mirror of
https://github.com/hwchase17/langchain
synced 2024-11-08 07:10:35 +00:00
314 lines
7.5 KiB
Plaintext
314 lines
7.5 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "7094e328",
|
|
"metadata": {},
|
|
"source": [
|
|
"# CSV Agent\n",
|
|
"\n",
|
|
"This notebook shows how to use agents to interact with a csv. It is mostly optimized for question answering.\n",
|
|
"\n",
|
|
"**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"
|
|
]
|
|
},
|
|
{
|
|
"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\n",
|
|
"from langchain.chat_models import ChatOpenAI\n",
|
|
"from langchain.agents.agent_types import AgentType"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "bd806175",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Using ZERO_SHOT_REACT_DESCRIPTION\n",
|
|
"\n",
|
|
"This shows how to initialize the agent using the ZERO_SHOT_REACT_DESCRIPTION agent type. Note that this is an alternative to the above."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 9,
|
|
"id": "a1717204",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"agent = create_csv_agent(\n",
|
|
" OpenAI(temperature=0),\n",
|
|
" \"titanic.csv\",\n",
|
|
" verbose=True,\n",
|
|
" agent_type=AgentType.ZERO_SHOT_REACT_DESCRIPTION,\n",
|
|
")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "c31bb8a6",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Using OpenAI Functions\n",
|
|
"\n",
|
|
"This shows how to initialize the agent using the OPENAI_FUNCTIONS agent type. Note that this is an alternative to the above."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"id": "16c4dc59",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"agent = create_csv_agent(\n",
|
|
" ChatOpenAI(temperature=0, model=\"gpt-3.5-turbo-0613\"),\n",
|
|
" \"titanic.csv\",\n",
|
|
" verbose=True,\n",
|
|
" agent_type=AgentType.OPENAI_FUNCTIONS,\n",
|
|
")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"id": "46b9489d",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stderr",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Error in on_chain_start callback: 'name'\n"
|
|
]
|
|
},
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"\u001b[32;1m\u001b[1;3m\n",
|
|
"Invoking: `python_repl_ast` with `df.shape[0]`\n",
|
|
"\n",
|
|
"\n",
|
|
"\u001b[0m\u001b[36;1m\u001b[1;3m891\u001b[0m\u001b[32;1m\u001b[1;3mThere 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.'"
|
|
]
|
|
},
|
|
"execution_count": 4,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"agent.run(\"how many rows are there?\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 5,
|
|
"id": "a96309be",
|
|
"metadata": {
|
|
"scrolled": false
|
|
},
|
|
"outputs": [
|
|
{
|
|
"name": "stderr",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Error in on_chain_start callback: 'name'\n"
|
|
]
|
|
},
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"\u001b[32;1m\u001b[1;3m\n",
|
|
"Invoking: `python_repl_ast` with `df[df['SibSp'] > 3]['PassengerId'].count()`\n",
|
|
"\n",
|
|
"\n",
|
|
"\u001b[0m\u001b[36;1m\u001b[1;3m30\u001b[0m\u001b[32;1m\u001b[1;3mThere are 30 people in the dataframe who have more than 3 siblings.\u001b[0m\n",
|
|
"\n",
|
|
"\u001b[1m> Finished chain.\u001b[0m\n"
|
|
]
|
|
},
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"'There are 30 people in the dataframe who have more than 3 siblings.'"
|
|
]
|
|
},
|
|
"execution_count": 5,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"agent.run(\"how many people have more than 3 siblings\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 6,
|
|
"id": "964a09f7",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stderr",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Error in on_chain_start callback: 'name'\n"
|
|
]
|
|
},
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"\u001b[32;1m\u001b[1;3m\n",
|
|
"Invoking: `python_repl_ast` with `import pandas as pd\n",
|
|
"import math\n",
|
|
"\n",
|
|
"# Create a dataframe\n",
|
|
"data = {'Age': [22, 38, 26, 35, 35]}\n",
|
|
"df = pd.DataFrame(data)\n",
|
|
"\n",
|
|
"# Calculate the average age\n",
|
|
"average_age = df['Age'].mean()\n",
|
|
"\n",
|
|
"# Calculate the square root of the average age\n",
|
|
"square_root = math.sqrt(average_age)\n",
|
|
"\n",
|
|
"square_root`\n",
|
|
"\n",
|
|
"\n",
|
|
"\u001b[0m\u001b[36;1m\u001b[1;3m5.585696017507576\u001b[0m\u001b[32;1m\u001b[1;3mThe square root of the average age is approximately 5.59.\u001b[0m\n",
|
|
"\n",
|
|
"\u001b[1m> Finished chain.\u001b[0m\n"
|
|
]
|
|
},
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"'The square root of the average age is approximately 5.59.'"
|
|
]
|
|
},
|
|
"execution_count": 6,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"agent.run(\"whats the square root of the average age?\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "09539c18",
|
|
"metadata": {},
|
|
"source": [
|
|
"### Multi CSV Example\n",
|
|
"\n",
|
|
"This next part shows how the agent can interact with multiple csv files passed in as a list."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 8,
|
|
"id": "15f11fbd",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stderr",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Error in on_chain_start callback: 'name'\n"
|
|
]
|
|
},
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"\u001b[32;1m\u001b[1;3m\n",
|
|
"Invoking: `python_repl_ast` with `df1['Age'].nunique() - df2['Age'].nunique()`\n",
|
|
"\n",
|
|
"\n",
|
|
"\u001b[0m\u001b[36;1m\u001b[1;3m-1\u001b[0m\u001b[32;1m\u001b[1;3mThere is 1 row in the age column that is different between the two dataframes.\u001b[0m\n",
|
|
"\n",
|
|
"\u001b[1m> Finished chain.\u001b[0m\n"
|
|
]
|
|
},
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"'There is 1 row in the age column that is different between the two dataframes.'"
|
|
]
|
|
},
|
|
"execution_count": 8,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"agent = create_csv_agent(\n",
|
|
" ChatOpenAI(temperature=0, model=\"gpt-3.5-turbo-0613\"),\n",
|
|
" [\"titanic.csv\", \"titanic_age_fillna.csv\"],\n",
|
|
" verbose=True,\n",
|
|
" agent_type=AgentType.OPENAI_FUNCTIONS,\n",
|
|
")\n",
|
|
"agent.run(\"how many rows in the age column are different between the two dfs?\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "f2909808",
|
|
"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
|
|
}
|