Bisheng | Awesome Repository

Bisheng is an enterprise AI framework and LLM DevOps platform designed to manage the full lifecycle of large language models. It provides a unified system for dataset curation, supervised fine-tuning, model versioning, and performance evaluation.

The platform features a visual workflow orchestrator for building retrieval-augmented generation pipelines and complex task sequences using flowcharts with conditional logic and human intervention points. It also includes an AI agent framework that uses a specialized guidance language to embed domain expertise and professional business logic into autonomous agents.

The system covers comprehensive enterprise AI governance through role-based access control, single sign-on, and integrated observability tools for monitoring system health and traffic. Additional capabilities include layout-aware document parsing for extracting text and tables from printed or handwritten sources and high-availability infrastructure deployment.

Features

LLM Lifecycle Management - Coordinates the full LLM lifecycle including dataset curation, supervised fine-tuning, versioning, and performance evaluation.
LLM Operations Platforms - Manages the full lifecycle of large language models including fine-tuning, dataset curation and performance evaluation in a corporate environment.
Expert Logic Embedding - Allows users to embed professional preferences and business logic into AI agents using a specialized guidance language.

Features

LLM Lifecycle Management - Coordinates the full LLM lifecycle including dataset curation, supervised fine-tuning, versioning, and performance evaluation.
LLM Operations Platforms - Manages the full lifecycle of large language models including fine-tuning, dataset curation and performance evaluation in a corporate environment.
Expert Logic Embedding - Allows users to embed professional preferences and business logic into AI agents using a specialized guidance language.