ReAct agents

Time to have a go at creating your own ReAct agent! Recall that ReAct stands for Reason and Act, which describes how they make decisions. In this exercise, you'll load the built-in wikipedia tool to integrate external data from Wikipedia with your LLM. An llm has already been defined for you that uses OpenAI's gpt-4o-mini model

Note: The wikipedia tool requires the wikipedia Python library to be installed as a dependency, which has been done for you in this case.

Questo esercizio fa parte del corso

Developing LLM Applications with LangChain

Visualizza il corso

Istruzioni dell'esercizio

Load the "wikipedia" tool using the load_tools() function.
Define a ReAct agent using create_react_agent(), passing it the llm and tools to use.
Run the agent on the input provided and print the content from the final message in response.

Esercizio pratico interattivo

Prova a risolvere questo esercizio completando il codice di esempio.

# 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].____)

Modifica ed esegui il codice

Questo esercizio fa parte del corso

Developing LLM Applications with 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

Esercizio in corso

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!