search

Qdrant Tests How Far EmbeddingGemma 2 Vectors Can Be Shrunk
Qdrant says quantized full-size EmbeddingGemma 2 vectors kept 99% of their retrieval quality while using 30x less vector RAM. The vector database company tested Google's…

Firecrawl Alexandria adds fantasy football data for AI agents
Firecrawl has made fantasy football data available in Firecrawl Alexandria, so AI agents can read a user's league, pull projections from six expert sources and recommend…

Google launches EmbeddingGemma 2, a multimodal embedding model for on-device search
Google DeepMind has launched EmbeddingGemma 2, an open-weight multimodal embedding model that maps text, images, video frames and audio into a single vector space.…

Appspace Named a Leader in 2026 Gartner Magic Quadrant for Intranet Packaged Solutions
Appspace, the workplace experience company, has been named a Leader in the 2026 Gartner Magic Quadrant for Intranet Packaged Solutions. According to the company, it is…

AWS shows how to train a search agent with multi-turn RL on SageMaker AI
AWS has published a walkthrough of how to fine-tune a search agent with Amazon SageMaker AI multi-turn reinforcement learning (MTRL). The post describes training a…

Cloudflare adds Web Search API to AI Gateway with three launch partners
Cloudflare has launched a Web Search API inside its AI Gateway, letting AI agents pull live information from the web instead of guessing URLs. The launch partners are…

Databricks details a real-time recommendation stack for fashion e-commerce
Databricks has published a reference architecture for a multi-stage e-commerce recommendation engine that runs entirely on its platform, from clickstream ingestion to…

Hebbia launches Headless Hebbia, an API and MCP server for firm knowledge
Hebbia has introduced Headless Hebbia, an API and MCP server that bring the company's retrieval, orchestration and analysis into custom applications built with customers…

Cloudflare: More Than Half of Internet Traffic Is Now Not Human
More than half of Internet traffic is no longer human, according to Cloudflare, which says AI agents have become a second audience for the web. The company is pairing…

Cohere launches Embed 5 with Pro and Fast tiers for enterprise retrieval
Cohere has released Embed 5, a new family of embedding models for enterprise search, RAG and agentic workflows. The family has two tiers, Embed 5 Pro for maximum quality…

Vigil wins Elastic's Forge the Future Hackathon 2026 in India
Vigil, a compliance auditing system for sales calls built by Team Frustrated Engineers, won the Forge the Future Hackathon 2026, according to Elastic. The winners were…

turbopuffer v3 drops the vector index as its primary index
turbopuffer is moving to a new storage architecture, v3, in which the ANN vector index is no longer the primary index but "just another" secondary index. According to…

Vercel AI Gateway adds Browserbase Search and Fetch tools for web access
Vercel has added Browserbase Search and Fetch to AI Gateway, letting developers give their models access to current web information and page contents. According to…

Meta's Forum App Adds AI-Powered Ask Tools and a New Member Role for Facebook Groups
Meta is adding new features to Forum, a standalone app it is exploring for people who want to go deeper on Facebook Groups. The updates include a new role for top…

Condé Nast cuts video search from 250 minutes to under 2 with Amazon Bedrock
Condé Nast has reduced the time its editors spend finding video clips from an average of 250 minutes per task to under 2 minutes, according to AWS. The publisher built…

Firecrawl Alexandria brings 100+ data providers into ChatGPT and Codex
Firecrawl Alexandria is now available inside the Firecrawl plugin for ChatGPT, giving ChatGPT and Codex access to more than 100 data providers and Firecrawl's own…

turbopuffer adds native embedding to cut semantic search latency
turbopuffer has launched native embedding, letting customers hand the embedding step to the search engine instead of running their own pipeline. According to the…

LangSmith adds Engine v2, Managed Deep Agents 0.8 and fine-tuning
LangChain has released a broad LangSmith update at Interrupt NYC, including Engine v2 with red teaming and automated fix validation, Managed Deep Agents v0.8…

Cohere launches Compass Cloud, a managed retrieval platform, in private beta
Cohere has opened a private beta of Compass Cloud, a managed version of its Compass retrieval platform for developers building AI applications on enterprise data. The…