langchain/docs/extras/integrations/text_embedding/gpt4all.ipynb

{
 "cells": [
  {
   "attachments": {},
   "cell_type": "markdown",
   "id": "d63d56c2",
   "metadata": {},
   "source": [
    "# GPT4All\n",
    "\n",
    "[GPT4All](https://gpt4all.io/index.html) is a free-to-use, locally running, privacy-aware chatbot. There is no GPU or internet required. It features popular models and its own models such as GPT4All Falcon, Wizard, etc.\n",
    "\n",
    "This notebook explains how to use [GPT4All embeddings](https://docs.gpt4all.io/gpt4all_python_embedding.html#gpt4all.gpt4all.Embed4All) with LangChain."
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "id": "46b7aa85",
   "metadata": {},
   "source": [
    "## Install GPT4All's Python Bindings"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "cdd68231",
   "metadata": {},
   "outputs": [],
   "source": [
    "%pip install gpt4all > /dev/null"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "id": "d80f4b92",
   "metadata": {},
   "source": [
    "Note: you may need to restart the kernel to use updated packages."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "08f267d6",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.embeddings import GPT4AllEmbeddings"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "0120e939",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|████████████████████████| 45.5M/45.5M [00:02<00:00, 18.5MiB/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model downloaded at:  /Users/rlm/.cache/gpt4all/ggml-all-MiniLM-L6-v2-f16.bin\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "objc[45711]: Class GGMLMetalClass is implemented in both /Users/rlm/anaconda3/envs/lcn2/lib/python3.9/site-packages/gpt4all/llmodel_DO_NOT_MODIFY/build/libreplit-mainline-metal.dylib (0x29fe18208) and /Users/rlm/anaconda3/envs/lcn2/lib/python3.9/site-packages/gpt4all/llmodel_DO_NOT_MODIFY/build/libllamamodel-mainline-metal.dylib (0x2a0244208). One of the two will be used. Which one is undefined.\n"
     ]
    }
   ],
   "source": [
    "gpt4all_embd = GPT4AllEmbeddings()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "53134a38",
   "metadata": {},
   "outputs": [],
   "source": [
    "text = \"This is a test document.\""
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "id": "eef36bde",
   "metadata": {},
   "source": [
    "## Embed the Textual Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "a55adf9f",
   "metadata": {},
   "outputs": [],
   "source": [
    "query_result = gpt4all_embd.embed_query(text)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "id": "12b24e69",
   "metadata": {},
   "source": [
    "With embed_documents you can embed multiple pieces of text. You can also map these embeddings with [Nomic's Atlas](https://docs.nomic.ai/index.html) to see a visual representation of your data."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "6ebd42d7",
   "metadata": {},
   "outputs": [],
   "source": [
    "doc_result = gpt4all_embd.embed_documents([text])"
   ]
  }
 ],
 "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": "3.9.16"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}