Videos
Leverage vector embeddings alongside operational data to build scalable semantic search experiences integrated within MongoDB Atlas.- Latest
- Highest Rated
Video
Navigating the Challenges of Building Centralized gen AI Tooling
The line between “super doable” and “super hard” isn’t always obvious when bringing AI to production. In the latest episode of our new People Who Ship series, Apoorva Joshi sits down with MongoDB’s John Ziegler to explore how his team built internal generative AI tools like Central RAG and MongoGPT and how they navigated challenges like permission-aware data, integrating diverse sources (think Google Drive and Zendesk!), and making it all work using MongoDB Atlas.
Jun 30, 2025
Video
How to Build an App with Semantic Search: Django, MongoDB Atlas & Voyage AI Tutorial
Read the written tutorial: https://dev.to/mongodb/grab-a-pint-with-django-mongodb-backend-voyage-ai-and-langchain-170n Watch the Django MongoDB Backend Quickstart tutorial: https://youtu.be/laXann1O0cg Sign-up for a free cluster → https://mdb.link/5s5ngllTB8E-register Access the Kaggle dataset here: https://www.kaggle.com/datasets/anaiya/guinnesswinebarsdublin Subscribe to MongoDB YouTube→ https://mdb.link/subscribe Looking for the best places to grab a drink in Dublin? Stop searching and start building! With the power of the Django-MongoDB-Backend Python package and AI, you can find the exact drink you're looking for. Build your own intelligent Dublin pub finder! This tutorial shows you how to combine Django, MongoDB, Voyage AI, and LangChain to create an AI-powered app with semantic search. Learn to set up your backend, embed data, and implement smart search functionality to help anyone discover the perfect pub in Dublin. Dive into the exciting world where Python, databases, and AI converge! Chapters: 0:00 Introduction to the Dublin Pub Finder 0:28 What is Django MongoDB Backend? 1:07 Understanding LangChain & MongoDB Integration 1:58 Why Voyage AI for Embeddings? 2:30 Project Prerequisites 3:25 Demo: Our Intelligent Pub Finder in Action 4:18 Data Collection & Preparation (Google Places API) 5:39 Setting up Django MongoDB Backend 7:24 Defining Django Models (models.py) 8:55 Generating Embeddings with Voyage AI 10:19 Importing Data to MongoDB Atlas 11:46 Creating Your Atlas Vector Search Index 13:10 Integrating LangChain for Semantic Search 14:48 Building the Django Application (views.py & URLs) 16:00 Crafting the User Interface (HTML/CSS) 17:15 Running the Application 17:35 Conclusion & Key Takeaways This video is not affiliated with, endorsed by, or sponsored by Python. The use of any trademark is solely for informational and identification purposes, so that we may provide clear and accurate descriptions. All opinions and critiques provided in this video are those of the creator and do not reflect the views of Python or its affiliates. Visit Mongodb.com → https://mdb.link/MongoDB Read the MongoDB Blog → https://mdb.link/Blog Read the Developer Blog → https://mdb.link/developerblog
Jun 23, 2025
Video
Build Agentic Workflows with Mastra - The TypeScript Agent Framework
✅ Sign-up for a free cluster → https://mdb.link/free-mastra-livestream ✅ Try Mastra.ai → https://mastra.ai/ Our special guest on this live stream is Shane Thomas from Mastra.ai. From the team that brought you Gatsby, Mastra will help you prototype and productionize AI features with a modern JavaScript stack. Let's see it in action!
May 27, 2025
Video
Master Parent Document Retrieval with MongoDB & LangChain for Smarter RAG apps | Live Code Guide
Written version → https://mdb.link/v5V3W-NNSQw-written Sign-up for a free cluster → https://mdb.link/v5V3W-NNSQw-try Subscribe to MongoDB YouTube→ https://mdb.link/subscribe 💡 Struggling with chunk sizes in RAG apps? Learn how MongoDB’s Parent Document Retrieval balances precision and context—no PhD required! Join this deep dive to: Solve the “chunking paradox” with small embeddings + large context retrieval 🧩 Live-code async ingestion for 40K+ documents (with batch processing hacks!) ⚡ Build a RAG pipeline and AI agent using LangChain & Atlas Vector Search 🤖 FREE GitHub repo included—steal the code for docs chatbots, legal research, or customer support! ⏱️ TIMESTAMPS: 00:00 - What is Parent Document Retrieval? (Spoiler: It’s a game-changer!) 02:35 - MongoDB + LangChain setup: Chunking strategies & metadata tips 10:06 - Async processing: Ingest 25K docs WITHOUT crashing your system 15:04 - Vector search indexes: Optimize for speed & accuracy 20:12 - AI Agent demo: Answer complex questions with context expansion 25:56 - Pro tips: Avoid “tool loops” in agents & access our Generative AI Cookbook Visit Mongodb.com → https://www.mongodb.com Read the MongoDB Blog → https://www.mongodb.com/blog Check out the MongoDB Developer Center → https://www.mongodb.com/developer
Mar 27, 2025
Video
How to Build an AI Agent with Semantic Kernel, MongoDB Atlas, C# and OpenAI
If you prefer to follow a written tutorial, it can be found here: https://mdb.link/lvQ-EC5afIA-tutorial Code Snippets: https://gist.github.com/LuceCarter/2efd3ae606da16aed1916ace5ef88595 Subscribe to MongoDB YouTube→ https://mdb.link/subscribe Have you ever wanted to write an AI Agent with Semantic Kernel? Join Developer Advocate Luce Carter in this tutorial to create a food agent to help you decide if you can cook tonight or should just go to a restaurant! Watch Getting Started with Microsoft Semantic Kernel with MongoDB Atlas in C# → https://youtu.be/qXswaD4IGUU?si=FacxfJK8PBYmtt3y Microsoft Learn Course: https://learn.microsoft.com/en-gb/training/paths/develop-ai-agents-azure-open-ai-semantic-kernel-sdk/%7C Vector Search Index Documentation: https://mdb.link/lvQ-EC5afIA-doc Visit Mongodb.com → https://www.mongodb.com Read the MongoDB Blog → https://www.mongodb.com/blog Check out the MongoDB Developer Center → https://www.mongodb.com/developer
Mar 19, 2025
Video
MongoDB vs PostgreSQL for AI Workloads: Speed, Scalability & Developer Wins Exposed!
Check out our Generative AI Showcase Repository: https://github.com/mongodb-developer/GenAI-Showcase Which database are you using for AI? Comment below! 👇 Curious which database dominates AI workloads? We pit MongoDB against PostgreSQL (with PG Vector) in a head-to-head performance showdown for vector search, ingestion speed, and real-time retrieval. Discover why developers are switching for AI scalability! 🔍 What You’ll Learn: ✅ Benchmark Results: Ingestion speed, query latency, and throughput under scale (local machine tests with 100k+ vectors). ✅ Why MongoDB Shines: Out-of-the-box performance for JSON data, zero serialization overhead, and seamless scalability. ✅ PostgreSQL PG Vector Deep Dive: Configuration challenges and when it might still work. ✅ Developer Productivity: Avoid “Postgres Regress” and focus on building AI features faster. 📊 Key Takeaways: MongoDB handles 4x faster ingestion and 2x lower latency at scale. Postgres requires tuning (HNSW parameters, JSONB serialization) for AI workloads. Why latency matters for RAG, conversational AI, and real-time apps in 2024. ⏱ Timestamps: 00:00 - Intro: The AI Database Battle 02:15 - Benchmark Setup (Local Instances, 100k Vectors) 05:40 - Ingestion Speed Showdown: MongoDB vs PG Vector 12:30 - Retrieval Latency: Why Milliseconds Matter for AI 18:50 - Throughput: Queries/Second Under Load 25:00 - Developer Experience: MongoDB’s JSON Advantage 30:45 - When to Choose Postgres? Honest Takeaways 🔔 Subscribe for more AI tech deep dives → https://mdb.link/subscribe Visit Mongodb.com → https://www.mongodb.com Read the MongoDB Blog → https://www.mongodb.com/blog Check out the MongoDB Developer Center → https://www.mongodb.com/developer
Mar 06, 2025
Video
Building a Semantic Search Application with MongoDB and Quarkus using Vector Search
✅ Try MongoDB 8.0 → https://mdb.link/91SzYGDmFoI ✅ Sign-up for a free cluster → https://mdb.link/91SzYGDmFoI-try ✅ Article link → https://mdb.link/91SzYGDmFoI-read - Discover how to harness the power of MongoDB's vector search capability to build a semantic search application using the Quarkus framework. In this comprehensive tutorial, we'll guide you step-by-step from understanding vector search fundamentals to implementing a functional Java application. Learn how to use Gemini AI for vector embeddings, create optimized queries, and set up your MongoDB Atlas cluster for seamless integration. Whether you're new to vector search or looking to enhance your generative AI applications, this video provides all the tools you need to get started. - 📚 Git repo: https://github.com/mongodb-developer/mongodb-vector-search-with-quarkus Resources: 📚 Vector Embeddings: https://mdb.link/91SzYGDmFoI-models 📚 Gemini AI: https://ai.google.dev/api?lang=python https://ai.google.dev/gemini-api/docs/api-key Similarity values: 📚 Euclidean: https://en.wikipedia.org/wiki/Euclidean_distance 📚 Cosine: https://en.wikipedia.org/wiki/Cosine_similarity 📚 Dot Product: https://en.wikipedia.org/wiki/Dot_product
Jan 21, 2025
Video
Transforming the Insurance Industry with MongoDB: Insights on AI and Data Modernization
✅ Try MongoDB 8.0 → https://mdb.link/oqBsHREc9PM-8.0 ✅ Sign-up for a free cluster → https://mdb.link/oqBsHREc9PM-try - In this episode, we sit down with industry experts to discuss how MongoDB is revolutionizing the insurance sector through data modernization and AI integration. Discover how MongoDB's document model simplifies data processing, enhances developer productivity, and reduces friction in application development. Learn about the exciting advancements in vector search and unstructured data handling that are set to transform customer experiences in insurance. Whether you're in the industry or just curious about the future of data management, this episode is packed with valuable insights and practical applications.
Dec 23, 2024
Video
What does Aperol Spritz have to do with MongoDB??
Let's find the closest Aperol spritz to you with MongoDB geospatial queries and Atlas Vector Search.
Dec 12, 2024
Video
Insights on Vector Search and Quantization for Developers and AI Enthusiasts
✅ Try MongoDB 8.0 → https://mdb.link/Nu70pFr88Cc-8.0 ✅ Sign-up for a free cluster → https://mdb.link/Nu70pFr88Cc-try - In this episode of the MongoDB Podcast, we dive deep into the exciting advancements in vector search technology. Join us as we discuss the recent launch of quantization capabilities and how they can significantly reduce costs while enhancing performance. Discover the implications for developers and customers alike, and learn about the future of AI integration within MongoDB. Whether you're a seasoned developer or just starting out, this episode is packed with valuable insights to help you leverage the benefits of vector search in your applications.
Dec 02, 2024