# Scaling Vector Search Infrastructure at Airtable Custom architecture designed to manage billions of embeddings. - **Source:** [Airtable Engineering](https://medium.com/airtable-eng) - **Published:** 2026-03-17 - **Topic:** [Data & AI](https://brifing.si/c/data-ai) - **Original article:** - **On Brifing:** https://brifing.si/s/1da47d8b-fea3-4881-bf1d-059572917774 ## Productionizing Semantic Search Airtable's data infrastructure team identified the need for a vector database to support semantic search at global scale. They designed a system capable of managing billions of embeddings, supporting multi-tenancy, and meeting performance targets in a distributed cloud environment. ## Use Cases Omni (Airtable's AI chat) answers natural language questions from large datasets. For example, it can respond to queries like 'What are customers saying about battery life lately?' across hundreds of thousands of rows, providing meaningful answers beyond traditional search methods. ## Design Priorities The system was built on four core goals: Low-latency queries (500ms p99), high write throughput, horizontal scalability, and self-hosted infrastructure. These objectives aim to protect customer data privacy while delivering top-tier user experience. ## Technology Selection In 2024, Milvus vector database was chosen after evaluation. Its self-hostable nature, elastic scalability, and strong tenant isolation made it ideal. Milvus's distributed architecture can manage millions of customer data points efficiently. ## Architectural Decisions Separate physical partitions were created for each Airtable base. This approach simplified data deletion while improving performance. Initial tests with 100k partitions showed latency issues, leading to a 1,000-partition limit per collection. ## Indexing Strategy HNSW indexing method was selected for its 99%-100% accuracy rate. While other options (IVF-SQ8, DiskANN) used less memory, HNSW's balance of performance and accuracy better met Airtable's requirements. ## Data Flow The system consists of two core flows: Ingestion flow (converting Airtable rows to embeddings and storing in Milvus) and query flow (processing user queries and delivering relevant rows to LLM). Both flows operate continuously and reliably at scale. ## Scalability Solutions Each Milvus cluster supports up to 400k bases. New clusters are provisioned as additional customers onboard. This approach optimizes resource usage while maintaining performance. Partition load times were reduced to under 30 seconds. ## The Future of Search Airtable's vector infrastructure demonstrates how semantic search is becoming a core product feature. This system enables meaningful search across large datasets while providing an architecture that meets enterprise requirements. ## Sources covering this story - https://medium.com/airtable-eng/productionizing-semantic-search-how-we-built-and-scaled-vector-infrastructure-at-airtable-180fff11a136?source=rss----103630b30187---4 — --- _Summary written by Brifing from the original reporting. Copyright in the original article belongs to its publisher; read the full piece at the link above._