Bring AI to your database! Integrate AI models and workflows with your database to implement custom AI applications, without moving your data. Including streaming inference, scalable model hosting, training and vector search. By transforming the database into the central AI platform, Superduper consolidates enterprise AI, instead of being spread across systems and environments. This eliminates ETL-pipelines, data migration and unnecessary complexity from the AI/MLOps stack.

Hi everyone! I am Timo, co-founder of SuperDuperDB. Here are are some key information about SuperDuperDB. We are keen to hear your feedback and would greatly appreciate it if you could help us spread the word by sharing with anyone that could be interested. SuperDuperDB is an open-source framework for integrating AI directly with your existing databases, including streaming inference, scalable model training, and vector search. SuperDuperDB is not a database. It transforms your favorite database into an AI development and deployment environment (𝘮𝘢𝘬𝘪𝘯𝘨 𝘪𝘵 𝘴𝘶𝘱𝘦𝘳-𝘥𝘶𝘱𝘦𝘳). SuperDuperDB eliminates complex MLOps pipelines, specialized vector databases - and the need to migrate and duplicate data by integrating AI at the data's source, directly on top of your existing data infrastructure. This massively simplifies building and managing AI applications. Currently Supported AI: Any model from PyTorch, Sklearn, HuggingFace as well as AI APIs such as OpenAI, Anthrophic, Cohere. Today’s release comes with the full integration of major SQL databases as well as further MongoDB support: PostgreSQL, MySQL, SQLite, DuckDB, Snowflake, BigQuery, ClickHouse, DataFusion, Druid, Impala, MSSQL, Oracle, pandas, Polars, PySpark, and Trino. 𝗦𝘂𝗽𝗲𝗿𝗗𝘂𝗽𝗲𝗿𝗗𝗕 𝗶𝘀 𝗼𝗽𝗲𝗻-𝘀𝗼𝘂𝗿𝗰𝗲. 𝗟𝗲𝗮𝘃𝗲 𝗮 𝘀𝘁𝗮𝗿 𝗼𝗻 𝗚𝗶𝘁𝗛𝘂𝗯: https://github.com/SuperDuperDB/... ⭐ 📣 𝗛𝗲𝗹𝗽 𝘂𝘀 𝘀𝗽𝗿𝗲𝗮𝗱 𝘁𝗵𝗲 𝘄𝗼𝗿𝗱 𝗮𝗻𝗱 𝘄𝗶𝗻 𝘀𝘄𝗮𝗴 𝗯𝘆 𝗿𝗲𝗽𝗼𝘀𝘁𝗶𝗻𝗴 𝘁𝗵𝗶𝘀 𝗽𝗼𝘀𝘁 https://www.linkedin.com/posts/s... 𝗮𝗻𝗱 𝘁𝗮𝗴𝗴𝗶𝗻𝗴 𝗮𝗻𝘆𝗼𝗻𝗲 𝘄𝗵𝗼 𝗰𝗼𝘂𝗹𝗱 𝗯𝗲 𝗶𝗻𝘁𝗲𝗿𝗲𝘀𝘁𝗲𝗱 𝗶𝗻 𝗦𝘂𝗽𝗲𝗿𝗗𝘂𝗽𝗲𝗿𝗗𝗕 (check the first comment for details). Check the uses cases that we have already implemented here 🔗 https://docs.superduperdb.com/do... as well as apps built by the community here 🔗 https://github.com/SuperDuperDB/... and try all of them with Jupyter your browser 🚀 https://demo.superduperdb.com/ For more information about SuperDuperDB and why we believe it is much needed, read the blog post 👉 https://docs.superduperdb.com/bl...

@tmhh 🚀🚀🚀🤞

If you want to build AI apps fast and want to save money while building AI apps -You should pay attention to SuperDuperDB! Say for example: You can build a RAG app and make an API in like 30 minutes. You can build a chatbot and make it live in no time. See here: You can use it with anything like FastAPI and build an API with it. You can build a chat your database thing. And most importantly you don't need a vector database as well. You can use your MongoDB as your Vector Database! **This is how you can build quickly and cost-effectively without the need for a complex pipeline!** 1. *Build AI apps fast*: For example, you can create a RAG app and make a FastAPI API in just 30 minutes, or build a chatbot and make it live in no time. [Follow this notebook](https://github.com/SuperDuperDB/...) and follow this [FastAPI codebase](https://github.com/SuperDuperDB/...) The beauty of SuperDuperDB is, that once you learn its APIs, you can build AI apps very very fast. Make it production-ready in no time. 2. *Integrate with existing tools*: SuperDuperDB is compatible with various ML frameworks and APIs, such as PyTorch, Sklearn, HuggingFace, and OpenAI. We have first class support for Cohere, Anthropic and OpenAI. 3. *Create custom AI applications*: You can build a chatbot, a database with AI integration, or any other AI app you can imagine. You can build a thousand things. Your imagination is your limit here. 4. *Extreme cost efficiency by efficiently managing data*: SuperDuperDB eliminates the need for data duplication and migration to different environments, simplifying data management and security. It saves you a lot of bucks. For example, to create a chatbot we didn't use an external vector database there. Which saves a lot of money for you. To get started with SuperDuperDB, you can refer to the documentation or explore [example](https://github.com/SuperDuperDB/...) repository for examples and tutorials.

Im sure SuperDuperDB will be a helpful tool for data scientist and ml engineers to integrate AI directly into their databases