Change model and parameters

Change the model type

LeMUR features the following LLMs:

• Claude 3.5 Sonnet
• Claude 3 Opus
• Claude 3 Haiku
• Claude 3 Sonnet

You can switch the model by specifying the final_model parameter.

1
result = transcript.lemur.task(
2
    prompt,
3
    final_model=aai.LemurModel.claude3_5_sonnet
4
)

You can find more information on pricing for each model here.

Change the maximum output size

1
result = transcript.lemur.task(
2
    prompt,
3
    max_output_size=1000
4
)

Change the temperature

You can change the temperature by specifying the temperature parameter, ranging from 0.0 to 1.0.

Higher values result in answers that are more creative, lower values are more conservative.

1
result = transcript.lemur.task(
2
    prompt,
3
    temperature=0.7
4
)

Send customized input

You can submit custom text inputs to LeMUR without transcript IDs. This allows you to customize the input, for example, you could include the speaker labels for the LLM.

1
config = aai.TranscriptionConfig(
2
  speaker_labels=True,
3
)
4
transcript = transcriber.transcribe(audio_url, config=config)
5
6
text_with_speaker_labels = ""
7
for utt in transcript.utterances:
8
    text_with_speaker_labels += f"Speaker {utt.speaker}:\n{utt.text}\n"
9
10
result = aai.Lemur().task(
11
    prompt,
12
    input_text=text_with_speaker_labels
13
)

Submit multiple transcripts

LeMUR can easily ingest multiple transcripts in a single API call.

You can feed in up to a maximum of 100 files or 100 hours, whichever is lower.

1
transcript_group = transcriber.transcribe_group(
2
    [
3
        "https://example.org/customer1.mp3",
4
        "https://example.org/customer2.mp3",
5
        "https://example.org/customer3.mp3",
6
    ],
7
)
8
9
# Or use existing transcripts:
10
# transcript_group = aai.TranscriptGroup.get_by_ids([id1, id2, id3])
11
12
result = transcript_group.lemur.task(
13
  prompt="Provide a summary of these customer calls."
14
)

Delete data

You can delete the data for a previously submitted LeMUR request.

Response data from the LLM, as well as any context provided in the original request will be removed.

1
result = transcript.lemur.task(prompt)
2
3
deletion_response = aai.Lemur.purge_request_data(result.request_id)

API reference

You can find detailed information about all LeMUR API endpoints and parameters in the LeMUR API reference.