$ articles --topic=vector-databases
Vector Databases
23 AI articles about Vector Databases.
Giving Back to the Open Source We Build OnLanceDB describes its contribution of ASOF join support to Apache DataFusion, which improves time-series joins. The post explains why the company contributes back to the open source projects it depends on.Observability · via LanceDB · 1d ago1 minBuilding a RAG Pipeline for Semantic Code Search: A Developer Diary and Field NotesPart 2 of a series on building Air Context, a production RAG system for code search, covers how to store millions of code vectors, keep indexes in sync with Git commits, and combine metadata filters like repo, branch, and permissions with approximate nearest-neighbor search.AI Coding Tools · via JetBrains AI · 2d ago9 minWeaviate 1.40 ReleaseWeaviate v1.40 makes named vector dropping and 4-bit Rotational Quantization generally available, adds multi-vector MUVERA support on HFresh and a new PathSeer filter strategy for HNSW. It also flags a breaking change to vector configuration defaults to check before upgrading.Model Releases · via Weaviate · 8d ago8 minIntroducing pg_pinecone: Open-Source Search for Your Postgres DataLearn what pg_pinecone is, an Apache 2.0 open-source Postgres extension that adds search over data you already store, built on the search engine Pinecone runs at scale. The post explains how it works with your existing Postgres tables.RAG · via Pinecone · 11d ago1 minHow to Migrate from Chroma Cloud to PineconeChroma Cloud stops accepting writes on November 22, 2026 and stops serving reads on December 22, 2026. This guide walks through moving a Chroma Cloud collection to Pinecone during a planned write pause.Vector Databases · via Pinecone · 12d ago1 minDeprecating the GraphQL API: timeline and migration pathsWeaviate is deprecating its GraphQL API on October 26, 2026, with end of life on Weaviate Cloud on May 1, 2027. The post explains who is affected, which gRPC client, web client or REST Search API to move to, and how to migrate and test with GraphQL disabled.Vector Databases · via Weaviate · 12d ago8 min🤖 LeRobot Trains on Lance, 🦾 Mining Robot Fleet Data Demo, 🔍 Vector Search at 10B ScaleThis newsletter roundup covers how LeRobot can train directly from Lance datasets stored in object storage, how a hybrid scan approach finds edge cases in robot fleet data, and how distributed vector search reached 1,066 QPS across 10 billion vectors. It also lists upcoming events, enterprise updates, and community contributions.Inference · via LanceDB · 16d ago1 minIntegrated embedding on the Documents APILearn how Pinecone's Documents API now embeds text for you at ingest time, so a single text field supports both semantic and full-text search without building a separate embedding pipeline.RAG · via Pinecone · 16d ago1 minWhen vectors became an implementation detailExplains how Pinecone added integrated embedding to its Documents API, so developers can send raw text instead of precomputed vectors. It also covers how the API combines full-text and vector search in a single workflow.RAG · via Pinecone · 16d ago1 minLance Blob V2: Making Multimodal Data a First-Class Citizen in the LakehouseExplains the redesign of blob storage in the Lance format to handle multimodal data in lakehouses. It covers four storage semantics, Inline, Packed, Dedicated, and External, and how each adapts automatically to the workload.RAG · via LanceDB · 16d ago1 min56 scanned pages to a cited answer in 5 minutes: RAG pipeline for the documents search cannot readLearn how to build a RAG pipeline that turns a 56-page scanned plant guide into a searchable, citable knowledge source. The walkthrough uses jina-ocr-v1 on Elastic Inference Service, semantic_text chunking, and hybrid retrieval inside one Elastic Cloud project.RAG · via Elastic Search Labs · 16d ago8 min📄 Lance Blob V2, 🤗 Upload Lance Datasets to HF Hub, 🦞 LanceDB for OpenClaw's MemoryThis newsletter covers three topics: Lance Blob V2, which adds adaptive storage semantics for large binary data; a way to upload Lance datasets to the Hugging Face Hub; and LanceDB's role as a default memory layer for OpenClaw agents. It also includes community and enterprise updates.Agents · via LanceDB · 22d ago1 min