langchain/docs/modules/models/llms/integrations/replicate.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Replicate\n",
    "This example goes over how to use LangChain to interact with Replicate models"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "from langchain.llms import Replicate\n",
    "from langchain import PromptTemplate, LLMChain\n",
    "\n",
    "os.environ[\"REPLICATE_API_TOKEN\"] = \"YOUR REPLICATE API TOKEN\""
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Setup"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "To run this notebook, you'll need to create a [replicate](https://replicate.com) account and install the [replicate python client](https://github.com/replicate/replicate-python)."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Calling a model\n",
    "\n",
    "Find a model on the [replicate explore page](https://replicate.com/explore), and then paste in the model name and version in this format: model_name/version\n",
    "\n",
    "For example, for this [flan-t5 model]( https://replicate.com/daanelson/flan-t5), click on the API tab. The model name/version would be: `daanelson/flan-t5:04e422a9b85baed86a4f24981d7f9953e20c5fd82f6103b74ebc431588e1cec8`\n",
    "\n",
    "Only the `model` param is required, but we can add other model params when initializing.\n",
    "\n",
    "For example, if we were running stable diffusion and wanted to change the image dimensions:\n",
    "\n",
    "```\n",
    "Replicate(model=\"stability-ai/stable-diffusion:db21e45d3f7023abc2a46ee38a23973f6dce16bb082a930b0c49861f96d1e5bf\", input={'image_dimensions': '512x512'})\n",
    "```\n",
    "                       \n",
    "*Note that only the first output of a model will be returned.*"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "llm = Replicate(model=\"daanelson/flan-t5:04e422a9b85baed86a4f24981d7f9953e20c5fd82f6103b74ebc431588e1cec8\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'The legal driving age of dogs is 2. Cars are designed for humans to drive. Therefore, the final answer is yes.'"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "prompt = \"\"\"\n",
    "Answer the following yes/no question by reasoning step by step. \n",
    "Can a dog drive a car?\n",
    "\"\"\"\n",
    "llm(prompt)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We can call any replicate model using this syntax. For example, we can call stable diffusion."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "text2image = Replicate(model=\"stability-ai/stable-diffusion:db21e45d3f7023abc2a46ee38a23973f6dce16bb082a930b0c49861f96d1e5bf\", \n",
    "                       input={'image_dimensions': '512x512'})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'https://replicate.delivery/pbxt/Cf07B1zqzFQLOSBQcKG7m9beE74wf7kuip5W9VxHJFembefKE/out-0.png'"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "image_output = text2image(\"A cat riding a motorcycle by Picasso\")\n",
    "image_output"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The model spits out a URL. Let's render it."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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
      "text/plain": [
       "<PIL.PngImagePlugin.PngImageFile image mode=RGB size=512x512 at 0x12394BB20>"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from PIL import Image\n",
    "import requests\n",
    "from io import BytesIO\n",
    "\n",
    "response = requests.get(image_output)\n",
    "img = Image.open(BytesIO(response.content))\n",
    "\n",
    "img"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Chaining Calls\n",
    "The whole point of langchain is to... chain! Here's an example of how do that."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.chains import SimpleSequentialChain"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "First, let's define the LLM for this model as a flan-5, and text2image as a stable diffusion model."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "llm = Replicate(model=\"daanelson/flan-t5:04e422a9b85baed86a4f24981d7f9953e20c5fd82f6103b74ebc431588e1cec8\")\n",
    "text2image = Replicate(model=\"stability-ai/stable-diffusion:db21e45d3f7023abc2a46ee38a23973f6dce16bb082a930b0c49861f96d1e5bf\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "First prompt in the chain"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "prompt = PromptTemplate(\n",
    "    input_variables=[\"product\"],\n",
    "    template=\"What is a good name for a company that makes {product}?\",\n",
    ")\n",
    "\n",
    "chain = LLMChain(llm=llm, prompt=prompt)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Second prompt to get the logo for company description"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [],
   "source": [
    "second_prompt = PromptTemplate(\n",
    "    input_variables=[\"company_name\"],\n",
    "    template=\"Write a description of a logo for this company: {company_name}\",\n",
    ")\n",
    "chain_two = LLMChain(llm=llm, prompt=second_prompt)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Third prompt, let's create the image based on the description output from prompt 2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [],
   "source": [
    "third_prompt = PromptTemplate(\n",
    "    input_variables=[\"company_logo_description\"],\n",
    "    template=\"{company_logo_description}\",\n",
    ")\n",
    "chain_three = LLMChain(llm=text2image, prompt=third_prompt)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now let's run it!"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new SimpleSequentialChain chain...\u001b[0m\n",
      "\u001b[36;1m\u001b[1;3mnovelty socks\u001b[0m\n",
      "\u001b[33;1m\u001b[1;3mtodd & co.\u001b[0m\n",
      "\u001b[38;5;200m\u001b[1;3mhttps://replicate.delivery/pbxt/BedAP1PPBwXFfkmeD7xDygXO4BcvApp1uvWOwUdHM4tcQfvCB/out-0.png\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n",
      "https://replicate.delivery/pbxt/BedAP1PPBwXFfkmeD7xDygXO4BcvApp1uvWOwUdHM4tcQfvCB/out-0.png\n"
     ]
    }
   ],
   "source": [
    "# Run the chain specifying only the input variable for the first chain.\n",
    "overall_chain = SimpleSequentialChain(chains=[chain, chain_two, chain_three], verbose=True)\n",
    "catchphrase = overall_chain.run(\"colorful socks\")\n",
    "print(catchphrase)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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
      "text/plain": [
       "<PIL.PngImagePlugin.PngImageFile image mode=RGB size=768x768 at 0x11EFD83A0>"
      ]
     },
     "execution_count": 70,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "response = requests.get(\"https://replicate.delivery/pbxt/eq6foRJngThCAEBqse3nL3Km2MBfLnWQNd0Hy2SQRo2LuprCB/out-0.png\")\n",
    "img = Image.open(BytesIO(response.content))\n",
    "img"
   ]
  },
  {
   "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": "3.9.1"
  },
  "vscode": {
   "interpreter": {
    "hash": "a0a0263b650d907a3bfe41c0f8d6a63a071b884df3cfdc1579f00cdc1aed6b03"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}