langchain/docs/docs/integrations/chat/litellm_router.ipynb

{
 "cells": [
  {
   "cell_type": "raw",
   "id": "59148044",
   "metadata": {},
   "source": [
    "---\n",
    "sidebar_label: LiteLLM Router\n",
    "---"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "247da7a6",
   "metadata": {},
   "source": []
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "id": "bf733a38-db84-4363-89e2-de6735c37230",
   "metadata": {},
   "source": [
    "# ChatLiteLLMRouter\n",
    "\n",
    "[LiteLLM](https://github.com/BerriAI/litellm) is a library that simplifies calling Anthropic, Azure, Huggingface, Replicate, etc. \n",
    "\n",
    "This notebook covers how to get started with using Langchain + the LiteLLM Router I/O library. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "d4a7c55d-b235-4ca4-a579-c90cc9570da9",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "from langchain_community.chat_models import ChatLiteLLMRouter\n",
    "from langchain_core.messages import HumanMessage\n",
    "from litellm import Router"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "70cf04e8-423a-4ff6-8b09-f11fb711c817",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "model_list = [\n",
    "    {\n",
    "        \"model_name\": \"gpt-4\",\n",
    "        \"litellm_params\": {\n",
    "            \"model\": \"azure/gpt-4-1106-preview\",\n",
    "            \"api_key\": \"<your-api-key>\",\n",
    "            \"api_version\": \"2023-05-15\",\n",
    "            \"api_base\": \"https://<your-endpoint>.openai.azure.com/\",\n",
    "        },\n",
    "    },\n",
    "    {\n",
    "        \"model_name\": \"gpt-4\",\n",
    "        \"litellm_params\": {\n",
    "            \"model\": \"azure/gpt-4-1106-preview\",\n",
    "            \"api_key\": \"<your-api-key>\",\n",
    "            \"api_version\": \"2023-05-15\",\n",
    "            \"api_base\": \"https://<your-endpoint>.openai.azure.com/\",\n",
    "        },\n",
    "    },\n",
    "]\n",
    "litellm_router = Router(model_list=model_list)\n",
    "chat = ChatLiteLLMRouter(router=litellm_router)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "8199ef8f-eb8b-4253-9ea0-6c24a013ca4c",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "AIMessage(content=\"J'aime programmer.\")"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "messages = [\n",
    "    HumanMessage(\n",
    "        content=\"Translate this sentence from English to French. I love programming.\"\n",
    "    )\n",
    "]\n",
    "chat(messages)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "id": "c361ab1e-8c0c-4206-9e3c-9d1424a12b9c",
   "metadata": {},
   "source": [
    "## `ChatLiteLLMRouter` also supports async and streaming functionality:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "93a21c5c-6ef9-4688-be60-b2e1f94842fb",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "from langchain.callbacks.manager import CallbackManager\n",
    "from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "c5fac0e9-05a4-4fc1-a3b3-e5bbb24b971b",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "LLMResult(generations=[[ChatGeneration(text=\"J'adore programmer.\", generation_info={'finish_reason': 'stop'}, message=AIMessage(content=\"J'adore programmer.\"))]], llm_output={'token_usage': {'completion_tokens': 6, 'prompt_tokens': 19, 'total_tokens': 25}, 'model_name': None}, run=[RunInfo(run_id=UUID('75003ec9-1e2b-43b7-a216-10dcc0f75e00'))])"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "await chat.agenerate([messages])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "025be980-e50d-4a68-93dc-c9c7b500ce34",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "J'adore programmer."
     ]
    },
    {
     "data": {
      "text/plain": [
       "AIMessage(content=\"J'adore programmer.\")"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "chat = ChatLiteLLMRouter(\n",
    "    router=litellm_router,\n",
    "    streaming=True,\n",
    "    verbose=True,\n",
    "    callback_manager=CallbackManager([StreamingStdOutCallbackHandler()]),\n",
    ")\n",
    "chat(messages)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "c253883f",
   "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": "3.9.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}