Agen ReAct

Saatnya mencoba membuat agen ReAct Anda sendiri! Ingat bahwa ReAct adalah singkatan dari Reason and Act, yang menggambarkan cara agen mengambil keputusan. Dalam latihan ini, Anda akan memuat tool bawaan wikipedia untuk mengintegrasikan data eksternal dari Wikipedia dengan LLM Anda. Sebuah llm telah disediakan untuk Anda yang menggunakan model gpt-4o-mini dari OpenAI.

Catatan: Tool wikipedia memerlukan pustaka Python wikipedia yang diinstal sebagai dependensi, dan hal tersebut telah dilakukan untuk Anda dalam kasus ini.

Latihan ini adalah bagian dari kursus

Mengembangkan Aplikasi LLM dengan LangChain

Petunjuk latihan

Muat tool "wikipedia" menggunakan fungsi load_tools().
Definisikan agen ReAct menggunakan create_react_agent(), dengan meneruskan llm dan daftar tool yang akan digunakan.
Jalankan agen pada masukan yang disediakan dan cetak konten dari pesan terakhir dalam response.

Latihan interaktif praktis

Cobalah latihan ini dengan menyelesaikan kode contoh berikut.

# Define the tools
tools = load_tools(["____"])

# Define the agent
agent = create_react_agent(____, ____)

# Invoke the agent
response = agent.____({"messages": [("human", "How many people live in New York City?")]})
print(response['messages'][-1].____)

Edit dan Jalankan Kode

Latihan ini adalah bagian dari kursus

Mengembangkan Aplikasi LLM dengan LangChain

SkillTag.level.intermediateSkillTag.label

4.8+

Mulai Kursus 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: Rantai berurutan Exercise 2: Menyusun prompt untuk sequential chains Exercise 3: Sequential chain dengan LCEL Exercise 4: Pengantar agent LangChain Exercise 5: Apa itu agent?Exercise 6: Agen ReAct

Latihan Saat Ini

Exercise 7: Alat kustom untuk agen Exercise 8: Mendefinisikan fungsi untuk penggunaan tool Exercise 9: Membuat tool kustom Exercise 10: Mengintegrasikan alat kustom dengan agent

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!