Clelia (Astra) Bertelli's picture

Clelia (Astra) Bertelli

as-cle-bert

AI & ML interests

Biology + Artificial Intelligence = โค๏ธ | AI for sustainable development, sustainable development for AI | Researching on Machine Learning Enhancement | I love automation for everyday things | Blogger | Open Source

Recent Activity

posted an update about 10 hours ago
I built an AI agent app in less than 8 hours๐Ÿคฏ And, believe me, this is ๐—ป๐—ผ๐˜ clickbaitโŒ GitHub ๐Ÿ‘‰ https://github.com/AstraBert/PapersChat Demo ๐Ÿ‘‰ https://huggingface.co/spaces/as-cle-bert/PapersChat The app is called ๐๐š๐ฉ๐ž๐ซ๐ฌ๐‚๐ก๐š๐ญ, and it is aimed at ๐—บ๐—ฎ๐—ธ๐—ถ๐—ป๐—ด ๐—ฐ๐—ต๐—ฎ๐˜๐˜๐—ถ๐—ป๐—ด ๐˜„๐—ถ๐˜๐—ต ๐˜€๐—ฐ๐—ถ๐—ฒ๐—ป๐˜๐—ถ๐—ณ๐—ถ๐—ฐ ๐—ฝ๐—ฎ๐—ฝ๐—ฒ๐—ฟ๐˜€ ๐—ฒ๐—ฎ๐˜€๐—ถ๐—ฒ๐—ฟ. ๐‡๐ž๐ซ๐ž ๐ข๐ฌ ๐ฐ๐ก๐š๐ญ ๐ญ๐ก๐ž ๐š๐ฉ๐ฉ ๐๐จ๐ž๐ฌ: ๐Ÿ“„ Parses the papers that you upload thanks to LlamaIndex๐Ÿฆ™ (either with LlamaParse or with simpler, local methods) ๐Ÿ“„ Embeds documents both with a sparse and with a dense encoder to enable hybrid search ๐Ÿ“„ Uploads the embeddings to Qdrant โš™๏ธ Activates an Agent based on https://huggingface.co/mistralai/Mistral-Small-24B-Instruct-2501 that will reply to your prompt ๐Ÿง  Retrieves information relevant to your question from the documents ๐Ÿง  If no relevant information is found, it searches PubMed and arXiv databases ๐Ÿง  Returns a grounded answer to your prompt ๐‡๐จ๐ฐ ๐๐ข๐ ๐ˆ ๐ฆ๐š๐ง๐š๐ ๐ž ๐ญ๐จ ๐ฆ๐š๐ค๐ž ๐ญ๐ก๐ข๐ฌ ๐š๐ฉ๐ฉ๐ฅ๐ข๐œ๐š๐ญ๐ข๐จ๐ง ๐ข๐ง ๐Ÿ– ๐ก๐จ๐ฎ๐ซ๐ฌ? Three key points: - LlamaIndex๐Ÿฆ™ 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!๐Ÿ”Œโšก - Qdrant is a vector database service extremely easy to set up and use: you just need a one-line Docker command๐Ÿ˜‰ - Gradio makes frontend development painless and fast, while still providing modern and responsive interfaces๐Ÿ—๏ธ And a bonus point: - Deploying the demo app couldn't be easier if you use Gradio-based Hugging Face Spaces๐Ÿค— So, no more excuses: build your own AI agent today and do it fast, (almost) for free and effortlessly๐Ÿš€ And if you need a starting point, the code for PapersChat is open and fully reproducible on GitHub ๐Ÿ‘‰ https://github.com/AstraBert/PapersChat
updated a Space 1 day ago
as-cle-bert/PapersChat
liked a Space 1 day ago
as-cle-bert/PapersChat
View all activity

Organizations

Social Post Explorers's profile picture Hugging Face Discord Community's profile picture GreenFit AI's profile picture

as-cle-bert's activity

posted an update about 10 hours ago
view post
Post
502
I built an AI agent app in less than 8 hours๐Ÿคฏ
And, believe me, this is ๐—ป๐—ผ๐˜ clickbaitโŒ

GitHub ๐Ÿ‘‰ https://github.com/AstraBert/PapersChat
Demo ๐Ÿ‘‰ as-cle-bert/PapersChat

The app is called ๐๐š๐ฉ๐ž๐ซ๐ฌ๐‚๐ก๐š๐ญ, and it is aimed at ๐—บ๐—ฎ๐—ธ๐—ถ๐—ป๐—ด ๐—ฐ๐—ต๐—ฎ๐˜๐˜๐—ถ๐—ป๐—ด ๐˜„๐—ถ๐˜๐—ต ๐˜€๐—ฐ๐—ถ๐—ฒ๐—ป๐˜๐—ถ๐—ณ๐—ถ๐—ฐ ๐—ฝ๐—ฎ๐—ฝ๐—ฒ๐—ฟ๐˜€ ๐—ฒ๐—ฎ๐˜€๐—ถ๐—ฒ๐—ฟ.

๐‡๐ž๐ซ๐ž ๐ข๐ฌ ๐ฐ๐ก๐š๐ญ ๐ญ๐ก๐ž ๐š๐ฉ๐ฉ ๐๐จ๐ž๐ฌ:

๐Ÿ“„ Parses the papers that you upload thanks to LlamaIndex๐Ÿฆ™ (either with LlamaParse or with simpler, local methods)
๐Ÿ“„ Embeds documents both with a sparse and with a dense encoder to enable hybrid search
๐Ÿ“„ Uploads the embeddings to Qdrant
โš™๏ธ Activates an Agent based on mistralai/Mistral-Small-24B-Instruct-2501 that will reply to your prompt
๐Ÿง  Retrieves information relevant to your question from the documents
๐Ÿง  If no relevant information is found, it searches PubMed and arXiv databases
๐Ÿง  Returns a grounded answer to your prompt

๐‡๐จ๐ฐ ๐๐ข๐ ๐ˆ ๐ฆ๐š๐ง๐š๐ ๐ž ๐ญ๐จ ๐ฆ๐š๐ค๐ž ๐ญ๐ก๐ข๐ฌ ๐š๐ฉ๐ฉ๐ฅ๐ข๐œ๐š๐ญ๐ข๐จ๐ง ๐ข๐ง ๐Ÿ– ๐ก๐จ๐ฎ๐ซ๐ฌ?

Three key points:

- LlamaIndex๐Ÿฆ™ 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!๐Ÿ”Œโšก
- Qdrant is a vector database service extremely easy to set up and use: you just need a one-line Docker command๐Ÿ˜‰
- Gradio makes frontend development painless and fast, while still providing modern and responsive interfaces๐Ÿ—๏ธ

And a bonus point:

- Deploying the demo app couldn't be easier if you use Gradio-based Hugging Face Spaces๐Ÿค—

So, no more excuses: build your own AI agent today and do it fast, (almost) for free and effortlessly๐Ÿš€

And if you need a starting point, the code for PapersChat is open and fully reproducible on GitHub ๐Ÿ‘‰ https://github.com/AstraBert/PapersChat
posted an update 4 days ago
view post
Post
1336
๐’๐œ๐ข๐๐ž๐ฐ๐ฌ๐๐จ๐ญ - ๐‘๐ž๐ฉ๐จ๐ซ๐ญ ๐๐š๐ข๐ฅ๐ฒ ๐’๐œ๐ข๐ž๐ง๐œ๐ž ๐ง๐ž๐ฐ๐ฌ ๐จ๐ง ๐๐ฅ๐ฎ๐ž๐’๐ค๐ฒ

GitHub ๐Ÿ‘‰ https://github.com/AstraBert/SciNewsBot
BlueSky ๐Ÿ‘‰ https://bsky.app/profile/sci-news-bot.bsky.social

Hi there HF Community!๐Ÿค—
I just created a very simple AI-powered bot that shares fact-checked news about Science, Environment, Energy and Technology on BlueSky :)

The bot takes news from Google News, filters out the sources that are not represented in the Media Bias Fact Check database, and then evaluates the reliability of the source based on the MBFC metrics. After that, it creates a catchy headline for the article and publishes the post on BlueSky๐Ÿ“ฐ

The cool thing? SciNewsBot is open-source and is cheap to maintain, as it is based on mistralai/Mistral-Small-24B-Instruct-2501 (via Mistral API). You can reproduce it locally, spinning it up on your machine, and even launch it on cloud through a comfy Docker setup๐Ÿ‹

Have fun and spread Science!โœจ
posted an update 7 days ago
view post
Post
2705
๐๐ก๐ข๐๐ฐ๐ž๐ง๐’๐“๐„๐Œ - ๐š ๐ซ๐ž๐š๐ฌ๐จ๐ง๐ข๐ง๐  ๐š๐ฌ๐ฌ๐ข๐ฌ๐ญ๐š๐ง๐ญ ๐Ÿ๐จ๐ซ ๐ฒ๐จ๐ฎ๐ซ ๐’๐“๐„๐Œ ๐ž๐๐ฎ๐œ๐š๐ญ๐ข๐จ๐ง

Demo ๐Ÿ‘‰ https://pqstem.org
GitHub ๐Ÿ‘‰ https://github.com/AstraBert/PhiQwenSTEM

Hello HF community!๐Ÿค—
Ever struggled with some complex Maths problem or with a very hard Physics question? Well, fear no more, because now you can rely on PhiQwenSTEM, an assistant specialized in answering STEM-related question!
The assistant can count on a knowledge base of ๐Ÿญ๐Ÿฑ๐—ธ+ ๐˜€๐—ฒ๐—น๐—ฒ๐—ฐ๐˜๐—ฒ๐—ฑ ๐—ฆ๐—ง๐—˜๐—  ๐—พ๐˜‚๐—ฒ๐˜€๐˜๐—ถ๐—ผ๐—ป-๐—ฎ๐—ป๐˜€๐˜„๐—ฒ๐—ฟ ๐—ฝ๐—ฎ๐—ถ๐—ฟ๐˜€ spanning the domains of Chemistry, Physics, Matemathics and Biochemistry (from EricLu/SCP-116K). It also relies on the combined power of microsoft/Phi-3.5-mini-instruct and Qwen/QwQ-32B-Preview to produce reliable and reasoned answers.
For the next 30 days, you will be able to try for free the web demo: https://pqstem.org
In the GitHub repo you can find all the information to reproduce PhiQwenSTEM ๐—ผ๐—ป ๐˜†๐—ผ๐˜‚๐—ฟ ๐—น๐—ผ๐—ฐ๐—ฎ๐—น ๐—บ๐—ฎ๐—ฐ๐—ต๐—ถ๐—ป๐—ฒ, ๐—ฏ๐—ผ๐˜๐—ต ๐˜ƒ๐—ถ๐—ฎ ๐˜€๐—ผ๐˜‚๐—ฟ๐—ฐ๐—ฒ ๐—ฐ๐—ผ๐—ฑ๐—ฒ ๐—ฎ๐—ป๐—ฑ ๐˜„๐—ถ๐˜๐—ต ๐—ฎ ๐—ฐ๐—ผ๐—บ๐—ณ๐˜† ๐——๐—ผ๐—ฐ๐—ธ๐—ฒ๐—ฟ๐Ÿ‹ ๐˜€๐—ฒ๐˜๐˜‚๐—ฝ: https://github.com/AstraBert/PhiQwenSTEM
posted an update 18 days ago
view post
Post
1017
Hi HuggingFace community!๐Ÿค—

I just published an article in which I try to articulate some counter-points to Dario Amodei's post "On DeepSeek and Export Control"๐Ÿ‘‰ https://huggingface.co/blog/as-cle-bert/why-we-dont-need-export-control

I try to address several key passages of the third section from Amodei's post (https://darioamodei.com/on-deepseek-and-export-controls), bringing my perspective on the importance of open source, open knowledge and multipolarity in a crucial field for our future such as Artificial Intelligence.

Happy reading!โœจ
replied to their post 29 days ago
view reply

Hi!

I generally use LangChain + PyPDF, I leave here a code snippet:

from langchain_community.document_loaders import PyPDFLoader

def preprocess(pdf: str) -> list:
    """
    Uses LangChain's PyPDFLoader to extract text.
    """
    loader = PyPDFLoader(pdf)
    documents = loader.load()
    for doc in documents:
        print(doc.page_content)    

This should give a more solid result :)

PS: Langchain is distributed under an MIT license, see their GitHub (https://github.com/langchain-ai/langchain)

posted an update 30 days ago
view post
Post
1597
๐Ÿš€๐๐ž๐ฐ ๐๐ž๐ฆ๐จ ๐š๐ฅ๐ž๐ซ๐ญ๐Ÿš€

Convert (almost) everything to PDF with ๐๐๐Ÿ๐ˆ๐ญ๐ƒ๐จ๐ฐ๐ง, now on Spaces! ๐Ÿ‘‰ as-cle-bert/pdfitdown

You can also install it locally:

python3 -m pip install pdfitdown


Don't forget to star it on GitHub, if you find it useful! ๐Ÿ‘‰ https://www.github.com/AstraBert/PdfItDown

  • 3 replies
ยท
posted an update about 1 month ago
view post
Post
564
Hi HuggingFace Community๐Ÿค—, I am thrilled to announce:

๐ช๐๐ฎ๐ซ๐ฅ๐ฅ๐ฆ ๐šŸ๐Ÿท-๐š›๐šŒ.๐Ÿท (https://github.com/AstraBert/qdurllm/tree/january-2025)

Qdurllm (๐—ค๐—ฑrant, ๐—จ๐—ฅLs, ๐—Ÿarge ๐—Ÿanguage ๐— odels) is a local Gradio (Gradio) application that lets you upload you web content to a local Qdrant (Qdrant) database and search through it or chat with it.

The ๐—ป๐—ฒ๐˜„ ๐—ฝ๐—ฟ๐—ฒ-๐—ฟ๐—ฒ๐—น๐—ฒ๐—ฎ๐˜€๐—ฒ (https://github.com/AstraBert/qdurllm/releases/tag/v1.0.0-rc.0) implements ๐˜€๐—ฝ๐—ฎ๐—ฟ๐˜€๐—ฒ ๐˜€๐—ฒ๐—ฎ๐—ฟ๐—ฐ๐—ต (with prithivida/Splade_PP_en_v1) + ๐—ฟ๐—ฒ๐—ฟ๐—ฎ๐—ป๐—ธ๐—ถ๐—ป๐—ด (with nomic-ai/modernbert-embed-base by Hugging Face + Nomic AI) and ๐˜€๐—ฒ๐—บ๐—ฎ๐—ป๐˜๐—ถ๐—ฐ ๐—ฐ๐—ฎ๐—ฐ๐—ต๐—ถ๐—ป๐—ด (based on Qdrant) and switched ๐—ณ๐—ฟ๐—ผ๐—บ google/gemma-2-2b-it ๐˜๐—ผ Qwen/Qwen2.5-1.5B-Instruct to conform to the SOTA landscape and to finally make the application based ๐—ผ๐—ป๐—น๐˜† ๐—ผ๐—ป ๐˜๐—ฟ๐˜‚๐—น๐˜† ๐—ผ๐—ฝ๐—ฒ๐—ป ๐—บ๐—ผ๐—ฑ๐—ฒ๐—น๐˜€.

The pre-release is ๐—ฎ๐˜ƒ๐—ฎ๐—ถ๐—น๐—ฎ๐—ฏ๐—น๐—ฒ ๐—ณ๐—ผ๐—ฟ ๐˜๐—ฒ๐˜€๐˜๐—ถ๐—ป๐—ด and I would be really really happy if you wanted to give it a try and leave your feedback on the discussion thread on GitHub (https://github.com/AstraBert/qdurllm/discussions/8) or here on Hugging Face forum via comments under this postโœจ.
Find all the information to install and launch it here ๐Ÿ‘‰ https://astrabert.github.io/qdurllm/#2-installation
replied to their post about 1 month ago
view reply

Thank you so much for letting me know! This is indeed a very interesting role :)

posted an update about 1 month ago
view post
Post
1378
Hi HuggingFace community!๐Ÿค—

I recently released PrAIvateSearch v2.0-beta.0 (https://github.com/AstraBert/PrAIvateSearch), my privacy-first, AI-powered, user-centered and data-safe application aimed at providing a local and open-source alternative to big AI search engines such as SearchGPT or Perplexity AI.

We have several key changes:

- New chat UI built with NextJS
- DuckDuckGo API used for web search instead of Google
- Qwen/Qwen2.5-1.5B-Instruct as a language model served on API (by FastAPI)
- Crawl4AI crawler used for web scraping
- Optimizations in the data workflow inside the application

Read more in my blog post ๐Ÿ‘‰ https://huggingface.co/blog/as-cle-bert/search-the-web-with-ai

Have fun and feel free to leave feedback about how to improve the application!โœจ
ยท
posted an update about 2 months ago
view post
Post
593
Are you using Obsidian to write your notes?
If the answer is yes, then this post might be for you!โœ…
I recently created ๐จ๐›๐ฌ๐ข๐๐ข๐š๐ง-๐๐ข๐ ๐ž๐ฌ๐ญ, a Google Gemini-powered application that gives you feedback on style and contents of the documents you have been working on๐Ÿง 

Repo ๐Ÿ‘‰ https://github.com/AstraBert/obsidian-digest
PyPi Package ๐Ÿ‘‰ https://pypi.org/project/obsidian-digest/

The app is available as:
- ๐œ๐จ๐ฆ๐ฆ๐š๐ง๐-๐ฅ๐ข๐ง๐ž ๐ญ๐จ๐จ๐ฅ: install it as a python package with ๐—ฝ๐—ถ๐—ฝ, and execute it from terminal anytime!๐Ÿ“ฆ
-๐ƒ๐ข๐ฌ๐œ๐จ๐ซ๐ ๐๐จ๐ญ ๐›๐ฎ๐ข๐ฅ๐ญ ๐Ÿ๐ซ๐จ๐ฆ ๐ฌ๐จ๐ฎ๐ซ๐œ๐ž ๐œ๐จ๐๐ž: clone the GitHub repo, install the needed dependencies through ๐—ฐ๐—ผ๐—ป๐—ฑ๐—ฎ, and run the bot: you will get hourly messages with suggestions and considerations about your activity on Obsidian in the previous hour๐Ÿค–
- ๐ƒ๐ข๐ฌ๐œ๐จ๐ซ๐ ๐๐จ๐ญ ๐๐ž๐ฉ๐ฅ๐จ๐ฒ๐ž๐ ๐ฅ๐จ๐œ๐š๐ฅ๐ฅ๐ฒ ๐ฐ๐ข๐ญ๐ก ๐๐จ๐œ๐ค๐ž๐ซ ๐œ๐จ๐ฆ๐ฉ๐จ๐ฌ๐ž: clone the GitHub repo and launch ๐—ฑ๐—ผ๐—ฐ๐—ธ๐—ฒ๐—ฟ ๐—ฐ๐—ผ๐—บ๐—ฝ๐—ผ๐˜€๐—ฒ ๐˜‚๐—ฝ. Docker builds an image on the fly with all the needed dependencies and scripts, and runs them. You'll have the same functionalities as the ones from source code, but with a way easier deployment process๐Ÿ‹

Go check out the GitHub repo for more info ๐Ÿ‘‰ https://github.com/AstraBert/obsidian-digest

Have fun!โœจ
  • 1 reply
ยท
replied to their post about 2 months ago
view reply

Hi and thanks a lot for the specification!๐Ÿฅฐ

Just as a note from my side, in the article I specify that there is a difference between "open weights" and "open source" models, and I link this blog post: https://www.agora.software/en/llm-open-source-open-weight-or-proprietary/ for a deeper explanation of the difference. I never (and I would never) claimed that Llama is open source, let alone a free software (see the introduction in this article of mine on privacy and data "stealing" risks: https://huggingface.co/blog/as-cle-bert/build-an-ai-powered-search-engine-from-scratch).

And I would have gladly used also DeepSeek, if it had been available on HuggingChat! :)

I nevertheless highly appreciate your comment and I'll for sure be more cautious in using the word "open/open source" in the future. Thanks!โœจ

replied to their post about 2 months ago
view reply

Both PdfItDown and SenTrEv only work with text for now: in future releases, support for image will be added :)
For text extraction, I use PyPDF + Langchain

posted an update about 2 months ago
view post
Post
2086
๐ŸŽ‰๐„๐š๐ซ๐ฅ๐ฒ ๐๐ž๐ฐ ๐˜๐ž๐š๐ซ ๐ซ๐ž๐ฅ๐ž๐š๐ฌ๐ž๐ฌ๐ŸŽ‰

Hi HuggingFacers๐Ÿค—, I decided to ship early this year, and here's what I came up with:

๐๐๐Ÿ๐ˆ๐ญ๐ƒ๐จ๐ฐ๐ง (https://github.com/AstraBert/PdfItDown) - If you're like me, and you have all your RAG pipeline optimized for PDFs, but not for other data formats, here is your solution! With PdfItDown, you can convert Word documents, presentations, HTML pages, markdown sheets and (why not?) CSVs and XMLs in PDF format, for seamless integration with your RAG pipelines. Built upon MarkItDown by Microsoft
GitHub Repo ๐Ÿ‘‰ https://github.com/AstraBert/PdfItDown
PyPi Package ๐Ÿ‘‰ https://pypi.org/project/pdfitdown/

๐’๐ž๐ง๐“๐ซ๐„๐ฏ ๐ฏ๐Ÿ.๐ŸŽ.๐ŸŽ (https://github.com/AstraBert/SenTrEv/tree/v1.0.0) - If you need to evaluate the ๐—ฟ๐—ฒ๐˜๐—ฟ๐—ถ๐—ฒ๐˜ƒ๐—ฎ๐—น performance of your ๐˜๐—ฒ๐˜…๐˜ ๐—ฒ๐—บ๐—ฏ๐—ฒ๐—ฑ๐—ฑ๐—ถ๐—ป๐—ด models, I have good news for you๐Ÿฅณ๐Ÿฅณ
The new release for ๐’๐ž๐ง๐“๐ซ๐„๐ฏ now supports ๐—ฑ๐—ฒ๐—ป๐˜€๐—ฒ and ๐˜€๐—ฝ๐—ฎ๐—ฟ๐˜€๐—ฒ retrieval (thanks to FastEmbed by Qdrant) with ๐˜๐—ฒ๐˜…๐˜-๐—ฏ๐—ฎ๐˜€๐—ฒ๐—ฑ ๐—ณ๐—ถ๐—น๐—ฒ ๐—ณ๐—ผ๐—ฟ๐—บ๐—ฎ๐˜๐˜€ (.docx, .pptx, .csv, .html, .xml, .md, .pdf) and new ๐—ฟ๐—ฒ๐—น๐—ฒ๐˜ƒ๐—ฎ๐—ป๐—ฐ๐—ฒ ๐—บ๐—ฒ๐˜๐—ฟ๐—ถ๐—ฐ๐˜€!
GitHub repo ๐Ÿ‘‰ https://github.com/AstraBert/SenTrEv
Release Notes ๐Ÿ‘‰ https://github.com/AstraBert/SenTrEv/releases/tag/v1.0.0
PyPi Package ๐Ÿ‘‰ https://pypi.org/project/sentrev/

Happy New Year and have fun!๐Ÿฅ‚
  • 2 replies
ยท
reacted to nroggendorff's post with โž• about 2 months ago
view post
Post
6327
hey nvidia, can you send me a gpu?
comment or react if you want ~~me~~ to get one too. ๐Ÿ‘‰๐Ÿ‘ˆ
ยท
posted an update about 2 months ago
view post
Post
561
Hi HF Community!๐Ÿค—

As my last 2024 contribution, I decided to write an article about a Competitive Debate Championship simulation I ran with 5 LLMs as competitors and 2 as judges:

https://huggingface.co/blog/as-cle-bert/debate-championship-for-llms

The article covers code, analyses and results, and you can find everything to reproduce this tournament in the GitHub repo ๐Ÿ‘‰ https://github.com/AstraBert/DebateLLM-Championship

I also released a dataset related to the data (motions, arguments, topics, winners...) collected during the tournament ๐Ÿ‘‰ as-cle-bert/DebateLLMs

Happy reading and happy new yeAIr!๐ŸŽ‰
  • 3 replies
ยท
posted an update about 2 months ago
posted an update about 2 months ago
view post
Post
1724
Hi HuggingFacers!๐Ÿคถ๐Ÿผ

As my last 2024 project, I've dropped a Discord Bot that knows a lot about Pokemons๐Ÿฆ‹

GitHub ๐Ÿ‘‰ https://github.com/AstraBert/Pokemon-Bot
Demo Space ๐Ÿ‘‰ as-cle-bert/pokemon-bot

The bot integrates:
- Chat features (Cohere's Command-R) with RAG functionalities (hybrid search and reranking with Qdrant) and chat memory (managed through PostgreSQL) to produce information about Pokemons
- Image-based search to identify Pokemons from their images (via Qdrant)
- Card package random extraction and description

HuggingFace๐Ÿค—, as usual, plays the most important role in the application stack, with the following models:

- sentence-transformers/LaBSE
- prithivida/Splade_PP_en_v1
- facebook/dinov2-large

And datasets:

- Karbo31881/Pokemon_images
- wanghaofan/pokemon-wiki-captions
- TheFusion21/PokemonCards

Have fun!๐Ÿ•
posted an update 2 months ago
posted an update 3 months ago
view post
Post
1419
Hi HuggingFacers!๐Ÿค—
December is here and time has come, for most of us, to wrap up our code projects and take stock of our 2024 contributions๐Ÿ—“๏ธ
In order to do this, I made a small Gradio application, what-a-git-year:

as-cle-bert/what-a-git-year

that scrapes information from your GitHub profile and summarizes them, producing also nice plots๐Ÿ“Š
Find also the GitHub repo here: https://github.com/AstraBert/what-a-git-year โญ

Hope that everyone had a Git year!๐ŸŽ‰
posted an update 3 months ago
view post
Post
1046
Hi there!๐Ÿค—

I just deployed a Streamlit-based space on HF that fetches your Home Feed on BlueSky and summarizes it with Cohere's CommandR via Langchain๐Ÿงช

Find it here:
as-cle-bert/bsky-feedllama-demo

I'm also working on a Gradio local implementation with Llama3.2 that for now only works with source code and doesn't have docs, but that will be soon supported by Docker๐Ÿณ and have a nice README:

https://github.com/AstraBert/bluesky-feedllama

Contributions and feedback are always welcome!๐Ÿค—๐Ÿฆ‹