qdrant
PulseAugur coverage of qdrant — every cluster mentioning qdrant across labs, papers, and developer communities, ranked by signal.
- 2026-11-01 product_launch Qdrant released version 1.20, enhancing its vector database with integrated BM25 keyword ranking and other features. source
- 2026-10-14 funding Qdrant closed a $50 million Series B funding round. source
- 2026-09-08 product_launch Qdrant has released a new dataset to benchmark AI search technologies. source
- 2026-08-15 product_launch OpenCrawling released a new output connector for the Qdrant vector database. source
- 2024-01-11 partnership Qdrant partnered with Replit to launch new developer templates.
16 day(s) with sentiment data
-
PostgreSQL 16 with pgvector offers unified hybrid search for RAG
This article explores the challenges of enterprise Retrieval-Augmented Generation (RAG) systems, arguing that pure dense vector search fails on queries requiring exact identifiers, while traditional keyword search (BM25…
-
Embedding model upgrades can silently break AI retrieval systems
Upgrading embedding models can silently break retrieval systems without throwing errors. This occurs when new query vectors are generated by a different model than the one used for existing document vectors, causing the…
-
RAG systems focus on retrieval improvements and reliability testing · 8 sources tracked
Researchers are exploring advanced techniques to improve Retrieval-Augmented Generation (RAG) systems, focusing on enhancing the retrieval component which is often the bottleneck. Apple Inc. has developed a method using…
-
Enterprise GenAI Platform Architecture for On-Premises Deployment
This article outlines a reference architecture for building an enterprise-grade Generative AI platform that operates entirely on-premises. It details the necessary soft artifacts, such as MLOps modules, model serving, s…
-
Qdrant 1.20 integrates BM25 keyword ranking into vector database index
Qdrant has released version 1.20, introducing significant enhancements to its open-source vector database. This update integrates BM25 keyword ranking directly into the full-text index, eliminating the need for separate…
-
Python script converts PDFs to structured Markdown for RAG pipelines
This article presents a Python script using the Apify platform to convert PDFs into structured Markdown chunks suitable for retrieval-augmented generation (RAG) pipelines. The script addresses common issues with PDF tex…
-
Linux kernel feature to reduce AI noise reverted; home AI lab Docker guide released
A new feature intended to reduce AI and LLM-generated noise in Linux kernel 7.4 has been reverted due to an issue within the VFIO subsystem. Separately, a guide highlights five essential Docker containers for setting up…
-
LLMs gain live web search capabilities without API keys
A new method allows Large Language Models (LLMs) to access live web search results without requiring API keys for services like Google or Bing. This approach uses the Apify platform to query search engines, fetch conten…
-
Production RAG Architecture Guide: Private LLMs, Vector DBs, and Hybrid Search
This guide details the architecture for building production-ready Retrieval-Augmented Generation (RAG) systems, focusing on overcoming challenges like latency and context overflow. It emphasizes using private, sovereign…
-
5 Docker Containers Essential for a Home AI Lab
This article outlines five essential Docker containers for setting up a home AI lab. It details the function of each container, including Ollama for running models, Open WebUI for an interface, Qdrant for vector search,…
-
Enterprise LLM Gateways: Semantic Caching and Prompt Guardrails Detailed
This technical guide details the implementation of semantic caching and prompt guardrails for enterprise LLM gateways. It outlines an architecture that sits at the L7 proxy layer within Kubernetes clusters, processing i…
-
Python script generates text embeddings for Qdrant vector store
A Python script has been developed to generate text embeddings and store them in Qdrant, a vector database. This intermediate-level code is designed to process any JSON input and is suitable for applications like semant…
-
TurboQuant AI quantization adopted with key modifications by Qdrant and vLLM
The TurboQuant quantization method, designed for efficient AI model compression, is being adopted in production systems with notable modifications. Qdrant's 1.18 version incorporates the MSE variant of TurboQuant, enhan…
-
Superlinked Inference Engine leads RAG platform comparison
The article compares inference platforms for production search and retrieval-augmented generation (RAG) systems, highlighting the challenges of scaling beyond simple demos to millions of documents. It emphasizes the nee…
-
AI agent tools show risky combinations, insecure descriptions
A recent analysis of 1,384 tools across 28 popular Python MCP servers revealed significant security concerns regarding AI agent attack surfaces. The study found that tool descriptions often contain direct instructions t…
-
LocalRAG Desktop simplifies Windows AI document Q&A, dropping Docker
A new beta version of LocalRAG Desktop has been released, offering a Docker-free solution for Windows users to run a local document Q&A system. This version aims to simplify the setup process for non-technical users by …
-
WhatsApp chatbot's hidden prompts steer LLM responses, raising transparency concerns
A recent investigation revealed that WhatsApp's customer support chatbot was using hidden instructions embedded within its knowledge base to influence its responses. These instructions, often in the form of HTML comment…
-
RAG systems need evaluation gates, not just demos, argues CodebaseRAG
This article argues that Retrieval-Augmented Generation (RAG) systems require rigorous evaluation beyond simple demos. The author introduces CodebaseRAG, an open-source RAG engine designed with an evaluation gate. This …
-
AI framework streamlines Bengali theatre production planning
Researchers have developed ThetreStageAI, a retrieval-augmented generation framework designed to assist in the structured planning of Bengali theatre productions. This system utilizes a multi-view approach, maintaining …
-
Databricks outlines top AI database solutions for 2026
Databricks has released a guide detailing the top AI database solutions for 2026, emphasizing that the best choice depends on an organization's existing data stack and specific workload requirements. The guide outlines …