Bear Brown
← All N8N workflows
AI & researchChain Retrieval QaCodeDocument Default Data LoaderEmbeddings Open AiIf

Telegram RAG pdf

Configured with Chain Retrieval Qa, Document Default Data Loader, Embeddings Open Ai, Limit, and additional nodes. Review the connections and setup before adapting this template.

Download workflow JSONView files on GitHub ↗18 nodes · MIT
Workflow preview
TriggerTelegram TriggerTelegram TriggerAI & modelsEmbeddings OpenAIEmbeddings Open AiFiles / mediaDefault Data LoaderDocument Default Data Lo…TransformRecursive CharacterText SplitterText Splitter Recursive …RoutingStop and ErrorStop And ErrorAI & modelsQuestion and AnswerChainChain Retrieval QaAI & modelsVector Store RetrieverRetriever Vector StoreData storePinecone Vector Store1Vector Store PineconeAI & modelsGroq Chat ModelLM Chat GroqRoutingCheck If is a documentIfCodeChange toapplication/pdfCodeMessagingTelegram get FileTelegramAI & modelsEmbeddingsEmbeddings Open AiMessagingTelegram ResponseTelegramMessagingTelegram Response aboutDatabaseTelegramRoutingStop and Error1Stop And ErrorData storePinecone Vector StoreVector Store PineconeTransformLimit to 1Limit

Node categories in this workflow

  • Trigger
  • AI & models
  • Files / media
  • Transform
  • Routing
  • Data store
  • Code
  • Messaging

Icons describe general node roles, inferred from node types. Inspect the parameters for the configured action.

Drag to pan; use + and − to zoom. Reconstructed from the exported node positions; nothing runs here. Dashed lines represent non-main connections. Full node names and notes appear below.

How it works

The exported workflow contains the following configured nodes. Their connections are shown above; inspect the JSON for the complete logic, expressions, and external actions.

Workflow node names, types, and operations
NodeCategoryTypeOperation
Telegram TriggerTriggerTelegram TriggerSee node parameters
Embeddings OpenAIAI & modelsEmbeddings Open AiSee node parameters
Default Data LoaderFiles / mediaDocument Default Data LoaderSee node parameters
Recursive Character Text SplitterTransformText Splitter Recursive Character Text SplitterSee node parameters
Stop and ErrorRoutingStop And ErrorSee node parameters
Question and Answer ChainAI & modelsChain Retrieval QaSee node parameters
Vector Store RetrieverAI & modelsRetriever Vector StoreSee node parameters
Pinecone Vector Store1Data storeVector Store PineconeSee node parameters
Groq Chat ModelAI & modelsLM Chat GroqSee node parameters
Check If is a documentRoutingIfSee node parameters
Change to application/pdfCodeCodeSee node parameters
Telegram get FileMessagingTelegramfile
EmbeddingsAI & modelsEmbeddings Open AiSee node parameters
Telegram ResponseMessagingTelegramSee node parameters
Telegram Response about DatabaseMessagingTelegramSee node parameters
Stop and Error1RoutingStop And ErrorSee node parameters
Pinecone Vector StoreData storeVector Store PineconeSee node parameters
Limit to 1TransformLimitSee node parameters

Setup

  1. Download the JSON and import it into an isolated n8n instance. Leave the workflow inactive.
  2. Connect your own credentials through n8n’s credential store. Replace REPLACE_WITH_* values with your resource identifiers.
  3. Inspect API destinations, Code nodes, database queries, file paths, and outbound actions.
  4. Run with synthetic data and harmless destinations. Enable triggers only after checking the actual outputs.

Requirements

An n8n instance with the listed node types and compatible versions. Service-connected workflows may require accounts, credentials, or paid APIs.

Credential types declared in the source

  • groqApi
  • openAiApi
  • pineconeApi
  • telegramApi

Workflow notes

Load data into database

Load data into database

Fetch 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

Chat with Database

Chat with Database

  1. Receive the incoming chat message.
  2. Retrieve relevant chunks from the vector store.
  3. Pass these chunks to the model.

The model will use the retrieved information to formulate a precise response.

Telegram RAG pdf

Telegram RAG pdf

Purpose and structure

This folder contains the Telegram RAG pdf workflow. Its executable nodes use chainRetrievalQa, code, documentDefaultDataLoader, embeddingsOpenAi, if, limit, lmChatGroq, retrieverVectorStore, stopAndError, telegram, telegramTrigger, textSplitterRecursiveCharacterTextSplitter, vectorStorePinecone. The table and connection map below are derived from the JSON, not an inferred guarantee of behavior.

Setup

Import inactive. Configure your own credentials and replace REPLACE_WITH_* values. Review external destinations and Code nodes before running.

Entry points

Telegram Trigger

Verification

Sanitized source candidate; not runtime-tested. This overview is generated from node metadata. Read the folder README for the connection map, credential types, and license.

Attribution

https://github.com/Zie619/n8n-workflows/blob/94007c1445d9258a7da116646b79473e7c7c3282/workflows/Stopanderror/1689_Stopanderror_Telegram_Automation_Triggered.json MIT; preserve source notices.

More in AI & research

"Hey Siri, Ask Agent" workflow#️⃣Nostr #damus AI Powered Reporting + Gmail + Telegram(G) - Email Classification