Hugging Face-modellen in LangChain!

Er zijn duizenden modellen gratis te downloaden en te gebruiken op Hugging Face. Hugging Face integreert heel goed met LangChain via de partnerbibliotheek langchain-huggingface, die je hier kunt gebruiken.

In deze oefening laad en roep je het crumb/nano-mistral-model van Hugging Face aan. Dit is een ultralichte LLM die is ontworpen om te finetunen voor betere prestaties.

Deze oefening maakt deel uit van de cursus

LLM-toepassingen ontwikkelen met LangChain

Cursus bekijken

Oefeninstructies

Importeer HuggingFacePipeline uit langchain_huggingface om met Hugging Face-modellen te werken.
Definieer een tekstgeneratie-LLM door HuggingFacePipeline.from_model_id() aan te roepen.
Stel de parameter model_id in om te bepalen welk Hugging Face-model je wilt gebruiken.

Praktische interactieve oefening

Probeer deze oefening eens door deze voorbeeldcode in te vullen.

# Import the HuggingFacePipeline class for defining Hugging Face pipelines
from langchain_huggingface import ____

# Define the LLM from the Hugging Face model ID
llm = ____.from_model_id(
    ____="crumb/nano-mistral",
    task="text-generation",
    pipeline_kwargs={"max_new_tokens": 20}
)

prompt = "Hugging Face is"

# Invoke the model
response = llm.invoke(prompt)
print(response)

Code bewerken en uitvoeren

Deze oefening maakt deel uit van de cursus

LLM-toepassingen ontwikkelen met LangChain

SkillTag.level.intermediateSkillTag.label

4.8+

Begin de cursus 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: Het LangChain-ecosysteem Exercise 2: OpenAI-modellen in LangChain!Exercise 3: Hugging Face-modellen in LangChain!

Huidige oefening

Exercise 4: Prompt-templates Exercise 5: Prompttemplates en chaining Exercise 6: Chatprompt-sjablonen Exercise 7: Few-shot prompting Exercise 8: De few-shot-voorbeelden maken Exercise 9: Een few-shot prompttemplate bouwen Exercise 10: Few-shot prompting implementeren

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: Integrating document loaders Exercise 2: PDF document loaders Exercise 3: CSV document loaders Exercise 4: HTML document loaders Exercise 5: Splitting external data for retrieval Exercise 6: Splitting by character Exercise 7: Recursively splitting by character Exercise 8: Splitting HTML Exercise 9: RAG storage and retrieval using vector databases Exercise 10: Preparing the documents and vector database Exercise 11: Building a retrieval prompt template Exercise 12: Creating a RAG chain Exercise 13: Wrap-up!