Subscribe
Topic

Databases

Databases for AI apps, from vector stores to classic engines. Posts compare embedded vector databases like LanceDB, sqlite-vec and Chroma, cover semantic caching and vector compression, and report news such as the PostgreSQL 19 delay and Amazon buying DuckLabs.

Articles

1-10
  1. PostgreSQL 19 GA Delayed to November Following LLM Code Review Findings and Feature Reverts

    The PostgreSQL Global Development Group has moved the targeted general availability date for PostgreSQL 19 from late September to November 19, 2026. The delay follows late-cycle code reviews using large language model tooling that surfaced roughly 40 defect reports, prompting core maintainers to revert between 8 and 10 major features slated for the release. Reverted Features and Architectural Defect Findings According to PostgreSQL committer and EDB vice president Peter Eisentraut, automated

    Databases
    3 min read
  2. Semantic Caching Engines in Production LLM Systems: Comparing GPTCache, RedisVL, Portkey, and Cloudflare AI Gateway

    Semantic Caching Engines in Production LLM Systems: Comparing GPTCache, RedisVL, Portkey, and Cloudflare AI Gateway Standard exact-match caching strategies fail in large language model applications. Because natural language is inherently variable, users asking the exact same question will use different phrasing, punctuation, sentence structures, or synonyms. Exact string hashing (such as MD5 or SHA-256 caching over raw prompt strings) rarely yields hit rates above 3% to 5% in production convers

    AI
    10 min read
  3. Amazon Acquires DuckLabs to Integrate DuckDB into AWS Analytics and AI Agent Workflows

    Amazon has entered into a definitive agreement to acquire DuckLabs, the Amsterdam-based company behind the open-source columnar database DuckDB. The acquisition brings the DuckLabs development team into Amazon Web Services (AWS), where they will operate as a wholly owned subsidiary starting in early September. Financial terms of the transaction were not disclosed. DuckDB creators and DuckLabs co-founders Hannes Mühleisen and Mark Raasveldt will continue leading the team from Amsterdam, maintain

    AI
    2 min read
  4. Temporal Knowledge Graphs in Production RAG: Bitemporal Schemas, Dynamic Entity Resolution, and Point-in-Time Context Retrieval

    Temporal Knowledge Graphs in Production RAG: Bitemporal Schemas, Dynamic Entity Resolution, and Point-in-Time Context Retrieval Standard Retrieval-Augmented Generation (RAG) pipelines operate on a flat assumption: facts retrieved from a vector database or static knowledge graph are treated as timeless truths. When an enterprise corpus contains documents spanning multiple quarters or years, this timeless representation breaks down. Information changes: executives step down, compliance policies a

    Analysis
    6 min read
  5. Vector Compression in Production Search: Comparing SQ, PQ, and RaBitQ Architecture, Recall Retention, and Memory Economics

    In production Retrieval-Augmented Generation (RAG) systems and enterprise search platforms, storing raw floating-point embedding vectors in RAM quickly encounters hard hardware limits. A dataset of 100 million 1536-dimensional embeddings stored in FP32 requires over 614 GB of high-speed memory solely for vector coordinates, before accounting for index graph structures like HNSW or DiskANN. To scale similarity search to billions of vectors while keeping indices memory-resident, production vector

    AI
    4 min read
  6. Distributed Vector Search and Sharding Architecture in Production: Horizontal Partitioning, Scatter-Gather Tail Latency, Filter-Aware Routing, and Dynamic Rebalancing

    Scaling vector search beyond tens of millions of high-dimensional embeddings inevitably hits a physical boundary: the single-node memory wall. Because graph-based approximate nearest neighbor (ANN) algorithms such as Hierarchical Navigable Small World (HNSW) require random memory access patterns across graph vertices and high-dimensional vectors, keeping embeddings and index structures in RAM is critical for sub-20ms query latencies. A collection of 100 million 1,536-dimensional float32 vectors

    Vector Search
    8 min read
  7. Binary Quantization and Matryoshka Embeddings in Production: Two-Stage Rescoring, Hamming Distance Acceleration, and Vector Storage Economics

    Production vector search workloads face a severe memory scaling bottleneck. In retrieval-augmented generation (RAG) and semantic search architectures, indexing tens of millions of high-dimensional embeddings in raw 32-bit floating-point (FP32) format exhausts memory capacity and drives up infrastructure costs. Indexing 100 million 1536-dimensional vectors requires 614.4 GB of RAM purely for vector payloads, before accounting for graph edges and memory fragmentation in Approximate Nearest Neighbo

    AI
    8 min read
  8. Vector Indexing in Production: HNSW vs. DiskANN vs. IVF-PQ Architecture, Memory Footprint, and Search Economics

    Vector Indexing in Production: HNSW vs. DiskANN vs. IVF-PQ Architecture, Memory Footprint, and Search Economics Scaling vector search beyond prototype deployments exposes a fundamental tension across three competing constraints: retrieval recall, query latency, and memory footprint. In high-dimensional representation spaces, exact k-nearest neighbor search via brute-force flat scans requires $O(N \cdot d)$ floating-point operations per query. For a corpus of 100 million 1536-dimensional FP32 em

    AI
    7 min read
  9. Text-to-SQL in Production: Schema Linking, Value Retrieval, and Execution-Guided Self-Correction

    Translating natural language into executable database queries is one of the most widely deployed applications of large language models in enterprise software. It is also one of the most brittle. On synthetic academic benchmarks such as Spider 1.0, frontier models regularly exceed 90% execution accuracy. However, evaluating those same models on realistic enterprise estates yields a steep drop. On the Spider 2.0 benchmark, which evaluates real-world data warehouses spanning BigQuery and Snowflake

    AI
    7 min read