Michael Seibel

Unify - The best LLM on every prompt

byโ€ข
Unify dynamically routes each prompt to the best LLM and provider so you can balance cost, latency, and output quality with ease. Sign up now and get $100 free credits.

Add a comment

Replies

Best
Daniel Lenton
Maker
๐Ÿ“Œ
Hey Everyone ๐Ÿ‘‹ Super excited to be launching today! ๐Ÿ˜ So, why did we build this? As a team of engineers, we faced tons of problems trying to build efficient and effective LLM applications. With new models and providers constantly coming onto the scene, it's overwhelming and very hard to keep up. So, what does Unify bring to the table? โš–๏ธImpartiality: We treat all models and providers equally, as we don't have a horse in the race. You can trust our quality, cost and speed benchmarks. โš™๏ธControl: Choose which models and providers you want to route to and then adjust three sliders: quality, cost, and latency. That's it; now the performance of your LLM app is fully in your hands, not the providers! ๐Ÿ“ˆ Self Improvement: As each new model and provider comes onto the scene, sit back and watch your LLM application automatically improve over time. We quickly add support for the latest and greatest, ensuring your custom cost-quality-speed requirements are always fully optimized. ๐Ÿง‘โ€๐Ÿ’ป Focus: Don't stress updating the model and provider every few weeks. Just specify your performance needs and get back to building great AI products. We'll handle the rest for you! ๐Ÿ“Š Observability: Don't want to route? No sweat. Quickly compare all models and providers, and see which are truly the best for your own needs, on your own prompts, for your own task. ๐Ÿ”‘ Convenience: The power of all models and providers behind a single endpoint, queryable individually or via the router, all with a single API key. pip install unifyai, and away you go! I'm super excited to hear what you think; I'm all ears for comments, feedback and especially criticisms. Thanks so much for your support, and you're very welcome to follow us on our journey as we strive to help unify AI ๐Ÿ”ฅ
Aris Nakos
@dan_lenton So this is a 'semi-automated' chat.lmsys.org for setting your ELO for your data, essentially? Looks nice. Glad to see you have a LangChain integration.
Daniel Lenton
Thanks so much @shivam_tiwari24! ๐Ÿ˜Š
Daniel Lenton
Hey @aris_nakos, yep that's one way of thinking about it! We use GPT4-as-a-judge which is a bit different to the ELO score, but the concept is definitely similar :)
Khethan RG
@dan_lenton congratulations ๐ŸŽ‰. When is the mobile version coming?
Daniel Lenton
Thanks @khethan_rg! You mean for the chat interface? It's on our roadmap, shouldn't be more than a couple of weeks!
Sheikh Irfan
Hey @founder_daksh congrats on the launch! ๐Ÿฅณ What could be the USP of your product which makes it different from another?? keep going.
Daniel Lenton
Great question @sheikhirfan10, one difference between us and other routers is that you can train your own custom router, as explained here: https://youtu.be/15wgxK1Cw0E
Sheikh Irfan
@dan_lenton Very Well. Go Big.
Daniel Lenton
Thanks @sheikhirfan10! We'll try ๐Ÿ˜
Soumik mahato
Congratulations ๐ŸŽ‰ Daniel on the launch
Daniel Lenton
Thanks a lot @soumikmahato!
Bankaido
Seem like a great project that will also help AI industry. I'll support for this launch.
Daniel Lenton
Thanks @bankaido! :)
Natalie Ermishina
It is a big big and important part to create the right prompt, esp if you have cost limits. The app sounds like a solution for solopreneurs like me :) Wish you luck guys and definitely want test 'Unify'
Daniel Lenton
Thanks @natalie_ermishina! Let us know how you find it! Feel free to hop on a call with us if you have any questions :)
Vรญtor Soares
Congratulations on the launch! ๐ŸŽ‰ Unify appears to be a robust remedy for navigating the intricate territory of LLM applications. The unbiased criteria, adaptable routing based on excellence, expense, and time lagging as well as automated upgrade towards modern models are all revolutionary advancements for developers. Moreover, the ease of having a solitary endpoint and API key amplifies simplicity even more. I am thrilled about witnessing how Unify will simplify and escalate AI development! ๐Ÿš€
Daniel Lenton
Thanks so much for the really kind words @vitor_pvsoares!
Moon
Exciting launch with Unify! Impartial routing, control over quality, cost, and latency plus automated improvements make it a game-changer for LLM applications. Kudos on simplifying the complex world of AI models!
Daniel Lenton
Thanks a lot @moon10! โค๏ธ
Binay Singh
Seems very powerful :) Congrats :)
Daniel Lenton
Thanks so much @binay_singh2!
Benjamin Sloutsky
Seems like a cool product with great research and data. Congrats on the launch!
Daniel Lenton
Thanks so much @benjamin_sloutsky! ๐Ÿ˜Š
Veit Josef Schneider
Congrats on the launch! Is there a specific location where I can enter the code to get the free credits? :)
123
Next
Last