Step-by-step tutorials on building voice and chat AI agents using OpenAI Agents SDK, Realtime API, function calling, multi-agent orchestration, and production deployment patterns.
9 of 1313 articles
Learn how to build a complete semantic search engine from scratch using sentence embeddings, approximate nearest neighbor indexing, and a query processing pipeline that returns relevant results by meaning rather than keywords.
Understand the difference between bi-encoders and cross-encoders, then build a re-ranking pipeline that dramatically improves search precision by scoring query-document pairs jointly rather than independently.
Configure Elasticsearch for hybrid search that combines traditional BM25 keyword matching with dense vector kNN search, giving you the precision of neural retrieval with the reliability of lexical matching.
Build an intelligent FAQ system that understands user questions by meaning rather than keywords, using vector similarity to match queries to answers with confidence thresholds and graceful fallback behavior.
Implement cross-lingual semantic search that lets users query in one language and retrieve results in any language, using multilingual embedding models that map all languages into a shared vector space.
Build a semantic code search engine that finds relevant functions and classes by intent rather than identifier names, using code-specific embeddings from CodeBERT and AST-aware parsing to understand code structure.
Learn how to combine metadata filters with vector similarity search, comparing pre-filter and post-filter strategies, designing filterable metadata schemas, and building a responsive faceted search UI.
Learn how Temporal provides durable execution guarantees for AI agent workflows. Covers workflow definition, activities, automatic retries, and state management for long-running agent pipelines.
