mirror of
https://github.com/hwchase17/langchain.git
synced 2025-04-30 12:55:25 +00:00
985496f4be
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>
88 lines
1.9 KiB
Plaintext
88 lines
1.9 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"# BashChain\n",
|
|
"This notebook showcases using LLMs and a bash process to do 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['```bash', 'echo \"Hello World\"', '```']\n",
|
|
"\n",
|
|
"Answer: \u001b[33;1m\u001b[1;3mHello World\n",
|
|
"\u001b[0m\n",
|
|
"\u001b[1m> Finished LLMBashChain chain.\u001b[0m\n"
|
|
]
|
|
},
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"'Hello World\\n'"
|
|
]
|
|
},
|
|
"execution_count": 1,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"from langchain.chains 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(llm=llm, verbose=True)\n",
|
|
"\n",
|
|
"bash_chain.run(text)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"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": "3.10.9"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 4
|
|
}
|