Nice, clear description of OLTP v OLAP :) Have you heard about Hydra since their launch? Curious whether you've played around with it and how that went?

yes I've met the founder actually! I have not played around with it yet though

Seems likely that the model has been trained on this (or other) riddles, which doesn't necessarily mean it's more powerful than others more generally.

There haven't been contributions to the repo in over a week. I saw a few days ago that Tecton posted to their site that they were looking for a new maintainer, but that message is gone now. Does anyone have an idea? Is this project dead?

Curious why Pinecone would invest in building their own RAG framework, esp given how quickly the space is moving. Curious how others here feel about this. Will RAG frameworks still be necessary in the same way, say ... 6 months to a year down the line?

Pinecone is in a tough spot. A huge number of database vendors are implementing vector functionality into their products, which risks the niche that Pinecone is attempting to carve out for their business. They are probably trying to gain adoption of their database by developing an open source RAG framework that leverages their database and gives companies a solution to quickly implement RAG in their specific applications.

Regarding whether RAG will still be required in the future, this is a good question. Increasing context window sizes may render this moot or much less important. However, there are still cost and performance implications of a RAG architecture for many use cases.

[Disclaimer, I work @ ClickHouse]

We agree - we currently have experimental support for JSON, but it is experimental and has some challenges. We're also working on a parallel track, to support semistructured columns (https://github.com/ClickHouse/ClickHouse/issues/54864). This is an alternative to the experimental JSON data type, that aims to address its drawbacks.

[Disclaimer: I work at ClickHouse] I see a lot of the responses here focus on the age-old ‘build v. buy’ debate.

It’s also worth considering the comparative cost of Snowflake against other saas warehouses or databases, depending on your needs. For instance, we’ve heard from users that ClickHouse Cloud can be much more cost-effective for many use cases when compared to Snowflake - real-time analytics is a great example. For those who can’t build (or run OSS themselves), this is another interesting (and important) dimension. What's great about ClickHouse is that it's open source, too :).

Vendor says their solution is cheaper than competitor solution. I'm shocked.