I create content about deep learning | The DevRel and Deep Learning Dude

Hacking on LLMs, curating multimodal datasets, and writing a book about RAG.

Harpreet Sahota 🥑

i've literally been waiting for years to have an OPEN SOURCE model like qwen3-vl-embedding

i tested its multimodal retrieval capabilities on a corpus of 412 short video clips and the results literally blew my mind

here are the queries i tested:

1. a cartoon guy drinks merlot wine

i like this query because we see how it can retrieve based on semantics (a cartoon), text (the label merlot), and temporal action in the video (the cartoon guy drinks the wine mid-way through the video)

2. garfield runs out of the door

semantics are awesome here, the model knows i'm talking about the cartoon character...

3. a woman in a blue dress sleeping on a red bench

the skeptic in you might think that it's retrieving just based on the red color block in the 2/3 of the video...but notice the specific part of the query "a woman in a blue dress..." and this is only shown in 3s out of the full 10s

this is such a huge release 

and it's gonna open up SO much more for multimodal video retrieval this year

on my wishlist is natural language search of pcd datasets, who gonna ship that?

you can hack around with the model using the resources below

check out the docs: here: https://lnkd.in/gh7yfBNP

and the quickstart nbhere:  https://lnkd.in/gbinsx7p

🤖 Hacker-in-Residence @ Voxel51| 👨🏽‍💻 AI/ML Engineer | 👷🏽‍♀️ Technical Developer Advocate | Learn. Do. Write. Teach. Repeat.

for those who missed it, or were there in-person and know the trouble i was facing 😆, my ODSC webinar is now live on youtube!

in this session i discuss visual ai techniques for automotive damage detection. 

i used the cardd dataset, which is a public dataset built specifically for vehicle damage analysis and demonstrated how fiftyone helps you explore, visualize, and build models to detect dents, scratches, cracks, glass shatter, tire flats, and broken lamps.

i feel like its a super practical workshop with some insightful workflows for visual AI in automotive settings, but as the creator i might be biased.

only one way to find out for yourself, watch the webinar!

https://lnkd.in/ewfz5vZD

Open video: Mastering Visual AI with Vision-Language Models & Advanced Evaluation Techniques by Harpreet Sahota on youtube.com

Mastering Visual AI with Vision-Language Models & Advanced Evaluation Techniques by Harpreet Sahota

sometimes i look back at the shit i get done and i genuinely impress myself

how teams really build Visual AI in the wild? what's the he messy reality?  

i don't know...and maybe its because nobody’s asking practitioners and compiling their answers so we can find out the landscape actually looks like. 

so, we at Voxel51 are kickin off the...

wait for it...

 State of Visual AI survey...vey...vey

for those out ther building visual AI systems i want your hot takes

what’s the hardest part about making visual ai a reality? 

let us know in this survey

it'll take you 30 minutes and is a much better use of time than baby sitting your runs and staring at your loss curves

i can't offer much beyond my heartiest thanks, but you will get early access to the full report with benchmarks, common pain points, and where you stand within the landscape. 

here's a link: https://lnkd.in/gnsADACy

MedGemma 1.5 supports detection, but for best results, you'll need to fine-tune. 

there's a kaggle competition using the model, i created a starter notebook to give you a jump start on how to fine-tune it for detection

checkout the starter notebook and additonal resources 👇🏼

cc Omar Sanseviero Megan Risdal Logan Kilpatrick

in the asu area and wanna get started with open source contributions? then don't miss this hack

On March 21, 2026, we’re hosting Agents World: Visual AI Hackathon @Arizona State University, together with Pavan Turaga 🚀 

This is a hands-on day: meet people, build with AI, eat pizza, and leave with something you created after a short workshop and a full day of hacking. 
You’ll work with the FiftyOne ecosystem and real models used in practice, like Qwen, Gemini Vision, Sharp, and more. 

If you’re an ASU student who wants to build, learn by doing, and work with real Visual AI tools, this is for you.

Registration is open:
https://lnkd.in/gBCHW5Fg

Hope to see you at ASU. I’ll be there with the amazing Voxel51 team:  Sid Mehta, Ritchie Martori, Jimmy Guerrero ! 🙌

looking forward to the next meetup in boston!

Join our in-person meetup at the Microsoft Research Lab at the Massachusetts Institute of Technology in Boston, Massachusetts on Feb 18 to hear talks from experts on cutting-edge topics across AI, ML, and computer vision. Register here: https://lnkd.in/gi4kpSMB

Talks will include:

• SNAP: Towards Segmenting Anything in Any Point Cloud - Hanhui Wang at Northeastern University

• Culturally Adaptive AI - Anku R. at Massachusetts Institute of Technology

• Data Foundations for Vision-Language-Action Models - Harpreet Sahota 🥑 at Voxel51

• Better Together: Leveraging Unpaired Multimodal Data for Stronger Unimodal Models - Sharut G. at Massachusetts Institute of Technology

• Neural Radiance Fields for Image Verification - Sage Simhon at Pasteur Labs & ISI

#computervision #ai #artificialintelligence #machinevision #machinelearning #datascience

Syed Abdul Sami Rizvi, Matthew Ebisu and 118 other attendees

View event: Feb 18 - Boston AI, ML and Computer Vision Meetup

Feb 18 - Boston AI, ML and Computer Vision Meetup

Inspired by the amazing Hugging Face’s 2025 AI Timeline, we created one for the Fiftyone community. The FiftyOne Community Development Timeline highlights more than 131 contributions from 2025, including datasets, models, plugins, and integrations.

You can filter by type or modality and jump straight to each integration.
https://lnkd.in/ev2kpCGN

Big thanks to the entire Voxel51 community for building all of this together.
Harpreet Sahota 🥑, Daniel Gural, Paula Ramos, PhD, Jimmy Guerrero, Derek Van de Streek, Nicholas Lotz 🚀

Gonna be a great series of talks, lots of technical depth!

Chief Community Officer @ Voxel51 | Startup Advisor

Join us on Feb 18 for the Boston AI, ML and Computer Vision Meetup! Pre-registration is mandatory to clear building security - https://lnkd.in/gHtBuH49

Talks will include:

* SNAP: Towards Segmenting Anything in Any Point Cloud - Hanhui Wang at Northeastern University

* Culturally Adaptive AI - Anku R. at MIT

* Data Foundations for Vision-Language-Action Models - Harpreet Sahota 🥑 at Voxel51

* Better Together: Leveraging Unpaired Multimodal Data for Stronger Unimodal Models - Sharut G. at MIT

* Neural Radiance Fields for Image Verification - Sage Simhon at Pasteur Labs & ISI

***********

Want to build better computer vision models? FiftyOne is an open source toolkit from Voxel51 (our Meetup sponsor) that helps you curate datasets, evaluate model performance, visualize embeddings, catch annotation errors, and eliminate duplicate images—all in one place.

“pip install fiftyone” is all it takes to get started - https://docs.voxel51.com/

#computervision #ai #artificialintelligence #machinevision
#machinelearning #datascience #physicalai

NLP Engineer | Generative AI | Open Source Developer | Freelancer

AI Consultant | Internal AI Systems for SMBs

I build production AI systems that remove operational bottlenecks — document processing, support automation, voice agents, and internal workflows.

Most AI projects fail not because of models, but because of architecture.
I specialize in resilient, maintainable systems that integrate with real businesses.

What I build:
• Internal AI tools (documents, OCR, Q&A, dashboards)
• AI voice & chat agents for operations
• Durable, long-running AI workflows (Azure-based orchestration)

Background:
• 7+ years building real-world software
• 100+ freelance & consulting projects
• Deep experience in backend systems, APIs, and distributed architectures

If you want AI that survives production and scales with your business, send me a message.

Mahimai Raja J ‎

Vector databases just became optional for RAG.

PageIndex proves reasoning beats similarity matching.

The fundamental flaw in current RAG: chunking documents arbitrarily, then hoping semantic similarity finds the right context. But similarity ≠ relevance.

Try asking a vector database: "What's the debt trend analysis?" 
Result: Random chunks containing "debt" and "trend"

PageIndex flips the approach:
❌ Chunk → Embed → Vector search
✅ Structure → Reason → Navigate

The breakthrough process:
- Build hierarchical document trees (like expert-level TOCs)
- Use LLM reasoning for navigation: "Debt trends → Financial summary → Appendix G"
- Return exact page references with full context

Real-world impact:
- Mafin 2.5: 98.7% accuracy on FinanceBench
- No vector infrastructure overhead
- No context-breaking chunking boundaries
- Traceable retrieval paths

Perfect for professional documents where domain expertise matters:
Financial reports, legal filings, technical manuals, research papers.

This is how humans actually read documents. Finally, RAG works the same way.

💻 https://lnkd.in/eP3MU9vy
🔗 https://pageindex.ai/

Open source. Production-ready.

Repost ♻️ for vectorless RAG revolution.

AI Consultant | Voice AI - Information Retrieval & Extraction

Chat Completions are officially legacy tech.

Open Responses just launched to replace them for the agent era.

The problem was obvious: Chat Completions were built for turn-based conversations. Agents need autonomous reasoning, tool calling, and multi-step workflows. The mismatch was killing performance.

Open Responses solves this with:
✅ Native agentic loops (reasoning → tool calls → execution → repeat)
✅ Stateless by default with encrypted reasoning support
✅ Semantic streaming events (not raw text deltas)
✅ Internal + external tool categories
✅ Provider-agnostic routing with custom parameters

Key technical wins:
- Single API call handles multi-step workflows
- `max_tool_calls` prevents infinite loops
- Standardized model configuration across providers
- Built on OpenAI's Responses API but fully open

Real impact: "Find Q3 sales data and email summary to team" = one request, complete autonomous execution.

The era of manually chaining API calls is over.

💻 openresponses.org
🔧 Try it: https://lnkd.in/e2B39PhC

Open source. Production-ready.

Repost ♻️ for the future of AI inference.

AI agents forget everything after each task.

Acontext just solved agent memory forever.

The problem is massive:
- Agents start from scratch every time
- No learning from past successes
- Context engineering is manual hell
- Success rates stay frustratingly low

Acontext's breakthrough:
✅ Context data platform for agents
✅ Auto-tracks tasks and preferences
✅ Self-learning from experiences (SOPs)
✅ Notion-like skill storage system

The magic workflow:
- Store agent sessions + artifacts
- Observe tasks automatically
- Learn patterns into "Spaces"
- Guide future agent decisions

Result: Higher success rates, fewer steps.

💻 https://lnkd.in/ejEJbbtw
⛳ https://lnkd.in/e5wjGej2

Open source. Production-ready.

Repost ♻️ for smarter AI agents.

taplio

The Battle

Harpreet Sahota 🥑

Mahimai Raja J ‎

Followers

Posts

Engagements

Likes

Performance ScoreHarpreet Sahota 🥑's LinkedIn Performance

Performance ScoreMahimai Raja J ‎'s LinkedIn Performance

Ready to grow your LinkedIn presence?

taplio

The Battle

Harpreet Sahota 🥑

Mahimai Raja J ‎

Followers

Posts

Engagements

Likes

Performance Score.css-goub6s{font-size:var(--chakra-fontSizes-md);font-weight:500;color:var(--chakra-colors-gray-600);display:block;margin-top:var(--chakra-space-1);}Harpreet Sahota 🥑's LinkedIn Performance

Performance ScoreMahimai Raja J ‎'s LinkedIn Performance

Ready to grow your LinkedIn presence?

Performance ScoreHarpreet Sahota 🥑's LinkedIn Performance