-
π I am a Full-Stack Developer and AI-Developer from El Salvador
-
π Visit my Portfolio
-
π Visit my Blog
-
π€ My AI models and datasets on HuggingFace
-
My Own Initiatives: Aquiles-ai - AI Solutions Ecosystem focused on RAG and inference optimization - View on HuggingFace
-
π οΈ Techstack:
- β‘ Back end: FastAPI (Python) for a lightweight, scalable backend
- π¨ Front end: HTML Templates + TailwindCSS or Vite + React with TailwindCSS for a clean, responsive UI
- πΎ Databases: PostgreSQL, SQLite, MySQL, Redis
- π€ AI & Integrations: OpenAI, Google Gemini, Anthropic Claude, RAG pipelines, text-to-speech, and more
- π Service Integration: REST APIs, WebSockets, real-time data
- π³ Payment Integration: Stripe, PayPal
- π RAG & Vector Search: Supabase pgvector, Pinecone, OpenAI Embeddings, semantic search
-
βοΈ Deployment:
- π Vercel: Serverless deployments with zero configuration and instant previews
- π³ DigitalOcean: Flexible Droplets for apps and databases
- π§ AWS EC2: Full control and scalability with custom instances
Pinned Loading
-
huggingface/diffusers
huggingface/diffusers Publicπ€ Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
-
Aquiles-ai/Aquiles-RAG
Aquiles-ai/Aquiles-RAG PublicAquiles-RAG is a high-performance Augmented Recovery-Generation (RAG) solution based on Redis, Qdrant or PostgreSQL. It offers a high-level interface using FastAPI REST APIs
-
LLaDA-from-scratch
LLaDA-from-scratch PublicLLaDA is a diffusion model for natural language that, unlike traditional autoregressive models, learns to model the distribution of text through a process of progressive data masking and its inversβ¦
Python 12
-
AtlasServer-Core/AtlasServer-Core
AtlasServer-Core/AtlasServer-Core Publicπ» Fast deploy. No cloud. Just code.
HTML 12
-
Aquiles-ai/aquiles-playground
Aquiles-ai/aquiles-playground PublicEasy-to-use chat interface for running and testing Aquiles AI models locally. Supports medical reasoning (Asclepio-8B) and image-to-code generation (Qwen2.5-VL).
TypeScript 1
If the problem persists, check the GitHub status page or contact support.