Lemur

Agent calls POST /lemur/v3/generate/task with both transcript_ids=['t_1','t_2'] and input_text='...' for the same prompt.

Use transcript_ids[] when the LLM should run over AssemblyAI-produced transcripts; use input_text for arbitrary text. Combining both has documented precedence — verify the docs and pick one cleanly. Multi-transcript LeMUR concatenates transcripts under a context budget set by final_model's context …

Agent wants Claude 3.5 Sonnet specifically for a LeMUR summary task. Sets final_model='anthropic/claude-3-5-sonnet'.

final_model selects the LLM backing LeMUR (default | basic | anthropic/* per current docs). Pin a model id you've evaluated; do not rely on 'default' across releases as the underlying model may shift. Verify available model ids in current docs [REQUIRES-VERIFICATION].

Agent calls /lemur/v3/generate/question-answer with questions=[{question:'What was the meeting outcome?', answer_format:'short sentence', answer_options:['signed','postponed','rejected']}].

answer_format constrains the answer shape (free text); answer_options forces a choice from a closed set. For categorical extraction always pass answer_options. Validate the returned answer matches an option exactly (case-insensitive); reject responses that drift outside the option list.