langchain/docs/extras/integrations/text_embedding/self-hosted.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "eec4efda",
   "metadata": {},
   "source": [
    "# Self Hosted\n",
    "Let's load the `SelfHostedEmbeddings`, `SelfHostedHuggingFaceEmbeddings`, and `SelfHostedHuggingFaceInstructEmbeddings` classes."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "d338722a",
   "metadata": {
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "from langchain.embeddings import (\n",
    "    SelfHostedEmbeddings,\n",
    "    SelfHostedHuggingFaceEmbeddings,\n",
    "    SelfHostedHuggingFaceInstructEmbeddings,\n",
    ")\n",
    "import runhouse as rh"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "146559e8",
   "metadata": {},
   "outputs": [],
   "source": [
    "# For an on-demand A100 with GCP, Azure, or Lambda\n",
    "gpu = rh.cluster(name=\"rh-a10x\", instance_type=\"A100:1\", use_spot=False)\n",
    "\n",
    "# For an on-demand A10G with AWS (no single A100s on AWS)\n",
    "# gpu = rh.cluster(name='rh-a10x', instance_type='g5.2xlarge', provider='aws')\n",
    "\n",
    "# For an existing cluster\n",
    "# gpu = rh.cluster(ips=['<ip of the cluster>'],\n",
    "#                  ssh_creds={'ssh_user': '...', 'ssh_private_key':'<path_to_key>'},\n",
    "#                  name='my-cluster')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "1230f7df",
   "metadata": {},
   "outputs": [],
   "source": [
    "embeddings = SelfHostedHuggingFaceEmbeddings(hardware=gpu)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "2684e928",
   "metadata": {},
   "outputs": [],
   "source": [
    "text = \"This is a test document.\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "1dc5e606",
   "metadata": {
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "query_result = embeddings.embed_query(text)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cef9cc54",
   "metadata": {},
   "source": [
    "And similarly for SelfHostedHuggingFaceInstructEmbeddings:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "81a17ca3",
   "metadata": {},
   "outputs": [],
   "source": [
    "embeddings = SelfHostedHuggingFaceInstructEmbeddings(hardware=gpu)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5a33d1c8",
   "metadata": {},
   "source": [
    "Now let's load an embedding model with a custom load function:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "c4af5679",
   "metadata": {},
   "outputs": [],
   "source": [
    "def get_pipeline():\n",
    "    from transformers import (\n",
    "        AutoModelForCausalLM,\n",
    "        AutoTokenizer,\n",
    "        pipeline,\n",
    "    )  # Must be inside the function in notebooks\n",
    "\n",
    "    model_id = \"facebook/bart-base\"\n",
    "    tokenizer = AutoTokenizer.from_pretrained(model_id)\n",
    "    model = AutoModelForCausalLM.from_pretrained(model_id)\n",
    "    return pipeline(\"feature-extraction\", model=model, tokenizer=tokenizer)\n",
    "\n",
    "\n",
    "def inference_fn(pipeline, prompt):\n",
    "    # Return last hidden state of the model\n",
    "    if isinstance(prompt, list):\n",
    "        return [emb[0][-1] for emb in pipeline(prompt)]\n",
    "    return pipeline(prompt)[0][-1]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "8654334b",
   "metadata": {},
   "outputs": [],
   "source": [
    "embeddings = SelfHostedEmbeddings(\n",
    "    model_load_fn=get_pipeline,\n",
    "    hardware=gpu,\n",
    "    model_reqs=[\"./\", \"torch\", \"transformers\"],\n",
    "    inference_fn=inference_fn,\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "fc1bfd0f",
   "metadata": {},
   "outputs": [],
   "source": [
    "query_result = embeddings.embed_query(text)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "aaad49f8",
   "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": "3.10.12"
  },
  "vscode": {
   "interpreter": {
    "hash": "7377c2ccc78bc62c2683122d48c8cd1fb85a53850a1b1fc29736ed39852c9885"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}