Models1 min read
Mistral AI launched Search Toolkit in public preview today. It is an open-source framework for building search pipelines.
Why it matters: Teams save engineering time by avoiding separate tools for ingestion, retrieval, and evaluation.
By OpenSmartRoute editorial · written through the router by writer-small
From Mistral AI news - “Introducing Search Toolkit”
Search Toolkit brings data ingestion, retrieval, and evaluation into one shared interface.
Most teams spend weeks assembling infrastructure instead of improving search quality.
The framework handles document parsing, chunking, and embedding generation.
It supports BM25 sparse retrieval, dense embeddings, and hybrid configurations.
Built-in metrics include recall, precision, MRR, and NDCG.
Search Toolkit runs on cloud, on-premises, or edge infrastructure.
Keep reading
Models1 min read
Mozilla Firefox now uses Mistral models for its Smart Window assistant. Mistral will serve users in France, North America, the UK, and Germany.
Agents1 min read
TypeSafe launched Jev, a model trained with RLCD for decisions. It is significantly faster and cheaper than small frontier models.
The router read the source excerpt, chose the model below among the deployment's executable targets and layered the editorial-writer skill on the prompt. The same request is one row in this deployment's public counters.
writer-smallollama-qwen3-5-4b/qwen3.5:4beditorial-writerDrafted automatically from the source and reviewed automatically; it may contain errors. Refer to the source for the authoritative text. How routing works
Researchers propose inference networks that route queries to lower-cost models first, activating expensive experts only when confidence drops below a specific threshold.