2023-03-01 06:19:11 +00:00
{
"cells": [
{
"cell_type": "markdown",
"id": "7094e328",
"metadata": {},
"source": [
2023-03-01 17:40:31 +00:00
"# CSV Agent\n",
2023-03-01 06:19:11 +00:00
"\n",
2023-03-01 17:40:31 +00:00
"This notebook shows how to use agents to interact with a csv. It is mostly optimized for question answering.\n",
2023-03-01 06:19:11 +00:00
"\n",
2023-03-01 17:40:31 +00:00
"**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.**\n",
"\n"
2023-03-01 06:19:11 +00:00
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "827982c7",
"metadata": {},
"outputs": [],
"source": [
"from langchain.agents import create_csv_agent"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "caae0bec",
"metadata": {},
"outputs": [],
"source": [
"from langchain.llms import OpenAI"
]
},
{
"cell_type": "code",
2023-04-16 20:15:21 +00:00
"execution_count": 3,
2023-03-01 06:19:11 +00:00
"id": "16c4dc59",
"metadata": {},
"outputs": [],
"source": [
"agent = create_csv_agent(OpenAI(temperature=0), 'titanic.csv', verbose=True)"
]
},
{
"cell_type": "code",
2023-04-16 20:15:21 +00:00
"execution_count": 4,
2023-03-01 06:19:11 +00:00
"id": "46b9489d",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mThought: I need to count the number of rows\n",
"Action: python_repl_ast\n",
"Action Input: len(df)\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m891\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: There are 891 rows in the dataframe.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'There are 891 rows in the dataframe.'"
]
},
2023-04-16 20:15:21 +00:00
"execution_count": 4,
2023-03-01 06:19:11 +00:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\"how many rows are there?\")"
]
},
{
"cell_type": "code",
2023-04-16 20:15:21 +00:00
"execution_count": 5,
2023-03-01 06:19:11 +00:00
"id": "a96309be",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mThought: I need to count the number of people with more than 3 siblings\n",
"Action: python_repl_ast\n",
"Action Input: df[df['SibSp'] > 3].shape[0]\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m30\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: 30 people have more than 3 siblings.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'30 people have more than 3 siblings.'"
]
},
2023-04-16 20:15:21 +00:00
"execution_count": 5,
2023-03-01 06:19:11 +00:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\"how many people have more than 3 sibligngs\")"
]
},
{
"cell_type": "code",
2023-04-16 20:15:21 +00:00
"execution_count": 6,
2023-03-01 06:19:11 +00:00
"id": "964a09f7",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mThought: I need to calculate the average age first\n",
"Action: python_repl_ast\n",
"Action Input: df['Age'].mean()\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m29.69911764705882\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I can now calculate the square root\n",
"Action: python_repl_ast\n",
"Action Input: math.sqrt(df['Age'].mean())\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mname 'math' is not defined\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to import the math library\n",
"Action: python_repl_ast\n",
"Action Input: import math\u001b[0m\n",
2023-04-16 20:15:21 +00:00
"Observation: \u001b[36;1m\u001b[1;3m\u001b[0m\n",
2023-03-01 06:19:11 +00:00
"Thought:\u001b[32;1m\u001b[1;3m I can now calculate the square root\n",
"Action: python_repl_ast\n",
"Action Input: math.sqrt(df['Age'].mean())\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m5.449689683556195\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: 5.449689683556195\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'5.449689683556195'"
]
},
2023-04-16 20:15:21 +00:00
"execution_count": 6,
2023-03-01 06:19:11 +00:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\"whats the square root of the average age?\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "551de2be",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.1"
}
},
"nbformat": 4,
"nbformat_minor": 5
}