letterbook-ai-chat 0.1.0

Python SDK for capturing AI chat issues in Letterbook.

Letterbook AI Chat Python SDK

Capture AI chat turns. Letterbook queues each conversation in Redis, waits 5 minutes after the last message by default, evaluates the full transcript server-side with an LLM, and dedupes by convo_id so one AI conversation does not create multiple tickets.

import letterbook

result = letterbook.capture(
    user_id="user123",
    event="user_message",
    model="gpt_4",
    input="The checkout page is broken and I was charged twice.",
    output="I am sorry, I cannot fix billing issues from here.",
    convo_id="conv789",
    customer_email="[e-mail]",
    debounce_seconds=300,
    properties={
        "system_prompt": "you are a helpful assistant",
        "experiment": "experiment_a",
    },
    attachments=[
        {
            "type": "text",
            "name": "Additional Info",
            "value": "A very long document",
            "role": "input",
        }
    ],
)

print(result.queued, result.evaluation_after_seconds)

Set LETTERBOOK_API_KEY, or instantiate letterbook.Letterbook(api_key=...) for explicit configuration. Set debounce_seconds to control how long Letterbook waits after the last message before evaluating the conversation.

If customer_email is omitted, the SDK looks for properties["customer_email"], properties["email"], or an email-shaped user_id. Email is only required if Letterbook promotes the capture to a ticket.