Build a JavaScript AI Agent With LangGraph.js and MongoDB

preview_player
Показать описание


We'll cover the following:
⭐ Understanding what AI agents are and how they work.
⭐ Integrating MongoDB for storing conversation history and data retrieval, specifically leveraging MongoDB Atlas Vector Search for context-aware responses.

By the end of this video, you'll have built an AI agent capable of managing HR-related queries, looking up employee info from a database, and continuing conversations across multiple sessions. It's like creating your own J.A.R.V.I.S., but for practical, real-world applications!

What You'll Learn:
⭐ How to integrate MongoDB Atlas to store and retrieve data.
⭐ How to build an AI agent that can manage conversations, look up data, and persist state across sessions.

Prerequisites:
✔︎ Free MongoDB Atlas account
✔︎ OpenAI and Anthropic API keys

Clone the project repo and follow along as we create this powerful AI tool. Let’s get started!

⏱️ Timestamps ⏱️
00:00 - Intro
02:50 - Setting up the project
04:29 - Configure MongoDB
05:36 - Seeding the database
12:45 - MongoDB Atlas Vector Search Index
25:44 - Testing the AI agent

Рекомендации по теме
Комментарии
Автор

Awesome tutorial, easy to set up and follow along

bidokris
Автор

Would have been great if there was a front end app as well. Great tutorial. Thank you

jaggyjut
Автор

This is good stuff. Unfortunately, I am familiar with mongoose.js and not Zod. Can the same result be achieve with mongoose.js instead of Zod? If the answer is yes, any video tutorials?

WongYamPan
Автор

I remember watching Jesse’s videos in early 2020 when I was learning to code.

IkraamDev
Автор

@MongoDb, This video is really very helpful for me. Thank you so much for this tutorial. I am currently implementing something using LangGraph and MongoDB. I cloned the repository and ran it locally. In the Agents.ts file, I replaced Anthropic with OpenAI:
const model = new ChatOpenAI({
modelName: "gpt-4o-mini",
temperature: 0,
}).bindTools(tools);
I was able to start the server and ask queries. However, it's not invoking the employeeLookupTool, and I'm not sure what I'm missing. Please help.
Also, I have the knowledge base vectors in another collection. I wanted to create a new agent for the knowledge base and will try to implement it.

pubsub