This article provides a complete, practical walkthrough of the Telegram Code Automate Triggered n8n agent. It connects HTTP Request, Webhook across approximately 1 node(s). Expect a Intermediate setup in 15-45 minutes. One‑time purchase: €29.

What This Agent Does

This agent orchestrates a reliable automation between HTTP Request, Webhook, handling triggers, data enrichment, and delivery with guardrails for errors and rate limits.

It streamlines multi‑step processes that would otherwise require manual exports, spreadsheet cleanup, and repeated API requests. By centralizing logic in n8n, it reduces context switching, lowers error rates, and ensures consistent results across teams.

Typical outcomes include faster lead handoffs, automated notifications, accurate data synchronization, and better visibility via execution logs and optional Slack/Email alerts.

How It Works

The workflow uses standard n8n building blocks like Webhook or Schedule triggers, HTTP Request for API calls, and control nodes (IF, Merge, Set) to validate inputs, branch on conditions, and format outputs. Retries and timeouts improve resilience, while credentials keep secrets safe.

Third‑Party Integrations

• HTTP Request
• Webhook

Import and Use in n8n

1. Open n8n and create a new workflow or collection.
2. Choose Import from File or Paste JSON.
3. Paste the JSON below, then click Import.
4. Show n8n JSON

   Title:
   Building an AI-Powered Email Chatbot with Semantic & Structured Search Using n8n, Telegram, and Pgvector
   
   Meta Description:
   Discover how to create a smart email chatbot using n8n, Telegram, LangChain, and Pgvector. Combine structured SQL queries with semantic vector embeddings for powerful retrieval-augmented generation (RAG) from your email database.
   
   Keywords:
   n8n, email chatbot, vector search, semantic search, structured RAG, Pgvector, LangChain, OpenAI, Telegram bot, AI chatbot, embeddings, SQL email query, Ollama, Mistral, unified search, workflow automation
   
   Third-party APIs and Services Used:
   
   - Telegram Bot API: For interacting with users via a Telegram chatbot interface.
   - Postgres with Pgvector: To store and retrieve semantic vector embeddings from email text bodies.
   - LangChain: For coordinating language model tools, memory management, agents, and embedding workflows across NLP tasks.
   - OpenAI API (alternatively configured with Ollama for local inference): Used with a Mistral model to power the AI agent's language reasoning and chat generation.
   - Ollama (nomic-embed-text model): For generating vector embeddings from email content.
   - LangChain Agent Toolkit: Includes tools like memory buffer, vector store connectors, and SQL workflow chaining.
   
   Article:
   
   Unlocking the Power of Email Intelligence: A Smart Chatbot with n8n, Pgvector, and Telegram
   
   In today's information-rich landscape, emails are one of the most critical and untapped data sources. While traditional keyword searches offer basic lookup capabilities, modern use cases call for smarter, context-aware systems that can interpret, reason, and retrieve information – even when it’s ambiguously phrased.
   
   Enter the email chatbot built with n8n, Telegram, LangChain, and Pgvector. This sophisticated workflow not only parses your email corpus semantically but also understands structured queries, offering a dual Retrieval-Augmented Generation (RAG) system that makes querying data as easy as chatting with a bot.
   
   Let’s break down how it works and why it’s a gamechanger.
   
   An AI Assistant with Multimodal Search Capabilities
   
   This n8n workflow bridges semantic search (via vector embeddings) and structured query (via SQL), enabling an AI chatbot that handles natural language prompts over Telegram or directly in n8n. It’s like giving superpowers to your inbox.
   
   When a user types a question like "Who am I interviewing next week?", the AI agent determines the intent involves a future event, prompting a structured SQL query. In another scenario, “When did I sign up for GitHub Copilot?” might require semantic understanding — best fetched via embeddings.
   
   Key Components of the Workflow
   
   1. Telegram Integration
   At the entrance of this interaction is the 'Telegram Trigger' node, listening for messages from a specific chat ID. This allows users to initiate queries directly from Telegram.
   
   2. Session Management and Message Context
   Each query is tagged with a session ID using the “Generate session id” node. This ensures the chatbot maintains conversational context, using LangChain’s memory buffer to track interactions.
   
   3. The AI Core – Multi-Tool Agent
   At the heart of the system lies a custom-configured LangChain agent connected to a language model (Mistral via OpenAI or Ollama). Advising the agent is a comprehensive system prompt describing the database schema and time-handling logic. This ensures the model doesn’t hallucinate, instead focusing on factual, structured instruction following.
   
   It uses two tools:
   
   - email_vector_search: Searches Pgvector-based email embeddings for semantically relevant content.
   - email_sql_search: A separate, generic workflow that composes SQL queries from natural language to retrieve structured data like timestamps, sender info, and full threads.
   
   4. Semantic Embeddings with Ollama
   The ‘Embeddings Ollama’ node uses a locally-hosted or API-based model like nomic-embed-text to convert message text into vector embeddings, which are then stored or searched via Postgres PGVector.
   
   5. Structured SQL Search Workflow
   A separate sub-workflow — “Generate email SQL queries” — receives plain language questions and crafts precise SQL queries. The bot routes questions intelligently based on the context or refines them after initial semantic results.
   
   6. Output Formatting & Delivery
   Before responding, the system organizes output in clean, human-readable markdown-less messages. These are intelligently chunked to avoid Telegram message limits and escaped for safe markdown rendering. Final responses are sent in sequence using batching logic.
   
   Real-World Benefits
   
   This AI chatbot transforms how we interact with email data:
   
   - Intelligent Answers: Queries like “What emails mention visa processing this year?” or “Find attachments related to performance reviews in Q2” become frictionless.
   - Multipurpose Interface: Use it in Telegram or directly in n8n for different UX preferences.
   - Dual Retrieval: Combines semantic and structured data retrieval for near-complete knowledge coverage.
   - Context Awareness: Thanks to LangChain memory, follow-up questions make sense — like “When was that sent?” after asking about a specific topic.
   
   Why This Matters
   
   Most email search tools are either strictly structured (Gmail advanced filters) or use black-box machine learning with limited transparency. With this open-source stack:
   
   - You control the logic.
   - You can easily extend the tooling.
   - You know exactly how the AI thinks and searches your data.
   
   Conclusion
   
   This workflow elegantly showcases how modern automation platforms like n8n, combined with vector databases and advanced AI agents, can unlock meaningful insights from everyday communication tools like email. From scheduling insights to contract tracking, the possibilities are endless.
   
   Whether you're an AI developer, a tech-savvy productivity optimizer, or an enterprise innovation lead — embedding this workflow into your tech stack can boost the way you retrieve, reason, and act upon the hidden gems in your inbox.
   
   Welcome to your smarter inbox.
   
   — End —

5. Set credentials for each API node (keys, OAuth) in Credentials.
6. Run a test via Execute Workflow. Inspect Run Data, then adjust parameters.
7. Enable the workflow to run on schedule, webhook, or triggers as configured.

Tips: keep secrets in credentials, add retries and timeouts on HTTP nodes, implement error notifications, and paginate large API fetches.

Validation: use IF/Code nodes to sanitize inputs and guard against empty payloads.

Why Automate This with AI Agents

AI‑assisted automations offload repetitive, error‑prone tasks to a predictable workflow. Instead of manual copy‑paste and ad‑hoc scripts, your team gets a governed pipeline with versioned state, auditability, and observable runs.

n8n’s node graph makes data flow transparent while AI‑powered enrichment (classification, extraction, summarization) boosts throughput and consistency. Teams reclaim time, reduce operational costs, and standardize best practices without sacrificing flexibility.

Compared to one‑off integrations, an AI agent is easier to extend: swap APIs, add filters, or bolt on notifications without rewriting everything. You get reliability, control, and a faster path from idea to production.

Best Practices

• Credentials: restrict scopes and rotate tokens regularly.
• Resilience: configure retries, timeouts, and backoff for API nodes.
• Data Quality: validate inputs; normalize fields early to reduce downstream branching.
• Performance: batch records and paginate for large datasets.
• Observability: add failure alerts (Email/Slack) and persistent logs for auditing.
• Security: avoid sensitive data in logs; use environment variables and n8n credentials.

FAQs

Can I swap integrations later? Yes. Replace or add nodes and re‑map fields without rebuilding the whole flow.

How do I monitor failures? Use Execution logs and add notifications on the Error Trigger path.

Does it scale? Use queues, batching, and sub‑workflows to split responsibilities and control load.

Is my data safe? Keep secrets in Credentials, restrict token scopes, and review access logs.