Skip to main content
Open In ColabOpen on GitHub

Cassandra 数据库工具包

Apache Cassandra® 是一个广泛用于存储事务性应用数据的数据库。大型语言模型中的函数和工具引入为生成式AI应用中的现有数据开辟了一些令人兴奋的用例。

Cassandra Database 工具包使AI工程师能够高效地将代理与Cassandra数据集成，提供以下功能：

  • 通过优化的查询实现快速数据访问。大多数查询应在个位数毫秒或更短时间内运行。
  • 模式内省以增强LLM推理能力
  • 兼容各种Cassandra部署，包括Apache Cassandra®、DataStax Enterprise™和DataStax Astra™
  • 目前，该工具包仅限于SELECT查询和模式内省操作。（安全第一）

有关创建Cassandra DB代理的更多信息，请参阅CQL代理手册

快速开始​

  • 安装 cassio 库
  • 设置您正在连接的Cassandra数据库的环境变量
  • 初始化 CassandraDatabase
  • 使用toolkit.get_tools()将工具传递给您的代理
  • 坐下来，看着它为你完成所有工作

操作理论​

Cassandra Query Language (CQL) 是与 Cassandra 数据库交互的主要以人为中心的方式。虽然在生成查询时提供了一定的灵活性，但它需要了解 Cassandra 数据建模的最佳实践。LLM 函数调用使代理能够进行推理，然后选择工具来满足请求。使用 LLM 的代理在选择适当的工具包或工具包链时，应使用 Cassandra 特定的逻辑进行推理。这减少了当 LLM 被迫提供自上而下的解决方案时引入的随机性。你希望 LLM 完全不受限制地访问你的数据库吗？是的。可能不是。为了实现这一点，我们提供了一个提示，用于在为代理构建问题时使用：

您是一个具有以下功能和规则的Apache Cassandra专家查询分析机器人：

  • 您将收到最终用户关于在数据库中查找特定数据的问题。
  • 您将检查数据库的模式并创建查询路径。
  • 您将为用户提供正确的查询以找到他们正在寻找的数据，并显示查询路径提供的步骤。
  • 您将使用最佳实践来查询Apache Cassandra，利用分区键和聚类列。
  • 避免在查询中使用 ALLOW FILTERING。
  • 目标是找到一个查询路径，因此可能需要查询其他表才能得到最终答案。

以下是一个JSON格式的查询路径示例：

 {
  "query_paths": [
    {
      "description": "Direct query to users table using email",
      "steps": [
        {
          "table": "user_credentials",
          "query": 
             "SELECT userid FROM user_credentials WHERE email = 'example@example.com';"
        },
        {
          "table": "users",
          "query": "SELECT * FROM users WHERE userid = ?;"
        }
      ]
    }
  ]
}

提供的工具​

cassandra_db_schema​

收集连接数据库或特定模式的所有模式信息。对于代理在确定操作时至关重要。

cassandra_db_select_table_data​

从特定的键空间和表中选择数据。代理可以传递谓词参数和返回记录数量的限制。

cassandra_db_query​

作为cassandra_db_select_table_data的实验性替代方案，它接受由代理完全形成的查询字符串，而不是参数。警告：这可能导致不寻常的查询，可能不会那么高效（甚至可能无法工作）。这可能会在未来的版本中移除。如果它做了一些很酷的事情，我们也想知道。你永远不知道！

环境设置​

安装以下Python模块：

pip install ipykernel python-dotenv cassio langchain_openai langchain langchain-community langchainhub

.env 文件​

连接是通过 cassio 使用 auto=True 参数进行的，笔记本使用 OpenAI。你应该相应地创建一个 .env 文件。

对于Casssandra，设置：

CASSANDRA_CONTACT_POINTS
CASSANDRA_USERNAME
CASSANDRA_PASSWORD
CASSANDRA_KEYSPACE

对于Astra，设置：

ASTRA_DB_APPLICATION_TOKEN
ASTRA_DB_DATABASE_ID
ASTRA_DB_KEYSPACE

例如：

# Connection to Astra:
ASTRA_DB_DATABASE_ID=a1b2c3d4-...
ASTRA_DB_APPLICATION_TOKEN=AstraCS:...
ASTRA_DB_KEYSPACE=notebooks

# Also set 
OPENAI_API_KEY=sk-....

（你也可以修改下面的代码直接连接到cassio。）

from dotenv import load_dotenv

load_dotenv(override=True)
# Import necessary libraries
import os

import cassio
from langchain import hub
from langchain.agents import AgentExecutor, create_openai_tools_agent
from langchain_community.agent_toolkits.cassandra_database.toolkit import (
    CassandraDatabaseToolkit,
)
from langchain_community.tools.cassandra_database.prompt import QUERY_PATH_PROMPT
from langchain_community.utilities.cassandra_database import CassandraDatabase
from langchain_openai import ChatOpenAI

连接到Cassandra数据库​

cassio.init(auto=True)
session = cassio.config.resolve_session()
if not session:
    raise Exception(
        "Check environment configuration or manually configure cassio connection parameters"
    )
# Test data pep

session = cassio.config.resolve_session()

session.execute("""DROP KEYSPACE IF EXISTS langchain_agent_test; """)

session.execute(
    """
CREATE KEYSPACE if not exists langchain_agent_test 
WITH replication = {'class': 'SimpleStrategy', 'replication_factor': 1};
"""
)

session.execute(
    """
    CREATE TABLE IF NOT EXISTS langchain_agent_test.user_credentials (
    user_email text PRIMARY KEY,
    user_id UUID,
    password TEXT
);
"""
)

session.execute(
    """
    CREATE TABLE IF NOT EXISTS langchain_agent_test.users (
    id UUID PRIMARY KEY,
    name TEXT,
    email TEXT
);"""
)

session.execute(
    """
    CREATE TABLE IF NOT EXISTS langchain_agent_test.user_videos ( 
    user_id UUID,
    video_id UUID,
    title TEXT,
    description TEXT,
    PRIMARY KEY (user_id, video_id)
);
"""
)

user_id = "522b1fe2-2e36-4cef-a667-cd4237d08b89"
video_id = "27066014-bad7-9f58-5a30-f63fe03718f6"

session.execute(
    f"""
    INSERT INTO langchain_agent_test.user_credentials (user_id, user_email) 
    VALUES ({user_id}, 'patrick@datastax.com');
"""
)

session.execute(
    f"""
    INSERT INTO langchain_agent_test.users (id, name, email) 
    VALUES ({user_id}, 'Patrick McFadin', 'patrick@datastax.com');
"""
)

session.execute(
    f"""
    INSERT INTO langchain_agent_test.user_videos (user_id, video_id, title)
    VALUES ({user_id}, {video_id}, 'Use Langflow to Build a LangChain LLM Application in 5 Minutes');
"""
)

session.set_keyspace("langchain_agent_test")
# Create a CassandraDatabase instance
# Uses the cassio session to connect to the database
db = CassandraDatabase()
# Choose the LLM that will drive the agent
# Only certain models support this
llm = ChatOpenAI(temperature=0, model="gpt-4-1106-preview")
toolkit = CassandraDatabaseToolkit(db=db)

tools = toolkit.get_tools()

print("Available tools:")
for tool in tools:
    print(tool.name + "\t- " + tool.description)
Available tools:
cassandra_db_schema	- 
    Input to this tool is a keyspace name, output is a table description 
    of Apache Cassandra tables.
    If the query is not correct, an error message will be returned.
    If an error is returned, report back to the user that the keyspace 
    doesn't exist and stop.
    
cassandra_db_query	- 
    Execute a CQL query against the database and get back the result.
    If the query is not correct, an error message will be returned.
    If an error is returned, rewrite the query, check the query, and try again.
    
cassandra_db_select_table_data	- 
    Tool for getting data from a table in an Apache Cassandra database. 
    Use the WHERE clause to specify the predicate for the query that uses the 
    primary key. A blank predicate will return all rows. Avoid this if possible. 
    Use the limit to specify the number of rows to return. A blank limit will 
    return all rows.
prompt = hub.pull("hwchase17/openai-tools-agent")

# Construct the OpenAI Tools agent
agent = create_openai_tools_agent(llm, tools, prompt)
input = (
    QUERY_PATH_PROMPT
    + "\n\nHere is your task: Find all the videos that the user with the email address 'patrick@datastax.com' has uploaded to the langchain_agent_test keyspace."
)

agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)

response = agent_executor.invoke({"input": input})

print(response["output"])


> Entering new AgentExecutor chain...

Invoking: `cassandra_db_schema` with `{'keyspace': 'langchain_agent_test'}`


Table Name: user_credentials
- Keyspace: langchain_agent_test
- Columns
  - password (text)
  - user_email (text)
  - user_id (uuid)
- Partition Keys: (user_email)
- Clustering Keys: 

Table Name: user_videos
- Keyspace: langchain_agent_test
- Columns
  - description (text)
  - title (text)
  - user_id (uuid)
  - video_id (uuid)
- Partition Keys: (user_id)
- Clustering Keys: (video_id asc)


Table Name: users
- Keyspace: langchain_agent_test
- Columns
  - email (text)
  - id (uuid)
  - name (text)
- Partition Keys: (id)
- Clustering Keys: 


Invoking: `cassandra_db_select_table_data` with `{'keyspace': 'langchain_agent_test', 'table': 'user_credentials', 'predicate': "user_email = 'patrick@datastax.com'", 'limit': 1}`


Row(user_email='patrick@datastax.com', password=None, user_id=UUID('522b1fe2-2e36-4cef-a667-cd4237d08b89'))
Invoking: `cassandra_db_select_table_data` with `{'keyspace': 'langchain_agent_test', 'table': 'user_videos', 'predicate': 'user_id = 522b1fe2-2e36-4cef-a667-cd4237d08b89', 'limit': 10}`


Row(user_id=UUID('522b1fe2-2e36-4cef-a667-cd4237d08b89'), video_id=UUID('27066014-bad7-9f58-5a30-f63fe03718f6'), description='DataStax Academy is a free resource for learning Apache Cassandra.', title='DataStax Academy')To find all the videos that the user with the email address 'patrick@datastax.com' has uploaded to the `langchain_agent_test` keyspace, we can follow these steps:

1. Query the `user_credentials` table to find the `user_id` associated with the email 'patrick@datastax.com'.
2. Use the `user_id` obtained from the first step to query the `user_videos` table to retrieve all the videos uploaded by the user.

Here is the query path in JSON format:

\`\`\`json
{
  "query_paths": [
    {
      "description": "Find user_id from user_credentials and then query user_videos for all videos uploaded by the user",
      "steps": [
        {
          "table": "user_credentials",
          "query": "SELECT user_id FROM user_credentials WHERE user_email = 'patrick@datastax.com';"
        },
        {
          "table": "user_videos",
          "query": "SELECT * FROM user_videos WHERE user_id = 522b1fe2-2e36-4cef-a667-cd4237d08b89;"
        }
      ]
    }
  ]
}
\`\`\`

Following this query path, we found that the user with the user_id `522b1fe2-2e36-4cef-a667-cd4237d08b89` has uploaded at least one video with the title 'DataStax Academy' and the description 'DataStax Academy is a free resource for learning Apache Cassandra.' The video_id for this video is `27066014-bad7-9f58-5a30-f63fe03718f6`. If there are more videos, the same query can be used to retrieve them, possibly with an increased limit if necessary.

> Finished chain.
To find all the videos that the user with the email address 'patrick@datastax.com' has uploaded to the `langchain_agent_test` keyspace, we can follow these steps:

1. Query the `user_credentials` table to find the `user_id` associated with the email 'patrick@datastax.com'.
2. Use the `user_id` obtained from the first step to query the `user_videos` table to retrieve all the videos uploaded by the user.

Here is the query path in JSON format:

\`\`\`json
{
  "query_paths": [
    {
      "description": "Find user_id from user_credentials and then query user_videos for all videos uploaded by the user",
      "steps": [
        {
          "table": "user_credentials",
          "query": "SELECT user_id FROM user_credentials WHERE user_email = 'patrick@datastax.com';"
        },
        {
          "table": "user_videos",
          "query": "SELECT * FROM user_videos WHERE user_id = 522b1fe2-2e36-4cef-a667-cd4237d08b89;"
        }
      ]
    }
  ]
}
\`\`\`

Following this query path, we found that the user with the user_id `522b1fe2-2e36-4cef-a667-cd4237d08b89` has uploaded at least one video with the title 'DataStax Academy' and the description 'DataStax Academy is a free resource for learning Apache Cassandra.' The video_id for this video is `27066014-bad7-9f58-5a30-f63fe03718f6`. If there are more videos, the same query can be used to retrieve them, possibly with an increased limit if necessary.

这个页面有帮助吗？