Automation library · Documents and files

Telegram chat with PDF

Started by an incoming Telegram message, and works across Pinecone and Telegram. It puts Groq and OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 18 steps, 1 branch: a working afternoon to understand properly.

MediumCalls a model: Groq, OpenAIRetrieval

18 stepsMedium: a working afternoon
1Branch: places the flow splits
0Loops or waits
2Services it connects to

The flow

Starts it 1Model 9Logic 5Service 3

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

  1. 1Telegram TriggerTelegram triggerStarts it
  2. 2Embeddings OpenAIEmbeddings Open AiModel
  3. 3Recursive Character Text SplitterText Splitter Recursive Character Text SplitterModel
  4. 4Groq Chat ModelLm Chat GroqModel
  5. 5EmbeddingsEmbeddings Open AiModel
  6. 6Check If is a documentIfLogic
  7. 7Pinecone Vector StoreVector Store PineconeModel
  8. 8Default Data LoaderDocument Default Data LoaderModel
  9. 9Question and Answer ChainChain Retrieval QaModel
  10. 10Pinecone Vector Store1Vector Store PineconeModel
  11. 11Telegram get FileTelegramService
  12. 12Limit to 1LimitLogic
  13. 13Telegram ResponseTelegramService
  14. 14Vector Store RetrieverRetriever Vector StoreModel
  15. 15Change to application/pdfCodeLogic
  16. 16Telegram Response about DatabaseTelegramService
  17. 17Stop and ErrorStop And ErrorLogic
  18. 18Stop and Error1Stop And ErrorLogic

How it's built

Starts on
An incoming Telegram message
Steps
18, with 1 branch
Size
Medium: a working afternoon
Connects to
Pinecone, Telegram
Model
Groq, 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 Telegram accounts, and a key for Groq and OpenAI. You connect your own accounts after importing it; none are included.

What starts it?

It starts on an incoming Telegram message.

Does it use AI?

Yes. It calls Groq and 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. 18 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.

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 18 steps before you point it at anything that matters.