In previous articles, we have been using the <span>app.invoke(inputs)</span> method to execute workflows. The invoke method returns the final execution result of the entire stream to the caller all at once. If the workflow execution time is long, the waiting time for users will also be long, leading to a poor experience. Currently, mainstream large … Read more
Embedding images and text in the same space allows us to perform high-precision searches on multimodal content such as web pages, PDFs, magazines, books, brochures, and various papers. Why is this technology so interesting? The most exciting aspect of embedding text and images in the same space is that you can search for and retrieve … Read more
How to Define the Input and Output Schema of a Graph By default, the StateGraph operates using a single schema, and all nodes should communicate using that schema. However, different input and output schemas can also be defined for the graph. When different schemas are specified, the internal schema will still be used for communication … Read more
In this tutorial, we will delve into how to build an intelligent Q&A system with conditional branching using the langgraph framework. We will analyze the code step by step, understand the functionality of each part, and explain the principles behind it. The ultimate goal is to enable you to create an AI assistant that can … Read more
LangGraph provides a hands-on approach to how humans can interact with agents. `LangGraph` is a library for building stateful, multi-participant applications using `LLM`, designed for creating agent and multi-agent workflows. Compared to other `LLM` frameworks, it has the following core advantages: loops, controllability, and persistence. `LangGraph` allows you to define processes that involve loops, which … Read more
Introduction With a single line of Cursor, develop a LangGraph program that can interact with any database, regardless of its structure! Preparation Download a copy of the LangGraph code, remember the location, and update to .cursorrules Prepare a .cursorrules file to store the following content Download the DB file and reference file main.py I provided, … Read more
Introduction In the field of artificial intelligence, Retrieval-Augmented Generation (RAG) systems have become common tools for handling simple queries and generating contextually relevant responses. However, with the growing demand for more complex AI applications, we need to go beyond these retrieval-capable systems. Thus, AI agents have emerged—these autonomous entities can perform complex multi-step tasks while … Read more
In this tutorial, we will learn how to build an intelligent document retrieval system using langgraph. This system can extract information from web pages, perform intelligent segmentation, and achieve precise Q&A functionality through query analysis and vector retrieval. 1. Install Dependencies <span>pip install beautifulsoup4</span> 2. Import Necessary Libraries import bs4 from typing import Literal from … Read more
The human-computer interaction feature allows us to involve the user in the decision-making process of the graph. The following guide demonstrates how to implement human-computer interaction workflows in the graph. The human-computer interaction workflow integrates user input into automated processes, allowing for decision-making, validation, or correction at critical stages. This is particularly useful in applications … Read more
In this blog, we will delve into how to build an intelligent SQL query assistant using LangChain and LangGraph. This assistant can convert natural language questions into SQL queries, execute the queries, and provide human-friendly answers. More importantly, it supports human-machine collaborative workflows, allowing users to intervene at critical steps. 0. Initialize SQL Data We … Read more