2022-12-07 05:57:50 +00:00
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
2022-12-07 16:40:08 +00:00
"# BashChain\n",
2022-12-07 05:57:50 +00:00
"This notebook showcases using LLMs and a bash process to do perform simple filesystem commands."
]
},
{
"cell_type": "code",
Docs refactor (#480)
Big docs refactor! Motivation is to make it easier for people to find
resources they are looking for. To accomplish this, there are now three
main sections:
- Getting Started: steps for getting started, walking through most core
functionality
- Modules: these are different modules of functionality that langchain
provides. Each part here has a "getting started", "how to", "key
concepts" and "reference" section (except in a few select cases where it
didnt easily fit).
- Use Cases: this is to separate use cases (like summarization, question
answering, evaluation, etc) from the modules, and provide a different
entry point to the code base.
There is also a full reference section, as well as extra resources
(glossary, gallery, etc)
Co-authored-by: Shreya Rajpal <ShreyaR@users.noreply.github.com>
2023-01-02 16:24:09 +00:00
"execution_count": 1,
2022-12-07 05:57:50 +00:00
"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",
2022-12-07 06:55:27 +00:00
"```\u001b[0m['```bash', 'echo \"Hello World\"', '```']\n",
"\n",
"Answer: \u001b[33;1m\u001b[1;3mHello World\n",
"\u001b[0m\n",
2023-01-14 15:22:52 +00:00
"\u001b[1m> Finished chain.\u001b[0m\n"
2022-12-07 05:57:50 +00:00
]
},
{
"data": {
"text/plain": [
2022-12-07 06:55:27 +00:00
"'Hello World\\n'"
2022-12-07 05:57:50 +00:00
]
},
Docs refactor (#480)
Big docs refactor! Motivation is to make it easier for people to find
resources they are looking for. To accomplish this, there are now three
main sections:
- Getting Started: steps for getting started, walking through most core
functionality
- Modules: these are different modules of functionality that langchain
provides. Each part here has a "getting started", "how to", "key
concepts" and "reference" section (except in a few select cases where it
didnt easily fit).
- Use Cases: this is to separate use cases (like summarization, question
answering, evaluation, etc) from the modules, and provide a different
entry point to the code base.
There is also a full reference section, as well as extra resources
(glossary, gallery, etc)
Co-authored-by: Shreya Rajpal <ShreyaR@users.noreply.github.com>
2023-01-02 16:24:09 +00:00
"execution_count": 1,
2022-12-07 05:57:50 +00:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
2022-12-07 06:55:27 +00:00
"from langchain.chains import LLMBashChain\n",
2022-12-07 05:57:50 +00:00
"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(llm=llm, verbose=True)\n",
"\n",
"bash_chain.run(text)"
]
},
2023-01-14 15:22:52 +00:00
{
"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"
]
},
2022-12-07 05:57:50 +00:00
{
"cell_type": "code",
2023-01-14 15:22:52 +00:00
"execution_count": 28,
2022-12-07 05:57:50 +00:00
"metadata": {},
"outputs": [],
2023-01-14 15:22:52 +00:00
"source": [
"from langchain.prompts.prompt import PromptTemplate\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(input_variables=[\"question\"], template=_PROMPT_TEMPLATE)"
]
},
{
"cell_type": "code",
"execution_count": 29,
"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['```bash', 'printf \"Hello World\\\\n\"', '```']\n",
"\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": 29,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"bash_chain = LLMBashChain(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)"
]
2022-12-07 05:57:50 +00:00
}
],
"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",
2023-01-14 15:22:52 +00:00
"version": "3.10.6"
2022-12-07 05:57:50 +00:00
}
},
"nbformat": 4,
"nbformat_minor": 4
2022-12-07 06:55:27 +00:00
}