Build enterprise RAG and agent workflows with Bisheng
Use Bisheng to assemble, evaluate, and publish enterprise RAG and agent workflows across internal data, models, and business users.
npx skills add agentskillexchange/skills --skill build-enterprise-rag-and-agent-workflows-with-bisheng
Bisheng is an open LLM DevOps platform for enterprise AI applications. This skill is for operators who need to build a repeatable RAG or agent workflow: connect data sources and model providers, assemble workflow steps, evaluate output quality, add observability, and publish the resulting application for business users. Invoke it when the job is to create or operate an enterprise AI workflow rather than simply browse the Bisheng product. The boundary is the end-to-end RAG/agent workflow lifecycle, not a generic platform listing.
What this skill actually does
Inputs and prerequisites: Bisheng, LLM provider credentials, enterprise data sources.
Setup notes: Follow the Bisheng repository setup instructions, configure model and data-source credentials, then create and evaluate a RAG or agent workflow before publishing it to users.
Source and verification boundary: use https://github.com/dataelement/bisheng as the canonical reference before running the workflow; keep commands, API calls, CLI usage, and generated outputs reviewable against that upstream source.
Framework fit: publish this as a Multi-Framework workflow only when the operator can invoke the documented toolchain directly, rather than treating the upstream project as a generic product listing.