News for hackers. Stuff that matters.

fnikol

Re: on Monday December 11, 2023 @08:35AM (#38600493)
We are excited to announce that hashtag#SuperDuperDB is now an official technology partner of MongoDB: https://lnkd.in/eXHwHMvD

At the core of our partnership is the belief that the fusion of data and AI within a single platform is the key to simplifying AI development and adoption.

This alliance highlights our mutual dedication to empowering developers with state-of-the-art tools to build AI (into their) applications more efficiently.

Just the other day we had a workshop in which we demonstrated how to easily build and manage RAG chat applications on MongoDB with SuperDuperDB. Check it out on our YouTube channel: https://lnkd.in/emEdyec7

hashtag#DataScience hashtag#AI hashtag#MachineLearning hashtag#Innovation hashtag#TechNews hashtag#MongoDB

Re:We are trending on #3 globally on GitHub (yesterday #9) on Friday December 08, 2023 @10:06AM (#38569877)
We are very happy that other developers also see the pain points of complex ETL and MLOps pipelines, specialized vector databases, and want to get rid of the need to move your data all over the place when building AI applications.

A big thank you to the community for the massive support!

Indeed both frameworks support model chaining.

However, achieving goals like "training your LLM" or enabling "real-time inference" requires more than just pipelines. For that, we have invested in enhancing compatibility with databases and facilitating parallel computing.

About your last point, I 'm not sure I fully understand. Do you mean to write a guide for moving lang-chain models to superduper? Or to create superduper wrappers for langchain ? Or to move the core functionalities of superduper to langchain ?

The guide, is something have in our immediate plans. The wrappers are under discussion. The latter I don't think it's possible due to architectural differences. For example, superduper is designed with multi-node environments in mind.

All things aside, it's a framework for building data workflows in Python.

Like taking the data from that source (e.g., SQL), processing them (e.g., pytorch or openai), and storing the results somewhere (e.g., data on Mongo metadata on SQL).

It actually consists of the following: 1. nifty abstractions for Data (e.g., sources, encoders, listeners), Metadata (e.g., vector indexes), Compute (e.g., sync, async, parallel). 2. gluing engine that transparently handles the interaction between components 3. out-of-the-box integrations with established tools (databases, AI models and APIs, compute engines)

This way, you can build customized data layers that sit on top of your database and save you from moving the data to dedicated systems (e.g., vector databases or MLops tools)

For further discussion, feel free to join our slack https://join.slack.com/t/superduperdb/shared_invite/zt-1zuoj...