mirror of
				https://github.com/hwchase17/langchain.git
				synced 2025-10-30 23:29:54 +00:00 
			
		
		
		
	
		
			
				
	
	
		
			103 lines
		
	
	
		
			2.7 KiB
		
	
	
	
		
			Plaintext
		
	
	
	
	
	
			
		
		
	
	
			103 lines
		
	
	
		
			2.7 KiB
		
	
	
	
		
			Plaintext
		
	
	
	
	
	
| {
 | |
|  "cells": [
 | |
|   {
 | |
|    "cell_type": "markdown",
 | |
|    "id": "13dc0983",
 | |
|    "metadata": {},
 | |
|    "source": [
 | |
|     "# Hugging Face Length Function\n",
 | |
|     "Most LLMs are constrained by the number of tokens that you can pass in, which is not the same as the number of characters. In order to get a more accurate estimate, we can use Hugging Face tokenizers to count the text length.\n",
 | |
|     "\n",
 | |
|     "1. How the text is split: by character passed in\n",
 | |
|     "2. How the chunk size is measured: by Hugging Face tokenizer"
 | |
|    ]
 | |
|   },
 | |
|   {
 | |
|    "cell_type": "code",
 | |
|    "execution_count": 1,
 | |
|    "id": "a8ce51d5",
 | |
|    "metadata": {},
 | |
|    "outputs": [],
 | |
|    "source": [
 | |
|     "from transformers import GPT2TokenizerFast\n",
 | |
|     "\n",
 | |
|     "tokenizer = GPT2TokenizerFast.from_pretrained(\"gpt2\")"
 | |
|    ]
 | |
|   },
 | |
|   {
 | |
|    "cell_type": "code",
 | |
|    "execution_count": 2,
 | |
|    "id": "388369ed",
 | |
|    "metadata": {},
 | |
|    "outputs": [],
 | |
|    "source": [
 | |
|     "# This is a long document we can split up.\n",
 | |
|     "with open('../../../state_of_the_union.txt') as f:\n",
 | |
|     "    state_of_the_union = f.read()\n",
 | |
|     "from langchain.text_splitter import CharacterTextSplitter"
 | |
|    ]
 | |
|   },
 | |
|   {
 | |
|    "cell_type": "code",
 | |
|    "execution_count": 3,
 | |
|    "id": "ca5e72c0",
 | |
|    "metadata": {},
 | |
|    "outputs": [],
 | |
|    "source": [
 | |
|     "text_splitter = CharacterTextSplitter.from_huggingface_tokenizer(tokenizer, chunk_size=100, chunk_overlap=0)\n",
 | |
|     "texts = text_splitter.split_text(state_of_the_union)"
 | |
|    ]
 | |
|   },
 | |
|   {
 | |
|    "cell_type": "code",
 | |
|    "execution_count": 4,
 | |
|    "id": "37cdfbeb",
 | |
|    "metadata": {},
 | |
|    "outputs": [
 | |
|     {
 | |
|      "name": "stdout",
 | |
|      "output_type": "stream",
 | |
|      "text": [
 | |
|       "Madam Speaker, Madam Vice President, our First Lady and Second Gentleman. Members of Congress and the Cabinet. Justices of the Supreme Court. My fellow Americans.  \n",
 | |
|       "\n",
 | |
|       "Last year COVID-19 kept us apart. This year we are finally together again. \n",
 | |
|       "\n",
 | |
|       "Tonight, we meet as Democrats Republicans and Independents. But most importantly as Americans. \n",
 | |
|       "\n",
 | |
|       "With a duty to one another to the American people to the Constitution.\n"
 | |
|      ]
 | |
|     }
 | |
|    ],
 | |
|    "source": [
 | |
|     "print(texts[0])"
 | |
|    ]
 | |
|   }
 | |
|  ],
 | |
|  "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": "aee8b7b246df8f9039afb4144a1f6fd8d2ca17a180786b69acc140d282b71a49"
 | |
|    }
 | |
|   }
 | |
|  },
 | |
|  "nbformat": 4,
 | |
|  "nbformat_minor": 5
 | |
| }
 |