langchain/docs/extras/integrations/llms/predibase.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Predibase\n",
    "\n",
    "[Predibase](https://predibase.com/) allows you to train, finetune, and deploy any ML model—from linear regression to large language model. \n",
    "\n",
    "This example demonstrates using Langchain with models deployed on Predibase"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Setup\n",
    "\n",
    "To run this notebook, you'll need a [Predibase account](https://predibase.com/free-trial/?utm_source=langchain) and an [API key](https://docs.predibase.com/sdk-guide/intro).\n",
    "\n",
    "You'll also need to install the Predibase Python package:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "!pip install predibase\n",
    "import os\n",
    "\n",
    "os.environ[\"PREDIBASE_API_TOKEN\"] = \"{PREDIBASE_API_TOKEN}\""
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Initial Call"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.llms import Predibase\n",
    "\n",
    "model = Predibase(\n",
    "    model=\"vicuna-13b\", predibase_api_key=os.environ.get(\"PREDIBASE_API_TOKEN\")\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "response = model(\"Can you recommend me a nice dry wine?\")\n",
    "print(response)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Chain Call Setup"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "llm = Predibase(\n",
    "    model=\"vicuna-13b\", predibase_api_key=os.environ.get(\"PREDIBASE_API_TOKEN\")\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "##  SequentialChain"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.chains import LLMChain\n",
    "from langchain.prompts import PromptTemplate"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# This is an LLMChain to write a synopsis given a title of a play.\n",
    "template = \"\"\"You are a playwright. Given the title of play, it is your job to write a synopsis for that title.\n",
    "\n",
    "Title: {title}\n",
    "Playwright: This is a synopsis for the above play:\"\"\"\n",
    "prompt_template = PromptTemplate(input_variables=[\"title\"], template=template)\n",
    "synopsis_chain = LLMChain(llm=llm, prompt=prompt_template)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# This is an LLMChain to write a review of a play given a synopsis.\n",
    "template = \"\"\"You are a play critic from the New York Times. Given the synopsis of play, it is your job to write a review for that play.\n",
    "\n",
    "Play Synopsis:\n",
    "{synopsis}\n",
    "Review from a New York Times play critic of the above play:\"\"\"\n",
    "prompt_template = PromptTemplate(input_variables=[\"synopsis\"], template=template)\n",
    "review_chain = LLMChain(llm=llm, prompt=prompt_template)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# This is the overall chain where we run these two chains in sequence.\n",
    "from langchain.chains import SimpleSequentialChain\n",
    "\n",
    "overall_chain = SimpleSequentialChain(\n",
    "    chains=[synopsis_chain, review_chain], verbose=True\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "review = overall_chain.run(\"Tragedy at sunset on the beach\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Fine-tuned LLM (Use your own fine-tuned LLM from Predibase)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.llms import Predibase\n",
    "\n",
    "model = Predibase(\n",
    "    model=\"my-finetuned-LLM\", predibase_api_key=os.environ.get(\"PREDIBASE_API_TOKEN\")\n",
    ")\n",
    "# replace my-finetuned-LLM with the name of your model in Predibase"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# response = model(\"Can you help categorize the following emails into positive, negative, and neutral?\")"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3.8.9 64-bit",
   "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": "3.8.9"
  },
  "orig_nbformat": 4,
  "vscode": {
   "interpreter": {
    "hash": "31f2aee4e71d21fbe5cf8b01ff0e069b9275f58929596ceb00d14d90e3e16cd6"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}