langchain/cookbook/llm_bash.ipynb

261 lines
7.1 KiB
Plaintext
Raw Normal View History

{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Bash chain\n",
"This notebook showcases using LLMs and a bash process to perform simple filesystem commands."
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new LLMBashChain chain...\u001b[0m\n",
"Please write a bash script that prints 'Hello World' to the console.\u001b[32;1m\u001b[1;3m\n",
"\n",
"```bash\n",
"echo \"Hello World\"\n",
"```\u001b[0m\n",
"Code: \u001b[33;1m\u001b[1;3m['echo \"Hello World\"']\u001b[0m\n",
2022-12-07 06:55:27 +00:00
"Answer: \u001b[33;1m\u001b[1;3mHello World\n",
"\u001b[0m\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
2022-12-07 06:55:27 +00:00
"'Hello World\\n'"
]
},
"execution_count": 1,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from langchain_experimental.llm_bash.base import LLMBashChain\n",
"from langchain.llms import OpenAI\n",
"\n",
"llm = OpenAI(temperature=0)\n",
"\n",
"text = \"Please write a bash script that prints 'Hello World' to the console.\"\n",
"\n",
"bash_chain = LLMBashChain.from_llm(llm, verbose=True)\n",
"\n",
"bash_chain.run(text)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Customize Prompt\n",
"You can also customize the prompt that is used. Here is an example prompting to avoid using the 'echo' utility"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"from langchain.prompts.prompt import PromptTemplate\n",
"from langchain.chains.llm_bash.prompt import BashOutputParser\n",
"\n",
"_PROMPT_TEMPLATE = \"\"\"If someone asks you to perform a task, your job is to come up with a series of bash commands that will perform the task. There is no need to put \"#!/bin/bash\" in your answer. Make sure to reason step by step, using this format:\n",
"Question: \"copy the files in the directory named 'target' into a new directory at the same level as target called 'myNewDirectory'\"\n",
"I need to take the following actions:\n",
"- List all files in the directory\n",
"- Create a new directory\n",
"- Copy the files from the first directory into the second directory\n",
"```bash\n",
"ls\n",
"mkdir myNewDirectory\n",
"cp -r target/* myNewDirectory\n",
"```\n",
"\n",
"Do not use 'echo' when writing the script.\n",
"\n",
"That is the format. Begin!\n",
"Question: {question}\"\"\"\n",
"\n",
"PROMPT = PromptTemplate(\n",
" input_variables=[\"question\"],\n",
" template=_PROMPT_TEMPLATE,\n",
" output_parser=BashOutputParser(),\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new LLMBashChain chain...\u001b[0m\n",
"Please write a bash script that prints 'Hello World' to the console.\u001b[32;1m\u001b[1;3m\n",
"\n",
"```bash\n",
"printf \"Hello World\\n\"\n",
"```\u001b[0m\n",
"Code: \u001b[33;1m\u001b[1;3m['printf \"Hello World\\\\n\"']\u001b[0m\n",
"Answer: \u001b[33;1m\u001b[1;3mHello World\n",
"\u001b[0m\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'Hello World\\n'"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"bash_chain = LLMBashChain.from_llm(llm, prompt=PROMPT, verbose=True)\n",
"\n",
"text = \"Please write a bash script that prints 'Hello World' to the console.\"\n",
"\n",
"bash_chain.run(text)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Persistent Terminal\n",
"\n",
"By default, the chain will run in a separate subprocess each time it is called. This behavior can be changed by instantiating with a persistent bash process."
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new LLMBashChain chain...\u001b[0m\n",
"List the current directory then move up a level.\u001b[32;1m\u001b[1;3m\n",
"\n",
"```bash\n",
"ls\n",
"cd ..\n",
"```\u001b[0m\n",
"Code: \u001b[33;1m\u001b[1;3m['ls', 'cd ..']\u001b[0m\n",
"Answer: \u001b[33;1m\u001b[1;3mcpal.ipynb llm_bash.ipynb llm_symbolic_math.ipynb\n",
"index.mdx llm_math.ipynb pal.ipynb\u001b[0m\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'cpal.ipynb llm_bash.ipynb llm_symbolic_math.ipynb\\r\\nindex.mdx llm_math.ipynb pal.ipynb'"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from langchain_experimental.llm_bash.bash import BashProcess\n",
"\n",
"\n",
"persistent_process = BashProcess(persistent=True)\n",
"bash_chain = LLMBashChain.from_llm(llm, bash_process=persistent_process, verbose=True)\n",
"\n",
"text = \"List the current directory then move up a level.\"\n",
"\n",
"bash_chain.run(text)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new LLMBashChain chain...\u001b[0m\n",
"List the current directory then move up a level.\u001b[32;1m\u001b[1;3m\n",
"\n",
"```bash\n",
"ls\n",
"cd ..\n",
"```\u001b[0m\n",
"Code: \u001b[33;1m\u001b[1;3m['ls', 'cd ..']\u001b[0m\n",
"Answer: \u001b[33;1m\u001b[1;3m_category_.yml\tdata_generation.ipynb\t\t self_check\n",
"agents\t\tgraph\n",
"code_writing\tlearned_prompt_optimization.ipynb\u001b[0m\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'_category_.yml\\tdata_generation.ipynb\\t\\t self_check\\r\\nagents\\t\\tgraph\\r\\ncode_writing\\tlearned_prompt_optimization.ipynb'"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Run the same command again and see that the state is maintained between calls\n",
"bash_chain.run(text)"
]
}
],
"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": "3.11.4"
}
},
"nbformat": 4,
"nbformat_minor": 4
2022-12-07 06:55:27 +00:00
}