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: <api-key>' \
  --data '
{
  "messages": [
    {
      "role": "user",
      "content": "<string>"
    }
  ],
  "context": "<string>",
  "model": "gpt-3.5-turbo",
  "latency": "default",
  "thread_id": "<string>"
}
'
{
  "data": {
    "text": "<string>",
    "finish_reason": "stop"
  },
  "entity": "chat.completion",
  "event": "stop"
}

Authorizations

​
x-api-key
string
header
required

Body

application/json
​
messages
MessageRequest · object[]
required

Manually supply the messages if no thread ID is provided.

Minimum length: 1
​
context
string
required

The ID of context to query on.

​
model
enum<string>
default:gpt-3.5-turbo

ID of the model to use.

Available options:
gpt-3.5-turbo,
gpt-3.5-turbo-16k,
gpt-4
​
latency
enum<string>
default:default

The latency of the response. Higher latency will yield a better response but take longer.

Available options:
default,
comprehensive
​
thread_id
string | null

By supplying a thread ID, relevant messages from the thread will be retrieved.

Response

Successful Response

​
data
object | null
required
​
entity
enum<string>
required
Available options:
chat.completion,
chat.context
​
event
enum<string>
required
Available options:
stop,
context-message,
completion-message,
error,
message