AI Briefing#vector-database
The latest AI and developer news about #vector-database, with the original source and a short summary.
The latest AI and developer news about #vector-database, with the original source and a short summary.
The open-source library supports exact k-NN, k-means, NN-Descent, and CAGRA algorithms, outperforming CPU-based hnswlib in both build time and search speed.
1-bit TurboQuant compression reduces vector size from 856 KB to 40 KB per page while retaining 96.5% of float32 retrieval scores.
Billing for AI Search begins November 1, 2026, with a free tier offering 5M ingestion tokens and 1,000 semantic queries per month.
The new feature delivers up to 5x more matching vectors on selective filters without requiring re-ingestion or additional costs.
turbopuffer is introducing v3, a new storage architecture that moves the ANN index from primary to secondary status to resolve write amplification and enable larger query blocks, with 100% CI passing as of early September 2026.
Pinecone has released VQ-bench, an open-source benchmarking tool that analyzes how major vector quantization techniques are composed of the same fundamental operations and compares their performance.
A CLI tool named 'raggy' has been released, performing RAG on local documents using Ollama and hybrid indexing.
Researchers have released EmbedFlow, an open-source tool that enables instant switching between embedding models by leveraging existing indexes without backfilling.
A new technique for converting embeddings without paired data has revealed security vulnerabilities in vector databases.
Booking.com disclosed the technical rationale behind migrating from OpenSearch to Weaviate for its RAG and semantic search infrastructure.
Xata announced integrations with LangChain for vector and memory stores, enhancing data processing capabilities for AI applications.
This article presents concrete implementation methods using LangChain based on OpenAI's RAG experiment results.
Integrating Qdrant with LangChain maximizes the performance and resource efficiency of RAG applications.
Toss Securities introduces the process of advancing its recommendation and search systems toward real-time personalization and RAG-based architectures.
Timescale Vector integrates with LangChain to significantly improve the speed and efficiency of vector search in PostgreSQL.
Cube announced a semantic layer integration with LangChain to enhance the accuracy of LLM-based applications.
LangChain adjusted its abstractions to allow flexible extension of retrieval methods.
LangChain has strengthened production data ingestion pipelines by adding a Destination to Airbyte.
Revealed the architecture and design decisions for building Papers with Code's hybrid search system using Hugging Face infrastructure.
Amazon DynamoDB supports real-time vector search without a separate vector database.
It's a tool that provides a markdown-based persistent memory layer so multiple AI coding agents can share context.
It's a local-first AI application that integrates document-based RAG and AI agent capabilities.
Manticore Search has introduced an ONNX Runtime backend, boosting embedding inference speed by an average of 14x compared to before.
HyperspaceDB, a Spatial AI engine that maximizes memory efficiency by introducing Matryoshka learning and Lorentz geometry, has been released.