AssemblyAI’s Post

“The advent of open-source large language models like #Llama and #Mixtral demands innovative deployment strategies for efficiency and cost-effectiveness. We will explore adaptive workload management for infrastructure optimization, crucial for handling varying demands efficiently.” At Systems @Scale on June 12, Jiaxin Cao shared his insight on scalable solutions for running large language models. To see his full talk, or past @Scale content, visit https://lnkd.in/ghezNnaP

it can help you to read and understand code written by others :)

https://lnkd.in/gJvaU-W2 In this episode of "Ask the Experts," Shawn Gordon and Chang She dive into the details of data versioning and time travel using the LanceDB vector database. They offer thorough explanations and demonstrate how it works in practical scenarios. 👉 Checkout Discovery Playlist for more interesting topics https://lnkd.in/gqYpZfY8 #vectordatabase #vectordb #datalake #dataengineering #ai #aiengineering

🗣️ Unlock the full potential of your recordings with LLMs and Speaker Diarization! 🤝 Learn how to use AssemblyAI and #Haystack together to enhance your RAG application by detecting multiple speakers in audio recordings, and providing a transcript that attributes each utterance to the speaker. 📚 Read more in this post: https://lnkd.in/eXGMTQEY 🧑🍳 Build a RAG application with speaker labels: https://lnkd.in/gq8zfdbU 🧩 AssemblyAI x Haystack Integration: https://lnkd.in/gcMgfntf #opensource #llm #rag #multimodality

BNSN just changed the game! Want your text more conversational? Or how about power-packed? Swipe and see the magic. Text transformation is here! What would you enhance in your messages?

Very much in the Redactive lane tldr; [the focus is on automating processes, reducing manual steps in workflows, and improving overall cost containment at scale], Clyde Fernandez and Matt Hallam, let's take a look.

There's still time to sign up for our free webinar next week! We're convinced that AI is a significant productivity enhancer for developers and we want to share our knowledge with you. The material is appropriate for devs or dev managers. Link in the comments!

This is truly a remarkable tool. The first time I used it, it reminded me of the first time I ran a Docker container. It pulls the model and exposes an inference point right out of the box. Also, it has great integration with LangChain. Really amazing! #langchain #llms #ai https://ollama.ai/

Running Inference on Edge just got a little bit easier. Check it out if you are or considering running an LLM on an edge device (Mobile, Desktop, IoT, etc)

ExecuTorch Alpha is here and it's bringing more AI #onArm! 🙌   Large language models already run on Arm CPUs, but with the release of ExecuTorch Alpha from PyTorch, developers now have additional support to ensure optimal performance of LLMs on the CPU alongside delegation to GPU and NPU.   See how you can get started with Meta’s Llama 2, 3 and other broad models in the link below.