mirror of
https://github.com/hwchase17/langchain.git
synced 2025-11-04 10:10:09 +00:00
229 lines
6.0 KiB
Plaintext
229 lines
6.0 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "82a4c2cc-20ea-4b20-a565-63e905dee8ff",
|
|
"metadata": {},
|
|
"source": [
|
|
"# Python Agent\n",
|
|
"\n",
|
|
"This notebook showcases an agent designed to write and execute python code to answer a question."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"id": "f98e9c90-5c37-4fb9-af3e-d09693af8543",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"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"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 5,
|
|
"id": "cc422f53-c51c-4694-a834-72ecd1e68363",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"agent_executor = create_python_agent(\n",
|
|
" llm=OpenAI(temperature=0, max_tokens=1000),\n",
|
|
" tool=PythonREPLTool(),\n",
|
|
" verbose=True\n",
|
|
")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "c16161de",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Fibonacci Example\n",
|
|
"This example was created by [John Wiseman](https://twitter.com/lemonodor/status/1628270074074398720?s=20)."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"id": "25cd4f92-ea9b-4fe6-9838-a4f85f81eebe",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"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",
|
|
" 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",
|
|
"\n",
|
|
"\u001b[1m> Finished chain.\u001b[0m\n"
|
|
]
|
|
},
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"'55'"
|
|
]
|
|
},
|
|
"execution_count": 3,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"agent_executor.run(\"What is the 10th fibonacci number?\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "7caa30de",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Training neural net\n",
|
|
"This example was created by [Samee Ur Rehman](https://twitter.com/sameeurehman/status/1630130518133207046?s=20)."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"id": "4b9f60e7-eb6a-4f14-8604-498d863d4482",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"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",
|
|
"\n",
|
|
"# Define the model\n",
|
|
"model = torch.nn.Sequential(\n",
|
|
" torch.nn.Linear(1, 1)\n",
|
|
")\n",
|
|
"\n",
|
|
"# Define the loss\n",
|
|
"loss_fn = torch.nn.MSELoss()\n",
|
|
"\n",
|
|
"# Define the optimizer\n",
|
|
"optimizer = torch.optim.SGD(model.parameters(), lr=0.01)\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",
|
|
"\n",
|
|
"# Train the model\n",
|
|
"for epoch in range(1000):\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",
|
|
" 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",
|
|
"\u001b[1m> Finished chain.\u001b[0m\n"
|
|
]
|
|
},
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"'The prediction for x = 5 is 10.0.'"
|
|
]
|
|
},
|
|
"execution_count": 4,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"agent_executor.run(\"\"\"Understand, write a single neuron neural network in PyTorch.\n",
|
|
"Take synthetic data for y=2x. Train for 1000 epochs and print every 100 epochs.\n",
|
|
"Return prediction for x = 5\"\"\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "eb654671",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": []
|
|
}
|
|
],
|
|
"metadata": {
|
|
"kernelspec": {
|
|
"display_name": "LangChain",
|
|
"language": "python",
|
|
"name": "langchain"
|
|
},
|
|
"language_info": {
|
|
"codemirror_mode": {
|
|
"name": "ipython",
|
|
"version": 3
|
|
},
|
|
"file_extension": ".py",
|
|
"mimetype": "text/x-python",
|
|
"name": "python",
|
|
"nbconvert_exporter": "python",
|
|
"pygments_lexer": "ipython3",
|
|
"version": "3.9.16"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 5
|
|
}
|