raindrop-bedrock 0.0.1

Raindrop integration for AWS Bedrock

raindrop-bedrock

Raindrop integration for AWS Bedrock (Python). Automatically captures converse() and invoke_model() calls by wrapping the boto3 bedrock-runtime client.

Installation

pip install raindrop-bedrock boto3

Usage

import boto3
from raindrop_bedrock import create_raindrop_bedrock

raindrop = create_raindrop_bedrock(
    api_key="rk_...",
    user_id="user-123",
)

client = boto3.client("bedrock-runtime", region_name="us-east-1")
wrapped = raindrop["wrap"](client)

response = wrapped.converse(
    modelId="anthropic.claude-3-5-sonnet-20241022-v2:0",
    messages=[
        {"role": "user", "content": [{"text": "Hello!"}]},
    ],
)

raindrop["flush"]()

What gets captured

• converse(): input messages, output text, model ID, token usage (inputTokens/outputTokens)
• invoke_model(): raw request/response bodies, model ID, token usage (Claude, Titan, and Llama formats)
• Errors: tracked and re-raised to the caller

Options

Option	Type	Default	Description
api_key	str	required	Raindrop API key
user_id	str	None	Associate all events with a user
convo_id	str	None	Group events into a conversation

Testing

cd packages/bedrock-python
pip install -e .
python -m pytest tests/ -v

Known Limitations

• InvokeModel body replacement: After consuming the response body stream, it's replaced with a BytesIO object. Callers using StreamingBody.read() will get the same bytes, but the original StreamingBody API is not preserved.
• No events.*, users.*, or signals.* APIs — Python SDK limitation. Use raindrop.analytics directly for these features.