Flowise开源可视化构建器，使用拖拽节点来创建 LLM 应用、代理和聊天机器人。

4.5 (4)

审阅者 Daniel Nikulshyn·更新 2026年5月

Open Source Low-Code LLM Agents RAG Self-Hosted Visual Builder API

1 / 4

概览

Flowise 是一款开源低代码平台，通过在可视化画布上连接节点来设计 AI 工作流。它封装了 LangChain、LlamaIndex 等流行框架，使开发者能够在不编写大量胶水代码的情况下快速原型化聊天机器人、检索增强生成（RAG）流水线和自主代理。构建好的工作流可以以 API 形式发布，嵌入为聊天小部件，或集成到现有应用中。Flowise 支持多种模型提供商、向量数据库和工具，并且可以通过 Docker 自行部署，亦可在云端运行，满足对数据和部署有更高控制需求的团队。

主要功能

拖拽式流程构建器
支持 LangChain 与 LlamaIndex 节点
RAG 与向量数据库集成
代理与工具编排
API 接口与聊天嵌入
基于 Docker 的自托管

价格

模型: Freemium
分类: 代码助手
评分: 4.5 / 5 (4)

使用场景

可视化原型化 RAG 聊天机器人

在画布上连接 LLM、嵌入和向量数据库节点，快速构建检索增强聊天机器人，无需编写大量 LangChain 或 LlamaIndex 的胶水代码。

在应用中嵌入 AI 助手

将构建好的流程以 API 接口或即插即用的聊天小部件形式发布，将定制 AI 助手集成到现有网站和内部工具中。

编排自主代理

使用代理和工具节点设计多步骤工作流，让 LLM 调用工具、查询数据并在可视化流水线中作出决策。

在 Docker 上自托管 LLM 工作流

通过 Docker 部署 Flowise，将模型交互、数据和流程逻辑置于团队掌控之下，适用于隐私敏感或受监管的环境。

优点 & 缺点

优点

开源且可自托管
可视化画布加速原型设计
与 LLM 和向量存储的广泛集成
可将流程导出为 API 与可嵌入的小部件

缺点

复杂的流程可能难以管理
需要一定的 LLM 概念理解
自托管会增加维护负担

对决战绩

在万神殿中参与了 1 对决。

第1

第2

第3

Last battle

#5
Code Assistants Showdown — May 12, 2025
May 12, 2025 · #5 of 9

评测

4.5

4 个评分的平均值。

登录以留下评测。

Esther Adeyemi

Apr 4, 2026

Skeptical, then convinced

I went in skeptical — most tools in this space overpromise. It actually delivers on langChain and LlamaIndex node support, and broad integrations with LLMs and vector stores caught me off guard. still, I'd recommend giving it a real trial.

Gunnar Eriksson

Mar 15, 2026

Compared a few options

Evaluated this against two competitors. Where it wins: docker-based self-hosting and visual canvas speeds up prototyping. Where it lags: complex flows can become hard to manage. On balance the feature set — especially drag-and-drop flow builder — justifies the 4 stars for our use case.

Carlos Mendoza

Jan 22, 2026

Solid for our team

We rolled this out across the team last quarter and broad integrations with LLMs and vector stores. Docker-based self-hosting fits neatly into how we already work, and docker-based self-hosting removed a step we used to do by hand. Requires some understanding of LLM concepts, which is the main caveat, but it has held up under daily use.

Priya Nair

Jul 14, 2025

Use it every day

Honestly didn't expect to like it this much. LangChain and LlamaIndex node support is exactly what I needed, and visual canvas speeds up prototyping. I do wish requires some understanding of LLM concepts, but I reach for it almost every day now and it just clicks.

问答

How can I expose a Flowise workflow to my existing application?

Built flows can be exported as API endpoints, embedded chat widgets, or accessed via the provided TypeScript and Python SDKs, allowing easy integration into web, mobile, or backend services.

Asked by Bianca Ferreira · Nov 8, 2025

Which AI frameworks and vector databases does Flowise integrate with?

Flowise wraps popular frameworks such as LangChain and LlamaIndex, and supports a wide range of LLM providers, embeddings models, and vector databases, enabling RAG pipelines and tool orchestration without custom glue code.

Asked by Priya Nair · Oct 30, 2025

Can Flowise be self‑hosted, and what deployment options are available?

Yes, Flowise is open source and can be self‑hosted via Docker for on‑premise deployments. It also offers cloud deployments that scale horizontally with message queues and workers for production use.

Asked by Greta Nowak · Oct 17, 2025

What pricing tiers does Flowise offer for individual vs. team use?

Flowise has a free tier with up to 2 flows, 100 predictions per month, and 5 MB storage. The paid “Starter” plan costs $35/month and includes unlimited flows, 10 000 predictions per month, and 1 GB storage, plus custom branding and evaluation metrics.

Asked by Sami Virtanen · Aug 8, 2025