HomeProjectsArticlesPK BoardAbout
Explore Projects

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

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

Strengths & Limitations

✅ Strengths

  • • Actively maintained, recent updates
  • • High community interest (11.9k stars)
  • • Permissive open-source license (Apache-2.0)
  • • Established track record (3 years in production)

Tags

llmops rag workflow evaluation enterprise typescript

Categories

📚 RAG Tools 🔄 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

FastGPT

29.5k · TypeScript
Active A

FastGPT is a knowledge-based platform built on LLMs, offering out-of-the-box capabilities such as data processing, RAG retrieval, and visual AI workflow orchestration for easily developing and deploying complex question-answering systems.

ragworkflowknowledge-base +2
  • · Visual workflow orchestration — Flow editor for dialogue and plugin flows with RPA nodes and bidirectional MCP
  • · Knowledge base management — supports txt/md/pdf/docx/pptx/csv import with hybrid search and reranking
  • · Application evaluation — complete call chain logs, knowledge base point testing, and app-level evaluations
View full details → View on GitHub

Unstract

7.2k · Python
Active A+

LLM-driven extraction of unstructured data, built for API deployments and ETL pipeline workflows. Automates document parsing, PDF extraction, and intelligent data processing with LLM-powered intelligence.

data-processingragpython +3
  • · Prompt Studio defines document extraction schemas with natural language
  • · Supports REST API deployment and ETL pipeline workflows
  • · MCP Server integration connecting to Claude and other AI agents
View full details → View on GitHub

DocETL

4.1k · Python
Active A

An agentic LLM-powered data processing and ETL system. Enables complex data transformations using natural language-defined pipelines, turning unstructured data into structured, analyzable outputs with LLM intelligence.

data-processingragpython +3
  • · LLM-powered data processing pipeline engine with operators like map, reduce, resolve, gleaning, and filter for complex document transformations
  • · DocWrangler interactive UI playground for iterative prompt engineering — experiment with prompts and see results in real-time
  • · Python package for production pipelines runnable from command line or Python code with full programmatic control
View on GitHub