Back

Chirotpal Das

Building an AI eco-s...ย โ€ขย 7m

I feel pride in announcing our Made in India, Real-Time Vector Database - SwarnDB. SwarnDB is a SarthiAI initiative towards an effort to create an end to end eco-system for the future of AI. We tested SwarnDB with 100K vector records of 1536 dimensions with Cosine similarity search for 300 queries and retrieved results (top_k=10) with an average latency of 10 milliseconds. We'll soon be launching in private beta, if you want early access do visit our website and join the waitlist. Website - https://app.swarndb.com/ Share this message with your network and help us take India's deep tech to the world.

Reply
3

More like this

Recommendations from Medial

Image Description
Image Description

Account Deleted

Hey I am on Medialย โ€ขย 8m

I am building an AI based platform that can read and selsct resumes based on the matching algorithms such as cosine similarity to give matching scores for candidate resumes against job desc. The platform can provide users with sourcing analytics and

See More
3 Replies
3

Saswata Kumar Dash

Buidling FedUp| AI R...ย โ€ขย 4m

๐Ÿšจ Everyone says "RAG is dead" โ€” but I say: Itโ€™s just been badly implemented. Iโ€™ve worked on AI systems where Retrieval-Augmented Generation (RAG) either changed the gameโ€ฆ or completely flopped. Hereโ€™s the hard truth ๐Ÿ‘‡ --- ๐Ÿคฏ Most teams mess up

See More
Reply
5

Rohit joshi

Dev dev devย โ€ขย 8m

๐Ÿš€ Excited to share my latest YouTube video! demonstrate how to integrate Microsoft's Semantic Kernel with Qdrant, the open-source vector database, to build an intelligent question-answering system for Wikipedia pages๎ˆ„ ๎ˆ€cite๎ˆ‚turn0search3๎ˆ† In this tu

See More
Reply
2
8
Image Description

Sanskar

Keen Learner and Exp...ย โ€ขย 1m

Day 14 of learning AI/ML as a beginner. Topic: Word2vec I think I am getting lost and that I have omitted some core concepts as there are many things I believe I am unfamiliar with and I am searching for some guidance. Can anybody please tell me wh

See More
2 Replies
2
18

Adrika Singh

Building LeXploR to ...ย โ€ขย 4m

If you're obsessed with problem-solving and have the ability to think outside the box, keep reading! โฌ We atย LeXploRย are hunting for razor-sharp software interns with an obsession for building from scratch and a passion for democratizing legal knowl

See More
Reply
3
Image Description
Image Description

Shuvodip Ray

ย โ€ขย 

Arizona State Universityย โ€ขย 5m

That hack worked partially, but this prompt is a gem ๐Ÿ’Ž. Yesterday, I posted how you can whitelist your lovable built website using lovable. I posted that just for meme content, but later I decided to try it, and it worked a little bit. I got this i

See More
14 Replies
1
12

Reticle

Live for Indiaย โ€ขย 5m

Now I will briefly explain how we buid my https://medial.app/idea/turtal-ai-caaaf91d0ac7f Our main unique feature is - 1)Turtal AI lightweight customizable turta IDE๐Ÿ˜Š 2) coder rankboard ๐Ÿ’ป 3) AI job searching ๐Ÿ—œ๏ธ 1)Turtal AI lightweight customizab

See More
Reply
2

Rahul Agarwal

Founder | Agentic AI...ย โ€ขย 1m

Fine-tune vs Prompt vs Context Engineering. Simple step-by-step breakdown for each approach. ๐—™๐—ถ๐—ป๐—ฒ-๐—ง๐˜‚๐—ป๐—ถ๐—ป๐—ด (๐— ๐—ผ๐—ฑ๐—ฒ๐—น-๐—Ÿ๐—ฒ๐˜ƒ๐—ฒ๐—น ๐—–๐˜‚๐˜€๐˜๐—ผ๐—บ๐—ถ๐˜‡๐—ฎ๐˜๐—ถ๐—ผ๐—ป) ๐—™๐—น๐—ผ๐˜„: 1. Collect Data โ†’ Gather domain-specific info (e.g., legal docs). 2. Sta

See More
Reply
2
13
Image Description
Image Description

Rahul Agarwal

Founder | Agentic AI...ย โ€ขย 1m

3 ways how most AI systems are built. Iโ€™ve explained each one step-by-step. 1) ๐—ง๐—ฟ๐—ฎ๐—ฑ๐—ถ๐˜๐—ถ๐—ผ๐—ป๐—ฎ๐—น ๐—”๐—œ (๐˜€๐˜๐—ฒ๐—ฝ-๐—ฏ๐˜†-๐˜€๐˜๐—ฒ๐—ฝ) 1. ๐—ฆ๐—ฒ๐˜ ๐˜๐—ฎ๐˜€๐—ธ โ€“ Decide what problem the model should solve. 2. ๐—–๐—ผ๐—น๐—น๐—ฒ๐—ฐ๐˜ ๐—ฑ๐—ฎ๐˜๐—ฎ โ€“ Gather lots of example

See More
1 Reply
8
17
1

Download the medial app to read full posts, comements and news.