langchain/docs/docs/integrations/llms/yandex.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# YandexGPT\n",
    "\n",
    "This notebook goes over how to use Langchain with [YandexGPT](https://cloud.yandex.com/en/services/yandexgpt).\n",
    "\n",
    "To use, you should have the `yandexcloud` python package installed."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "%pip install yandexcloud"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "First, you should [create service account](https://cloud.yandex.com/en/docs/iam/operations/sa/create) with the `ai.languageModels.user` role.\n",
    "\n",
    "Next, you have two authentication options:\n",
    "- [IAM token](https://cloud.yandex.com/en/docs/iam/operations/iam-token/create-for-sa).\n",
    "    You can specify the token in a constructor parameter `iam_token` or in an environment variable `YC_IAM_TOKEN`.\n",
    "- [API key](https://cloud.yandex.com/en/docs/iam/operations/api-key/create)\n",
    "    You can specify the key in a constructor parameter `api_key` or in an environment variable `YC_API_KEY`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 246,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.chains import LLMChain\n",
    "from langchain.llms import YandexGPT\n",
    "from langchain.prompts import PromptTemplate"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 247,
   "metadata": {},
   "outputs": [],
   "source": [
    "template = \"What is the capital of {country}?\"\n",
    "prompt = PromptTemplate(template=template, input_variables=[\"country\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 248,
   "metadata": {},
   "outputs": [],
   "source": [
    "llm = YandexGPT()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 249,
   "metadata": {},
   "outputs": [],
   "source": [
    "llm_chain = LLMChain(prompt=prompt, llm=llm)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 250,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'Moscow'"
      ]
     },
     "execution_count": 250,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "country = \"Russia\"\n",
    "\n",
    "llm_chain.run(country)"
   ]
  }
 ],
 "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": "3.9.18"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}