Skip to main content

TiDB

TiDB Cloud, is a comprehensive Database-as-a-Service (DBaaS) solution, that provides dedicated and serverless options. TiDB Serverless is now integrating a built-in vector search into the MySQL landscape. With this enhancement, you can seamlessly develop AI applications using TiDB Serverless without the need for a new database or additional technical stacks. Be among the first to experience it by joining the waitlist for the private beta at https://tidb.cloud/ai.

This notebook introduces how to use TiDB to store chat message history.

Setup​

Firstly, we will install the following dependencies:

%pip install --upgrade --quiet langchain langchain_openai

Configuring your OpenAI Key

import getpass
import os

os.environ["OPENAI_API_KEY"] = getpass.getpass("Input your OpenAI API key:")

Finally, we will configure the connection to a TiDB. In this notebook, we will follow the standard connection method provided by TiDB Cloud to establish a secure and efficient database connection.

# copy from tidb cloud console
tidb_connection_string_template = "mysql+pymysql://<USER>:<PASSWORD>@<HOST>:4000/<DB>?ssl_ca=/etc/ssl/cert.pem&ssl_verify_cert=true&ssl_verify_identity=true"
tidb_password = getpass.getpass("Input your TiDB password:")
tidb_connection_string = tidb_connection_string_template.replace(
    "<PASSWORD>", tidb_password
)

Generating historical data​

Creating a set of historical data, which will serve as the foundation for our upcoming demonstrations.

from datetime import datetime

from langchain_community.chat_message_histories import TiDBChatMessageHistory

history = TiDBChatMessageHistory(
    connection_string=tidb_connection_string,
    session_id="code_gen",
    earliest_time=datetime.utcnow(),  # Optional to set earliest_time to load messages after this time point.
)

history.add_user_message("How's our feature going?")
history.add_ai_message(
    "It's going well. We are working on testing now. It will be released in Feb."
)
history.messages
[HumanMessage(content="How's our feature going?"),
 AIMessage(content="It's going well. We are working on testing now. It will be released in Feb.")]

Chatting with historical data​

Let’s build upon the historical data generated earlier to create a dynamic chat interaction.

Firstly, Creating a Chat Chain with LangChain:

from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
from langchain_openai import ChatOpenAI

prompt = ChatPromptTemplate.from_messages(
    [
        (
            "system",
            "You're an assistant who's good at coding. You're helping a startup build",
        ),
        MessagesPlaceholder(variable_name="history"),
        ("human", "{question}"),
    ]
)
chain = prompt | ChatOpenAI()

Building a Runnable on History:

from langchain_core.runnables.history import RunnableWithMessageHistory

chain_with_history = RunnableWithMessageHistory(
    chain,
    lambda session_id: TiDBChatMessageHistory(
        session_id=session_id, connection_string=tidb_connection_string
    ),
    input_messages_key="question",
    history_messages_key="history",
)

Initiating the Chat:

response = chain_with_history.invoke(
    {"question": "Today is Jan 1st. How many days until our feature is released?"},
    config={"configurable": {"session_id": "code_gen"}},
)
response
AIMessage(content='There are 31 days in January, so there are 30 days until our feature is released in February.')

Checking the history data​

history.reload_cache()
history.messages
[HumanMessage(content="How's our feature going?"),
 AIMessage(content="It's going well. We are working on testing now. It will be released in Feb."),
 HumanMessage(content='Today is Jan 1st. How many days until our feature is released?'),
 AIMessage(content='There are 31 days in January, so there are 30 days until our feature is released in February.')]

Help us out by providing feedback on this documentation page: