Built a new Python lib to make chatbots steerable, make agentic RAG (and tool use) superfast, and provide safety guardrails:. Videos coming soon. #ArtificialIntelligence #GenAI #LLMs.

Semantic Router v0.1.10 is out — this release is focused on expanding async support for QdrantIndex, PostgresIndex, and HybridRouter, alongside many synchronization / testing improvements:. - Brought QdrantIndex async methods inline with our other indexes.- Added async methods to.

I'm considering deprecating dynamic routes in semantic router — we briefly used dynamic routes when LLMs were not too strong as decision makes for tool use and the grammar restriction was incredibly helpful for local LLM use. We've since moved on from this. For a long time.

Semantic router v0.1.9 has just been released!. v0.1.9 focused on alignment between various index types and broadening async support, including:. - Full async support for `PostgresIndex`.- A new @NVIDIAAI NIM encoder.- Improved async support for @pinecone.

RT @tbpn: "You can break AI down into 5 tiers." - @realGeorgeHotz. "Data centers - tier 1, fabs - tier 2, Nvidia/AMD - tier 3, OpenAI/Anthr….

RT @LysandreJik: I have bittersweet news to share. Yesterday we merged a PR deprecating TensorFlow and Flax support in transformers. Goin….

RT @budududuroiu: I'm gloating that our bare metal servers that cost us 4% of what we were paying on GCP (for same CPU cores & memory) were….

@NVIDIAAI Links.📌 NeMo Microservices: 🚢 Deploying NeMo Code: 👾 LoRA Fine-tuning Code:

Releasing this comprehensive mini-course on fine-tuning LLMs with LoRA using @NVIDIAAI's NeMo Microservices. We cover a ton on building prod AI applications, including:. - LoRA fine-tuning of Llama 3.2 1B.- Deploying private AI agent systems.- Using NVIDIA NIMs to host our

RT @sophiamyang: Announcing @MistralAI Small 3.1: multimodal, multilingual, Apache 2.0, the best model in its weight class. 💻 Lightweight:….

RT @DigitalEU: ⚡️ Six additional proposals to establish AI Factories in the EU powered by EU’s world-class network of supercomputers. Toge….

First look at @OpenAI 's new agent framework - Agents SDK. Includes hands-on walkthrough for:.- agents & runners.- tools (now called tool_functions. ).- async & streaming.- guardrails.- chat memory

RT @joakial_:

RT @villigm: Estonia is the first country in the world to launch AI into schools with @OpenAI and @AnthropicAI. It's been great to see th….

Master LangChain! This 5 hour course teaches how to build agentic systems, AI observability with LangSmith, prompting, memory, streaming, LCEL and more — all with v0.3. Full AI app capstone project included! 🚀.

RT @euacchq: Happy to see the word simplification proudly displayed by @EU_Commission . Now, we urge @vonderleyen ‘s team to increase 10x t….

RT @euacchq: @EU_Commission It has to be way way more ambitious. From cross European investmemt processes to compete with US Delaware, to….

RT @andreasklinger: EU-Inc is now even mentioned by the World Economic Forum newssite. 🔥. First impossible, then inevitable. Less whining.….

RT @solomonstre: Just like we containerized webapps, we'll have to containerize AI agents. but how? What first principles led to containe….

First look at the new features for @pinecone assistant:.