Divisione ricorsiva per carattere

Molti sviluppatori usano uno splitter ricorsivo per caratteri per dividere i documenti in base a un elenco specifico di caratteri. Per impostazione predefinita, questi caratteri sono paragrafi, a capo, spazi e stringhe vuote: ["\n\n", "\n", " ", ""].

In pratica, lo splitter prova prima a dividere per paragrafi, verifica se i valori di chunk_size e chunk_overlap sono rispettati e, in caso contrario, divide per frasi, poi parole e infine singoli caratteri.

Spesso dovrai sperimentare con diversi valori di chunk_size e chunk_overlap per trovare quelli che funzionano meglio per i tuoi documenti.

Questo esercizio fa parte del corso

Sviluppare applicazioni LLM con LangChain

Visualizza il corso

Istruzioni dell'esercizio

Importa la classe RecursiveCharacterTextSplitter da langchain_text_splitters.
Crea un'istanza di RecursiveCharacterTextSplitter con separators=["\n", " ", ""], chunk_size=24 e chunk_overlap=10.
Usa il metodo .split_text() per dividere quote e stampa i chunk e le rispettive lunghezze.

Esercizio pratico interattivo

Prova a risolvere questo esercizio completando il codice di esempio.

# Import the recursive character splitter
from langchain_text_splitters import ____

quote = 'Words are flowing out like endless rain into a paper cup,\nthey slither while they pass,\nthey slip away across the universe.'
chunk_size = 24
chunk_overlap = 10

# Create an instance of the splitter class
splitter = RecursiveCharacterTextSplitter(
    separators=____,
    chunk_size=____,
    chunk_overlap=____)

# Split the document and print the chunks
docs = splitter.____(quote)
print(docs)
print([len(doc) for doc in docs])

Modifica ed esegui il codice

Questo esercizio fa parte del corso

Sviluppare applicazioni LLM con LangChain

IntermediárioNível de habilidade

4.8+

Inizia il corso gratis

Welcome to the LangChain framework for building applications on LLMs! You'll learn about the main components of LangChain, including models, chains, agents, prompts, and parsers. You'll create chatbots using both open-source models from Hugging Face and proprietary models from OpenAI, create prompt templates, and integrate different chatbot memory strategies to manage context and resources during conversations.

Exercise 1: The LangChain ecosystem Exercise 2: OpenAI models in LangChain!Exercise 3: Hugging Face models in LangChain!Exercise 4: Prompt templates Exercise 5: Prompt templates and chaining Exercise 6: Chat prompt templates Exercise 7: Few-shot prompting Exercise 8: Creating the few-shot example set Exercise 9: Building the few-shot prompt template Exercise 10: Implementing few-shot prompting

Time to level up your LangChain chains! You'll learn to use the LangChain Expression Language (LCEL) for defining chains with greater flexibility. You'll create sequential chains, where inputs are passed between components to create more advanced applications. You'll also begin to integrate agents, which use LLMs for decision-making.

Exercise 1: Sequential chains Exercise 2: Building prompts for sequential chains Exercise 3: Sequential chains with LCEL Exercise 4: Introduction to LangChain agents Exercise 5: What's an agent?Exercise 6: ReAct agents Exercise 7: Custom tools for agents Exercise 8: Defining a function for tool use Exercise 9: Creating custom tools Exercise 10: Integrating custom tools with agents

One limitation of LLMs is that they have a knowledge cut-off due to being trained on data up to a certain point. In this chapter, you'll learn to create applications that use Retrieval Augmented Generation (RAG) to integrate external data with LLMs. The RAG workflow contains a few different processes, including splitting data, creating and storing the embeddings using a vector database, and retrieving the most relevant information for use in the application. You'll learn to master the entire workflow!

Exercise 1: Integrazione di caricatori di documenti Exercise 2: PDF caricatori di documenti Exercise 3: CSV caricatori di documenti Exercise 4: HTML caricatori di documenti Exercise 5: Suddivisione dei dati esterni per il recupero Exercise 6: Suddivisione per carattere Exercise 7: Divisione ricorsiva per carattere

Esercizio in corso

Exercise 8: Suddividere HTML Exercise 9: RAG archiviazione e recupero con database vettoriali Exercise 10: Preparazione dei documenti e del database vettoriale Exercise 11: Creare un prompt template per il retrieval Exercise 12: Creare una chain RAG Exercise 13: Conclusione!