Vector databases for enterprise AI / Emma McGrattan.

Format:

Book

Author/Creator:

McGrattan, Emma, author.

Language:

English

Subjects (All):

Databases.

Artificial intelligence.

Physical Description:

1 online resource (49 pages)

Edition:

[First edition].

Place of Publication:

Santa Rosa, CA : O'Reilly Media, Inc., [2026]

Summary:

Enterprise generative AI has reached a turning point. Pilots have proven the models work. What's struggling is the infrastructure underneath them. Semantic search, RAG, and agentic workflows require data retrieval based on meaning and similarity, not keywords and exact matches. Better models won't fix an architecture that was never designed for this kind of reasoning. Vector Databases for Enterprise AI gives architects and platform engineering leaders the grounding they need to get this right. This focused guide covers how vector embeddings and similarity search work, how to integrate vector databases responsibly into your existing data estate, and what trust, governance, and lifecycle management look like in real production environments. Understand the retrieval gap that makes vector databases essential for AI workloads Design semantic retrieval systems that avoid siloed, ungovernable AI sidecars Evaluate performance, cost, and accuracy trade-offs before committing to an approach Apply governance and metadata frameworks suited to production-grade deployment Integrate vector capabilities into existing platforms without disrupting what already works.

Notes:

OCLC-licensed vendor bibliographic record.

OCLC:

1587399419