mirror of
https://github.com/hwchase17/langchain
synced 2024-10-31 15:20:26 +00:00
138 lines
3.7 KiB
Plaintext
138 lines
3.7 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"# OpenLM\n",
|
|
"[OpenLM](https://github.com/r2d4/openlm) is a zero-dependency OpenAI-compatible LLM provider that can call different inference endpoints directly via HTTP. \n",
|
|
"\n",
|
|
"\n",
|
|
"It implements the OpenAI Completion class so that it can be used as a drop-in replacement for the OpenAI API. This changeset utilizes BaseOpenAI for minimal added code.\n",
|
|
"\n",
|
|
"This examples goes over how to use LangChain to interact with both OpenAI and HuggingFace. You'll need API keys from both."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"### Setup\n",
|
|
"Install dependencies and set API keys."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 1,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Uncomment to install openlm and openai if you haven't already\n",
|
|
"\n",
|
|
"# !pip install openlm\n",
|
|
"# !pip install openai"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from getpass import getpass\n",
|
|
"import os\n",
|
|
"import subprocess\n",
|
|
"\n",
|
|
"\n",
|
|
"# Check if OPENAI_API_KEY environment variable is set\n",
|
|
"if \"OPENAI_API_KEY\" not in os.environ:\n",
|
|
" print(\"Enter your OpenAI API key:\")\n",
|
|
" os.environ[\"OPENAI_API_KEY\"] = getpass()\n",
|
|
"\n",
|
|
"# Check if HF_API_TOKEN environment variable is set\n",
|
|
"if \"HF_API_TOKEN\" not in os.environ:\n",
|
|
" print(\"Enter your HuggingFace Hub API key:\")\n",
|
|
" os.environ[\"HF_API_TOKEN\"] = getpass()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"### Using LangChain with OpenLM\n",
|
|
"\n",
|
|
"Here we're going to call two models in an LLMChain, `text-davinci-003` from OpenAI and `gpt2` on HuggingFace."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from langchain.llms import OpenLM\n",
|
|
"from langchain import PromptTemplate, LLMChain"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 5,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Model: text-davinci-003\n",
|
|
"Result: France is a country in Europe. The capital of France is Paris.\n",
|
|
"Model: huggingface.co/gpt2\n",
|
|
"Result: Question: What is the capital of France?\n",
|
|
"\n",
|
|
"Answer: Let's think step by step. I am not going to lie, this is a complicated issue, and I don't see any solutions to all this, but it is still far more\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"question = \"What is the capital of France?\"\n",
|
|
"template = \"\"\"Question: {question}\n",
|
|
"\n",
|
|
"Answer: Let's think step by step.\"\"\"\n",
|
|
"\n",
|
|
"prompt = PromptTemplate(template=template, input_variables=[\"question\"])\n",
|
|
"\n",
|
|
"for model in [\"text-davinci-003\", \"huggingface.co/gpt2\"]:\n",
|
|
" llm = OpenLM(model=model)\n",
|
|
" llm_chain = LLMChain(prompt=prompt, llm=llm)\n",
|
|
" result = llm_chain.run(question)\n",
|
|
" print(\n",
|
|
" \"\"\"Model: {}\n",
|
|
"Result: {}\"\"\".format(\n",
|
|
" model, result\n",
|
|
" )\n",
|
|
" )"
|
|
]
|
|
}
|
|
],
|
|
"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": "3.11.3"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 2
|
|
}
|