Answer HR questions with OpenAI and PostgreSQL: n8n workflow

Answer HR questions with OpenAI and PostgreSQL

Started by another system calling it, and works across Pinecone and Postgres. It puts OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 26 steps, 5 branches: large, and worth reading before you trust it with anything live.

LargeCalls a model: OpenAIRetrieval

The flow

Starts it 5Model 7Logic 11Service 3

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

1Webhook - HR Bot ChatWebhookStarts it
2OpenAI Model - TranslationLm Chat Open AiModel
3OpenAI GPT-4o-miniLm Chat Open AiModel
4PostgreSQL - HR Database ToolPostgres ToolService
5OpenAI EmbeddingsEmbeddings Open AiModel
6PostgreSQL Chat MemoryMemory Postgres ChatModel
7Validate Identity (Mobile/Email)IfLogic
8Translate to EnglishChain LlmModel
9HR Assistant AI AgentAgentModel
10Pinecone - HR Policy Knowledge BaseVector Store PineconeModel
11Check Audio InputIfLogic
12Error - Invalid Mobile/EmailRespond To WebhookStarts it
13Merge Translation ContextSetLogic
14Format Final ResponseCodeLogic
15ElevenLabs - Transcribe AudioEleven LabsService
16Validate MessageIfLogic
17Fetch Employee DataPostgresService
18Send Success ResponseRespond To WebhookStarts it
19Extract TranscriptSetLogic
20Parse Input & Detect LanguageCodeLogic
21Error - Invalid MessageRespond To WebhookStarts it
22Validate EmployeeIfLogic
23Needs Translation?IfLogic
24Merge Employee & Language ContextCodeLogic
25Error - Employee Not FoundRespond To WebhookStarts it
26Skip Translation (English)SetLogic

How it's built

Starts on: Another system calling it
Steps: 26, with 5 branches
Size: Large: read it before trusting it with anything live
Connects to: Pinecone, Postgres
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, plus your own Pinecone and Postgres accounts, and a key for OpenAI. You connect your own accounts after importing it; none are included.

What starts it?

It starts on another system calling 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 26 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 26 steps before you point it at anything that matters.