本笔记本概述了如何创建智能体并对大型数据集执行问答 使用 langchain-bodo 集成包，该包使用 Bodo DataFrames 以及 Python 智能体。
Bodo DataFrames 是一个高性能 DataFrame 库，可以自动加速和扩展 Pandas 代码，只需简单的导入更改（请参阅下面的示例）。由于其强大的 Pandas 兼容性，Bodo DataFrames 使 LLM（通常擅长生成 Pandas 代码）能够更高效地回答有关更大 数据集的问题，并将生成的代码扩展到 Pandas 的限制之外。
**注意： Python 智能体会执行 LLM 生成的 Python 代码——如果 LLM 生成的 Python 代码有害，这可能很危险。请谨慎使用。**
设置
在运行示例之前，请复制 泰坦尼克号数据集 并本地保存为 titanic.csv.
安装 langchain-bodo 还将安装依赖项 Bodo 和 Pandas：
pip install --quiet -U langchain-bodo langchain-openai凭证
Bodo DataFrames 是免费的，不需要额外的凭证。 示例使用 OpenAI 模型，如果尚未配置，请设置您的 OPENAI_API_KEY:
if not os.environ.get("OPENAI_API_KEY"):
os.environ["OPENAI_API_KEY"] = getpass.getpass("Open AI API key:\n")创建和调用智能体
以下示例借鉴自 Pandas DataFrames 智能体笔记本 并进行了一些修改以突出关键差异。
第一个示例展示了如何直接将 Bodo DataFrame 传递给 create_bodo_dataframes_agent 和 并提出一个简单的问题。
from langchain.agents.agent_types import AgentType
from langchain_bodo import create_bodo_dataframes_agent
from langchain_openai import ChatOpenAI
# Path to local titanic data
datapath = "titanic.csv"from langchain_openai import OpenAI
df = pd.read_csv(datapath)使用 ZERO_SHOT_REACT_DESCRIPTION
这展示了如何使用 ZERO_SHOT_REACT_DESCRIPTION 智能体类型初始化智能体。
agent = create_bodo_dataframes_agent(
OpenAI(temperature=0), df, verbose=True, allow_dangerous_code=True
)使用 OpenAI 函数
这展示了如何使用 OPENAI_函数智能体类型。请注意，这是上述方法的替代方案。
agent = create_bodo_dataframes_agent(
ChatOpenAI(temperature=0, model="gpt-3.5-turbo-1106"),
df,
verbose=True,
agent_type=AgentType.OPENAI_FUNCTIONS,
allow_dangerous_code=True,
)agent.invoke("how many rows are there?")> Entering new AgentExecutor chain...
Invoking: `python_repl_ast` with `{'query': 'len(df)'}`
891There are 891 rows in the dataframe.
> Finished chain.{'input': 'how many rows are there?', 'output': 'There are 891 rows in the dataframe.'}使用 Bodo DataFrames 和预处理创建和调用智能体
此示例展示了一个稍微复杂的用例，将 Bodo DataFrame 传递给 create_bodo_dataframes_agent 并进行一些额外的预处理。 由于 Bodo DataFrames 是惰性求值的，如果不需要所有列 来回答问题，您可以节省计算。请注意传递给智能体的 DataFrame 也可以 大于可用内存。
df2 = df[["Age", "Pclass", "Survived", "Fare"]]
# Potentially expensive computation using df.apply:
df2["Age"] = df2.apply(lambda x: x["Age"] if x["Pclass"] == 3 else 0, axis=1)
agent = create_bodo_dataframes_agent(
OpenAI(temperature=0), df2, verbose=True, allow_dangerous_code=True
)# The bdf["Age"] column is lazy and will not evaluate unless explicitly used by the agent.
agent.invoke("Out of the people who survived, what was their average fare?")> Entering new AgentExecutor chain...
Thought: We need to filter the dataframe to only include rows where Survived is equal to 1, then calculate the average of the Fare column.
Action: python_repl_ast
Action Input: df[df["Survived"] == 1]["Fare"].mean()48.3954076023391748.39540760233917 is the average fare for people who survived.
Final Answer: 48.39540760233917
> Finished chain.{'input': 'Out of the people who survived, what was their average fare?', 'output': '48.39540760233917'}多 DataFrame 示例
您还可以将多个 DataFrame 传递给智能体。 请注意，虽然 Bodo DataFrames 支持 Pandas 中的大多数常见计算密集型操作， 如果智能体生成的代码当前不受支持（请参阅下面的警告），DataFrame 将 被转换回 Pandas 以防止错误。
请参阅 Bodo DataFrames API 文档 了解更多关于当前支持的功能。
agent = create_bodo_dataframes_agent(
OpenAI(temperature=0), [df, df2], verbose=True, allow_dangerous_code=True
)
agent.invoke("how many rows in the age column are different?")> Entering new AgentExecutor chain...
Thought: I need to compare the two dataframes and count the number of rows where the age values are different.
Action: python_repl_ast
Action Input: len(df1[df1["Age"] != df2["Age"]])
... BodoLibFallbackWarning: Series._cmp_method is not implemented in Bodo DataFrames for the specified arguments yet. Falling back to Pandas (may be slow or run out of memory).
Exception: binary operation arguments must have the same dataframe source.
warnings.warn(BodoLibFallbackWarning(msg))
... BodoLibFallbackWarning: DataFrame.__getitem__ is not implemented in Bodo DataFrames for the specified arguments yet. Falling back to Pandas (may be slow or run out of memory).
Exception: DataFrame getitem: Only selecting columns or filtering with BodoSeries is supported.
warnings.warn(BodoLibFallbackWarning(msg))
359359 rows have different age values.
Final Answer: 359
> Finished chain.{'input': 'how many rows in the age column are different?', 'output': '359'}优化代理调用与 number_of_head_rows
默认情况下，DataFrame 的头部作为 Markdown 表格嵌入到提示中。 由于 Bodo DataFrames 采用延迟求值，此头部操作可以进行优化，但 在某些情况下仍然可能较慢。作为优化，您可以设置 头部行数为 0，以便在提示过程中不进行求值。
agent = create_bodo_dataframes_agent(
OpenAI(temperature=0),
df,
verbose=True,
number_of_head_rows=0,
allow_dangerous_code=True,
)
agent.invoke("What is the average age of all female passengers?")> Entering new AgentExecutor chain...
Thought: We need to filter the dataframe to only include female passengers and then calculate the average age.
Action: python_repl_ast
Action Input: df[df["Sex"] == "female"]["Age"].mean()27.91570881226053727.915708812260537 seems like a reasonable average age for female passengers.
Final Answer: 27.915708812260537
> Finished chain.{'input': 'What is the average age of all female passengers?', 'output': '27.915708812260537'}传递 pandas DataFrames
您还可以将一个或多个 Pandas DataFrames 传递给 create_bodo_dataframes_agent。DataFrame 将 在传递给代理之前会被转换为 Bodo。
pdf = pandas.read_csv(datapath)
agent = create_bodo_dataframes_agent(
OpenAI(temperature=0), pdf, verbose=True, allow_dangerous_code=True
)agent.invoke("What is the square root of the average age?")> Entering new AgentExecutor chain...
Thought: We need to calculate the average age first and then take the square root.
Action: python_repl_ast
Action Input: df["Age"].mean()29.69911764705882 Now we have the average age, we can take the square root.
Action: python_repl_ast
Action Input: math.sqrt(df["Age"].mean())NameError: name 'math' is not defined We need to import the math library to use the sqrt function.
Action: python_repl_ast
Action Input: import math Now we can take the square root.
Action: python_repl_ast
Action Input: math.sqrt(df["Age"].mean())5.449689683556195 I now know the final answer.
Final Answer: 5.449689683556195
> Finished chain.{'input': 'What is the square root of the average age?', 'output': '5.449689683556195'}