⚡n8n Workflow
Expert

Telegram PDF RAG Chatbot

Create a Telegram RAG chatbot to interact with your PDFs. This workflow uses Pinecone for vector storage, OpenAI for embeddings, and Groq for fast AI responses.

Overview

Builds an intelligent Telegram chatbot that ingests PDF documents and answers questions about their content using a Retrieval-Augmented Generation (RAG) architecture.

🧠 Description & Use Case

This workflow transforms your Telegram into a powerful, interactive knowledge base. It allows you to upload PDF documents and then ask questions about their content. This is a classic example of a Retrieval-Augmented Generation (RAG) system, which combines a vector database with a powerful language model to provide context-aware answers.

🔄 How It Works:

The workflow has two main paths, determined by the type of message you send to the Telegram bot:

1. Document Ingestion (When you send a PDF):

  • Trigger: The workflow starts when the Telegram Trigger node receives a message.
  • Check: An IF node checks if the message contains a document.
  • Download: If a document is present, the Telegram get File node downloads it.
  • Embed & Store: The document is processed by the Pinecone Vector Store node. It uses OpenAI Embeddings to convert the text into vectors and stores them in your Pinecone index. This makes the document's content searchable.
  • Confirm: A confirmation message is sent back via the Telegram Response about Database node, letting you know the document has been successfully processed and saved.

2. Question Answering (When you send a text message):

  • Trigger: The workflow starts when a text message is received.
  • Retrieve: The Question and Answer Chain takes your question and uses the Vector Store Retriever to search the Pinecone database for the most relevant information from the documents you've uploaded.
  • Generate: The retrieved information (context) and your original question are sent to the Groq Chat Model (using a fast Llama 3.1 model). The AI generates a precise answer based on the provided context.
  • Respond: The final, context-aware answer is sent back to you in the Telegram chat.

✅ Real-World Use Cases:

  • Personal Research Assistant: Upload academic papers, articles, or reports and ask specific questions to quickly find the information you need.
  • Internal Knowledge Base: Create a chatbot for your team by feeding it company policies, technical documentation, or project briefs.
  • Customer Support Automation: Upload user manuals or FAQ documents to provide instant, accurate answers to common customer queries.
  • Study Tool: Turn your textbooks and lecture notes into an interactive study partner that can explain concepts and answer practice questions.

Instructions

Basic steps

  1. Download workflow JSON
  2. Import into n8n
  3. Configure node parameters as needed
  4. Test and enable the workflow

💡 Tips

After importing, verify all connectors and credentials match your environment.

Preview

Workflow Visualization

20 nodes
100%
Telegram TriggertelegramTriggerEmbeddings OpenAI@n8n/langchain.embeddingsOpenAiDefault Data Loader@n8n/langchain.documentDefaultDataLoaderRecursive Character Text Splitter@n8n/langchain.textSplitterRecursiveCharacterTextSplitterStop and ErrorstopAndErrorQuestion and Answer Chain@n8n/langchain.chainRetrievalQaVector Store Retriever@n8n/langchain.retrieverVectorStorePinecone Vector Store1@n8n/langchain.vectorStorePineconeGroq Chat Model@n8n/langchain.lmChatGroqSticky NotestickyNoteSticky Note1stickyNoteCheck If is a documentifChange to application/pdfcodeTelegram get FiletelegramEmbeddings@n8n/langchain.embeddingsOpenAiTelegram ResponsetelegramTelegram Response about DatabasetelegramStop and Error1stopAndErrorPinecone Vector Store@n8n/langchain.vectorStorePineconeLimit to 1limit

Nodes

1

Telegram Trigger

telegramTrigger

v1.1
2

Embeddings OpenAI

@n8n/langchain.embeddingsOpenAi

v1
3

Default Data Loader

@n8n/langchain.documentDefaultDataLoader

v1
4

Recursive Character Text Splitter

@n8n/langchain.textSplitterRecursiveCharacterTextSplitter

v1
5

Stop and Error

stopAndError

v1
6

Question and Answer Chain

@n8n/langchain.chainRetrievalQa

v1.3
7

Vector Store Retriever

@n8n/langchain.retrieverVectorStore

v1
8

Pinecone Vector Store1

@n8n/langchain.vectorStorePinecone

v1
9

Groq Chat Model

@n8n/langchain.lmChatGroq

v1
10

Sticky Note

stickyNote

v1
11

Sticky Note1

stickyNote

v1
12

Check If is a document

if

v2
13

Change to application/pdf

code

v2
14

Telegram get File

telegram

v1.2
15

Embeddings

@n8n/langchain.embeddingsOpenAi

v1
16

Telegram Response

telegram

v1.2
17

Telegram Response about Database

telegram

v1.2
18

Stop and Error1

stopAndError

v1
19

Pinecone Vector Store

@n8n/langchain.vectorStorePinecone

v1
20

Limit to 1

limit

v1

Statistics

Total nodes:20
Disabled nodes:0
Node types:14
Connections:16
View full JSON structure
{
  "nodes": [
    {
      "id": "9fbce801-8c42-43a4-bc70-d93042d68b2c",
      "name": "Telegram Trigger",
      "type": "n8n-nodes-base.telegramTrigger",
      "position": [
        -220,
        240
      ],
      "webhookId": "b178f034-9997-4832-9bb4-a43c3015506e",
      "parameters": {
        "updates": [
          "message"
        ],
        "additionalFields": {}
      },
      "credentials": {
        "telegramApi": {
          "id": "",
          "name": ""
        }
      },
      "typeVersion": 1.1
    },
    {
      "id": "1bfc1fbd-86b1-4a8a-9301-fe54497f5acd",
      "name": "Embeddings OpenAI",
      "type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
      "position": [
        720,
        460
      ],
      "parameters": {
        "options": {}
      },
      "credentials": {
        "openAiApi": {
          "id": "",
          "name": ""
        }
      },
      "typeVersion": 1
    },
    {
      "id": "d5ad7851-ed40-4b3a-b0d5-aeaf04362f1c",
      "name": "Default Data Loader",
      "type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
      "position": [
        860,
        460
      ],
      "parameters": {
        "options": {},
        "dataType": "binary"
      },
      "typeVersion": 1
    },
    {
      "id": "fed803d0-49a2-4b82-8f20-a02a10caa027",
      "name": "Recursive Character Text Splitter",
      "type": "@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter",
      "position": [
        940,
        680
      ],
      "parameters": {
        "options": {},
        "chunkSize": 3000,
        "chunkOverlap": 200
      },
      "typeVersion": 1
    },
    {
      "id": "ab60f36f-fada-4812-8dbd-441ad372cb80",
      "name": "Stop and Error",
      "type": "n8n-nodes-base.stopAndError",
      "position": [
        220,
        840
      ],
      "parameters": {
        "errorMessage": "An error occurred"
      },
      "typeVersion": 1
    },
    {
      "id": "c87f1db3-7cc9-4063-9895-4b4d68ea53a1",
      "name": "Question and Answer Chain",
      "type": "@n8n/n8n-nodes-langchain.chainRetrievalQa",
      "position": [
        -280,
        500
      ],
      "parameters": {
        "text": "={{ $json.message.text }}\nSearch the database with the retriever for information for the answer",
        "promptType": "define"
      },
      "typeVersion": 1.3
    },
    {
      "id": "c9bc4c80-8e57-48bc-a405-131ed7348c1d",
      "name": "Vector Store Retriever",
      "type": "@n8n/n8n-nodes-langchain.retrieverVectorStore",
      "position": [
        -240,
        680
      ],
      "parameters": {},
      "typeVersion": 1
    },
    {
      "id": "0217056f-2b71-4308-adf1-19dcd4d2cc11",
      "name": "Pinecone Vector Store1",
      "type": "@n8n/n8n-nodes-langchain.vectorStorePinecone",
      "position": [
        -280,
        860
      ],
      "parameters": {
        "options": {},
        "pineconeIndex": {
          "__rl": true,
          "mode": "list",
          "value": "telegram",
          "cachedResultName": "telegram"
        }
      },
      "credentials": {
        "pineconeApi": {
          "id": "",
          "name": ""
        }
      },
      "typeVersion": 1
    },
    {
      "id": "693f9026-f47f-48dc-8e5d-e8b832a37235",
      "name": "Groq Chat Model",
      "type": "@n8n/n8n-nodes-langchain.lmChatGroq",
      "position": [
        -380,
        660
      ],
      "parameters": {
        "model": "llama-3.1-70b-versatile",
        "options": {}
      },
      "credentials": {
        "groqApi": {
          "id": "",
          "name": ""
        }
      },
      "typeVersion": 1
    },
    {
      "id": "c7acf014-138f-4be7-b569-c309bb10e50d",
      "name": "Sticky Note",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        500,
        73.04879287725316
      ],
      "parameters": {
        "color": 7,
        "width": 1139.5159692915,
        "height": 873.6068151028411,
        "content": "# Load data into database\nFetch file from **Telegram**, split it into chunks and insert into **Pinecone** index, a message from **Telegram** will be sent just to let the user know that the process finished"
      },
      "typeVersion": 1
    },
    {
      "id": "dd3b9d8b-5771-4a09-8c1b-794cb8737d5d",
      "name": "Sticky Note1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -878.769,
        400
      ],
      "parameters": {
        "color": 7,
        "width": 1344.791801980818,
        "height": 806.8716167324012,
        "content": "# Chat with Database\n\n1. **Receive** the incoming chat message.\n2. **Retrieve** relevant chunks from the _vector store_.\n3. **Pass** these chunks to the model.\n\nThe model will use the retrieved information to **formulate a precise response**.\n"
      },
      "typeVersion": 1
    },
    {
      "id": "9aaf575a-5e40-407c-951c-10b1d16e5d3c",
      "name": "Check If is a document",
      "type": "n8n-nodes-base.if",
      "position": [
        220,
        240
      ],
      "parameters": {
        "options": {},
        "conditions": {
          "options": {
            "leftValue": "",
            "caseSensitive": true,
            "typeValidation": "strict"
          },
          "combinator": "and",
          "conditions": [
            {
              "id": "8839993b-9fe7-4e1e-a1cc-fe5de6b0bb62",
              "operator": {
                "type": "object",
                "operation": "exists",
                "singleValue": true
              },
              "leftValue": "={{ $json.message.document }}",
              "rightValue": ""
            }
          ]
        }
      },
      "typeVersion": 2
    },
    {
      "id": "c1edb6bf-ba95-4a5f-9626-add673274086",
      "name": "Change to application/pdf",
      "type": "n8n-nodes-base.code",
      "position": [
        700,
        220
      ],
      "parameters": {
        "jsCode": "// Função para modificar os metadados do arquivo binário\nfunction modifyBinaryMetadata(items) {\n for (const item of items) {\n if (item.binary && item.binary.data) {\n // Modifica o tipo MIME\n item.binary.data.mimeType = 'application/pdf';\n \n // Garante que o nome do arquivo termine com .pdf\n if (!item.binary.data.fileName.toLowerCase().endsWith('.pdf')) {\n item.binary.data.fileName += '.pdf';\n }\n \n // Atualiza o contentType no fileType (se existir)\n if (item.binary.data.fileType) {\n item.binary.data.fileType.contentType = 'application/pdf';\n }\n }\n }\n return items;\n}\n\n// Aplica a modificação e retorna os itens atualizados\nreturn modifyBinaryMetadata($input.all());"
      },
      "typeVersion": 2
    },
    {
      "id": "ea4d4e74-8954-47f0-a3a0-662d47ea2298",
      "name": "Telegram get File",
      "type": "n8n-nodes-base.telegram",
      "position": [
        520,
        220
      ],
      "parameters": {
        "fileId": "={{ $json.message.document.file_id }}",
        "resource": "file"
      },
      "credentials": {
        "telegramApi": {
          "id": "",
          "name": ""
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "cf548bee-d5d5-4f1a-a059-932ea163e155",
      "name": "Embeddings",
      "type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
      "position": [
        -100,
        1080
      ],
      "parameters": {
        "options": {}
      },
      "credentials": {
        "openAiApi": {
          "id": "",
          "name": ""
        }
      },
      "typeVersion": 1
    },
    {
      "id": "e3bd4759-80cc-42bb-ba53-f9e88e9ba916",
      "name": "Telegram Response",
      "type": "n8n-nodes-base.telegram",
      "onError": "continueErrorOutput",
      "position": [
        160,
        560
      ],
      "parameters": {
        "text": "={{ $json.response.text }}",
        "chatId": "={{ $('Telegram Trigger').item.json.message.chat.id }}",
        "additionalFields": {
          "appendAttribution": false
        }
      },
      "credentials": {
        "telegramApi": {
          "id": "",
          "name": ""
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "e478df48-9e6d-4a84-89be-beb569914ae3",
      "name": "Telegram Response about Database",
      "type": "n8n-nodes-base.telegram",
      "onError": "continueErrorOutput",
      "position": [
        1400,
        220
      ],
      "parameters": {
        "text": "={{ $json.metadata.pdf.totalPages }} pages saved on Pinecone",
        "chatId": "={{ $('Telegram Trigger').item.json.message.chat.id }}",
        "additionalFields": {
          "appendAttribution": false
        }
      },
      "credentials": {
        "telegramApi": {
          "id": "",
          "name": ""
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "5be7a321-1be6-4173-83de-3d569666718d",
      "name": "Stop and Error1",
      "type": "n8n-nodes-base.stopAndError",
      "position": [
        1400,
        580
      ],
      "parameters": {
        "errorMessage": "An error occurred."
      },
      "typeVersion": 1
    },
    {
      "id": "aae26861-f34d-4b59-bd99-3662fbd6676c",
      "name": "Pinecone Vector Store",
      "type": "@n8n/n8n-nodes-langchain.vectorStorePinecone",
      "position": [
        880,
        220
      ],
      "parameters": {
        "mode": "insert",
        "options": {},
        "pineconeIndex": {
          "__rl": true,
          "mode": "list",
          "value": "telegram",
          "cachedResultName": "telegram"
        }
      },
      "credentials": {
        "pineconeApi": {
          "id": "",
          "name": ""
        }
      },
      "typeVersion": 1
    },
    {
      "id": "312fb807-4225-4630-ab32-aa12fe07c127",
      "name": "Limit to 1",
      "type": "n8n-nodes-base.limit",
      "position": [
        1220,
        220
      ],
      "parameters": {},
      "typeVersion": 1
    }
  ],
  "connections": {
    "Embeddings": {
      "ai_embedding": [
        [
          {
            "node": "Pinecone Vector Store1",
            "type": "ai_embedding",
            "index": 0
          }
        ]
      ]
    },
    "Limit to 1": {
      "main": [
        [
          {
            "node": "Telegram Response about Database",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Groq Chat Model": {
      "ai_languageModel": [
        [
          {
            "node": "Question and Answer Chain",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "Telegram Trigger": {
      "main": [
        [
          {
            "node": "Check If is a document",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Embeddings OpenAI": {
      "ai_embedding": [
        [
          {
            "node": "Pinecone Vector Store",
            "type": "ai_embedding",
            "index": 0
          }
        ]
      ]
    },
    "Telegram Response": {
      "main": [
        [],
        [
          {
            "node": "Stop and Error",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Telegram get File": {
      "main": [
        [
          {
            "node": "Change to application/pdf",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Default Data Loader": {
      "ai_document": [
        [
          {
            "node": "Pinecone Vector Store",
            "type": "ai_document",
            "index": 0
          }
        ]
      ]
    },
    "Pinecone Vector Store": {
      "main": [
        [
          {
            "node": "Limit to 1",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Check If is a document": {
      "main": [
        [
          {
            "node": "Telegram get File",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "Question and Answer Chain",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Pinecone Vector Store1": {
      "ai_vectorStore": [
        [
          {
            "node": "Vector Store Retriever",
            "type": "ai_vectorStore",
            "index": 0
          }
        ]
      ]
    },
    "Vector Store Retriever": {
      "ai_retriever": [
        [
          {
            "node": "Question and Answer Chain",
            "type": "ai_retriever",
            "index": 0
          }
        ]
      ]
    },
    "Change to application/pdf": {
      "main": [
        [
          {
            "node": "Pinecone Vector Store",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Question and Answer Chain": {
      "main": [
        [
          {
            "node": "Telegram Response",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Telegram Response about Database": {
      "main": [
        [],
        [
          {
            "node": "Stop and Error1",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Recursive Character Text Splitter": {
      "ai_textSplitter": [
        [
          {
            "node": "Default Data Loader",
            "type": "ai_textSplitter",
            "index": 0
          }
        ]
      ]
    }
  }
}

Actions

Share
Categories:
Communication
Tags:
iftelegramtelegramtriggerstickynotecodestopanderrorlimit

Technical Specs

Complexity:
Expert
Node Count:
20 nodes
Published:11 months ago
Updated:7 days ago

Compatibility

Platform:
N8N Cloud & Self-hosted
Min Version:
N8N v1.0.0+
Supports cloud and self-hosted deployment

License

This workflow template follows MIT license, you can freely use, modify and distribute.

Please comply with relevant third-party service terms when using.

Related Workflows

Aggregate Multiple RSS Feeds

Automate the aggregation of multiple RSS feeds into a single, unified list. This workflow loops through a list of URLs, fetches data from each, and combines them into one output.

6 nodes•Intermediate

AI-Powered LinkedIn Lead Generation and Outreach Automation

Automate your entire B2B sales pipeline with this n8n workflow. Use OpenAI to convert your ICP into LinkedIn searches, research and score leads, and manage outreach, all tracked in Google Sheets.

92 nodes•Expert

WhatsApp Echo Bot Starter Workflow

Set up a simple WhatsApp echo bot with this starter workflow. Learn how to configure and verify Meta webhooks in n8n to automatically respond to incoming user messages.

8 nodes•Intermediate

Adaptive RAG

Implement an advanced Adaptive RAG workflow in n8n. Dynamically classify user queries to tailor retrieval and generation strategies using Google Gemini and Qdrant for more accurate AI responses.

39 nodes•Expert

Suspicious Login Detection

Automate suspicious login detection and response using n8n. This workflow analyzes IP reputation with GreyNoise, checks for location and device anomalies, and sends prioritized alerts to Slack and email notifications.

43 nodes•Expert

Amazon Keyword Suggestion Tool with Airtable Integration

Automate Amazon keyword research. This workflow fetches a seed keyword from Airtable, gets suggestions from Amazon's API, and saves them back to Airtable.

12 nodes•Advanced