Topic · 25 stories · page 1 of 2
25 stories tagged rag on AI Tamer, newest first.
Before 0.40.0, LanceDB's Cloud client put table names into REST URLs unencoded, so a name with ../ could reach another table or tenant. Upgrade.
fastembed-rs 7.4.0 puts ONNX Runtime behind a default onnx feature and splits qwen3 into text and VL features. Default builds are unchanged.
Before 1.20, any host that reached Qdrant's internal port 6335 could join a cluster and copy shards. The fix needs an API key. BM25 and turbo8 also land.
Five open NVIDIA retrieval models search page images and text, rerank results and parse PDFs, under the permissive OpenMDW license. What to check first.
Exa 3.0 adds a larger embedding model, GA highlights that use 95% fewer tokens, billions of new documents and a $4 Lite search tier. Benchmarks self-run.
DeepSeek's API guide documents Search and Fetch at 5 requests a second. The Chinese pages price each at 5 yuan per 1,000 successes; the English pages say $0.75.
XERJ published v1.0.0-rc.96 on 16 October, a Rust engine for local search. Corpus Hub is not enabled in this build.
HyDE embeds a passage a language model writes in answer to the query, then searches with it. How to build it, and where it stops helping.
Cross-encoders score a query and a document in one pass, which makes them more accurate than embedding search and too slow for a whole corpus. Use them to rerank the top hits.
Google published EmbeddingGemma 2, an open model that maps text, code, images, video, and audio into one 768-wide vector. Developers can load fewer encoders or store a shorter vector.
Chunk size, overlap and boundaries decide what a retriever can return. This post covers defaults documented by Azure AI Search and OpenAI, plus a way to test a setting on your own questions.
SQLite puts application data, full-text search and, with an extension, vector search in a local database file. Here is where that fits and when PostgreSQL fits better.
Retrieval-augmented generation is an architecture, and the vector database is one box in it. The whole loop, the RAG variants worth knowing, reranking, and when a knowledge graph beats similarity.
LlamaIndex (Oct 1, 2026) shipped Extract v2.5: schema-based document extraction agents with Advanced Citations on Agentic and Agentic Plus, same per-page pricing, and native spreadsheet mode.
turbopuffer made native embedding generally available (Sep 29, 2026): embed on write, on query, or keep BYOE. Systems overlap with index metadata fetch; Linear/Readwise beta color is vendor-stated.
Weaviate v1.39.3 (Oct 1, 2026) fixes a High CVSS 7.1 credential disclosure in text2vec-google, multi2vec-google, and generative-google. Impacted: < v1.39.3. CVE pending MITRE assignment.
AI Search generally available (blog Oct 1, 2026). Billing starts November 1, 2026; free tier remains. Blog pricing: ingestion $0.75/1M + image +$0.50/1M; storage $2/GB-mo; semantic $0.75/1k · full-text $0.10/1k. Qwen3-VL-Embedding; OCR; files to 10 MiB. Video/audio = roadmap not GA.
Same-day Sep 30, 2026: Voyage ships rerank-3 and rerank-3-lite (“available today”, with no GA claim). MongoDB Atlas Native Reranking via $rerank is Preview only (docs). The Voyage and MongoDB lift claims are theirs. Separate from Atlas Agent Engine, and neither is a Vector Search substitute.
Qdrant’s Clelia Bertelli blog (Sep 25, 2026) covers cross-encode-rs—a Rust ONNX Runtime cross-encoder for reranking. crates.io owner is AstraBert (not a Qdrant-org crate). ~1.1×/~1.4× vs Python stacks on M4 Max are vendor-reported; all three hand work to onnxruntime. Linux/macOS only.
Qdrant’s Constella research preview (Sep 29, 2026): index docs once with Stella (400M English), then query with Zero, Nano, or Stella against the same collection—no re-embedding. Research preview, not GA. Encode-speed and nDCG figures are vendor-reported.
DiskANN approximate vector indexes are GA in Azure SQL Database, Azure SQL Managed Instance (Always-up-to-date), and Fabric SQL (Hoffman Sep 29; Thota Sep 28). Vectors sit next to operational rows under the same T-SQL/security model—no separate vector store. SQL Server 2025 / MI on SQL Server 2025 policy stay preview.
Databricks GA’d Lakebase Search on AWS/Azure (blog 2026-09-28): lakebase_vector (ANN) + lakebase_text (BM25) in the same serverless Postgres OLTP—hybrid via RRF, no separate search cluster. VectorDBBench/Conexiom figures are vendor-reported.
Cohere GA’d Embed 5 (2026-09-30): embed-v5.0-pro / embed-v5.0-fast share one space (index Pro → query Fast). Blog pricing $0.12 / $0.08 per 1M text; image $0.40 both. 128K, Matryoshka dims, multimodal—ViDoRe/finance benches are Cohere-reported.
AWS S3 Vectors (Sep 30, 2026) adds ENHANCED index mode that filters metadata before similarity search, plus $startsWith. AWS claims up to 5× more matching vectors on highly selective filters—vendor figure, not house-verified. No extra cost; CLASSIC until you upgrade.
