We just hit 19k messages analyzed in ONE minute with phospho! π€―
So, here at phospho, we're all about one thing: helping awesome people build awesome AI products and get them out there FAST. π
And let me tell you, things have been getting wild lately! π’
More and more of our customers (π) are leveling up from "Hey, maybe this AI thing could work" to "Holy crap, we're live and people love it!" Which means... yep, you guessed it - we needed to seriously step up our game. π’
If we religiously followed the Y Combinator motto of "Do things that don't scale" at the beginning, we now are aggressively scaling our infrastructure to always provide the experience our customers deserve. While others (I wonβt say namesβ¦) might struggle with such volumes, we just make it work. Kudos to @nicolasoulianov and @Research__Quant for the hard work! π
Personally, I am super pumped that more and more great genAI products are finally being released to everyone. And partly thanks to phospho! π
Wanna join the phospho party and supercharge your AI game? Slide into my DMs or go to phospho[dot]ai! Let's get your AI POC finally out in the wild. π¬
We are thrilled to announce our integration with @langfuse . This partnership brings together phospho's powerful text analysis capabilities with Langfuse's comprehensive LLM application development toolkit.
Learn more and try it today at phospho[dot]ai
Excited to announce self-hosted phospho on AWS, Azure & GCP! π
β Complete data ownership
β Enhanced security
β Customizable compliance
Same great features & support, now on your infrastructure. We'll handle setup!
Interested? Contact us: [email protected] or DMs
π phospho first technical paper is out! We are releasing Intent Embed, an intention embedding model for text messages!
π€π¬ Intent Embed is designed to capture and represent user intention within dense embedding vectors. Unlike traditional text embedding models that focus on semantic or syntactic aspects, Intent Embed zeroes in on the underlying user intent, making it a powerful tool for developers and machine learning engineers working on LLM-based applications.
Key highlights from our report:
β Demonstrated effectiveness in capturing user intent from complex inputs
π Superior performance compared to industry-standard models like OpenAI's text-embedding-3-small
π Generates 1536-dimensional vectors, ensuring compatibility with existing vector infrastructure
π‘ Robust to noise, typing errors and adversarial prompts
π Potential use cases include user request classification, out-of-topic exclusion, and user message analysis
π We believe Intent Embed has the potential to improve how developers and ML engineers approach user-centric applications, contributing to more effective and intuitive LLM interactions.
π€« We already use it extensively for our user intent clustering in the phospho platform. Of course, you can access it via the phospho API (link in the comments).
π° Read the full technical report below!
π Automatic clustering of user messages is now available in phospho! In just one click, cluster user messages based on their intention and topics.
Try out for free the User Intention Clustering on your own data in the phospho platform. It is as simple as importing a CSV file!
πΌ Add vision to your LLM app, with just an API call.
You can now enable your LLM app to see images with the phospho multimodal LLM API.
phospho multimodal LLM is generally available via API, as on premises deployment and directly in the platform.
Examples and link below