richardmeng
richardmeng on Hacker News
Posted by
richardmeng on Tuesday November 03, 2026 @01:44AM
from the show-hn dept.
Hi HN! Sharing our latest open-source project: PrivatoAgents now get access to our email, texts, calendar, files, everything. They can read whatever they like, whenever they like. We sacrifice personal data privacy for max productivity.But we no longer have to. Privato gives AI agents a scoped, temporary pass to ONLY the data it needs to answer a question.If you ask "When does my flight to...
good idea. Renamed to Valet.
Posted by
richardmeng on Sunday November 01, 2026 @04:44PM
from the show-hn dept.
https://www.anonce.io/
Hi HN! We built nonce, an open-source tool that sits between personal AI agents (Muse, Grok, ChatGPT, Claude) and your personal data in Gmail, Calendar, Drive and more.Today, if you connect Gmail to an AI agent like Muse, it can read your entire inbox. Whether on purpose or not, they can read far more emails than needed. This poses a huge data-privilege risk, in which personal data is accessed...
Posted by
richardmeng on Sunday September 28, 2025 @05:00PM
from the now-hiring dept.
ROE is building AI Agents for risk and compliance. We are trusted by companies like eBay, Affirm and Tier 1 banks.Hiring ambitious, talented founding engineers. Base $150K-250K, 0.75-2% options.San Mateo office, 3 days hybrid working mode. Free lunch.We sponsor H1B / PERM.Link to apply https://www.ycombinator.com/companies/roe/jobs/OFFxite-found...
what's wrong with vercel?
Posted by
richardmeng on Monday August 11, 2025 @12:09AM
from the self-post dept.
Open-sourcing "Vectorless", a new PDF chatbot without embedding vectors.Github Repo: https://github.com/roe-ai/vectorless-chatbot
Demo app: https://vectorless-chatbot.vercel.app/How it works:
1. Select best docs – Feed the LLM high-level descriptions + doc names. It picks which docs to use.
2. Select best pages – The Agent goes through the doc pages and pulls out the most relevant...
Sumble has been my critical tool to research the organization structure and responsibility in a large company, technology adoption like which organization has the LLM adoption.
Congrats on the launch!
A lot of infrastructure work is needed to make the SQL experience seamless work for unstructured data. And at the most part we do fork the open core data warehouse and build on top of it.
I think by parse it means more like document understanding
Today's large vision models like GPT-4o can parse the content heavy papers pretty well (and respect their structures).
Yah basically it allows you to send PDFs as image patches into GPT-4o model that workflow can be easily built.
Feel free to send me an email [email protected], happy to evaluate your case and try to save that 200K :p
We use Gemini to analyze the video in its raw format.
To add to Jason's point -
There is a big UI part here, because for multimodal data analytics, we think it's crucial for people to see and hear data.
For the RAG search, many DBs have built-in vector search, but chunking, indexing, and maintaining the index are kind of on your own. This may not be a problem for technical people, but it's a hassle for data people who own hundreds of data products within a company. Therefore, we have a semantic search index builder that allows one to build an auto-refreshing semantic search index with no code, and completely keep hands free from coming up with their own vectors.
In addition, data analysis often needs to interrogate the search results further. For example, let's say we have used pgvector to find all the photos related to the Golden Gate Bridge. But then we want to interrogate questions like which of these images has someone wearing a blue shirt. We have to apply another model, and that is outside of a normal DB's responsibility.
I guess to add to Jason's point, it depends on how data engineers/data analysts are perceived in their roles within the company. For some companies, we see a data analyst taking end-to-end responsibility from the data engineering to BI, but for others we also see a clear separation, data engineers doing data pipelining and data modeling, but data analysts are, in fact, business analysts.
Regardless, we think that SQL is the common interface for both of the parties, and we're excited to see who will be the power users.
This does not work with Redshift. This is a query engine for unstructured data like documents, images, videos. Those data do not quite fit into Redshift / Bigquery data warehouse.
Right, our product is designed for data practitioners who want snappy data analytics on unstructured data.
Thanks for sharing your project, super cool idea! What does it take if we want to integrate our SQL engine with datachain?
Likely, can you elaborate on your use case and what db do you use?
Good points! We'll update our landing pages as you suggested.
Posted by
richardmeng on Friday August 09, 2024 @11:17AM
from the self-post dept.
Hey HN, we’re Richard and Jason from Roe AI (https://getroe.ai). We’re building a query engine that lets data people do SQL queries on various kinds of unstructured data (videos, images, webpages, documents) using LLM-powered data processors.Here is a 3-minute video: https://www.youtube.com/watch?v=9-WwJk1v5mI, showing how to create an LLM data processor to process videos, build a semantic...