Python 排行榜

Train a SmolLM-style llm on fineweb-edu in JAX/Flax with an assortment of optimizers.

MultimodalHugs is an extension of Hugging Face that offers a generalized framework for training, evaluating, and using multimodal AI models with minimal code differences, ensuring seamless compatibility with Hugging Face pipelines.

Llava, Ollama and Streamlit | Create POWERFUL Image Analyzer Chatbot for FREE - Windows & Mac

My own playground for PLP (Programming Language Processing) using DeepLearning techniques

Perform visual question answering on your images

Bringing some SQL to Qdrant

Vector compression with TurboQuant codecs for embeddings, retrieval, and KV-cache. 10x compression, pure NumPy core — optional GPU acceleration via PyTorch (CUDA/MPS) or MLX (Metal).

A Python SDK for OceanBase Multimodal Store—enabling vector search, full-text search, and JSON table operations—offers both Milvus-compatible API and SQLAlchemy-based SQL mode, and supports both OceanBase and OceanBase seekdb.

Turn your Google Search Console data into a vector database and analyze search performance with AI (Gemini, Grok, Claude)

PostgreSQL-native semantic search engine with multi-modal capabilities. Add AI-powered search to your existing database without separate vector databases, vendor fees, or complex setup. Features text + image search using CLIP embeddings, native SQL joins, and 10-minute Docker deployment.

Unraid CA template and Docker build for Mem0 (OpenMemory). This mega-container utilizes s6-overlay to seamlessly bundle the pre-compiled Qdrant Vector Database, the Python FastAPI/MCP server, and the Next.js Dashboard UI into a single, click-and-play local AI memory layer. Built for homelabs, privacy, and true agentic AI memory retention.

Code from the ODSC Agentic Graph RAG workshop combining vector, FTS & graph retrieval for RAG. Includes observability and guardrails for evaluating outputs.

Local AI load balancer for Ollama and MLX fleets. Auto-discovery, smart routing, OpenAI-compatible API, zero config. Perfect for Mac Minis & Studios.

Generate editable scientific SVG figures from method text with local SAM3 and dual-provider routing.

Official Implementation for Pre-CoFact (AAAI-22 DeFactify Workshop Best Paper)

ComfyUI custom nodes for Google Gemini Omni — text-to-video, image-to-video, and video editing via the Gemini Omni API on muapi.ai

基于 SiliconFlow API 的语音转文字桌面工具，支持 PyQt5 图形界面、音频文件批量转录和结果编辑管理 | A PyQt5 desktop app for speech-to-text transcription using SiliconFlow API

A global voice dictation tool for Linux using local OpenAI Whisper. Fast, accurate, and works on Wayland/X11.

Mandarin Chinese audio datasets aligned with Montreal Forced Aligner

Many ASRs under one roof. With Benchmarking... answering the question. What is the best ASR for my dataset?