Enterprise RAG needs more than vectors. Hologres stores searchable text with embeddings, uses HGraph for vector retrieval, queries relationships with Cypher, and composes results with SQL. Break free from single-retrieval limits. Deliver a complete "decision evidence package" to significantly boost search efficiency in complex scenarios and elevate business decision-making. 🚀📊 #RAG# #Hologres# #MultiModalSearch#

The model is perfect for building multimodal search, retrieval, classification, and clustering applications. PS: Huge shout-out to @shadersweden for inspiring the liquid glass carousel UI! 🤗 Demo:

Tomorrow's newsletter is queued up with my take on the top stories in Search & AI including: ▪️Gemini 4 ▪️Google's latest spam update ▪️Why we need to watch Meta's Muse ▪️The new multimodal search filter in GSC ▪️What I built this week - a new OKF based chatbot that uses my cloned voice, and several other really cool things. Newsletter is email only now so if you want to get this one sign up here:

Search it. See it. Keep reasoning with it. 👀 That last part is harder than it sounds. In many search-agent setups, images retrieved along the way are not preserved in the model’s later context. As a result, a seemingly multimodal search trajectory can gradually collapse back into text-only reasoning. WeAgent-MMSearch, developed by the Weixin AI team at Tencent, is designed to keep visual evidence in the loop. With a persistent multimodal state, retrieved images remain accessible throughout the search trajectory. The agent can revisit them, cross-check visual evidence across turns, perform reverse-image searches, and reason over the retrieved images directly in subsequent reasoning and tool calls — rather than reducing everything to text. With agentic SFT followed by Failure-Aware GSPO, WeAgent-MMSearch reaches an average score of 55.97 across 8 benchmarks, up 19.22 points from baseline. We also introduce VisTarget-Bench, a human-verified benchmark of 150 tasks designed to disentangle two failure modes that standard evaluation often conflates: failing to retrieve the right visual evidence, and failing to answer correctly even after that evidence has been retrieved. Each task is paired with a held-out target image, allowing us to separately measure whether the agent retrieves the intended evidence and whether it can answer correctly once that evidence has been found. For multimodal search, finding the evidence is only the beginning. More on WeAgent-MMSearch:

Today we're launching Agent Bucket: native storage for AI agents at scale. Standard S3 API, so you spin up independent space for billions of agents with tools you already know. Object storage was not built for agents. One bucket each hits limits fast. One shared bucket pushes isolation into your app code. So we rebuilt the foundation. → Independent space at scale. Each agent gets its own Space, with dedicated credentials, quota, and rate limits. Isolation becomes a system capability, not app code. → File management out of the box. Dedup, POSIX semantics, multimodal search, sharing links, recycle bin, content moderation. All at the storage layer. → Fast and low cost. GooseFS acceleration keeps hot data close to compute, with hot and cold tiering to balance speed against cost. → Proven at scale. Already running inside Tencent's own agents WorkBuddy, QClaw, and across external use cases such as Asus AI-PC drives, connected cars.