Stars
A JavaScript / TypeScript / Python / C# / PHP cryptocurrency trading API with support for more than 100 bitcoin/altcoin exchanges
A high-throughput and memory-efficient inference and serving engine for LLMs
Cloud-native search engine for observability. An open-source alternative to Datadog, Elasticsearch, Loki, and Tempo.
The Short-Term Predictability of Returns in Order Book Markets: A Deep Learning Perspective.
Feature engineering of a Limit Order Book. Extraction of features from a LOB in order to analyse the behaviour of trade market.
A LLM RAG application based on LlamaIndex and Streamlit. Optimized for Chinese users by adopting BAAI embedding / reranker models, Ollama local models and using LLM API from Chinese LLM service pro…
Developer-friendly, serverless vector database for AI applications. Easily add long-term memory to your LLM apps!
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
Netease Youdao's open-source embedding and reranker models for RAG products.
Question and Answer based on Anything.
FastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabilities such as data processing, RAG retrieval, and visual AI workflow orchestration, le…
A simple feature-based time series classifier using Kolmogorov–Arnold Networks
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
A compact LLM pretrained in 9 days by using high quality data
Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of …
LlamaIndex is a data framework for your LLM applications
code for turning data sets into trading strategies
ShapeFormer: Shapelet Transformer for Multivariate Time Series Classification
DSPy: The framework for programming—not prompting—foundation models
a python-based fast quantitative investment module
GraphRAG using Local LLMs - Features robust API and multiple apps for Indexing/Prompt Tuning/Query/Chat/Visualizing/Etc. This is meant to be the ultimate GraphRAG/KG local LLM app.
Implementation of TabTransformer, attention network for tabular data, in Pytorch
FinHack®，一个易于拓展的量化金融框架，它在当前版本中集成了数据采集、因子计算、因子挖掘、因子分析、机器学习、策略编写、量化回测、实盘接入等全流程的量化投研工作。
Python toolkit for quantitative finance