bisheng
BISHENG is an open LLM devops platform for next generation Enterprise AI applications. Powerful and comprehensive features include: GenAI workflow, RAG, Agent,
What is bisheng?
BISHENG is an open LLM devops platform for next generation Enterprise AI applications. Powerful and comprehensive features include: GenAI workflow, RAG, Agent, Unified model management, Evaluation, SFT, Dataset Management, Enterprise-level System Management, Observability and more.
Overview of bisheng
What it is
BISHENG is an open LLM application devops platform focusing on enterprise scenarios. It is named after Bi Sheng, the inventor of movable type printing. The platform has been used by industry leading organizations and Fortune 500 companies.
Key features
- Lingsight, a general-purpose agent using the AGL (Agent Guidance Language) framework to embed domain experts’ preferences, experience, and business logic.
- Unique BISHENG Workflow: independent and comprehensive application orchestration framework; human-in-the-loop intervention; supports loops, parallelism, batch processing, conditional logic; user-friendly visual flowchart.
- Designed for enterprise applications: document review, fixed-layout report generation, multi-agent collaboration, policy update comparison, support ticket assistance, customer service assistance, meeting minutes generation, resume screening, call record analysis, unstructured data governance, knowledge mining, data analysis, and more.
- Enterprise-grade features: security review, RBAC, user group management, traffic control by group, SSO/LDAP, vulnerability scanning and patching, high availability deployment, monitoring, statistics.
- High-Precision Document Parsing: trained on a large amount of high-quality data accumulated over 5 years; includes printed text, handwritten text, rare character recognition, table recognition, layout analysis, and seal models; can be deployed privately for free.
- A community for sharing best practices across various enterprise scenarios.
Use cases
The platform supports construction of highly complex enterprise application scenarios. Example use cases include document review, fixed-layout report generation, multi-agent collaboration, policy update comparison, support ticket assistance, customer service assistance, meeting minutes generation, resume screening, call record analysis, unstructured data governance, knowledge mining, and data analysis.
Getting started
Prerequisites: CPU >= 4 Virtual Cores, RAM >= 16 GB, Docker 19.03.9+, Docker Compose 1.25.1+. Recommended hardware: 18 virtual cores, 48 GB RAM. Third-party components (ES, Milvus, Onlyoffice) are installed by default. Download BISHENG: bash git clone https://github.com/dataelement/bisheng.git cd bisheng/docker Alternatively, download as zip: bash wget https://github.com/dataelement/bisheng/archive/refs/heads/main.zip unzip main.zip && cd bisheng-main/docker Start BISHENG: bash docker compose -f docker-compose.yml -p bisheng up -d After startup, access http://IP:3001 in browser. The first registered user becomes the system admin.
License and pricing
The license is Apache-2.0. The project is open source.
Based on the project's public README and repository metadata.
