Top all-time · #6742
Marqo
Company blog · marqo.ai/blogaidata
Marqo is the company blog at marqo.ai, writing about ai and data. Since 2023, 12 different Hacker News readers have linked it 34 times, most often “AI Search That Understands the Way Your Customer's Think”. No feed was found, so read it on the site itself.
Too few sampled comments (11) to say how often HN recommends it.?
Why HN links it
Marqo's blog posts cover embedding models, contrastive learning for search, RAG retrieval and multimodal search. HN commenters cite them as support for their own points, mostly while mentioning Marqo's open-source search engine.
Summarised by Claude from a sample of 11 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
AI-native search, recommendations, and merchandising trained on your catalog. Marqo delivers $130M+ in proven revenue for enterprise retailers.
Most-linked posts?
- AI Search That Understands the Way Your Customer's Think4 people · 4 mentions · first linked 2023-09-04
- From “iron manual” to “Iron Man” – augmenting GPT with a fast editable memory3 people · 3 mentions · first linked 2023-02-08
- Generalizing Open AI's Clip: Generalized Contrastive Learning2 people · 3 mentions · first linked 2024-06-05
What Hacker News says?
Yup, and you can train these in-domain contextual relationships into the embedding models. https://www.marqo.ai/blog/generalized-contrastive-learning-f...
Comment linking /blog/generalized-contrastive-learning-for-multi-modal-retrieval-and-ranking
on “Show HN: Wordllama – Things you can do with the token embeddings of an LLM”Submitted Binarize CLIP for Multimodal Applications as a story · 38 points
HN discussionYou can also train query awareness into the embedding model. This avoids LLMs rewriting questions poorly and lets you embed questions the way your customers actually ask them. For an example with multimodal: https://www.marqo.ai/blog/generalized-contrastive-learning-f... But the same approach works with text.
Comment linking /blog/generalized-contrastive-learning-for-multi-modal-retrieval-and-ranking
on “Solving the out-of-context chunk problem for RAG”Submitted Matryoshka Representation Learning with CLIP as a story · 31 points
HN discussionMarqo.ai | Senior Engineer | Hybrid (Melbourne) | Full-Time | https://marqo.ai At Marqo we’re building an open-source search engine that thinks like humans. Marqo's open-source tensor search engine uses machine learning models for search, improving relevance, and providing solutions to problems that were previously difficult or impossible to solve. We are growing and looking for a senior engineer to spearhead the de…
Comment linking /
on “Ask HN: Who is hiring? (March 2023)”Submitted New Marqo Ecommerce Models Outperform Amazon by Up to 88% as a story · 5 points
HN discussionMarqo 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
Comment linking /
on “Vector Search with OpenAI Embeddings: Lucene Is All You Need”Submitted HNSW Under Real-World Scenarios – Explored as a story · 5 points
HN discussionMarqo does: https://www.marqo.ai/
Comment linking /
on “Pinecone integrates AI inferencing with vector database”Submitted How to Create Hugging Face Spaces Demos – A Beginner's Guide as a story · 4 points
HN discussionIt will depend on the type of data you are using, and then what you are planning on doing with it. Various open source models will take various modalities (e.g. images of models), and will create an embedding/vector for them (even if just as an internal representation). You can take these, and store them in a vector DB. This may help https://www.marqo.ai/blog/how-to-implement-text-to-image-sea...
Comment linking /blog/how-to-implement-text-to-image-search-on-marqo-in-5-lines-of-code
on “Faiss: A library for efficient similarity search”Submitted Fine-Tuning Embedding Models Course as a story · 4 points
HN discussionJust a heads-up: I'm having trouble loading the website as linked here without `www.`, but https://www.marqo.ai as linked on the GitHub repo works fine.
Comment linking /
on “Ask HN: Who is hiring? (April 2023)”Submitted Getting Started with Google Colab (Run Python in the Browser) as a story · 4 points
HN discussionMarqo.ai | Senior Engineer | Hybrid (Melbourne) | Full-Time | https://marqo.ai At Marqo we’re building an open-source search engine that thinks like humans. Marqo's open-source tensor search engine uses machine learning models for search, improving relevance, and providing solutions to problems that were previously difficult or impossible to solve. We are growing and looking for a senior engineer to spearhead the de…
Comment linking /
on “Ask HN: Who is hiring? (April 2023)”Submitted How to Fine-Tune and Deploy Embedding Models as a story · 3 points
HN discussionI have a hosted code-first agent builder platform in production, so I respond these question a lot from our customers. 1. Probably the best is fly.io IMHO. It has a nice balance between running ephemeral containers that can support long running tasks, and quickly booting up to respond to a tool call. [1] 2. If your task is truly long running, (I'm thinking several minutes), probably wise to put trigger [2] or tempor…
Comment linking /
on “Ask HN: What's your serverless stack for AI/LLM apps in production?”Submitted Multimodal Models for Search and Recommendations in Fashion as a story · 3 points
HN discussionThis 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...
Comment linking /blog/from-iron-manual-to-ironman-augmenting-gpt-with-marqo-for-fast-editable-memory-to-enable-context-aware-question-answering
on “Show HN: Summaries and Q&A for dense financial disclosures”Submitted A Guide to Fine-Tuning Clip Models as a story · 3 points
HN discussionPretty similar open source project here: https://www.marqo.ai/blog/from-iron-manual-to-ironman-augmen...
Comment linking /blog/from-iron-manual-to-ironman-augmenting-gpt-with-marqo-for-fast-editable-memory-to-enable-context-aware-question-answering
on “ChatPDF – Chat with Any PDF”Submitted Generalizing Open AI's Clip: Generalized Contrastive Learning as a story · 3 points
HN discussionSubmitted Legacy Ecommerce Search Is Dead, and It's Costing You Sales as a story · 2 points
HN discussionSubmitted The New Embedding Model Training Platform as a story · 2 points
HN discussionSubmitted Fine-Tuning Embedding Models Course as a story · 2 points
HN discussionSubmitted AI Search That Understands the Way Your Customer's Think as a story · 2 points
HN discussionSubmitted Generalized Contrastive Learning for Multi-Modal Retrieval and Ranking as a story · 2 points
HN discussionSubmitted How to Create an AI Podcast with Google's NotebookLM as a story · 1 points
HN discussionSubmitted How to Build a Multimodal Hybrid Search System with Vectors and Full Text as a story · 1 points
HN discussionSubmitted Marqo Launches Family of Embedding Models for Ecommerce and Retail as a story · 1 points
HN discussion