News for hackers. Stuff that matters.

dhruv_anand

dhruv_anand on Hacker News

Show HN: Agent Launch – One CLI for Codex, Claude Code, Cursor, Gemini, OpenCode

Posted by dhruv_anand on Tuesday May 26, 2026 @07:18AM
from the show-hn dept.

I built a small CLI that unifies launching local coding agents.Instead of remembering different flags for Codex, Claude Code, Cursor Agent, OpenCode, and Antigravity CLI, I use one command with consistent options for agent, prompt, cwd, mode, model class, interactive/non-interactive and resume.GitHub: https://github.com/dhruv-anand-aintech/agent-launchYou can use `agent-launch` or `agl` to...

( Read More... | no comments | 2 points | on HN )

Show HN: Move data from any vector DB to any other vector DB

Posted by dhruv_anand on Monday May 13, 2024 @04:53PM
from the show-hn dept.

https://github.com/AI-Northstar-Tech/vector-io

While building semantic search and LLM-powered apps, one needs to try out various vector databases because they differ widely in feature set, cost and other characteristics.The Vector-io library introduces a universal open format for storing vector datasets (Vectors, along with their metadata), along with import and export scripts for a wide range of vector databases: - Pinecone - Qdrant -...

( Read More... | no comments | 2 points | on HN )
Re:Radient – vectorize many data types, not just text on Friday May 10, 2024 @06:32PM (#40324388)
Things are what people call them. Featurization/Feature Extraction used to refer to manual feature engineering, where you could tell what each numerical value is.

Vectorization, as colloquially used by developers in the AI space today, refers to the same thing being done via deep learning models, so it is less to do with ML Features, and more to do with generating a Vector all at once, with each dimension not having a specific meaning.

Show HN: Move data from any Vector DB to any other Vector DB

Posted by dhruv_anand on Friday May 10, 2024 @02:27PM
from the show-hn dept.

https://github.com/AI-Northstar-Tech/vector-io

While building semantic search and LLM-powered apps, one needs to try out various vector databases because they differ widely in feature set, cost and other characteristics.The Vector-io library introduces a universal open format for storing vector datasets (Vectors, along with their metadata), along with import and export scripts for a wide range of vector databases: - Pinecone - Qdrant -...

( Read More... | no comments | on HN )
Re:Radient – vectorize many data types, not just text on Friday May 10, 2024 @07:13AM (#40317562)
for vector sinks, it would be good to integrate with Vector-io (https://github.com/ai-northstar-tech/vector-io) which provides import functions for ~10 vector databases already.

disclosure: I'm the author of Vector-io

Re:Radient – vectorize many data types, not just text on Friday May 10, 2024 @07:11AM (#40317551)
nice library. for text embeddings, it would be good to integrate with a framework like litellm, which has enabled doing embeddings using a variety of methods and API providers: https://litellm.vercel.app/docs/embedding/supported_embeddin...
Re:Ask HN: Is there a need for entity-based RAG? on Tuesday March 19, 2024 @08:03AM (#39754877)
Can you link to your solution?

Show HN: Vector-Io: Universal Vector Data Import/Export

Posted by dhruv_anand on Tuesday February 13, 2024 @01:48AM
from the show-hn dept.

https://github.com/AI-Northstar-Tech/vector-io

While building semantic search and LLM-powered apps, one needs to try out various vector databases because they differ widely in feature set, cost and other characteristics.The Vector-io library introduces a universal open format for storing vector datasets (Vectors, along with their metadata), along with import and export scripts for a wide range of vector databases (more to come!).This will...

( Read More... | no comments | on HN )
Re:Are we at peak vector database? on Wednesday February 07, 2024 @03:13PM (#39293667)
Is your YOShInOn RSS reader available as an app or open-source library?
Re:Ask HN: Semantic Vector Searching in WASM? on Wednesday January 03, 2024 @04:34AM (#38852222)
Not sure if this helps, but you can create embeddings using transformers.js (feature extraction pipeline) in the browser.
Re:On a roll: Qdrant brings sparse vectors, discovery search and custo... on Wednesday December 13, 2023 @01:36PM (#38632038)
You can have a look at this sheet: https://docs.google.com/spreadsheets/d/170HErOyOkLDjQfy3TJ6a...

It shows which Vector DBs have a particular feature. "In-built Text Embeddings creation" is a column you can look at.

Re:New ways to find just what you need on Search on Tuesday December 05, 2023 @06:01AM (#38529373)
They have it. It's called Bard. It's just not as good as one might expect from them.
Re:Show HN: Marbbble, discover alternatives using domains, URLs and ke... on Tuesday November 14, 2023 @02:53PM (#38268669)
Why not index a DB of competitors. Something like crunchbase or an open equivalent?
Re:Show HN: VectorAdmin – An open-source vector database management sy... on Thursday October 12, 2023 @05:35AM (#37855104)
cool idea!
Re:Any startups working on RAG infra for LLMs? on Tuesday September 26, 2023 @11:53AM (#37661186)
Perplexity.ai and a whole bunch of other companies are doing this.
Re:Show HN: LLaMA tokenizer that runs in browser on Wednesday June 14, 2023 @04:05AM (#36322918)
https://news.ycombinator.com/item?id=36105660

Models under sentence-transformers are commonly used by people.

You can check this leaderboard, where OpenAI's embeddings are outperformed by open source ones: https://huggingface.co/spaces/mteb/leaderboard

Re:Ask HN: In-Browser Vector DB? on Monday June 05, 2023 @01:00PM (#36199314)
https://docs.trychroma.com/getting-started?lang=js#:~:text=C...