{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Huggingface TextGen Inference\n",
    "\n",
    "[Text Generation Inference](https://github.com/huggingface/text-generation-inference) is a Rust, Python and gRPC server for text generation inference. Used in production at [HuggingFace](https://huggingface.co/) to power LLMs api-inference widgets.\n",
    "\n",
    "This notebooks goes over how to use a self hosted LLM using `Text Generation Inference`."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "To use, you should have the `text_generation` python package installed."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "# !pip3 install text_generation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.llms import HuggingFaceTextGenInference\n",
    "\n",
    "llm = HuggingFaceTextGenInference(\n",
    "    inference_server_url=\"http://localhost:8010/\",\n",
    "    max_new_tokens=512,\n",
    "    top_k=10,\n",
    "    top_p=0.95,\n",
    "    typical_p=0.95,\n",
    "    temperature=0.01,\n",
    "    repetition_penalty=1.03,\n",
    ")\n",
    "llm(\"What did foo say about bar?\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Streaming"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.llms import HuggingFaceTextGenInference\n",
    "from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler\n",
    "\n",
    "\n",
    "llm = HuggingFaceTextGenInference(\n",
    "    inference_server_url=\"http://localhost:8010/\",\n",
    "    max_new_tokens=512,\n",
    "    top_k=10,\n",
    "    top_p=0.95,\n",
    "    typical_p=0.95,\n",
    "    temperature=0.01,\n",
    "    repetition_penalty=1.03,\n",
    "    streaming=True\n",
    ")\n",
    "llm(\"What did foo say about bar?\", callbacks=[StreamingStdOutCallbackHandler()])"
   ]
  }
 ],
 "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": "3.11.3"
  },
  "vscode": {
   "interpreter": {
    "hash": "31f2aee4e71d21fbe5cf8b01ff0e069b9275f58929596ceb00d14d90e3e16cd6"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}