Run a task using LeMUR
LeMUR is currently not available on the EU endpoint.
Headers
Authorization
Request
Params to run the task
final_model
The model that is used for the final prompt after compression is performed.
prompt
Your text to prompt the model to produce a desired output, including any context you want to pass into the model.
context
Context to provide the model. This can be a string or a free-form JSON value.
input_text
Custom formatted transcript data. Maximum size is the context limit of the selected model, which defaults to 100000. Use either transcript_ids or input_text as input into LeMUR.
max_output_size
Max output size in tokens, up to 4000
temperature
The temperature to use for the model.
Higher values result in answers that are more creative, lower values are more conservative.
Can be any value between 0.0 and 1.0 inclusive.
transcript_ids
A list of completed transcripts with text. Up to a maximum of 100 files or 100 hours, whichever is lower. Use either transcript_ids or input_text as input into LeMUR.
Response
LeMUR task response
request_id
The ID of the LeMUR request
response
The response generated by LeMUR.
usage
The usage numbers for the LeMUR request