The flow
Starts it 3Model 9Logic 1Service 1
The steps in the order they run, from what starts it.
- 1Create Embeddings for IndexingEmbeddings Open AiModel
- 2Split Document into ChunksText Splitter Recursive Character Text SplitterModel
- 3Manual Trigger - Index Knowledge BaseManual triggerStarts it
- 4OpenAI Chat ModelLm Chat Open AiModel
- 5Create Query EmbeddingEmbeddings Open AiModel
- 6Chatbot Webhook TriggerWebhookStarts it
- 7Insert Documents into PineconeVector Store PineconeModel
- 8Load Downloaded DocumentDocument Default Data LoaderModel
- 9Download Knowledge FileGoogle DriveService
- 10Answer Question with Retrieved ContextChain Retrieval QaModel
- 11Search Pinecone Knowledge BaseVector Store PineconeModel
- 12Format Chatbot ResponseCodeLogic
- 13Retrieve Matching KnowledgeRetriever Vector StoreModel
- 14Return Answer to FrontendRespond To WebhookStarts it
How it's built
- Starts on
- Another system calling it
- Steps
- 14
- Size
- Medium: a working afternoon
- Connects to
- Google Drive, Pinecone
- 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 Google Drive and Pinecone 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?
Plan an afternoon. 14 steps is enough that you should read each one before running it.
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.
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 14 steps before you point it at anything that matters.