Use Endpoints
Submit Question Completions
Submits a user question for processing
POST
/
v1
/
completions
Authorizations
Authorization
string
headerrequiredBearer authentication header of the form Bearer <token>
, where <token>
is your auth token.
Body
application/json
model
enum<string>
requiredThe model name to use for processing the question
Available options:
llama2_70b
, llama3_70b
, llama2_7b
, codellama_70b
, mixtral_8x7
, mistral_7b
question
string
requiredThe user's question to be processed
max_tokens
integer
default: 10Max output tokens for the response
list_inputs
string[]
Optionally list batch input contents as a list of strings
storage_provider
string
Storage where data is stored (e.g., 's3', 'gcs')
bucket_name
string
Name of the bucket for storing results
session
string
Session name for the request
system_prompt
string
default: Answer the question based only on the given content. Do not give explanations or examples. Do not continue generating more text after the answer.Additional system prompt for processing the user's question
role_arn
string
AWS IAM role ARN for S3 access
region
string
default: eu-west-2The region the bucket belongs to
return_output
boolean
default: falseBoolean indicating whether to return the output or not
input_json_file
string
The name of the input json file in your s3 bucket
structured_output
string
json schema for the response output
Response
200 - application/json
status
enum<string>
requiredAvailable options:
Submitted
job_id
string
requiredThe job ID assigned to the submitted question