mirror of
https://github.com/hwchase17/langchain.git
synced 2025-09-05 13:06:03 +00:00
Harrison/use functions agent (#6185)
Co-authored-by: Francisco Ingham <24279597+fpingham@users.noreply.github.com>
This commit is contained in:
Harrison Chase
GitHub
@@ -30,38 +30,83 @@
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.llms import OpenAI"
|
||||
"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": "16c4dc59",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"agent = create_csv_agent(OpenAI(temperature=0), 'titanic.csv', verbose=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"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[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: df.shape[0]\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.\u001b[0m\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"
|
||||
]
|
||||
@@ -69,10 +114,10 @@
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'There are 891 rows.'"
|
||||
"'There are 891 rows in the dataframe.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 5,
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
@@ -83,23 +128,28 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"execution_count": 5,
|
||||
"id": "a96309be",
|
||||
"metadata": {},
|
||||
"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[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",
|
||||
"\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"
|
||||
]
|
||||
@@ -107,10 +157,10 @@
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'30 people have more than 3 siblings.'"
|
||||
"'There are 30 people in the dataframe who have more than 3 siblings.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 6,
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
@@ -121,35 +171,39 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"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[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 now need to calculate the square root of the average age\n",
|
||||
"Action: python_repl_ast\n",
|
||||
"Action Input: math.sqrt(df['Age'].mean())\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mNameError(\"name '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",
|
||||
"Observation: \u001b[36;1m\u001b[1;3m\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now need to calculate the square root of the average age\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",
|
||||
"\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"
|
||||
]
|
||||
@@ -157,10 +211,10 @@
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'5.449689683556195'"
|
||||
"'The square root of the average age is approximately 5.59.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 7,
|
||||
"execution_count": 6,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
@@ -181,23 +235,26 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"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[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3mThought: I need to compare the age columns in both dataframes\n",
|
||||
"Action: python_repl_ast\n",
|
||||
"Action Input: len(df1[df1['Age'] != df2['Age']])\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3m177\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
|
||||
"Final Answer: 177 rows in the age column are different.\u001b[0m\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"
|
||||
]
|
||||
@@ -205,17 +262,17 @@
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'177 rows in the age column are different.'"
|
||||
"'There is 1 row in the age column that is different between the two dataframes.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 3,
|
||||
"execution_count": 8,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent = create_csv_agent(OpenAI(temperature=0), ['titanic.csv', 'titanic_age_fillna.csv'], verbose=True)\n",
|
||||
"agent.run(\"how many rows in the age column are different?\")"
|
||||
"agent = create_csv_agent(ChatOpenAI(temperature=0, model=\"gpt-3.5-turbo-0613\"), ['titanic.csv', 'titanic_age_fillna.csv'], verbose=True, agent_type=AgentType.OPENAI_FUNCTIONS)\n",
|
||||
"agent.run(\"how many rows in the age column are different between the two dfs?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
||||
@@ -19,7 +19,9 @@
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.agents import create_pandas_dataframe_agent"
|
||||
"from langchain.agents import create_pandas_dataframe_agent\n",
|
||||
"from langchain.chat_models import ChatOpenAI\n",
|
||||
"from langchain.agents.agent_types import AgentType"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -35,6 +37,16 @@
|
||||
"df = pd.read_csv('titanic.csv')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "a62858e2",
|
||||
"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": 3,
|
||||
@@ -45,9 +57,34 @@
|
||||
"agent = create_pandas_dataframe_agent(OpenAI(temperature=0), df, verbose=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "7233ab56",
|
||||
"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": 4,
|
||||
"id": "a8ea710e",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"agent = create_pandas_dataframe_agent(\n",
|
||||
" ChatOpenAI(temperature=0, model=\"gpt-3.5-turbo-0613\"), \n",
|
||||
" df, \n",
|
||||
" verbose=True, \n",
|
||||
" agent_type=AgentType.OPENAI_FUNCTIONS\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "a9207a2e",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
@@ -57,13 +94,12 @@
|
||||
"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: df.shape[0]\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.\u001b[0m\n",
|
||||
"\u001b[1m> Entering new chain...\u001b[0m\n",
|
||||
"\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"
|
||||
]
|
||||
@@ -71,10 +107,10 @@
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'There are 891 rows.'"
|
||||
"'There are 891 rows in the dataframe.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 4,
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
@@ -172,7 +208,6 @@
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "c4bc0584",
|
||||
"metadata": {},
|
||||
@@ -257,7 +292,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.16"
|
||||
"version": "3.9.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
|
||||
@@ -12,7 +12,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"execution_count": 1,
|
||||
"id": "f98e9c90-5c37-4fb9-af3e-d09693af8543",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
@@ -22,12 +22,24 @@
|
||||
"from langchain.agents.agent_toolkits import create_python_agent\n",
|
||||
"from langchain.tools.python.tool import PythonREPLTool\n",
|
||||
"from langchain.python import PythonREPL\n",
|
||||
"from langchain.llms.openai import OpenAI"
|
||||
"from langchain.llms.openai import OpenAI\n",
|
||||
"from langchain.agents.agent_types import AgentType\n",
|
||||
"from langchain.chat_models import ChatOpenAI"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "ca30d64c",
|
||||
"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": 5,
|
||||
"execution_count": 2,
|
||||
"id": "cc422f53-c51c-4694-a834-72ecd1e68363",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
@@ -37,7 +49,34 @@
|
||||
"agent_executor = create_python_agent(\n",
|
||||
" llm=OpenAI(temperature=0, max_tokens=1000),\n",
|
||||
" tool=PythonREPLTool(),\n",
|
||||
" verbose=True\n",
|
||||
" verbose=True,\n",
|
||||
" agent_type=AgentType.ZERO_SHOT_REACT_DESCRIPTION\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "bb487e8e",
|
||||
"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": "6e651822",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"agent_executor = create_python_agent(\n",
|
||||
" llm=ChatOpenAI(temperature=0, model=\"gpt-3.5-turbo-0613\"),\n",
|
||||
" tool=PythonREPLTool(),\n",
|
||||
" verbose=True,\n",
|
||||
" agent_type=AgentType.OPENAI_FUNCTIONS,\n",
|
||||
" agent_executor_kwargs={\"handle_parsing_errors\": True},\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
@@ -52,7 +91,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"execution_count": 4,
|
||||
"id": "25cd4f92-ea9b-4fe6-9838-a4f85f81eebe",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
@@ -64,23 +103,20 @@
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3m I need to calculate the 10th fibonacci number\n",
|
||||
"Action: Python REPL\n",
|
||||
"Action Input: def fibonacci(n):\n",
|
||||
" if n == 0:\n",
|
||||
"\u001b[1m> Entering new chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3m\n",
|
||||
"Invoking: `Python_REPL` with `def fibonacci(n):\n",
|
||||
" if n <= 0:\n",
|
||||
" return 0\n",
|
||||
" elif n == 1:\n",
|
||||
" return 1\n",
|
||||
" else:\n",
|
||||
" return fibonacci(n-1) + fibonacci(n-2)\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3m\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I need to call the function with 10 as the argument\n",
|
||||
"Action: Python REPL\n",
|
||||
"Action Input: fibonacci(10)\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3m\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
|
||||
"Final Answer: 55\u001b[0m\n",
|
||||
" return fibonacci(n-1) + fibonacci(n-2)\n",
|
||||
"\n",
|
||||
"fibonacci(10)`\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[0m\u001b[36;1m\u001b[1;3m\u001b[0m\u001b[32;1m\u001b[1;3mThe 10th Fibonacci number is 55.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
@@ -88,10 +124,10 @@
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'55'"
|
||||
"'The 10th Fibonacci number is 55.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 3,
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
@@ -111,9 +147,11 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"execution_count": 5,
|
||||
"id": "4b9f60e7-eb6a-4f14-8604-498d863d4482",
|
||||
"metadata": {},
|
||||
"metadata": {
|
||||
"scrolled": false
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
@@ -121,59 +159,70 @@
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3m I need to write a neural network in PyTorch and train it on the given data.\n",
|
||||
"Action: Python REPL\n",
|
||||
"Action Input: \n",
|
||||
"import torch\n",
|
||||
"\u001b[1m> Entering new chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3mCould not parse tool input: {'name': 'python', 'arguments': 'import torch\\nimport torch.nn as nn\\nimport torch.optim as optim\\n\\n# Define the neural network\\nclass SingleNeuron(nn.Module):\\n def __init__(self):\\n super(SingleNeuron, self).__init__()\\n self.linear = nn.Linear(1, 1)\\n \\n def forward(self, x):\\n return self.linear(x)\\n\\n# Create the synthetic data\\nx_train = torch.tensor([[1.0], [2.0], [3.0], [4.0]], dtype=torch.float32)\\ny_train = torch.tensor([[2.0], [4.0], [6.0], [8.0]], dtype=torch.float32)\\n\\n# Create the neural network\\nmodel = SingleNeuron()\\n\\n# Define the loss function and optimizer\\ncriterion = nn.MSELoss()\\noptimizer = optim.SGD(model.parameters(), lr=0.01)\\n\\n# Train the neural network\\nfor epoch in range(1, 1001):\\n # Forward pass\\n y_pred = model(x_train)\\n \\n # Compute loss\\n loss = criterion(y_pred, y_train)\\n \\n # Backward pass and optimization\\n optimizer.zero_grad()\\n loss.backward()\\n optimizer.step()\\n \\n # Print the loss every 100 epochs\\n if epoch % 100 == 0:\\n print(f\"Epoch {epoch}: Loss = {loss.item()}\")\\n\\n# Make a prediction for x = 5\\nx_test = torch.tensor([[5.0]], dtype=torch.float32)\\ny_pred = model(x_test)\\ny_pred.item()'} because the `arguments` is not valid JSON.\u001b[0mInvalid or incomplete response\u001b[32;1m\u001b[1;3m\n",
|
||||
"Invoking: `Python_REPL` with `import torch\n",
|
||||
"import torch.nn as nn\n",
|
||||
"import torch.optim as optim\n",
|
||||
"\n",
|
||||
"# Define the model\n",
|
||||
"model = torch.nn.Sequential(\n",
|
||||
" torch.nn.Linear(1, 1)\n",
|
||||
")\n",
|
||||
"# Define the neural network\n",
|
||||
"class SingleNeuron(nn.Module):\n",
|
||||
" def __init__(self):\n",
|
||||
" super(SingleNeuron, self).__init__()\n",
|
||||
" self.linear = nn.Linear(1, 1)\n",
|
||||
" \n",
|
||||
" def forward(self, x):\n",
|
||||
" return self.linear(x)\n",
|
||||
"\n",
|
||||
"# Define the loss\n",
|
||||
"loss_fn = torch.nn.MSELoss()\n",
|
||||
"# Create the synthetic data\n",
|
||||
"x_train = torch.tensor([[1.0], [2.0], [3.0], [4.0]], dtype=torch.float32)\n",
|
||||
"y_train = torch.tensor([[2.0], [4.0], [6.0], [8.0]], dtype=torch.float32)\n",
|
||||
"\n",
|
||||
"# Define the optimizer\n",
|
||||
"optimizer = torch.optim.SGD(model.parameters(), lr=0.01)\n",
|
||||
"# Create the neural network\n",
|
||||
"model = SingleNeuron()\n",
|
||||
"\n",
|
||||
"# Define the data\n",
|
||||
"x_data = torch.tensor([[1.0], [2.0], [3.0], [4.0]])\n",
|
||||
"y_data = torch.tensor([[2.0], [4.0], [6.0], [8.0]])\n",
|
||||
"# Define the loss function and optimizer\n",
|
||||
"criterion = nn.MSELoss()\n",
|
||||
"optimizer = optim.SGD(model.parameters(), lr=0.01)\n",
|
||||
"\n",
|
||||
"# Train the model\n",
|
||||
"for epoch in range(1000):\n",
|
||||
"# Train the neural network\n",
|
||||
"for epoch in range(1, 1001):\n",
|
||||
" # Forward pass\n",
|
||||
" y_pred = model(x_data)\n",
|
||||
"\n",
|
||||
" # Compute and print loss\n",
|
||||
" loss = loss_fn(y_pred, y_data)\n",
|
||||
" if (epoch+1) % 100 == 0:\n",
|
||||
" print(f'Epoch {epoch+1}: loss = {loss.item():.4f}')\n",
|
||||
"\n",
|
||||
" # Zero the gradients\n",
|
||||
" y_pred = model(x_train)\n",
|
||||
" \n",
|
||||
" # Compute loss\n",
|
||||
" loss = criterion(y_pred, y_train)\n",
|
||||
" \n",
|
||||
" # Backward pass and optimization\n",
|
||||
" optimizer.zero_grad()\n",
|
||||
"\n",
|
||||
" # Backward pass\n",
|
||||
" loss.backward()\n",
|
||||
"\n",
|
||||
" # Update the weights\n",
|
||||
" optimizer.step()\n",
|
||||
"\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mEpoch 100: loss = 0.0013\n",
|
||||
"Epoch 200: loss = 0.0007\n",
|
||||
"Epoch 300: loss = 0.0004\n",
|
||||
"Epoch 400: loss = 0.0002\n",
|
||||
"Epoch 500: loss = 0.0001\n",
|
||||
"Epoch 600: loss = 0.0001\n",
|
||||
"Epoch 700: loss = 0.0000\n",
|
||||
"Epoch 800: loss = 0.0000\n",
|
||||
"Epoch 900: loss = 0.0000\n",
|
||||
"Epoch 1000: loss = 0.0000\n",
|
||||
"\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
|
||||
"Final Answer: The prediction for x = 5 is 10.0.\u001b[0m\n",
|
||||
" \n",
|
||||
" # Print the loss every 100 epochs\n",
|
||||
" if epoch % 100 == 0:\n",
|
||||
" print(f\"Epoch {epoch}: Loss = {loss.item()}\")\n",
|
||||
"\n",
|
||||
"# Make a prediction for x = 5\n",
|
||||
"x_test = torch.tensor([[5.0]], dtype=torch.float32)\n",
|
||||
"y_pred = model(x_test)\n",
|
||||
"y_pred.item()`\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[0m\u001b[36;1m\u001b[1;3mEpoch 100: Loss = 0.03825576975941658\n",
|
||||
"Epoch 200: Loss = 0.02100197970867157\n",
|
||||
"Epoch 300: Loss = 0.01152981910854578\n",
|
||||
"Epoch 400: Loss = 0.006329738534986973\n",
|
||||
"Epoch 500: Loss = 0.0034749575424939394\n",
|
||||
"Epoch 600: Loss = 0.0019077073084190488\n",
|
||||
"Epoch 700: Loss = 0.001047312980517745\n",
|
||||
"Epoch 800: Loss = 0.0005749554838985205\n",
|
||||
"Epoch 900: Loss = 0.0003156439634039998\n",
|
||||
"Epoch 1000: Loss = 0.00017328384274151176\n",
|
||||
"\u001b[0m\u001b[32;1m\u001b[1;3m\n",
|
||||
"Invoking: `Python_REPL` with `x_test.item()`\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[0m\u001b[36;1m\u001b[1;3m\u001b[0m\u001b[32;1m\u001b[1;3mThe prediction for x = 5 is 10.000173568725586.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
@@ -181,10 +230,10 @@
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'The prediction for x = 5 is 10.0.'"
|
||||
"'The prediction for x = 5 is 10.000173568725586.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 4,
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
@@ -206,9 +255,9 @@
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "LangChain",
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "langchain"
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
@@ -220,7 +269,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.16"
|
||||
"version": "3.9.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
|
||||
@@ -37,7 +37,30 @@
|
||||
"from langchain.agents.agent_toolkits import SQLDatabaseToolkit\n",
|
||||
"from langchain.sql_database import SQLDatabase\n",
|
||||
"from langchain.llms.openai import OpenAI\n",
|
||||
"from langchain.agents import AgentExecutor"
|
||||
"from langchain.agents import AgentExecutor\n",
|
||||
"from langchain.agents.agent_types import AgentType\n",
|
||||
"from langchain.chat_models import ChatOpenAI"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "65ec5bb3",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"db = SQLDatabase.from_uri(\"sqlite:///../../../../../notebooks/Chinook.db\")\n",
|
||||
"toolkit = SQLDatabaseToolkit(db=db, llm=OpenAI(temperature=0))\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "f74d1792",
|
||||
"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."
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -49,16 +72,39 @@
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"db = SQLDatabase.from_uri(\"sqlite:///../../../../notebooks/Chinook.db\")\n",
|
||||
"toolkit = SQLDatabaseToolkit(db=db)\n",
|
||||
"\n",
|
||||
"agent_executor = create_sql_agent(\n",
|
||||
" llm=OpenAI(temperature=0),\n",
|
||||
" toolkit=toolkit,\n",
|
||||
" verbose=True\n",
|
||||
" verbose=True,\n",
|
||||
" agent_type=AgentType.ZERO_SHOT_REACT_DESCRIPTION\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "971cc455",
|
||||
"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": "6426a27d",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# agent_executor = create_sql_agent(\n",
|
||||
"# llm=ChatOpenAI(temperature=0, model=\"gpt-3.5-turbo-0613\"),\n",
|
||||
"# toolkit=toolkit,\n",
|
||||
"# verbose=True,\n",
|
||||
"# agent_type=AgentType.OPENAI_FUNCTIONS\n",
|
||||
"# )"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "36ae48c7-cb08-4fef-977e-c7d4b96a464b",
|
||||
@@ -69,7 +115,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"execution_count": 4,
|
||||
"id": "ff70e83d-5ad0-4fc7-bb96-27d82ac166d7",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
@@ -81,14 +127,16 @@
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3mAction: list_tables_sql_db\n",
|
||||
"Action Input: \"\"\u001b[0m\n",
|
||||
"Observation: \u001b[38;5;200m\u001b[1;3mArtist, Invoice, Playlist, Genre, Album, PlaylistTrack, Track, InvoiceLine, MediaType, Employee, Customer\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I should look at the schema of the playlisttrack table\n",
|
||||
"Action: schema_sql_db\n",
|
||||
"Action Input: \"PlaylistTrack\"\u001b[0m\n",
|
||||
"Observation: \u001b[33;1m\u001b[1;3m\n",
|
||||
"\u001b[1m> Entering new chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3m\n",
|
||||
"Invoking: `list_tables_sql_db` with `{}`\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[0m\u001b[38;5;200m\u001b[1;3mAlbum, Artist, Track, PlaylistTrack, InvoiceLine, sales_table, Playlist, Genre, Employee, Customer, Invoice, MediaType\u001b[0m\u001b[32;1m\u001b[1;3m\n",
|
||||
"Invoking: `schema_sql_db` with `PlaylistTrack`\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[0m\u001b[33;1m\u001b[1;3m\n",
|
||||
"CREATE TABLE \"PlaylistTrack\" (\n",
|
||||
"\t\"PlaylistId\" INTEGER NOT NULL, \n",
|
||||
"\t\"TrackId\" INTEGER NOT NULL, \n",
|
||||
@@ -97,13 +145,36 @@
|
||||
"\tFOREIGN KEY(\"PlaylistId\") REFERENCES \"Playlist\" (\"PlaylistId\")\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"SELECT * FROM 'PlaylistTrack' LIMIT 3;\n",
|
||||
"PlaylistId TrackId\n",
|
||||
"1 3402\n",
|
||||
"1 3389\n",
|
||||
"1 3390\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
|
||||
"Final Answer: The PlaylistTrack table has two columns, PlaylistId and TrackId, and is linked to the Playlist and Track tables.\u001b[0m\n",
|
||||
"/*\n",
|
||||
"3 rows from PlaylistTrack table:\n",
|
||||
"PlaylistId\tTrackId\n",
|
||||
"1\t3402\n",
|
||||
"1\t3389\n",
|
||||
"1\t3390\n",
|
||||
"*/\u001b[0m\u001b[32;1m\u001b[1;3mThe `PlaylistTrack` table has two columns: `PlaylistId` and `TrackId`. It is a junction table that represents the relationship between playlists and tracks. \n",
|
||||
"\n",
|
||||
"Here is the schema of the `PlaylistTrack` table:\n",
|
||||
"\n",
|
||||
"```\n",
|
||||
"CREATE TABLE \"PlaylistTrack\" (\n",
|
||||
"\t\"PlaylistId\" INTEGER NOT NULL, \n",
|
||||
"\t\"TrackId\" INTEGER NOT NULL, \n",
|
||||
"\tPRIMARY KEY (\"PlaylistId\", \"TrackId\"), \n",
|
||||
"\tFOREIGN KEY(\"TrackId\") REFERENCES \"Track\" (\"TrackId\"), \n",
|
||||
"\tFOREIGN KEY(\"PlaylistId\") REFERENCES \"Playlist\" (\"PlaylistId\")\n",
|
||||
")\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"Here are three sample rows from the `PlaylistTrack` table:\n",
|
||||
"\n",
|
||||
"```\n",
|
||||
"PlaylistId TrackId\n",
|
||||
"1 3402\n",
|
||||
"1 3389\n",
|
||||
"1 3390\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"Please let me know if there is anything else I can help you with.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
@@ -111,10 +182,10 @@
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'The PlaylistTrack table has two columns, PlaylistId and TrackId, and is linked to the Playlist and Track tables.'"
|
||||
"'The `PlaylistTrack` table has two columns: `PlaylistId` and `TrackId`. It is a junction table that represents the relationship between playlists and tracks. \\n\\nHere is the schema of the `PlaylistTrack` table:\\n\\n```\\nCREATE TABLE \"PlaylistTrack\" (\\n\\t\"PlaylistId\" INTEGER NOT NULL, \\n\\t\"TrackId\" INTEGER NOT NULL, \\n\\tPRIMARY KEY (\"PlaylistId\", \"TrackId\"), \\n\\tFOREIGN KEY(\"TrackId\") REFERENCES \"Track\" (\"TrackId\"), \\n\\tFOREIGN KEY(\"PlaylistId\") REFERENCES \"Playlist\" (\"PlaylistId\")\\n)\\n```\\n\\nHere are three sample rows from the `PlaylistTrack` table:\\n\\n```\\nPlaylistId TrackId\\n1 3402\\n1 3389\\n1 3390\\n```\\n\\nPlease let me know if there is anything else I can help you with.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 3,
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
@@ -519,7 +590,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.10.9"
|
||||
"version": "3.9.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
|
||||
Reference in New Issue
Block a user