Import & Vectorize Data with Weaviate at Scale | Weaviate
Jun 18, 2026

Summary
Introduces server-side batching for efficient data import, a retry-with-checkpoint pattern for robust error handling, and the `blobHash` data type for storing media embeddings while omitting raw bytes. Also discusses multimodal ingestion for PDFs and images using Weaviate Embeddings and `multi2vec-google`.
More from the Semantic Search for Creative Assets trail
- Building Foundry Part 3: From archive to creative search | Weaviate
- How to extract meaning from charts and tables in PDFs | Weaviate
- Building Foundry Part 2: Where creative workflows break | Weaviate
- Building Foundry: AI isn’t replacing creativity, it’s removing friction | Weaviate
- Your LLM Is Only as Good as What It Retrieves | Weaviate