AITOPAI热报
ProductsMulti-source

Box 基于 Nvidia Nemotron 推出面向智能体的内容检索系统

Box taps Nvidia’s Nemotron for new agent-first content retrieval system

techcrunch@Russell Brandom
Blog/Media· 11 sources
Read the original
Why we picked it

Box 拿 Nvidia 的 Nemotron 重做了内容检索，速度快 4 倍、错误少 20%、token 省九成，做企业 Agent 的可以看看。

Box 采用 Nvidia 的 Nemotron 模型构建了一套面向智能体的企业内容检索系统。新系统回答查询的速度提升 4 倍，错误减少 20%，token 消耗降低 90%。这套系统定位为智能体优先的检索架构，让 Agent 在企业文档中定位信息时更快、更省、更准。

Image · techcrunch
Original · techcrunch

Box taps Nvidia’s Nemotron for new agent-first content retrieval system

The system can answer queries four times faster, with 20% fewer errors and 90% fewer tokens used.

#Nemotron#Box#Nvidia#RAG#智能体

Keep reading

Recent stories with the same tag or section
ModelsBuildersMulti-sourceSelected03:23
NVIDIA Nemotron 3.5 Transcribe Tops Hugging Face Trending

An open-weight 30B MoE with only ~4B active parameters makes speech-to-text with speaker diarisation and translation runnable on modest hardware, undercutting the usual cost of per-language ASR pipelines. Builders working on voice agents or meeting transcription can self-host one checkpoint instead of chaining multiple services. With 40-language coverage, it is a practical candidate for multilingual Southeast Asian speech workloads.

#NVIDIA#Nemotron#speech recognition#open-source models
Event
官方账号NVIDIA AI@NVIDIAAI11 sourcesSource
ModelsBuildersMulti-sourceSelected23:32
NVIDIA Nemotron 3.5 Transcribe speech model launches on vLLM

Day-0 vLLM support means teams can self-host a multilingual transcription model immediately instead of routing audio through paid APIs. The NVFP4 quantised weights are notable for developers running inference on NVIDIA GPUs, cutting memory costs at scale. Teams building voice agents across Southeast Asian languages can compare it with Whisper-based pipelines on their target locales.

#NVIDIA#Nemotron#vLLM#speech recognition
Event
官方账号vLLM@vllm_project11 sourcesSource