bobvanluijt

> The Auto API allows you to simply tell Weaviate what kind of search you want and WeaviateGraphQLGorilla formats the request under the hood.

Would be great to include inference times as well

Ooo we can help (I'm affiliated with Weaviate). You mind posting it here? https://forum.weaviate.io/

There is a paywall, but it's a nice article

> Is there some weird toxic subculture in the vector database space

(I work for Weaviate)

Unfortunately, some players in the space (who are on this list) are cheating and playing an unfair game. I guess that this comes with a rapidly growing space.

I hope we can all quickly go back to focussing on our respective communities and educating the market (together) on the awesome things one can do with vector DBs.

> despite being the first […]

This is false

> […] and most popular vector database

Based on what?

Ah - Sterling, always great. He didn't do his iconic closing speech at SXSW this year. Does anybody know why?

Demo showing Retrieval Augmented Generation (RAG) and Generative Feedback Loops (RFL) on an Airbnb dataset.

This is really cool, especially with enterprises moving to using LLMs in production. These K8s tools make a lot of sense.

Good point re: implement/apply

Very cool to see Weaviate + retrieval augmented generation in there

Will there be a video stream?

[...] mechanosensitive proteins, such as talin, scaffold each synapse, creating a meshwork of switches that together form a code, the so-called MeshCODE.

Article in nature: https://www.nature.com/articles/s41586-023-06223-0

Ooo very cool

Based on this research paper: https://arxiv.org/pdf/2307.03172.pdf

It was great fun!

* Multi-tenancy – A scalable, efficient and easy solution for use-cases with many tenants per Weaviate cluster.

* PQ + Re-scoring – Product quantization (PQ) allows for faster vector search - now at basically no cost to accuracy!

* Autocut – A new way to set a threshold - set how many groups of results to retrieve from the result set.

* Search re-ranking – Multi-stage search (& re-ranking) for better end results. Multiple re-rankers available!

* New hybrid search ranking algorithm – Additional method available for deriving hybrid search scores.

This was a fun interview, maybe others like it too.

Congrats! Very cool. I also love the collaboration with Weaviate!

Very cool!

Also, the concept of generative feedback loops is described here: https://weaviate.io/blog/generative-feedback-loops-with-llms

That depends a bit on the scale and use case specifics. But commoditized billion-scale vector search is indeed a thing. We published this for Weaviate in December last year https://weaviate.io/blog/sphere-dataset-in-weaviate

Thanks, that's nice feedback

Weaviate (https://weaviate.io) | REMOTE (US / Europe)

Weaviate is an open-source vector database. It allows you to store data objects and vector embeddings from your favorite ML-models, and scale seamlessly into billions of data objects.

* Software Engineer - Research, Algorithms, and Performance * Software Engineer - Distributed & Cloud * Software Engineer - Database * Polyglot Software Engineer (for language clients)

More: https://weaviate.io/company/careers

Ha, great question! Coincidentally, at Weaviate, we are thinking about this too! There are a few ways to do this with AirByte (https://docs.airbyte.com/integrations/destinations/weaviate/) or (potentially) with Spark (https://github.com/weaviate/spark-connector). Would love to collaborate on this; feel free to reach out over Slack or so.

This is great news! Things are moving so fast; I remember we started to help out with our team after we saw the first Weaviate pull request https://github.com/hwchase17/langchain/pull/261

Interesting - could it be the case that your use case is more suited for a library like FAISS instead of a vector DB? Would love to understand this. (I’m affiliated with Weaviate).

Faiss is awesome but note that it's an ANN library that might not be suitable for all use cases; hence vector databases exist. Two things that might be of interest: the main contributor of Faiss on the Weaviate podcast: https://youtu.be/5o1YTp1IL5o and Weaviate as vector DB itself: https://weaviate.io

We are experimenting with Weaviate Embedded so that users can embed the vector database inside their Python (notebook) or TypeScript application. This should help with prototyping, CI pipelines, etc. This request came up a few times from community members, and we are looking for feedback.