42 35 26

Xuan-Son Nguyen

ngxson

https://blog.ngxson.com

AI & ML interests

Doing AI for fun, not for profit

Recent Activity

commented on an article about 18 hours ago

Topic 28: What is Mixture-of-Mamba?

updated a model about 18 hours ago

ngxson/hf-blog-podcast

commented on an article about 18 hours ago

SmolVLM2: Bringing Video Understanding to Every Device

View all activity

Organizations

ngxson's activity

commented on Topic 28: What is Mixture-of-Mamba? about 18 hours ago

📻 🎙️ Hey, I generated an AI podcast about this blog post, check it out!

This podcast is generated via ngxson/kokoro-podcast-generator, using DeepSeek-R1 and Kokoro-TTS.

updated a model about 18 hours ago

ngxson/hf-blog-podcast

Updated about 18 hours ago

commented on SmolVLM2: Bringing Video Understanding to Every Device about 18 hours ago

📻 🎙️ Hey, I generated an AI podcast about this blog post, check it out!

This podcast is generated via ngxson/kokoro-podcast-generator, using DeepSeek-R1 and Kokoro-TTS.

upvoted an article about 18 hours ago

Article

SmolVLM2: Bringing Video Understanding to Every Device

1 day ago

• 99

commented on Mixture of Tunable Experts - Behavior Modification of DeepSeek-R1 at Inference Time about 21 hours ago

Hi, thanks for the feedback! For now, it's only based on the blog post, not the paper. Probably that's why it hallucinates on some small details.

commented on Mixture of Tunable Experts - Behavior Modification of DeepSeek-R1 at Inference Time 2 days ago

📻 🎙️ Hey, I generated an AI podcast about this blog post, check it out!

This podcast is generated via ngxson/kokoro-podcast-generator, using DeepSeek-R1 and Kokoro-TTS.

commented on Mahjong: Where Grandmas Beat The Best LLMs 2 days ago

📻 🎙️ Hey, I generated an AI podcast about this blog post, check it out!

This podcast is generated via ngxson/kokoro-podcast-generator, using DeepSeek-R1 and Kokoro-TTS.

commented on Synthetic Face Embeddings: Research Notes and Methodology 2 days ago

📻 🎙️ Hey, I generated an AI podcast about this blog post, check it out!

This podcast is generated via ngxson/kokoro-podcast-generator, using DeepSeek-R1 and Kokoro-TTS.

updated a Space 2 days ago

Kokoro Podcast Generator

🎙

AI-generated podcast!

upvoted an article 3 days ago

Article

Introducing Three New Serverless Inference Providers: Hyperbolic, Nebius AI Studio, and Novita 🔥

4 days ago

• 85

commented on Introducing Three New Serverless Inference Providers: Hyperbolic, Nebius AI Studio, and Novita 🔥 3 days ago

📻 🎙️ Hey, I generated an AI podcast about this blog post, check it out!

This podcast is generated via ngxson/kokoro-podcast-generator, using DeepSeek-R1 and Kokoro-TTS.

reacted to as-cle-bert's post with 🚀👍 3 days ago

Post

2160

I built an AI agent app in less than 8 hours🤯
And, believe me, this is 𝗻𝗼𝘁 clickbait❌

GitHub 👉 https://github.com/AstraBert/PapersChat
Demo 👉 as-cle-bert/PapersChat

The app is called 𝐏𝐚𝐩𝐞𝐫𝐬𝐂𝐡𝐚𝐭, and it is aimed at 𝗺𝗮𝗸𝗶𝗻𝗴 𝗰𝗵𝗮𝘁𝘁𝗶𝗻𝗴 𝘄𝗶𝘁𝗵 𝘀𝗰𝗶𝗲𝗻𝘁𝗶𝗳𝗶𝗰 𝗽𝗮𝗽𝗲𝗿𝘀 𝗲𝗮𝘀𝗶𝗲𝗿.

𝐇𝐞𝐫𝐞 𝐢𝐬 𝐰𝐡𝐚𝐭 𝐭𝐡𝐞 𝐚𝐩𝐩 𝐝𝐨𝐞𝐬:

📄 Parses the papers that you upload thanks to LlamaIndex🦙 (either with LlamaParse or with simpler, local methods)
📄 Embeds documents both with a sparse and with a dense encoder to enable hybrid search
📄 Uploads the embeddings to Qdrant
⚙️ Activates an Agent based on mistralai/Mistral-Small-24B-Instruct-2501 that will reply to your prompt
🧠 Retrieves information relevant to your question from the documents
🧠 If no relevant information is found, it searches PubMed and arXiv databases
🧠 Returns a grounded answer to your prompt

𝐇𝐨𝐰 𝐝𝐢𝐝 𝐈 𝐦𝐚𝐧𝐚𝐠𝐞 𝐭𝐨 𝐦𝐚𝐤𝐞 𝐭𝐡𝐢𝐬 𝐚𝐩𝐩𝐥𝐢𝐜𝐚𝐭𝐢𝐨𝐧 𝐢𝐧 𝟖 𝐡𝐨𝐮𝐫𝐬?

Three key points:

- LlamaIndex🦙 provides countless integrations with LLM providers, text embedding models and vectorstore services, and takes care of the internal architecture of the Agent. You just plug it in, and it works!🔌⚡
- Qdrant is a vector database service extremely easy to set up and use: you just need a one-line Docker command😉
- Gradio makes frontend development painless and fast, while still providing modern and responsive interfaces🏗️

And a bonus point:

- Deploying the demo app couldn't be easier if you use Gradio-based Hugging Face Spaces🤗

So, no more excuses: build your own AI agent today and do it fast, (almost) for free and effortlessly🚀

And if you need a starting point, the code for PapersChat is open and fully reproducible on GitHub 👉 https://github.com/AstraBert/PapersChat