Build Custom AI Agent with LangChain & Gemini (Self-Hosted) — n8n 工作流

复杂度 触发器4 个节点🏷️ Miscellaneous👁 4,410 次查看作者:shepard

概览

Overview
This workflow leverages the LangChain code node to implement a fully customizable conversational agent. Ideal for users who need granular control over their agent's prompts while reducing unnecessary token consumption from reserved tool-calling functionality (compared to n8n's built-in Conversation Agent).

Setup Instructions
Configure Gemini Credentials: Set up your Google Gemini API key (Get API key here if needed). Alternatively, you may use other AI provider nodes.
Interacti

使用的节点

LangChain CodeSimple MemoryGoogle Gemini Chat Model

工作流预览

👇 Prompt Engineering
- Define agent personality and conversation structur
- ⚠️ Template must preserve `{chat_history}` and
Setup Instructions
1. Configure Gemini Credentials: Set up your Google Gem
👆 Interface Settings
Configure chat UI elements (e.g., title) in the `When C
👆 Model Selection
Swap language models through the `language model` input
👆 Memory Control
Adjust conversation history length in the `Store Conver
modelmemorymemory
W
When chat message received
Google Gemini Chat Model
Store conversation history
Construct & Execute LLM …
4 nodes4 edges

工作原理

  1. 1

    触发器

    工作流由 触发器 触发器启动。

  2. 2

    处理

    数据流经 4 个节点, connecting chattrigger, code, lmchatgooglegemini。

  3. 3

    输出

    工作流完成自动化并将结果发送到配置的目标。

节点详情 (4)

LA

LangChain Code

n8n-nodes-langchain.code

#1
SI

Simple Memory

n8n-nodes-langchain.memoryBufferWindow

#2
GO

Google Gemini Chat Model

n8n-nodes-langchain.lmChatGoogleGemini

#3

如何导入此工作流

  1. 1点击右侧 下载 JSON 按钮保存工作流文件。
  2. 2打开你的 n8n 实例,依次点击 工作流 → 新建 → 从文件导入
  3. 3选择下载的 build-custom-ai-agent-with-langchain-gemini-self-hosted 文件并点击导入。
  4. 4为每个服务节点配置 凭证(API 密钥、OAuth 等)。
  5. 5点击 测试工作流 验证一切正常,然后激活它。

或直接在 n8n → 从 JSON 导入 中粘贴:

{ "name": "Build Custom AI Agent with LangChain & Gemini (Self-Hosted)", "nodes": [...], ...}

集成

chattriggercodelmchatgooglegeminimemorybufferwindow

获取此工作流

一键下载并导入

下载 JSON在 n8n.io 上查看
节点4
复杂度low
触发器trigger
查看次数4,410

创建者

shepard

shepard

@shepard

标签

chattriggercodelmchatgooglegeminimemorybufferwindow

n8n 新手?

n8n 是一款免费开源的工作流自动化工具,支持自托管或使用云版本。

免费获取 n8n →

Related Miscellaneous Workflows