langchain/docs/modules/agents/toolkits/examples/csv.ipynb

CSV Agent

This notebook shows how to use agents to interact with a csv. It is mostly optimized for question answering.

NOTE: this agent calls the Pandas DataFrame agent under the hood, which in turn calls the Python agent, which executes LLM generated Python code - this can be bad if the LLM generated Python code is harmful. Use cautiously.

In [1]:

from langchain.agents import create_csv_agent

In [2]:

from langchain.llms import OpenAI

In [4]:

agent = create_csv_agent(OpenAI(temperature=0), 'titanic.csv', verbose=True)

In [5]:

agent.run("how many rows are there?")

Out [5]:

> Entering new AgentExecutor chain...
Thought: I need to count the number of rows
Action: python_repl_ast
Action Input: df.shape[0]
Observation: 891
Thought: I now know the final answer
Final Answer: There are 891 rows.

> Finished chain.

'There are 891 rows.'

In [6]:

agent.run("how many people have more than 3 siblings")

Out [6]:

> Entering new AgentExecutor chain...
Thought: I need to count the number of people with more than 3 siblings
Action: python_repl_ast
Action Input: df[df['SibSp'] > 3].shape[0]
Observation: 30
Thought: I now know the final answer
Final Answer: 30 people have more than 3 siblings.

> Finished chain.

'30 people have more than 3 siblings.'

In [7]:

agent.run("whats the square root of the average age?")

Out [7]:

> Entering new AgentExecutor chain...
Thought: I need to calculate the average age first
Action: python_repl_ast
Action Input: df['Age'].mean()
Observation: 29.69911764705882
Thought: I now need to calculate the square root of the average age
Action: python_repl_ast
Action Input: math.sqrt(df['Age'].mean())
Observation: NameError("name 'math' is not defined")
Thought: I need to import the math library
Action: python_repl_ast
Action Input: import math
Observation: 
Thought: I now need to calculate the square root of the average age
Action: python_repl_ast
Action Input: math.sqrt(df['Age'].mean())
Observation: 5.449689683556195
Thought: I now know the final answer
Final Answer: 5.449689683556195

> Finished chain.

'5.449689683556195'

Multi CSV Example

This next part shows how the agent can interact with multiple csv files passed in as a list.

In [3]:

agent = create_csv_agent(OpenAI(temperature=0), ['titanic.csv', 'titanic_age_fillna.csv'], verbose=True)
agent.run("how many rows in the age column are different?")

Out [3]:

> Entering new AgentExecutor chain...
Thought: I need to compare the age columns in both dataframes
Action: python_repl_ast
Action Input: len(df1[df1['Age'] != df2['Age']])
Observation: 177
Thought: I now know the final answer
Final Answer: 177 rows in the age column are different.

> Finished chain.

'177 rows in the age column are different.'

In [ ]: