LeMUR

Extract action items

POST
Use LeMUR to generate a list of action items from a transcript

Request

This endpoint expects an object.
answer_format
stringOptional
How you want the action items to be returned. This can be any text. Defaults to "Bullet Points".
context
unionOptional
Context to provide the model. This can be a string or a free-form JSON value.
final_model
enumOptional
The model that is used for the final prompt after compression is performed. Defaults to "default".
Allowed values: defaultbasicassemblyai/mistral-7banthropic/claude-2-1
input_text
stringOptional

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
integerOptional
Max output size in tokens, up to 4000
temperature
doubleOptional
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
list of stringsOptional

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

This endpoint returns an object
request_id
string
The ID of the LeMUR request
response
string
The response generated by LeMUR
POST
1curl -X POST https://api.assemblyai.com/lemur/v3/generate/action-items \
2     -H "Authorization: <apiKey>" \
3     -H "Content-Type: application/json" \
4     -d '{
5  "answer_format": "Bullet Points",
6  "context": "This is an interview about wildfires.",
7  "final_model": "default",
8  "max_output_size": 3000,
9  "temperature": 0,
10  "transcript_ids": [
11    "64nygnr62k-405c-4ae8-8a6b-d90b40ff3cce"
12  ]
13}'
200
Successful
1{
2  "request_id": "5e1b27c2-691f-4414-8bc5-f14678442f9e",
3  "response": "Here are some potential action items based on the transcript:\n\n- Monitor air quality levels in affected areas and issue warnings as needed.\n\n- Advise vulnerable populations like children, the elderly, and those with respiratory conditions to limit time outdoors.\n\n- Have schools cancel outdoor activities when air quality is poor.\n\n- Educate the public on health impacts of smoke inhalation and precautions to take.\n\n- Track progression of smoke plumes using weather and air quality monitoring systems.\n\n- Coordinate cross-regionally to manage smoke exposure as air masses shift.\n\n- Plan for likely increase in such events due to climate change. Expand monitoring and forecasting capabilities.\n\n- Conduct research to better understand health impacts of wildfire smoke and mitigation strategies.\n\n- Develop strategies to prevent and manage wildfires to limit air quality impacts.\n"
4}