Mesolitica’s Post

OpenAI announcements today, fresh from the oven! Got two from my wish list! (realtime API and prompt caching) Realtime API: OpenAI introduced a public beta of its Realtime API, enabling developers to create low-latency, speech-to-speech applications using AI-generated voices. Vision Fine-tuning: Developers can now fine-tune GPT-4 models using images, improving tasks involving visual understanding. Model Distillation: New feature allows developers to fine-tune smaller models like GPT-4o mini using larger models, saving costs. Prompt Caching: This feature reduces API costs by 50%, allowing developers to cache frequently used context between calls

📢 OpenAI just launched their most powerful embedding models yet - 𝐭𝐞𝐱𝐭-𝐞𝐦𝐛𝐞𝐝𝐝𝐢𝐧𝐠-3-𝐬𝐦𝐚𝐥𝐥 and 𝐭𝐞𝐱𝐭-𝐞𝐦𝐛𝐞𝐝𝐝𝐢𝐧𝐠-3-𝐥𝐚𝐫𝐠𝐞. 🚀 Discover what's new: https://lnkd.in/dSvkm5WD Qdrant makes it super easy to start implementing the new #OpenAI V3 Embeddings in your applications. Here's how to get started: https://lnkd.in/dUf8-FHr

Recent Updates from OpenAI dev Day, Real time Voice API looks interesting so far, let's see how actually it turns out to be. #openai #devday

Still at super early stage but this seems to be promising and interesting. By leveraging function call features of OpenAI API, we can create an interactive chat with our internal system data without having to worry about the data security issues as we have total control over what data we want to provide to the model

OpenAI o1 is here … Today I’ve seen the preview launch of OpenAI's latest release, OpenAI o1, and can’t wait to play with it more. What's New in OpenAI o1 compared to 4o (spoiler alert … it isn’t a better naming convention) … 🚀 Speedier performance … Quicker responses but there’s action descriptions now to show you what it’s doing while processing your command 🧠 Smarter language understanding … More natural interactions, yet to see if this has a significant improvement to the voice conversation experience 🎨 Enhanced creativity … Generates innovative ideas to inspire and assist. I hope this is good because charting and image generation on the previous version was 💩 🔧 Greater customisation … Tailors to our specific needs for a more personalised experience. Not sure how this interacts with the new memory features but I’m hoping it at least more reliably maintains context through longer conversations and thought development 🔒 Improved security … Stronger protection to keep our data safe I believe human & machine co-creation is just getting started. This should be a nice little level-up … and with Elon having just launched a 100k GPU data centre in 122 days for Grok training the competition is hotting up!

OpenAI Dev Day recap! (Speech to Speech API finally released) Denys Linkov and I went through the OpenAI Dev Day releases yesterday and explain what each of them are and how they impact you. 1. Realtime API: This is the official release of openAI's speech to speech model that allows you to stream speech or text (and later video) to OpenAIs API and receive responses back in realtime. We spent most of the video talking about this as it'll have a big impact on democratizing access to high quality voice agents. 2. Prompt Caching on the API: Useful if you're doing a high volume - it caches larger responses and saves them for a 5-10 minute period but has a reduce cost for use. 3. Finetuning the Vision Model: Being able to fine tune their vision models with your own data set. 4. Model distillation - which allows you to fine tune a smaller model with the outputs from a larger more expensive model. I'll send over the full video after its uploaded :)

The greatest option for implementing LLM-based applications is and will always be OpenAI. However, we might not be able to use it due to problems like #openAI Error 429 - Quota issue. Let's look at the straightforward and basic #AI21Labs substitute as a solution with -

OpenAI's Swarm Web Extractor This can autonomously search the web, map entire websites, and extract data. This is built on top of OpenAI’s new multi-agent framework Swarm, Serp AI and Firecrawl API. - Swarm is a lightweight and experimental framework introduced by OpenAI to develop multi-agent systems. - SerpApi is a real-time API that allows users to access Google search results. - Firecrawl API turns entire websites into clean, LLM-ready markdown or structured data. Scrape, crawl and extract the web with a single API. Video credits: Eric Ciarla #webextraction #llms #nlproc #swarm #multiagents

In this article, we will explore how the combination of OpenAI LangChain and Streamlit provides a robust and accessible platform for automated generation of research article summaries. Utilizing the refinement technique with custom prompts, this application offers an efficient and accurate way to condense complex information into concise and readable summaries. (Code included)

This blog shows you how to set up LLM observability using OpenTelemetry for managed LLMs, like OpenAI to collect, debug, and optimize your application in production.