# Handle customer support queries with Redis and LangCache: n8n workflow

> Started by someone opening a chat with it. It calls services over plain HTTP rather than through connectors.

Source: https://millionrounds.com/workflow/handle-customer-support-queries-with-redis-and-langcache (Millionrounds; every figure on the page links to its filing or article)

[Automation library](https://millionrounds.com/workflows) · [Customer support](https://millionrounds.com/workflows?category=Customer+support#library)

# Handle customer support queries with Redis and LangCache

Started by someone opening a chat with it. It calls services over plain HTTP rather than through connectors. It puts OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 28 steps, 2 branches, 1 loop or waits: large, and worth reading before you trust it with anything live.

Large Calls a model: OpenAI Retrieval

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fhandle-customer-support-queries-with-redis-and-langcache)

**28 steps** Large: read it before trusting it with anything live

**2** Branches: places the flow splits

**1** Loop or waits

**0** Services by connector: it calls them over plain HTTP

## The flow

Starts it 2 Model 14 Logic 10 Service 2

The steps in the order they run, from what starts it.

- 1 **When chat message received** Chat trigger *Starts it*
- 2 **Structured Output Parser** Output Parser Structured *Model*
- 3 **Embeddings OpenAI** Embeddings Open Ai *Model*
- 4 **Embeddings OpenAI1** Embeddings Open Ai *Model*
- 5 **Default Data Loader** Document Default Data Loader *Model*
- 6 **OpenAI Chat Model** Lm Chat Open Ai *Model*
- 7 **Schedule Trigger** Schedule trigger *Starts it*
- 8 **Simple Memory** Memory Buffer Window *Model*
- 9 **Simple Memory1** Memory Buffer Window *Model*
- 10 **Simple Memory2** Memory Buffer Window *Model*
- 11 **LangCache Config** Set *Logic*
- 12 **decompose_query** Agent *Model*
- 13 **Redis Vector Store2** Vector Store Redis *Model*
- 14 **Redis Vector Store** Vector Store Redis *Model*
- 15 **synthesize_response_node** Agent *Model*
- 16 **search_node1** Agent *Model*
- 17 **example Data** Set *Logic*
- 18 **Split Out** Split Out *Logic*
- 19 **evaluate_quality** Open Ai *Model*
- 20 **Loop Over Items** Split In Batches *Logic*
- 21 **getScore** Set *Logic*
- 22 **Aggregate** Aggregate *Logic*
- 23 **Search LangCache** Http Request *Service*
- 24 **low quality?** If *Logic*
- 25 **Is Cache Hit?** If *Logic*
- 26 **current_iteration** Set *Logic*
- 27 **increase iteration** Set *Logic*
- 28 **Save to LangCache** Http Request *Service*

## How it's built

- **Starts on:** Someone opening a chat with it
- **Steps:** 28, with 2 branches, 1 loop or waits
- **Size:** Large: read it before trusting it with anything live
- **Connects to:** Nothing by connector; it calls services over plain HTTP
- **Model:** OpenAI
- **Retrieval:** Answers are drawn from documents you supply, not from the model alone

## Questions

What does it need to run?

An n8n account, and a key for OpenAI. You connect your own accounts after importing it; none are included.

What starts it?

It starts on someone opening a chat with it.

Does it use AI?

Yes. It calls OpenAI. Its answers draw on documents you give it, not on the model alone. Model calls are billed by the provider, not by n8n.

How long does it take to set up?

Take your time. At 28 steps it is large: read it before trusting it with anything live.

How do I import it?

Copy the workflow, open a new workflow in n8n and paste. The steps appear on the canvas, ready for your own accounts.

**Before you run it**

Nothing here has been tested by us. It is somebody's working automation, read and described from its own steps. Treat the connections it wants as a list of accounts it will touch, and read the 28 steps before you point it at anything that matters.

## Run it in n8n

- **Create your n8n account** Free to start. n8n is where the workflow runs. [Create an n8n account ↗](https://millionrounds.com/n8n)
- **Download the workflow** Free with a Millionrounds account. [Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fhandle-customer-support-queries-with-redis-and-langcache)
- **Paste it into n8n** Open a new workflow in n8n and paste. Then connect your own accounts.

Stored with the author's traces removed: canvas notes, instance identifiers, saved credential names and any live document they had left behind.

## Workflows like it

Also customer support, with the same services where possible, closest in size first.

- [**Auto-assign support tickets with Jira and Supabase** 28 steps · calls a model · Jira, Supabase vectors](https://millionrounds.com/workflow/auto-assign-support-tickets-with-jira-and-supabase)
- [**Automate customer support issue resolution with OpenAI** 29 steps · calls a model · Jira, Notion](https://millionrounds.com/workflow/automate-customer-support-issue-resolution-with-openai)
- [**Automate customer support with Slack and CRM** 27 steps · calls a model · Gmail, Google Sheets](https://millionrounds.com/workflow/automate-customer-support-with-slack-and-crm)
- [**Triage and resolve stale Jira tickets with OpenAI and Notion** 29 steps · calls a model · Jira, Notion](https://millionrounds.com/workflow/triage-and-resolve-stale-jira-tickets-with-openai-and-notion)
- [**Answer BigQuery questions in Microsoft Teams with Claude** 27 steps](https://millionrounds.com/workflow/answer-bigquery-questions-in-microsoft-teams-with-claude)
- [**Answer FAQs and route Telegram users to support with Postgres** 29 steps · Postgres, Telegram](https://millionrounds.com/workflow/answer-faqs-and-route-telegram-users-to-support-with-postgre)