Fundamentos de los Agentes Inteligentes y LangChain
Introducción a LangChain
Agiliza procesos usando Agentes AI
Agentes inteligentes de LangChain
Instalación y configuración de LangChain
Quiz: Fundamentos de los Agentes Inteligentes y LangChain
Chat Models y Prompt templates
Chat Messages con OpenAI
Introducción a los modelos de chat
Output parsers
Prompt templates en LangChain
Tipos de ChatTemplates: Few-Shot Prompting
Quiz: Chat Models y Prompt templates
Cadenas en LangChain
Introducción a Chains y LCEL
Chat con historial
Integración de cadena: Runnable y OutputParser
Chat Memory
Implementación de memoria en cadenas
Quiz: Cadenas en LangChain
Carga de documentos en LangChain
Cargar HTML y Directorio con LangChain
Carga de PDF y CSV con LangChain
Text Splitters
Quiz: Carga de documentos en LangChain
Retrieval-augmented generation (RAG)
VectorStore: Chroma
Introducción a Embeddings
Vectorstore: Pinecone
Chatbot RAG: carga de documentos a Vectorstore
Chatbot RAG: prompt templates, cadenas y memoria
Quiz: Retrieval-augmented generation (RAG)
Agentes en LangChain
Construcción de agentes en LangChain
LangChain Tools
Construcción de agentes con memoria
Quiz: Agentes en LangChain
Ecosistema de LangChain
Ecosistema de LangChain
To complement the learning about the use of language models and advanced tools such as LangChain, it is important to reinforce some key concepts that will allow a better understanding of how these technologies work and how they are integrated into real applications. Here I leave you a summary with some additional points that help to broaden the understanding of the topic.
LangChain not only allows connecting large language models (LLM) such as GPT-2, but also offers a modular structure that facilitates the development of advanced applications. Some of the most important components are:
Hugging Face is one of the most popular platforms for accessing open source language models such as GPT-2. The language models available on Hugging Face are based on transformer architectures, a technique that revolutionized the field of natural language processing (NLP). It is important to remember some key details about transformers:
Once models are put into production, it is critical to have mechanisms in place to constantly evaluate and improve them. This is where LangChain can also be useful, as it offers functionality to monitor model performance, capture errors and improve interactions over time.
The class mentioned the example of a virtual agent that books flights. An interesting aspect to note is that these agents can go beyond simply executing commands. A truly autonomous agent could analyze multiple flight options, check the availability of nearby hotels, compare prices and offer the best option according to the user's preferences, all without direct human intervention.
This is just one example of the applications that autonomous agents can have, but the possibilities are almost endless, from customer service assistants to recommendation systems in streaming services.
Contributions 21
Questions 9
Want to see more contributions, questions and answers from the community?