> Markdown version of [/playlists/embeddings-vector-search](https://www.wearedevelopers.com/playlists/embeddings-vector-search). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Playlist: Embeddings & vector search 20 videos · 25 moments · 77.8 minutes ## Build RAG from Scratch - **Searching by semantic meaning with vector embeddings** (04:26, 1min) — Converting text into structured lists of numbers allows systems to mathematically represent and search for semantic meaning. - **Scaling vector similarity search using dedicated databases** (22:53, 3min) — Vector databases handle high-volume embedding storage and native nearest-neighbor indexing far more efficiently than iterated local arrays. [Learn more](https://www.wearedevelopers.com/videos/1115-build-rag-from-scratch) ## Harry Potter and the Elastic Semantic Search - **Enabling semantic search with automated query vectorization** (11:07, 1min) — Vectorizing incoming questions queries isolates contextually matching documents stored within the same embedding space. - **Mapping data relations through vector embedding spaces** (07:22, 1min) — Analyzing multidimensional proximity reveals contextual relationships between distinct words and concepts. [Learn more](https://www.wearedevelopers.com/videos/860-harry-potter-and-the-elastic-semantic-search) ## Knowledge graph based chatbot - **Using vector embeddings for unstructured text search** (05:03, 2min) — Converting raw text chunks into dense numeric arrays enables semantic similarity comparisons for retrieving document context. [Learn more](https://www.wearedevelopers.com/videos/754-knowledge-graph-based-chatbot) ## Vision for Websites: Training Your Frontend to See - **Executing vector search queries using spatial distance** (14:01, 4min) — Plotting queries and data into numbered vector coordinates measures physical distance to determine search relevance. - **Unifying distinct media formats across shared vector spaces** (18:30, 2min) — Processing varying media through specialized encoders deposits uniform embeddings into a shared retrieval environment. [Learn more](https://www.wearedevelopers.com/videos/1213-vision-for-websites-training-your-frontend-to-see) ## WeAreDevelopers LIVE - Vector Similarity Search Patterns for Efficiency and more - **Mitigating language model costs with vector search patterns** (12:15, 8min) — Using vector databases to handle semantic embeddings reduces repetitive token costs and execution delays. [Learn more](https://www.wearedevelopers.com/videos/1709-wearedevelopers-live-vector-similarity-search-patterns-for-efficiency-and-more) ## Building AI-Driven Spring Applications With Spring AI - **Understanding vector databases and retrieval-augmented generation pipelines** (27:20, 1min) — How ETL pipelines process, split, and embed documents into a vector database for similarity searches. [Learn more](https://www.wearedevelopers.com/videos/1141-building-ai-driven-spring-applications-with-spring-ai) ## Reducing LLM Calls with Vector Search Patterns - Raphael De Lio (Redis) - **Encoding textual meaning into numerical vector representations** (02:53, 2min) — Embedding models convert text into discrete numerical vectors to allow engines to compute semantic similarities. - **Classifying text rapidly using reference embedding generation** (05:24, 4min) — Pre-generating and storing embedded text references enables fast vector similarity searches for classification tasks. [Learn more](https://www.wearedevelopers.com/videos/1714-reducing-llm-calls-with-vector-search-patterns-raphael-de-lio-redis) ## Develop AI-powered Applications with OpenAI Embeddings and Azure Search - **Storing calculated embeddings in Azure Cognitive Search** (29:47, 5min) — Writing pre-calculated embedding vectors into specialized databases optimizes retrieval speed during live semantic searches. [Learn more](https://www.wearedevelopers.com/videos/828-develop-ai-powered-applications-with-openai-embeddings-and-azure-search) ## Martin O'Hanlon - Make LLMs make sense with GraphRAG - **Limitations of vector embeddings for precise factual querying** (13:46, 4min) — While vector embeddings streamline fuzzy semantic searches, they consistently struggle to reliably resolve strict arithmetic or fact-oriented const... [Learn more](https://www.wearedevelopers.com/videos/1323-martin-o-hanlon-make-llms-make-sense-with-graphrag) ## Enter the Brave New World of GenAI with Vector Search - **Understanding numerical representations of vector embeddings** (37:22, 3min) — How textual data is converted into floating-point coordinates across high-dimensional spaces to represent semantic proximity. - **Common application scenarios leveraging vector similarity matching** (43:16, 2min) — Practical ways to utilize vector embeddings for clustering, anomaly detection, recommendations, and text classification. [Learn more](https://www.wearedevelopers.com/videos/844-enter-the-brave-new-world-of-genai-with-vector-search) ## Building Real-Time AI/ML Agents with Distributed Data using Apache Cassandra and Astra DB - **Processing text for semantic vector search operations** (13:34, 5min) — Splitting content into manageable chunks allows the generation of embeddings for similarity matching. [Learn more](https://www.wearedevelopers.com/videos/782-building-real-time-ai-ml-agents-with-distributed-data-using-apache-cassandra-and-astra-db) ## What comes after ChatGPT? Vector Databases - the Simple and powerful future of ML? - **Mathematical search techniques for locating similar dataset embeddings** (23:19, 2min) — Applying mathematical formulas like cosine similarity and Euclidean distance to calculate the contextual relatedness of search vectors. [Learn more](https://www.wearedevelopers.com/videos/830-what-comes-after-chatgpt-vector-databases-the-simple-and-powerful-future-of-ml) ## When Should You Use an Agent? Architectural Trade-offs in Agentic Systems - **Implementing semantic search flows utilizing Amazon Bedrock foundation models** (22:09, 5min) — Fully managed vector databases and embedding models retrieve localized data structures before engaging external foundation models. [Learn more](https://www.wearedevelopers.com/videos/100109-when-should-you-use-an-agent-architectural-trade-offs-in-agentic-systems) ## RAG like a hero with Docling - **Traditional architecture for retrieval-augmented generation pipelines** (03:57, 1min) — Implementing structural vector databases enables retrieval strategies to match token embeddings logically alongside user inquiries. [Learn more](https://www.wearedevelopers.com/videos/1602-rag-like-a-hero-with-docling) ## Tomb rAIder: AI Search with Kotlin - **Calculating and storing embeddings in PostgreSQL** (02:02, 2min) — Textual metadata converts into high-dimensional vectors stored in a database for fast proximity scanning. [Learn more](https://www.wearedevelopers.com/videos/1989-tomb-raider-ai-search-with-kotlin) ## The Retrieval Layer for Edge AI - **Bringing semantic memory to devices with Qdrant Edge** (06:29, 2min) — Embedding a Rust-based vector search engine locally allows low-resource environments to index unstructured data and maintain persistent personalize... [Learn more](https://www.wearedevelopers.com/videos/100033-the-retrieval-layer-for-edge-ai) ## Why LLMs Need Observability and How to Do It - **Breaking down execution operations into individual trace spans** (11:35, 1min) — Segmenting user interactions explains how single requests map into embeddings and required vector search actions. [Learn more](https://www.wearedevelopers.com/videos/2117-why-llms-need-observability-and-how-to-do-it) ## Make it simple, using generative AI to accelerate learning - **Implementing retrieval augmented generation architecture for domain context** (10:29, 1min) — Converting document chunks into searchable vector representations allows models to reference validated facts dynamically before responding. [Learn more](https://www.wearedevelopers.com/videos/969-make-it-simple-using-generative-ai-to-accelerate-learning) ## AI Model Management Life Circles: ML Ops For Generative AI Models From Research to Deployment - **Baseline architecture of retrieval-augmented generation systems** (04:13, 2min) — Converting raw domain knowledge into digestible embeddings enables language models to generate accurate and contextual answers. [Learn more](https://www.wearedevelopers.com/videos/1152-ai-model-management-life-circles-ml-ops-for-generative-ai-models-from-research-to-deployment) ## OpenAI for FinTech: Building a Stock Market Advisor Chatbot - **Handling vector embeddings and multi-model formats in SingleStore** (10:04, 3min) — Native compatibility with document stores and foundational vector engines provides robust persistence for diverse analytical datasets. [Learn more](https://www.wearedevelopers.com/videos/805-openai-for-fintech-building-a-stock-market-advisor-chatbot)