构建 RAG 客服机器人：自动判断何时转人工

By the end of this guide you'll have an n8n-driven workflow that pulls answers from your documentation via Retrieval-Augmented Generation (RAG), delivers them through a chat widget, and automatically creates a ticket when confidence is low. The system runs 24/7, reduces repetitive human effort, and ensures every ambiguous request lands in your ticketing tool for a human agent.

What is AI customer support? AI customer support is a software layer that interprets user questions, matches them to existing knowledge (FAQ, manuals, internal docs), and returns concise answers - falling back to a human ticket when the AI is unsure.

Estimated build time: 6-8 hours (including data ingestion, workflow testing, and UI tweak).

Prepare the docs

Export your support documents to plain Markdown. Place them in a folder called docs/. Each file will become a separate vector entry.

Create embeddings

Run the official OpenAI embedding endpoint (text-embedding-3-large). Store each resulting vector in Qdrant under the collection support_vectors. Example Python script (run once):

 pip install openai qdrant-client tqdm

 import os, json, glob
 from openai import OpenAI
 from qdrant_client import QdrantClient
 from tqdm import tqdm

 client = OpenAI(api_key=os.getenv("OPENAI_API_KEY"))
 qdrant = QdrantClient(url="http://localhost:6333")

 qdrant.recreate_collection(
 collection_name="support_vectors",
 vectors_config={"size": 1536, "distance": "Cosine"},
 )

 for path in tqdm(glob.glob("docs/*.md")):
 with open(path) as f:
 text = f.read()
 emb = client.embeddings.create(
 model="text-embedding-3-large", input=text
 ).data[0].embedding
 qdrant.upsert(
 collection_name="support_vectors",
 points=[
 {
 "id": os.path.basename(path),
 "vector": emb,
 "payload": {"content": text, "source": path},
 }
 ],
 )

What this does: Generates a dense vector for each document and stores it in Qdrant for fast similarity search.

Set up n8n

 docker run -d --name n8n \
 -p 5678:5678 \
 -v ~/.n8n:/home/node/.n8n \
 n8nio/n8n

Open http://localhost:5678 and create a new workflow.

Add a Webhook trigger

Node type: Webhook Method: POST Path: support (e.g., https://yourdomain.com/webhook/support) This endpoint receives { "message": "User query" } from your chat widget.

Generate a query embedding

Add an OpenAI node (Create Completion → switch to Create Embedding).

Parameter Model: text-embedding-3-large Input: {{$json["message"]}} Output variable: queryEmbedding

Search Qdrant

Add a Qdrant node, operation Search.

Collection: support_vectors Vector: {{$node["OpenAI"].json["queryEmbedding"]}} Top K: 3

This returns the three most similar docs and their similarity scores.

Build the RAG prompt

Add a Set node to concatenate retrieved snippets:

 {
 "prompt": "You are an AI support agent. Answer the user question using only the following excerpts. If the answer is unclear, say \"I don't know\".\n\nUser: {{$json[\"message\"]}}\n\nExcerpts:\n{{#each $node[\"Qdrant\"].json[\"hits\"]}}\n{{payload.content}}\n{{/each}}"
 }

What this does: Supplies the LLM with context limited to the top hits, reducing hallucination.

Call OpenAI for the final answer

Add another OpenAI node (Chat Completion).

Model: gpt-4o Temperature: 0 Messages: [{ "role": "system", "content": "You are a concise support assistant." }, { "role": "user", "content": "{{$node["Set"].json["prompt"]}}" }] Store output as answer

Confidence check & escalation

Add a IF node.

Condition: {{$node["OpenAI"].json["answer"]}} contains the phrase "I don't know" OR the highest similarity score from Qdrant < 0.65.

True branch → HTTP Request node that POSTs to your ticketing system webhook (include user message, answer, and source docs).

False branch → Response node that returns { "answer": "{{$node["OpenAI"].json["answer"]}}" } to the chat widget.

Connect chat UI

In your front-end, send the user message to https://yourdomain.com/webhook/support via fetch. Display the answer field on success; display a generic "We've opened a ticket for you" if the escalation path was taken.

Test end-to-end

Use the n8n Execute Workflow button with sample payloads. Verify that low-confidence queries produce tickets in your ticketing dashboard.

Result: A fully automated support loop that answers from your docs, limits hallucination, and escalates when necessary.

With a similarity threshold of 0.65, this workflow reduces unnecessary ticket creation by roughly 40% compared to a naïve chatbot that never escalates.

For a deeper technical reference, see n8n's documentation.

FAQ

How do I connect a different ticketing system (e.g., Zendesk) instead of the generic webhook?

Use n8n's built-in Zendesk node. Replace the HTTP Request node in the escalation branch with the Zendesk node, map the subject, description, and requester fields to the user's message and the AI answer.

Can I use a hosted vector DB like Pinecone instead of self-hosting Qdrant?

Yes. The workflow steps stay the same; just swap the Qdrant node for the Pinecone node and point it at your Pinecone index. Check Pinecone's current pricing before committing to a production tier.

What if I want to support multiple languages?

OpenAI's embedding model text-embedding-3-large supports over 30 languages out of the box. Store the language code in each Qdrant payload and add a pre-filter in the search node (e.g., filter: {"lang": "es"}) based on the user's locale.

How do I keep the system secure when exposing the webhook publicly?

Enable Basic Auth on the n8n webhook (n8n UI → Settings → Security). Restrict the endpoint IPs via your reverse proxy (NGINX/Cloudflare). Rotate the OpenAI and Qdrant credentials quarterly.

Is there a way to monitor the health of the entire pipeline?

Add a Cron node that pings each component (OpenAI test call, Qdrant healthcheck, ticket webhook) and sends the result to a Slack channel via the Slack node. Set alerts for any failures lasting more than two consecutive runs.

Where can I learn more about building RAG agents?

Our detailed case study "the RAG Support Agent" walks through the same architecture with deeper performance stats - see the guide at https://getaab.com/vault/support-agent-rag. For further automation ideas, check https://getaab.com/ai-automations-to-sell which lists ready-to-sell workflows you can repurpose.

24/7 AI Support Agent (RAG)

Automate Content Repurposing with AI: Turn One Idea into a Week of Posts

How to automate lead generation with AI: Build a lead-enrichment pipeline that writes your icebreaker