langchain/docs/modules/llms/async_llm.ipynb

161 lines
5.9 KiB
Plaintext
Raw Normal View History

{
"cells": [
{
"cell_type": "markdown",
"id": "f6574496-b360-4ffa-9523-7fd34a590164",
"metadata": {},
"source": [
"# Async API for LLM\n",
"\n",
"LangChain provides async support for LLMs by leveraging the [asyncio](https://docs.python.org/3/library/asyncio.html) library.\n",
"\n",
"Async support is particularly useful for calling multiple LLMs concurrently, as these calls are network-bound. Currently, only `OpenAI` `OpenAIChat`, and `PromptLayerOpenAI` are supported, but async support for other LLMs is on the roadmap.\n",
"\n",
"You can use the `agenerate` method to call an OpenAI LLM asynchronously."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "5e49e96c-0f88-466d-b3d3-ea0966bdf19e",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"As an AI language model, I don't have feelings like humans, but I'm functioning properly. How may I assist you?\n",
"\n",
"\n",
"I'm an AI language model, so I don't have emotions, but I'm functioning properly. How may I assist you today?\n",
"\n",
"\n",
"As an AI language model, I do not have emotions like humans, but I'm functioning normally. How can I assist you today?\n",
"\n",
"\n",
"I am an AI language model, so I do not have feelings, but I am here to assist you. How may I help you today?\n",
"\n",
"\n",
"As an AI language model, I do not have feelings or emotions but I'm always ready to assist you. How may I assist you today?\n",
"\n",
"\n",
"As an AI language model, I don't have feelings, but I'm functioning normally. How may I assist you today?\n",
"\n",
"\n",
"As an AI language model, I don't have feelings, but I'm functioning properly. Thank you. How may I assist you today?\n",
"\n",
"\n",
"As an AI language model, I don't have emotions, so I don't have a specific feeling or emotion. How can I assist you today?\n",
"\n",
"\n",
"As an AI language model, I do not have feelings or emotions. However, I am functioning as intended and ready to assist you with any queries you may have. How can I be of assistance today?\n",
"\n",
"\n",
"As an AI language model, I do not have feelings, but I am functioning well. Thank you for asking. How can I assist you today?\n",
"\u001b[1mConcurrent executed in 0.92 seconds.\u001b[0m\n",
"\n",
"\n",
"As an AI language model, I don't have feelings, but I'm functioning well. How can I assist you today?\n",
"\n",
"\n",
"As an AI language model, I don't have feelings, but I'm functioning well. Thank you for asking. How may I assist you today?\n",
"\n",
"\n",
"I'm an AI language model, so I don't have feelings, but I'm functioning well. How can I assist you today?\n",
"\n",
"\n",
"As an AI language model, I don't have feelings, but I'm functioning well. Thank you for asking. How may I assist you today?\n",
"\n",
"\n",
"As an AI language model, I don't have feelings, but I am functioning well. How can I assist you today?\n",
"\n",
"\n",
"As an AI language model, I don't have feelings but I'm functioning well. How can I assist you today?\n",
"\n",
"\n",
"As an AI language model, I do not have personal emotions. However, I am functioning well and ready to assist you with any queries or tasks you have. How may I assist you today?\n",
"\n",
"\n",
"As an AI language model, I do not have feelings or emotions, but I'm functioning well. How can I assist you today?\n",
"\n",
"\n",
"I am an AI language model and do not have feelings. But I am functioning properly and ready to assist you with any task. How may I help you today?\n",
"\n",
"\n",
"As an AI language model, I do not have emotions, but I am functioning well. How can I assist you today?\n",
"\u001b[1mSerial executed in 5.00 seconds.\u001b[0m\n"
]
}
],
"source": [
"import time\n",
"import asyncio\n",
"\n",
"from langchain.llms import OpenAIChat\n",
"\n",
"def generate_serially():\n",
" llm = OpenAIChat(temperature=0.9)\n",
" for _ in range(10):\n",
" resp = llm.generate([\"Hello, how are you?\"])\n",
" print(resp.generations[0][0].text)\n",
"\n",
"\n",
"async def async_generate(llm):\n",
" resp = await llm.agenerate([\"Hello, how are you?\"])\n",
" print(resp.generations[0][0].text)\n",
"\n",
"\n",
"async def generate_concurrently():\n",
" llm = OpenAIChat(temperature=0.9)\n",
" tasks = [async_generate(llm) for _ in range(10)]\n",
" await asyncio.gather(*tasks)\n",
"\n",
"\n",
"s = time.perf_counter()\n",
"# If running this outside of Jupyter, use asyncio.run(generate_concurrently())\n",
"await generate_concurrently() \n",
"elapsed = time.perf_counter() - s\n",
"print('\\033[1m' + f\"Concurrent executed in {elapsed:0.2f} seconds.\" + '\\033[0m')\n",
"\n",
"s = time.perf_counter()\n",
"generate_serially()\n",
"elapsed = time.perf_counter() - s\n",
"print('\\033[1m' + f\"Serial executed in {elapsed:0.2f} seconds.\" + '\\033[0m')"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "e1d3a966-3a27-44e8-9441-ed72f01b86f4",
"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": 5
}