# yvain13/servicenow-n8n-rag-chatbot architecture

> Architecture diagram of the GitHub repository yvain13/servicenow-n8n-rag-chatbot, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2025-08-18). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/yvain13/servicenow-n8n-rag-chatbot
- Repository: https://github.com/yvain13/servicenow-n8n-rag-chatbot

## Overview

##### Project Type & Purpose
- This is an n8n-based orchestration system providing two ServiceNow automation solutions:
a) L1 Support Triage Agent (LLM-powered ticket routing)
b) Knowledge RAG Chatbot (ingest Knowledge Articles into Qdrant + retrieval-augmented chat)

##### Main Components
- Frontend Chat Widget (ServiceNow Virtual Agent XML)
- n8n Orchestrator instance hosting two workflows
- ServiceNow REST API (Incident table, Knowledge Article table, Service Catalog API)
- AI Services:
- OpenAI Chat (LLM for classification & responses)
- OpenAI Embeddings (vector generation)
- SerpAPI (web search)
- Memory Store (Simple Memory node in n8n)
- Qdrant Vector Database

##### Workflows & Subcomponents
A. L1 Support Triage Agent Workflow
1) Chat Trigger Node (webhook)
2) Text Classifier Node (OpenAI chat model) → three branches:
- INCIDENT → ServiceNow Incident Creation Node
- REQUEST → HTTP Request Node (Service Catalog endpoint)
- GENERAL → AI Agent sub-flow:
– OpenAI Chat Response
– SerpAPI Search
– Simple Memory for context
– Summarization Chain to create ticket description
3) Return response to Chat UI

B. Knowledge RAG Chatbot Workflow
Pink Panel – Data Ingestion (manual trigger):
1) Execute Workflow Trigger
2) Get Many Table Records (ServiceNow Knowledge Articles)
3) Default Data Loader
4) Recursive Character Text Splitter
5) OpenAI Embeddings → high-dim vectors
6) Qdrant Vector Store → persist embeddings & metadata

Green Panel – RAG Chat Interaction:
1) Chat Trigger Node (webhook)
2) Query Embedding Node (OpenAI Embeddings)
3) Qdrant Search Node → retrieve top N chunks
4) AI Agent Node (OpenAI Chat Model + Simple Memory)
5) Return response to Chat UI

##### Relationships & Data Flows
- Frontend UI → n8n Chat Trigger → appropriate workflow
- In L1 Agent: classification branch → external API call → back to UI
- In Knowledge Chat: query embedding → Qdrant search → LLM response → UI
- Ingestion flow separate from chat flow, both within same n8n instance

##### Architectural Patterns & Principles
- Event-driven orchestration (n8n triggers)
- Pipeline pattern for data ingestion
- Decision router pattern (LLM-powered branching)
- Retrieval-Augmented Generation (RAG) for knowledge chat
- Separation of concerns: triage vs. knowledge retrieval

## Diagram (Mermaid)

```mermaid
graph TD
    %% Zones
    subgraph "Chat UI / Virtual Agent"
        UI["Frontend Chat Widget"]:::external
        click UI "https://github.com/yvain13/servicenow-n8n-rag-chatbot/blob/main/SN N8N RAG Chatbot/ServiceNow N8N Chat widget.xml"
    end

    subgraph "n8n Orchestrator"
        direction TB
        %% L1 Triage
        subgraph "L1 Support Triage Agent Workflow"
            direction TB
            L1Workflow["L1 Support Triage Agent Workflow"]:::n8n
            click L1Workflow "https://github.com/yvain13/servicenow-n8n-rag-chatbot/blob/main/SN N8N L1 Triage Agent/ServiceNow L1 Support Agent.json"
            ChatTrigger1["Chat Trigger Node (webhook)"]:::n8n
            Classifier["Text Classifier Node"]:::n8n
            IncidentNode["Incident Creation Node"]:::api
            CatalogNode["Service Catalog HTTP Request Node"]:::api
            GeneralFlow["AI Agent Sub-flow"]:::n8n
            ChatResp["OpenAI Chat Response"]:::ai
            SerpAPI["SerpAPI Search"]:::api
            Memory["Simple Memory"]:::n8n
            Summarize["Summarization Chain"]:::n8n
        end

        %% RAG Chatbot
        subgraph "Knowledge RAG Chatbot Workflow"
            direction TB
            KRWorkflow["Knowledge RAG Chatbot Workflow"]:::n8n
            click KRWorkflow "https://github.com/yvain13/servicenow-n8n-rag-chatbot/blob/main/SN N8N RAG Chatbot/ServiceNow Knowledge Chatbot.json"

            subgraph "Pink Panel - Data Ingestion"
                direction TB
                TriggerIngest["Execute Workflow Trigger"]:::n8n
                click TriggerIngest "https://github.com/yvain13/servicenow-n8n-rag-chatbot/blob/main/SN N8N RAG Chatbot/ServiceNow Knowledge Chatbot.json"
                GetRecords["Get Many Table Records"]:::api
                DataLoader["Default Data Loader"]:::n8n
                Splitter["Recursive Text Splitter"]:::n8n
                EmbeddingsIngest["OpenAI Embeddings"]:::ai
                QdrantStore["Qdrant Vector Store"]:::db
            end

            subgraph "Green Panel - RAG Chat Interaction"
                direction TB
                ChatTrigger2["Chat Trigger Node (webhook)"]:::n8n
                click ChatTrigger2 "https://github.com/yvain13/servicenow-n8n-rag-chatbot/blob/main/SN N8N RAG Chatbot/ServiceNow Knowledge Chatbot.json"
                QueryEmbed["Query Embedding Node"]:::ai
                QdrantSearch["Qdrant Search Node"]:::db
                AIAgentChat["AI Agent Node"]:::n8n
            end
        end
    end

    subgraph "ServiceNow Instance"
        SN_Incident["Incident API"]:::api
        SN_Catalog["Catalog API"]:::api
        SN_Knowledge["Knowledge Article Table"]:::db
    end

    subgraph "AI Services"
        OpenAIChat["OpenAI Chat"]:::ai
        OpenAIEmbed["OpenAI Embeddings"]:::ai
        SerpAPIservice["SerpAPI"]:::api
    end

    QdrantVector["Qdrant Vector DB"]:::db

    README["README (Project Overview)"]:::doc
    click README "https://github.com/yvain13/servicenow-n8n-rag-chatbot/blob/main/README.md"

    %% Connections - L1 Triage
    UI -->|"user message"| ChatTrigger1
    ChatTrigger1 -->|"classify message"| Classifier
    Classifier -->|"Incident"| IncidentNode
    Classifier -->|"Request"| CatalogNode
    Classifier -->|"General"| ChatResp

    ChatResp -->|uses| OpenAIChat
    ChatResp -->|"search web"| SerpAPIservice
    ChatResp -->|"retrieve context"| Memory
    ChatResp -->|"summarize"| Summarize
    Summarize -->|"ticket description"| IncidentNode

    IncidentNode -->|"create incident"| SN_Incident
    IncidentNode -->|"response"| UI
    CatalogNode -->|"request service"| SN_Catalog
    CatalogNode -->|"response"| UI
    ChatResp -->|"response"| UI

    %% Connections - Ingestion
    TriggerIngest --> GetRecords
    GetRecords --> SN_Knowledge
    GetRecords --> DataLoader
    DataLoader --> Splitter
    Splitter --> EmbeddingsIngest
    EmbeddingsIngest --> QdrantStore
    QdrantStore --> QdrantVector

    %% Connections - Chat
    UI -->|"user query"| ChatTrigger2
    ChatTrigger2 --> QueryEmbed
    QueryEmbed --> OpenAIEmbed
    OpenAIEmbed --> QdrantVector
    QueryEmbed --> QdrantSearch
    QdrantSearch --> QdrantVector
    QdrantSearch --> AIAgentChat
    AIAgentChat -->|uses| OpenAIChat
    AIAgentChat -->|use memory| Memory
    AIAgentChat -->|"response"| UI

    %% Class Definitions
    classDef n8n fill:#D0E8FF,stroke:#0284C7;
    classDef api fill:#FFE4B5,stroke:#E09000;
    classDef ai fill:#F0E68C,stroke:#B8860B;
    classDef db fill:#E0FFE0,stroke:#00A000;
    classDef external fill:#FFC0CB,stroke:#C00050;
    classDef doc fill:#F5F5F5,stroke:#333;
```
