Hugging Face's logo

EuroPython 2022
non-profit
https://ep2022.europython.eu/
Activity Feed Request to join this org

AI & ML interests

None defined yet.
albertvillanova 
posted an update 2 days ago
view post
Post
190
🚀 New in smolagents v1.20.0: Remote Python Execution via WebAssembly (Wasm)

We've just merged a major new capability into the smolagents framework: the CodeAgent can now execute Python code remotely in a secure, sandboxed WebAssembly environment!

🔧 Powered by Pyodide and Deno, this new WasmExecutor lets your agent-generated Python code run safely: without relying on Docker or local execution.

Why this matters:
✅ Isolated execution = no host access
✅ No need for Python on the user's machine
✅ Safer evaluation of arbitrary code
✅ Compatible with serverless / edge agent workloads
✅ Ideal for constrained or untrusted environments

This is just the beginning: a focused initial implementation with known limitations. A solid MVP designed for secure, sandboxed use cases. 💡

💡 We're inviting the open-source community to help evolve this executor:
• Tackle more advanced Python features
• Expand compatibility
• Add test coverage
• Shape the next-gen secure agent runtime

🔗 Check out the PR: https://github.com/huggingface/smolagents/pull/1261

Let's reimagine what agent-driven Python execution can look like: remote-first, wasm-secure, and community-built.

This feature is live in smolagents v1.20.0!
Try it out.
Break things. Extend it. Give us feedback.
Let's build safer, smarter agents; together 🧠⚙️

👉 https://github.com/huggingface/smolagents/releases/tag/v1.20.0

#smolagents #WebAssembly #Python #AIagents #Pyodide #Deno #OpenSource #HuggingFace #AgenticAI
taesiri 
authored a paper 2 days ago
albertvillanova 
posted an update 19 days ago
view post
Post
1578
🚀 SmolAgents v1.19.0 is live!
This release brings major improvements to agent flexibility, UI usability, streaming architecture, and developer experience: making it easier than ever to build smart, interactive AI agents. Here's what's new:

🔧 Agent Upgrades
- Support for managed agents in ToolCallingAgent
- Context manager support for cleaner agent lifecycle handling
- Output formatting now uses XML tags for consistency

🖥️ UI Enhancements
- GradioUI now supports reset_agent_memory: perfect for fresh starts in dev & demos.

🔄 Streaming Refactor
- Streaming event aggregation moved off the Model class
- ➡️ Better architecture & maintainability

📦 Output Tracking
- CodeAgent outputs are now stored in ActionStep
- ✅ More visibility and structure to agent decisions

🐛 Bug Fixes
- Smarter planning logic
- Cleaner Docker logs
- Better prompt formatting for additional_args
- Safer internal functions and final answer matching

📚 Docs Improvements
- Added quickstart examples with tool usage
- One-click Colab launch buttons
- Expanded reference docs (AgentMemory, GradioUI docstrings)
- Fixed broken links and migrated to .md format

🔗 Full release notes:
https://github.com/huggingface/smolagents/releases/tag/v1.19.0

💬 Try it out, explore the new features, and let us know what you build!

#smolagents #opensource #AIagents #LLM #HuggingFace
reach-vb 
posted an update about 1 month ago
view post
Post
2755
Excited to onboard FeatherlessAI on Hugging Face as an Inference Provider - they bring a fleet of 6,700+ LLMs on-demand on the Hugging Face Hub 🤯

Starting today, you'd be able to access all those LLMs (OpenAI compatible) on HF model pages and via OpenAI client libraries too! 💥

Go, play with it today: https://huggingface.co/blog/inference-providers-featherless

P.S. They're also bringing on more GPUs to support all your concurrent requests!
albertvillanova 
posted an update about 2 months ago
reach-vb 
posted an update about 2 months ago
view post
Post
4074
hey hey @mradermacher - VB from Hugging Face here, we'd love to onboard you over to our optimised xet backend! 💥

as you know we're in the process of upgrading our storage backend to xet (which helps us scale and offer blazingly fast upload/ download speeds too): https://huggingface.co/blog/xet-on-the-hub and now that we are certain that the backend can scale with even big models like Llama 4/ Qwen 3 - we;re moving to the next phase of inviting impactful orgs and users on the hub over as you are a big part of the open source ML community - we would love to onboard you next and create some excitement about it in the community too!

in terms of actual steps - it should be as simple as one of the org admins to join hf.co/join/xet - we'll take care of the rest.

p.s. you'd need to have a the latest hf_xet version of huggingface_hub lib but everything else should be the same: https://huggingface.co/docs/hub/storage-backends#using-xet-storage

p.p.s. this is fully backwards compatible so everything will work as it should! 🤗
·
albertvillanova 
posted an update about 2 months ago
albertvillanova 
posted an update 3 months ago
view post
Post
2793
smolagents v1.14.0 is out! 🚀
🔌 MCPClient: A sleek new client for connecting to remote MCP servers, making integrations more flexible and scalable.
🪨 Amazon Bedrock: Native support for Bedrock-hosted models.
SmolAgents is now more powerful, flexible, and enterprise-ready. 💼

Full release 👉 https://github.com/huggingface/smolagents/releases/tag/v1.14.0
#smolagents #LLM #AgenticAI
reach-vb 
authored a paper 3 months ago
awacke1 
posted an update 3 months ago
view post
Post
1999
AI Vision & SFT Titans 🌟 Turns PDFs into text, snaps pics, and births AI art.

https://huggingface.co/spaces/awacke1/TorchTransformers-Diffusion-CV-SFT

1. OCR a grocery list or train a titan while sipping coffee? ☕
2. Camera Snap 📷: Capture life’s chaos—your cat’s face or that weird receipt. Proof you’re a spy!
3. OCR 🔍: PDFs beg for mercy as GPT-4o extracts text.
4. Image Gen 🎨: Prompt “neon superhero me”
5. PDF 📄: Double-page OCR Single-page sniping

Build Titans 🌱: Train tiny AI models. 💪Characters🧑‍🎨: Craft quirky heroes.
🎥
osanseviero 
authored a paper 4 months ago
awacke1 
posted an update 4 months ago
albertvillanova 
posted an update 4 months ago
view post
Post
4140
🚀 New smolagents update: Safer Local Python Execution! 🦾🐍

With the latest release, we've added security checks to the local Python interpreter: every evaluation is now analyzed for dangerous builtins, modules, and functions. 🔒

Here's why this matters & what you need to know! 🧵👇

1️⃣ Why is local execution risky? ⚠️
AI agents that run arbitrary Python code can unintentionally (or maliciously) access system files, run unsafe commands, or exfiltrate data.

2️⃣ New Safety Layer in smolagents 🛡️
We now inspect every return value during execution:
✅ Allowed: Safe built-in types (e.g., numbers, strings, lists)
⛔ Blocked: Dangerous functions/modules (e.g., os.system, subprocess, exec, shutil)

3️⃣ Immediate Benefits 💡
- Prevent agents from accessing unsafe builtins
- Block unauthorized file or network access
- Reduce accidental security vulnerabilities

4️⃣ Security Disclaimer ⚠️
🚨 Despite these improvements, local Python execution is NEVER 100% safe. 🚨
If you need true isolation, use a remote sandboxed executor like Docker or E2B.

5️⃣ The Best Practice: Use Sandboxed Execution 🔐
For production-grade AI agents, we strongly recommend running code in a Docker or E2B sandbox to ensure complete isolation.

6️⃣ Upgrade Now & Stay Safe! 🚀
Check out the latest smolagents release and start building safer AI agents today.

🔗 https://github.com/huggingface/smolagents

What security measures do you take when running AI-generated code? Let’s discuss! 👇

#AI #smolagents #Python #Security
  • 2 replies
·
taesiri 
authored a paper 4 months ago
albertvillanova 
posted an update 4 months ago
view post
Post
4045
🚀 Big news for AI agents! With the latest release of smolagents, you can now securely execute Python code in sandboxed Docker or E2B environments. 🦾🔒

Here's why this is a game-changer for agent-based systems: 🧵👇

1️⃣ Security First 🔐
Running AI agents in unrestricted Python environments is risky! With sandboxing, your agents are isolated, preventing unintended file access, network abuse, or system modifications.

2️⃣ Deterministic & Reproducible Runs 📦
By running agents in containerized environments, you ensure that every execution happens in a controlled and predictable setting—no more environment mismatches or dependency issues!

3️⃣ Resource Control & Limits 🚦
Docker and E2B allow you to enforce CPU, memory, and execution time limits, so rogue or inefficient agents don’t spiral out of control.

4️⃣ Safer Code Execution in Production 🏭
Deploy AI agents confidently, knowing that any generated code runs in an ephemeral, isolated environment, protecting your host machine and infrastructure.

5️⃣ Easy to Integrate 🛠️
With smolagents, you can simply configure your agent to use Docker or E2B as its execution backend—no need for complex security setups!

6️⃣ Perfect for Autonomous AI Agents 🤖
If your AI agents generate and execute code dynamically, this is a must-have to avoid security pitfalls while enabling advanced automation.

⚡ Get started now: https://github.com/huggingface/smolagents

What will you build with smolagents? Let us know! 🚀💡
awacke1 
posted an update 5 months ago
view post
Post
2496
🚀 Blast into the future with ZaxxonGalaxian – a thrilling 3D action game where you navigate epic battles through towering 3D cityscapes! Face off against relentless swarm bots, climb the leaderboard, and dominate the skies. awacke1/ZaxxoGalaxian
taesiri 
authored a paper 5 months ago
reach-vb 
authored a paper 5 months ago
albertvillanova 
posted an update 5 months ago
view post
Post
4129
🚀 Introducing @huggingface Open Deep-Research💥

In just 24 hours, we built an open-source agent that:
✅ Autonomously browse the web
✅ Search, scroll & extract info
✅ Download & manipulate files
✅ Run calculations on data

55% on GAIA validation set! Help us improve it!💡
https://huggingface.co/blog/open-deep-research
  • 3 replies
·
awacke1 
posted an update 6 months ago
view post
Post
3215
Deep Research Evaluator was asked:
" design a coral defense mechanism that upon sensing say an acid that's causing coral reefs to have a carbon dioxide issue it develops... please create a plan and a design for this\n
"
It picks these three as best combined solution.

1. [Reef-insight: A framework for reef habitat mapping with clustering methods via remote sensing]...
2. Phone a friend: [Learning to Communicate and Collaborate in a Competitive Multi-Agent Setup to Clean the Ocean from Macroplastics]...
3. World Solve: [Dependence of Physiochemical Features on Marine Chlorophyll Analysis with Learning Techniques]


To design a system that allows coralows coral reefs to respond to increased acidity levels in their environment, we can create a network of pH sensors and dispersal units that can detect changes in pH levels and release a base solution to neutralize the acid.

1. pH Sensors: The first component of the system would be a network of pH sensors placed strategically throughout the coral reef. These sensors would be small, durable, and able to withstand the harsh conditions of the ocean. They would be placed at various depths and locations within the reef to ensure accurate and comprehensive monitoring of pH levels.
2. Base Dispersal Units: Once the pH sensors detect a decrease in pH levels, they would trigger the base dispersal units to release a base solution into the water. These units would be strategically placed around the reef and would be able to release a controlled amount of base solution to neutralize the acidity in the water.
3. Water Dispersal Mechanism: The base dispersal units would be connected to a water dispersal mechanism that would allow the base solution to be distributed evenly around the reef. This could be achieved through a series of pipes or channels that would distribute the base solution in a controlled and targeted manner.