Bisheng

Active
GitHub Python Apache-2.0

Description

Open-source LLM DevOps platform providing one-stop AI application development with GenAI workflow, RAG, Agent, model management, evaluation, and enterprise system administration.

Key Features

  • Lingsight general-purpose agent: embeds domain expert preferences via AGL (Agent Guidance Language) for expert-level task handling
  • Unique workflow engine: supports loops, parallelism, batch processing, conditional logic, and human-in-the-loop intervention
  • Enterprise-grade platform: RBAC, SSO/LDAP, user group management, traffic control, vulnerability scanning, and high-availability deployment
  • High-precision document parsing: trained OCR for printed text, handwriting, rare characters, tables, layout analysis, and seals
  • RAG, Agent, model management, evaluation, and dataset management in one unified platform
  • One-click Docker deployment with ES, Milvus, and OnlyOffice pre-configured

Use Cases

πŸ’‘ Enterprise document review and fixed-layout report generation with AI-assisted workflows
πŸ’‘ Policy update comparison, support ticket assistance, and meeting minutes generation
πŸ’‘ Multi-agent collaboration for complex business processes with human-in-the-loop approval
πŸ’‘ Unstructured data governance, knowledge mining, and data analysis for Fortune 500 companies

Tags

llmops rag workflow evaluation enterprise typescript

Categories

πŸ“š RAG Tools πŸ”„ Workflow

Quick Start

Clone the repo, run `cd bisheng/docker && docker compose -f docker-compose.yml -p bisheng up -d`, then access http://IP:3001 in your browser. The first registered user becomes the system admin. Minimum requirements: 4 CPU cores, 16GB RAM, Docker 19.03.9+.
Visit GitHub

Related Projects