Sujee Maniyam

Friday fun - open source models wrap up - "pelican style" 🪿

This is my favorite 'vibe benchmark' comparing latest OS models (GPT-OSS, GLM 4.5, Qwen3-2507) released 😀

Prompt: create an svg of a pelican riding a bicycle

Run all the latest open models on Nebius AI Studio - studio.nebius.com

Wherever you are in the world, lend your voice and share your open-source experience with hundreds of other data scientists at PyData Global 2025 by submitting your proposal by TOMORROW, August 6! pydata.org/global2025/c...

Migrating from Pelican to Hugo using Claude Code How I migrated my site from Pelican to Hugo using Claude Code

Moved my site from Pelican → Hugo using Claude Code.
✅ Claude did 95% of the work:

Lessons?
💡 Treat AI like a junior dev.
💡 Sanity check.
💡 Best way to learn: do a real project.

By the end, Claude and I were basically pair programming:
“Looks good! git commit”

👉 sujee.dev/post/migrati...

Docling is my go-to for document parsing.

Used it in Allycat (github.com/The-AI-Allia...) + Data Prep Kit — handles PDFs, DOCX, HTML like a champ.

Super easy to use. Just works.

PDF benchmark: procycons.com/en/blogs/pdf...

#Docling #OpenSource #AI #DataTools #PDFParsing @linuxfoundation.org

😎 Cool project: make-it-heavy by Pietro Schirano.

Dylan Bristot got it running on Nebius AI Studio.
github.com/demianarc/ma...

Tried it with QWEN3-30B-A3B 💥
Prompt: “Growth of solar power in US data centers”
4 agents → 1 solid report. Just so cool! 🧠

#MultiAgent #LLM #OpenSourceLLM

GitHub - The-AI-Alliance/allycat: Chat with your website using LLMs Chat with your website using LLMs. Contribute to The-AI-Alliance/allycat development by creating an account on GitHub.

🚀 Allycat update – open source stack to chat with your website using LLMs!
🕷️ Faster crawler
🤖 LiteLLM for local/remote
📄 File support via Docling (PDF, DOCX…)
📦 Now with uv
⚙️ Cleaner config
📖 better docs

🔗 github.com/The-AI-Allia...

#allycat #OpenSourceAI @aialliance.bsky.social

YouTube video by Sujee Maniyam Data Prep Kit - pdf processing 1

- PDF processing with DPK
Code walkthrough on how to process PDF documents (parse, dedupe, filter out spam)

🎥video: youtu.be/u4OgkmG94fs?...

💻 Data prep kit examples : github.com/data-prep-ki...

#dataprepkit

YouTube video by Sujee Maniyam Data Prep Kit Intro 1

Data Prep Kit videos:

- Data Prep Kit Intro
Introduction and feature walk through (document parsing, exact and fuzzy de-duping, chunking, vectorizing, PII removal, document quality)

🎥 video : www.youtube.com/watch?v=wCbM...

💻 Data prep kit examples : github.com/data-prep-ki...

#dataprepkit

Have you deployed and monitored AI systems in production at scale?

I'd love to have you share your experience at an upcoming Silicon Valley GenAI meetup!

📍 South/East Bay, SF Bay Area
🔗 More info: svgenai.dev
📅 Events calendar: lu.ma/svgenai

🎤 Interested in speaking?
DM me!

#svgenai

SVGenAI June meetup content is live : svgenai.dev/meetups/2025...

📜 slides + 💻 code + 🎥 recordings

Youtube : www.youtube.com/@svgenai

Sign up to be notified of future meetups : lu.ma/svgenai

find past events @ svgenai.dev

#svgenai @melhq.bsky.social @ramnivas.com @davenielsen.bsky.social

🎤 upcoming talk: "What powers software engineering agents"

📅 July 9 Wednesday, 2025
⏰ 10am PT / 1pm ET / 7 PM CET
📹 Zoom
👉 Register: nebius.zoom.us/webinar/regi...

#webinar #AgenticAI

Another #svgenai meetup is a wrap.

1) 📜 slides : svgenai.dev/meetups/2025...
video coming soon.

2) 👉 Sign up: lu.ma/svgenai
website: svgenai.dev

3) 💰 I gave out credits for Nebius AI Studio. studio.nebius.com. DM me if you'd like some.

@davenielsen.bsky.social @ramnivas.com @melhq.bsky.social

Devstral-Small-2505 - a top open-source #LLM optimized for coding agents, from @mistralai.bsky.social , available on Nebius AI Studio!

✨ #1 on SWE-Bench
📈 128K context window
🏛️ Apache 2.0 ✅

🤗 huggingface.co/mistralai/De...

Try it out : studio.nebius.com/playground?m...

#devstral #nebiusAI

🚀 AllyCat Update – Shiny New UI!

- Sleek, modern interface
- Toggle between dark and light themes
- Built-in example prompts to help you get started
- Transparent query processing – view retrieved documents from the vector DB

🎥: www.loom.com/share/360b09...

github.com/The-AI-Allia...

#AllyCat

🚀 Talk: Building Multi-Agent Systems with Open Standards by @rodriveracom.bsky.social
🎁 Attendees get Nebius AI Studio credits!
📅 June 25 | ⏰ 10am PT / 1pm ET / 7pm CET
👉 Register: nebius.zoom.us/webinar/regi...

#MultiAgent #OpenStandards

🧠 Five days, five launches: MiniMax just shifted the AI landscape 🧠 Week of June 23rd, 2025

Good day-by-day breakdown of @minimaxAI's #MiniMaxWeek campaign

open.substack.com/pub/aicollec...

minimax on HF : huggingface.co/MiniMaxAI

#minimax

Silicon Valley Gen AI Meetup - MCP & Langflow · Luma Our 2nd Silicon Valley Gen AI event. The Silicon Valley Gen AI Meetup is a community for Developers, Engineers, UX, Ops, Applied Researchers, and anyone…

🚀 SVGenAI June Meetup – MCP & Langflow

🎤 Talks:
- Langflow by @melhq.bsky.social (Langflow @datastax.com
- MCP by @ramnivas.com (Exograph)

Hosted by ASAComputersInc & RackLive

📅 Thurs, Jun 26 – 5:30pm | 📍 Fremont, CA
🍕 + 🥤 served
👉 lu.ma/uz10jjfs

#GenAI #Langflow #MCP #SVGenAI #meetup

AI Agents & Open Source Tools · Luma Join us for food & beer while learning about AI Agents & Open Source Tools from OpenPipe, Nebius, IBM, AI Alliance and Intel. We will raffle off some free CPU…

I will be at the SF Agents meetup and doing a lightning talk "Using open (source) models in agentic applications"

🗓️: June 17, 2025
⏰: 530pm
📍: San Francisco
👉 : lu.ma/2ezblh3t?tk=...

@aialliance.bsky.social @davenielsen.bsky.social #OpenSourceLLMs #meetup #agents

LiteLLM now supports all models on Nebius AI Studio.

Run all the latest open source models (DeepSeek-R1-0528, Qwen3-235B-A22B) and many more : studio.nebius.com

doc & examples : docs.litellm.ai/docs/provide...

code : github.com/nebius/ai-st...

#LiteLLM #NebiusAIStudio

> Open Source Summit, North America - Denver, CO - June 23 - events.linuxfoundation.org/open-source-... - @linuxfoundation.org

please add your favorites...

Interesting upcoming #conference s in June 2025

> Fully Connected / Weights and Biases - San Francisco, CA - June 17 - wandb.ai/site/resourc...

> World Summit AI - SF - San Francisco, CA - June 18 - usa.worldsummit.ai - @worldsummitai.bsky.social

DeployCon: A GenAI Mini-Summit in SF · Luma Serving a model isn’t the finish line—it’s the starting gun. Welcome to DeployCon, a free, no-fluff, engineer-first summit for teams building the next…

DeployCon: A GenAI Mini-Summit in SF.

🗓️June 25, 2025
📍AWS GenAI Loft, San Francisco
👉 lu.ma/DeployCon?tk... via @LumaHQ

#aiconference #GenAI

What is Agent Communication Protocol (ACP)? | IBM Agent Communication Protocol (ACP) is an open standard for agent-to-agent communication. With this protocol, we can transform our current landscape of siloed agents into interoperable agentic systems ...

Confused by agent protocols like MCP / ACP / A2A ?

This post by Sandi Besen gives a good overview and comparison of these protocols

www.ibm.com/think/topics...

#MCP

Agents-MCP-Hackathon (Agents-MCP-Hackathon) Org profile for Agents-MCP-Hackathon on Hugging Face, the AI community building the future.

Agents MCP hackathon with @gradio-hf.bsky.social starting today

huggingface.co/Agents-MCP-H...

#hackathon #MCP

Mastering Data Cleaning for Fine-Tuning LLMs and RAG Architectures | AI Alliance In the rapidly advancing field of artificial intelligence, data cleaning has become a mission-critical step in ensuring the success of Large Language Models (LLMs) and Retrieval-Augmented Generation (...

Good read: "Mastering Data Cleaning for Fine-Tuning LLMs and RAG Architectures"
thealliance.ai/blog/masteri...

@aialliance.bsky.social @davenielsen.bsky.social

#dataprepkit #RAG #dataprep #finetuning

GitHub - The-AI-Alliance/allycat: Chat with your website using LLMs Chat with your website using LLMs. Contribute to The-AI-Alliance/allycat development by creating an account on GitHub.

I will be talking about AllyCat (github.com/The-AI-Allia...) - a full open source stack that allows you to crawl, index and chat with web content using LLMs at Open.Intel 'Code and Deploy' session with Ezequiel Lanza.

🗓️ May 22, 2025. 10am PT
👉 www.linkedin.com/events/73280...

#AllyCat

YouTube video by Sujee Maniyam Data Prep Kit Intro 1

Check out Data Prep Kit (DPK) — an open-source tool to simplify your data wrangling tasks.

📺 Intro video: www.youtube.com/watch?v=wCbM...

🔗 GitHub: github.com/data-prep-ki...

#dataprepkit

GitHub - The-AI-Alliance/allycat: Chat with your website using LLMs Chat with your website using LLMs. Contribute to The-AI-Alliance/allycat development by creating an account on GitHub.

**Chat with a website using LLM**

AllyCat (github.com/The-AI-Allia...) can
- crawl a website
- extract, clean chunk content
- save to vector db
- query using LLM

Session:
🗓️ May 1, 2025
⏰ 9am PT / 12 pm ET / 4pm GMT
👉 www.meetup.com/ibm-develope...

#allycat @aialliance.bsky.social #ragstack

Silicon Valley Gen AI Meetup - AI Powered Engineer: Use AI to boost your productivity and enhance your career · Luma Our 1st Silicon Valley Gen AI event. The Silicon Valley Gen AI Meetup is a new community for Developers, Engineers, UX, Ops, Applied Researchers, and anyone…

🚀 Launching the Silicon Valley Generative AI Meetup!

First event topic:

"AI Powered Engineer: Use AI to Boost Your Productivity and Enhance Your Career"

🗓️May 1, 2025
⏰ 5:30 PM
📍Beckhoff Automation, San Jose
👉 Luma: lu.ma/lbgs81uy

Learn, Network, Grow!

#meetup #genai

LlamaCon | AI Innovation Event A one-day virtual event to share the innovations and creativity advancing AI.

LLamaCon 2025 (All Llama. All day) - A one-day virtual event
Apr 29, 2025
sign up: www.llama.com/events/llama...

#LlamaCon2025 #conferences