What Happened
Weaviate fixed a medium-severity authorization flaw in the GraphQL nearObject operator in v1.39.3. In earlier versions, a user without read access to a target collection could infer an object’s vector from search distances if they knew its collection name and UUID, could read collection definitions, and had a separate collection in which to…
What Happened
Weaviate 1.40 added PathSeer, a filtered vector-search strategy that adapts between distance-first and filter-first exploration as filter selectivity changes. It uses existing HNSW indices, so teams can test filterStrategy: pathseer without reindexing. ACORN remains the default, and the existing flat-search cutoff still applies [1].
In Weaviate’s tests, PathSeer was generally fastest at 0.90…
What Happened
Perplexity released two pplx-embed-v2-late models that search PDF pages as images using late interaction. They can represent tables, charts, and page layout without an OCR step during indexing [1]. This addresses a common weakness of text-only retrieval: a financial figure is easy to misinterpret when its row, column, unit, or label is missing…
What Happened
Elastic Agent Builder now supports live shared conversations on Elastic Cloud Serverless. Authorized teammates can read a thread’s history and continue questioning the same agent, rather than receiving a static transcript. Elastic describes incident-response handoffs as one use case. Support for Elastic Cloud Hosted and Self-Managed is planned for version 9.6, but timing…
What Happened
Elastic described a context engine that prepares reusable knowledge about schemas, fields, entities and documents before an agent receives a question. It stores these “Knowledge Indicators” in an AI index and retrieves them through lexical, semantic, hybrid and agentic search. Agent traces feed a loop for improving the indicators over time [1].
In…
What Happened
Google DeepMind’s EmbeddingGemma 2 can run on a phone, but serving its embeddings across a large document collection is a different resource problem. For 10 million documents, full-size float32 vectors alone require 30.7 GB of RAM, before indexes, metadata, replicas or application overhead [1].
In early Qdrant tests, quantized full-size vectors used 30…
What Happened
Weaviate v1.39.3 fixes a high-severity credential disclosure vulnerability in its Google-backed embedding and generation modules. Earlier versions could send a configured Google API key or OAuth token to an attacker-controlled host if an unvalidated apiEndpoint was supplied. An attacker could set that endpoint through collection configuration with schema-write access or, for generative-google, through…
What Happened
Recent work shows that retrieval — not the generator — is the primary failure point in retrieval-augmented generation (RAG) and agent workflows: missing or low-quality candidates cause hallucination, context rot, excessive tool calls and unpredictable latency. Improving search quality reduces downstream errors and tool usage, but “improve retrieval” is too vague: you must…
Findings [1] 2026-09-29 How Elasticsearch Serverless hollow shards cut indexing-node shutdowns by 30% Elasticsearch Serverless now unloads idle indexing shards from memory. We call them hollow shards; the shard stays allocated, but its Lucene IndexWriter and segment readers are gone until the next write arrives. Hollow shards build on thin indexing shards, which… It…
Findings [1] 2026-09-28 The best LLM writes correct Elasticsearch ES|QL 59% of the time. Here's what breaks the other 41%. We gave four models 500 natural-language questions from BIRD's Mini-Dev set, asked each for one Elasticsearch Query Language (ES|QL) query, and graded all 6,000 answers on whether the right rows came back. The best…
Findings [1] 2026-09-25 GPU-accelerated vector indexing in Elasticsearch with NVIDIA cuVS: 138M vectors in under 10 minutes Modern enterprise applications are ingesting terabyte- to petabyte-scale unstructured data to power semantic search, large language model–based (LLM-based) retrieval augmented generation (RAG), and recommender systems. At this scale, vector indexing on CPUs can take days or even…
Findings [1] 2026-09-24 Ask Elastic Agent Builder why it's slow: Natural-language trace analysis Ask Elastic Agent Builder how many tokens your agents burned today, and it writes the Elasticsearch Query Language (ES|QL) and runs it against your OpenTelemetry (OTel) trace data. Then it answers in the chat UI. The same holds for your… That…