tomhamer
Re:Celeris-1: A diffusion LLM benchmarked at 2,082 output tokens/s
on Wednesday August 05, 2026 @11:07AM (#49184027)
Tom here, CEO at Celeris. I'll be around all morning. Ask me anything about the model, diffusion LMs, or the numbers.
Re:Nixiesearch: Running Lucene over S3, and why we're building a new s...
on Thursday October 10, 2024 @08:30PM (#41804964)
I might be missing something but how is this different to amazon opensearch with ultrawarm storage? I think amazon launched this about 4 years ago right?
Re:Vector Search with OpenAI Embeddings: Lucene Is All You Need
on Sunday September 03, 2023 @10:21PM (#37376550)
Marqo lets you use state of the art e5 embeddings (which are significantly more performant in retrieval than the openai embeddings), and will handle the embedding generation and retrieval on lucene indexes: https://www.marqo.ai/
It's also available opensource: https://github.com/marqo-ai/marqo
Re:Vector databases: analyzing the trade-offs
on Monday August 21, 2023 @04:59AM (#37206970)
marqo.ai has excellent indexing throughput as vector generation and vector retrieval are both contained within a marqo cluster. You can use it with multi-gpu, cpu, etc. It's also horizontally scalable.
Re:Vector databases: analyzing the trade-offs
on Sunday August 20, 2023 @11:07PM (#37205045)
Just to quickly add to ukuina's comment, marqo.ai does embedding generation and vector search end to end, so you can put in documents and the embeddings are automatically generated.
Re:Vector databases: analyzing the trade-offs
on Sunday August 20, 2023 @08:19PM (#37204203)
Marqo is an end-to-end vector search engine that handles both embedding creation and retrieval: https://github.com/marqo-ai/marqo
Re:The fully bootstrapped and vector search engine
on Friday July 21, 2023 @01:24AM (#36810293)
Just adding here that if you want a vector DB that handles inference for you too, you can try Marqo https://github.com/marqo-ai/marqo
Re:Ask HN: Seeking advice on open source end user distributed vector d...
on Sunday July 16, 2023 @08:07PM (#36752665)
Marqo will generate embeddings for you as well as run on a mac/in the cloud. https://github.com/marqo-ai/marqo
Re:AI for AWS Documentation
on Thursday July 06, 2023 @10:26PM (#36626270)
Marqo provides automatic, configurable chunking (for example with overlap) and can allow you to bring your own model or choose from a wide range of opensource models. I think e5-large would be a good one to try. https://github.com/marqo-ai/marqo
Re:Ask HN: Can someone ELI5 Transformers and the “Attention is all we ...
on Saturday May 20, 2023 @05:10AM (#36010421)
Disclaimer - someone from Marqo here.
Marqo supports E5 models: https://github.com/marqo-ai/marqo
Re:Kdb.ai Vector Database
on Saturday May 20, 2023 @05:05AM (#36010407)
Someone from Marqo here - if you're looking for an end-to-end vector search DB that handles vector search and transformation you should check out marqo. https://github.com/marqo-ai/marqo
Re:Ask HN: Seeking a Vector Database for ClickHouse Users – Suggestion...
on Thursday April 20, 2023 @05:41AM (#35637954)
You should check out https://github.com/marqo-ai/marqo for an end-to-end vector search database with batteries included.
Disclaimer, I'm from the Marqo team.
Re:Show HN: Summaries and Q&A for dense financial disclosures
on Wednesday March 01, 2023 @12:08AM (#34978997)
Sounds great! Lets connect on linkedin? https://www.linkedin.com/in/tom-hamer-%F0%9F%A6%9B-04a6369b/
Re:Beating OpenAI CLIP with 100x less data and compute
on Tuesday February 28, 2023 @06:54PM (#34976666)
UKV looks really cool. At Marqo.ai we are achieving end-to-end semantic search building on top of existing embedding search functionality, keen to take a closer look at what you are doing. Seeing UKV come out on the cloud serverless will be super interesting - it's something thats taken us a while for us to work out.
Re:Show HN: Summaries and Q&A for dense financial disclosures
on Tuesday February 28, 2023 @06:49PM (#34976637)
This is really cool - would be awesome to connect at some point. I co-founded Marqo which also enables this through providing the semantic search component of this workflow. We've found some interesting results combining it with LLMs. https://www.marqo.ai/blog/from-iron-manual-to-ironman-augmen...