Skip to content
View plaguss's full-sized avatar

Block or report plaguss

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
plaguss/README.md

👋 Hi there


I'm Agustín Piqueres (my friends call me Agus), I love building things using open source software, machine learning and python.

Agustín Piqueres' GitHub stats

📫 How to reach me: Gmail   LinkedIn  

Projects

The following table is a summary of some hobby projects, along with the stack used. Python won't be added as it is a constant across projects :).

Javascript 

Project links Summary
talking-python App to look for talk python to me podcasts using semantic search on
chroma vector database with the embeddings over the transcripts.
New data is added automatically on a weekly basis using GitHub Actions.
Deployed to Streamlit cloud.
Chroma  huggingface  Docker  Prefect  Streamlit 
translate-md (Work in progress)
Translator of markdown files using HuggingFace's Transformers.
huggingface  Rust 
spanglish Demo of a spanish to englis translator service using HuggingFace's
Transformers. Built on top of Ray Serve and FastAPI.
ray  Rust  huggingface  Docker 
helpner CLI program to detect (and highlight) the contents of other CLI help
messages directly from the console. The model is trained on a synthetic
dataset using spaCy, and the console rendering is done with rich.
spaCy  spaCy 
pytokei Python bindings to Rust's tokei.
Rust  PyO3 
Master thesis (Spanish only)
App to classify CrossFit movement videos using a fine-tuned
version of MoViNets on a novel dataset, deployed behind an AWS
Lambda function on a Docker image.
Created with Plotly's Dash, deployed to AWS ECS,
CI/CD with CodeDeploy and CodePipeline.
tensorflow  opencv  aws 

Pinned Loading

  1. argilla-io/distilabel argilla-io/distilabel Public

    Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers.

    Python 1.7k 132

  2. argilla-io/argilla argilla-io/argilla Public

    Argilla is a collaboration tool for AI engineers and domain experts to build high-quality datasets

    Python 4.1k 382

  3. talking-python talking-python Public

    🐍 Repository for the explore talk python to me app

    Python 1

  4. pytokei pytokei Public

    Python bindings for tokei

    Python 4 1