Rockset

Rockset is a real-time analytics database service for serving low latency, high concurrency analytical queries at scale. It builds a Converged Index™ on structured and semi-structured data with an efficient store for vector embeddings. Its support for running SQL on schemaless data makes it a perfect choice for running vector search with metadata filters.

This notebook goes over how to use Rockset to store chat message history.

Setting up

%pip install --upgrade --quiet  rockset langchain-community

To begin, with get your API key from the Rockset console. Find your API region for the Rockset API reference.

Example

from langchain_community.chat_message_histories import (
    RocksetChatMessageHistory,
)
from rockset import Regions, RocksetClient

history = RocksetChatMessageHistory(
    session_id="MySession",
    client=RocksetClient(
        api_key="YOUR API KEY",
        host=Regions.usw2a1,  # us-west-2 Oregon
    ),
    collection="langchain_demo",
    sync=True,
)
history.add_user_message("hi!")
history.add_ai_message("whats up?")
print(history.messages)

API Reference:RocksetChatMessageHistory

The output should be something like:

[
    HumanMessage(content='hi!', additional_kwargs={'id': '2e62f1c2-e9f7-465e-b551-49bae07fe9f0'}, example=False), 
    AIMessage(content='whats up?', additional_kwargs={'id': 'b9be8eda-4c18-4cf8-81c3-e91e876927d0'}, example=False)
]