Stars
Created pipelines for Semantic Search, Metadata Filtering, Hybrid Search, Reranking, and Retrieval-Augmented Generation (RAG) for the TriviaQA, ARC, PopQA, FactScore, and Edgar datasets. These pipe…
Dataloaders is a versatile library designed for processing and formatting datasets to support various Retrieval-Augmented Generation (RAG) pipelines, facilitating efficient evaluation and analysis.
Effect of Optimizer Selection and Hyperparameter Tuning on Training Efficiency and LLM Performance
Performance Evaluation of Rankers and RRF Techniques for Retrieval Pipelines
MTEB: Massive Text Embedding Benchmark
Automatically generate comprehensive Pull Request descriptions with LLMs
AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data…
Open-source tools for prompt testing and experimentation, with support for both LLMs (e.g. OpenAI, LLaMA) and vector databases (e.g. Chroma, Weaviate, LanceDB).
🤗 Evaluate: A library for easily evaluating machine learning models and datasets.
scikit-learn: machine learning in Python