Back to Catalog

Self-learning AI assistant with permanent memory | GPT,Telegram & Pinecone RAG

TianyiTianyi
6138 views
2/3/2026
Official Page

Your AI secretary that self-learning every day and remembers everything you said (text, audio, image).

Imagine having a personal AI secretary accessible right from your Telegram, ready to assist you with information and remember everything you discuss. This n8n workflow transforms Telegram into your intelligent assistant, capable of understanding text, audio, and images, and continuously learning from your interactions. It integrates RAG's offline data ingestion and online querying functionalities, letting you save inspiration and key information permanently in real-time, and giving you an AI assistant that remembers all your dialogues and information. It builds and queries a powerful vector database in real-time, ensuring relevant and accurate responses. Video guidance on how to set up Telegram integration is also included.

Who is this for?

This template is ideal for:

  • Individuals seeking a personal AI assistant for quick information retrieval and note-taking.
  • Professionals who need to keep track of important conversations and insights.
  • Anyone interested in leveraging the power of Retrieval-Augmented Generation (RAG) and vector databases for personal knowledge management.
  • Users who want a self-learning AI that improves over time based on their interactions.

What problem is this workflow solving?

This workflow integrates RAG's offline data ingestion and online querying functionalities, letting you save inspiration and key information permanently in real-time, and giving you an AI assistant that remembers all your dialogues and information. This workflow addresses the challenge of information overload and the need for an easily accessible, personalized knowledge base. It eliminates the need to manually organize notes and search through past conversations. By automatically storing and retrieving information from a vector database, this workflow makes it effortless to access the knowledge you need, when you need it. It also provides a way to retain information from various media types like voice notes and images.

What this workflow does:

This workflow automates the following steps:

  • Instant Information Capture: Receives text messages, audio notes (transcribed), and images (with content analysis) directly from your Telegram.
  • Intelligent Question Answering: When you ask a question, the AI searches its knowledge base (Pinecone vector store) for relevant information and provides a comprehensive answer. It even considers your recent conversations for context.
  • Automatic Knowledge Storage: When you make a statement or provide information, the AI extracts key details and saves them in a Google Docs "memory palace."
  • Daily Self-Learning: Every day, the workflow automatically takes all the information stored in the Google Docs, converts it into a vector representation, and adds it to its knowledge base (Pinecone vector store). This ensures the AI continuously learns and remembers everything you've shared.
  • Image Understanding: Extracts text and information from images you send.
  • Audio Transcription: Automatically transcribes your voice notes into text for processing and storage.
  • Short-Term Memory: Remembers recent interactions within a session for more context-aware conversations.

Setup:

To get started, you'll need to connect the following services to your n8n instance:

  1. Telegram: Connect your Telegram bot API credentials. A video guidance is included for telegram integration setup.
  2. OpenAI: Provide your OpenAI API key for audio transcription and image analysis.
  3. Pinecone: Set up a Pinecone account and provide your API key and environment. Create a namespace in Pinecone.
  4. Google Docs: Connect your Google account with access to Google Docs. You'll need to create a Google Doc that will serve as the daily "memory palace" and provide its ID in the workflow.

How to customize this workflow:

  • Adjust the AI Agent's Personality: Modify the system prompt in the "AI Agent" node to tailor the AI's tone and behavior.
  • Expand Knowledge Sources: Integrate other data sources into the daily learning process, such as emails or other documents, by adding more nodes to the scheduled trigger workflow.
  • Add More Tools for the AI Agent: Integrate additional tools into the AI Agent, such as web search or other APIs, to further enhance its capabilities.
  • Modify the Daily Schedule: Adjust the schedule trigger to run at a different time or interval.

n8n Self-Learning AI Assistant with Permanent Memory (GPT, Telegram, Pinecone RAG)

This n8n workflow creates a self-learning AI assistant that interacts via Telegram, leveraging OpenAI's GPT models for conversational intelligence and Pinecone for permanent memory (Retrieval Augmented Generation - RAG). This allows the AI to remember past conversations and adapt its responses based on previously stored information.

What it does

This workflow automates the following steps:

  1. Listens for Telegram Messages: It acts as a Telegram bot, triggering whenever a new message is received.
  2. Initializes AI Agent: Sets up an AI agent using Langchain, configuring it with an OpenAI Chat Model and a Simple Memory buffer to manage short-term conversation context.
  3. Integrates Permanent Memory (Pinecone): Connects to a Pinecone Vector Store, allowing the AI to retrieve relevant information from a long-term memory database. This enables the assistant to answer questions based on previously ingested data.
  4. Processes User Input: The AI agent processes the incoming Telegram message, considering both the current conversation context (Simple Memory) and relevant information from Pinecone.
  5. Generates AI Response: Uses the OpenAI Chat Model to generate a coherent and contextually appropriate response.
  6. Sends Response to Telegram: Posts the AI's generated response back to the user via Telegram.
  7. Manages Knowledge Base (Optional/Manual Trigger):
    • A separate branch allows for manual ingestion of documents into the Pinecone vector store.
    • It uses a "Schedule Trigger" (though configured for manual execution in this JSON) to initiate the process.
    • It retrieves content from a Google Docs document.
    • Splits the document content into smaller, manageable chunks using a "Recursive Character Text Splitter".
    • Generates embeddings for these text chunks using "Embeddings OpenAI".
    • Stores these embeddings in the Pinecone Vector Store, effectively updating the AI's permanent memory.

Prerequisites/Requirements

To use this workflow, you will need:

  • n8n Instance: A running n8n instance.
  • Telegram Bot Token: A Telegram bot token obtained from BotFather.
  • OpenAI API Key: An API key from OpenAI for accessing their GPT chat models and embedding services.
  • Pinecone Account and API Key: An account with Pinecone, including an API key and environment details for your vector database.
  • Google Docs Document (Optional for knowledge ingestion): If you plan to use the document ingestion part, a Google Docs document containing the knowledge you want your AI to learn.

Setup/Usage

  1. Import the workflow: Import the provided JSON into your n8n instance.
  2. Configure Credentials:
    • Telegram Trigger & Telegram Node: Set up a Telegram credential with your bot token.
    • OpenAI Chat Model & Embeddings OpenAI: Set up an OpenAI credential with your API key.
    • Pinecone Vector Store: Set up a Pinecone credential with your API key and environment.
    • Google Docs (Optional): Set up a Google Docs credential if you intend to use the document ingestion part.
  3. Activate the workflow: Once credentials are set, activate the main workflow (triggered by Telegram messages).
  4. Ingest Knowledge (Optional): If you want your AI to have a permanent memory, manually execute the "Schedule Trigger" branch. Ensure the "Google Docs" node points to the correct document ID. This will populate your Pinecone vector store with the document's content.
  5. Interact with your bot: Send messages to your configured Telegram bot. The AI assistant will respond, leveraging its short-term memory and the long-term knowledge stored in Pinecone.

Related Templates

Automate Dutch Public Procurement Data Collection with TenderNed

TenderNed Public Procurement What This Workflow Does This workflow automates the collection of public procurement data from TenderNed (the official Dutch tender platform). It: Fetches the latest tender publications from the TenderNed API Retrieves detailed information in both XML and JSON formats for each tender Parses and extracts key information like organization names, titles, descriptions, and reference numbers Filters results based on your custom criteria Stores the data in a database for easy querying and analysis Setup Instructions This template comes with sticky notes providing step-by-step instructions in Dutch and various query options you can customize. Prerequisites TenderNed API Access - Register at TenderNed for API credentials Configuration Steps Set up TenderNed credentials: Add HTTP Basic Auth credentials with your TenderNed API username and password Apply these credentials to the three HTTP Request nodes: "Tenderned Publicaties" "Haal XML Details" "Haal JSON Details" Customize filters: Modify the "Filter op ..." node to match your specific requirements Examples: specific organizations, contract values, regions, etc. How It Works Step 1: Trigger The workflow can be triggered either manually for testing or automatically on a daily schedule. Step 2: Fetch Publications Makes an API call to TenderNed to retrieve a list of recent publications (up to 100 per request). Step 3: Process & Split Extracts the tender array from the response and splits it into individual items for processing. Step 4: Fetch Details For each tender, the workflow makes two parallel API calls: XML endpoint - Retrieves the complete tender documentation in XML format JSON endpoint - Fetches metadata including reference numbers and keywords Step 5: Parse & Merge Parses the XML data and merges it with the JSON metadata and batch information into a single data structure. Step 6: Extract Fields Maps the raw API data to clean, structured fields including: Publication ID and date Organization name Tender title and description Reference numbers (kenmerk, TED number) Step 7: Filter Applies your custom filter criteria to focus on relevant tenders only. Step 8: Store Inserts the processed data into your database for storage and future analysis. Customization Tips Modify API Parameters In the "Tenderned Publicaties" node, you can adjust: offset: Starting position for pagination size: Number of results per request (max 100) Add query parameters for date ranges, status filters, etc. Add More Fields Extend the "Splits Alle Velden" node to extract additional fields from the XML/JSON data, such as: Contract value estimates Deadline dates CPV codes (procurement classification) Contact information Integrate Notifications Add a Slack, Email, or Discord node after the filter to get notified about new matching tenders. Incremental Updates Modify the workflow to only fetch new tenders by: Storing the last execution timestamp Adding date filters to the API query Only processing publications newer than the last run Troubleshooting No data returned? Verify your TenderNed API credentials are correct Check that you have setup youre filter proper Need help setting this up or interested in a complete tender analysis solution? Get in touch πŸ”— LinkedIn – Wessel Bulte

Wessel BulteBy Wessel Bulte
247

πŸŽ“ How to transform unstructured email data into structured format with AI agent

This workflow automates the process of extracting structured, usable information from unstructured email messages across multiple platforms. It connects directly to Gmail, Outlook, and IMAP accounts, retrieves incoming emails, and sends their content to an AI-powered parsing agent built on OpenAI GPT models. The AI agent analyzes each email, identifies relevant details, and returns a clean JSON structure containing key fields: From – sender’s email address To – recipient’s email address Subject – email subject line Summary – short AI-generated summary of the email body The extracted information is then automatically inserted into an n8n Data Table, creating a structured database of email metadata and summaries ready for indexing, reporting, or integration with other tools. --- Key Benefits βœ… Full Automation: Eliminates manual reading and data entry from incoming emails. βœ… Multi-Source Integration: Handles data from different email providers seamlessly. βœ… AI-Driven Accuracy: Uses advanced language models to interpret complex or unformatted content. βœ… Structured Storage: Creates a standardized, query-ready dataset from previously unstructured text. βœ… Time Efficiency: Processes emails in real time, improving productivity and response speed. *βœ… Scalability: Easily extendable to handle additional sources or extract more data fields. --- How it works This workflow automates the transformation of unstructured email data into a structured, queryable format. It operates through a series of connected steps: Email Triggering: The workflow is initiated by one of three different email triggers (Gmail, Microsoft Outlook, or a generic IMAP account), which constantly monitor for new incoming emails. AI-Powered Parsing & Structuring: When a new email is detected, its raw, unstructured content is passed to a central "Parsing Agent." This agent uses a specified OpenAI language model to intelligently analyze the email text. Data Extraction & Standardization: Following a predefined system prompt, the AI agent extracts key information from the email, such as the sender, recipient, subject, and a generated summary. It then forces the output into a strict JSON structure using a "Structured Output Parser" node, ensuring data consistency. Data Storage: Finally, the clean, structured data (the from, to, subject, and summarize fields) is inserted as a new row into a specified n8n Data Table, creating a searchable and reportable database of email information. --- Set up steps To implement this workflow, follow these configuration steps: Prepare the Data Table: Create a new Data Table within n8n. Define the columns with the following names and string type: From, To, Subject, and Summary. Configure Email Credentials: Set up the credential connections for the email services you wish to use (Gmail OAuth2, Microsoft Outlook OAuth2, and/or IMAP). Ensure the accounts have the necessary permissions to read emails. Configure AI Model Credentials: Set up the OpenAI API credential with a valid API key. The workflow is configured to use the model, but this can be changed in the respective nodes if needed. Connect the Nodes: The workflow canvas is already correctly wired. Visually confirm that the email triggers are connected to the "Parsing Agent," which is connected to the "Insert row" (Data Table) node. Also, ensure the "OpenAI Chat Model" and "Structured Output Parser" are connected to the "Parsing Agent" as its AI model and output parser, respectively. Activate the Workflow: Save the workflow and toggle the "Active" switch to ON. The triggers will begin polling for new emails according to their schedule (e.g., every minute), and the automation will start processing incoming messages. --- Need help customizing? Contact me for consulting and support or add me on Linkedin.

DavideBy Davide
1616

Tax deadline management & compliance alerts with GPT-4, Google Sheets & Slack

AI-Driven Tax Compliance & Deadline Management System Description Automate tax deadline monitoring with AI-powered insights. This workflow checks your tax calendar daily at 8 AM, uses GPT-4 to analyze upcoming deadlines across multiple jurisdictions, detects overdue and critical items, and sends intelligent alerts via email and Slack only when immediate action is required. Perfect for finance teams and accounting firms who need proactive compliance management without manual tracking. πŸ›οΈπŸ€–πŸ“Š Good to Know AI-Powered: GPT-4 provides risk assessment and strategic recommendations Multi-Jurisdiction: Handles Federal, State, and Local tax requirements automatically Smart Alerts: Only notifies executives when deadlines are overdue or critical (≀3 days) Priority Classification: Categorizes deadlines as Overdue, Critical, High, or Medium priority Dual Notifications: Critical alerts to leadership + daily summaries to team channel Complete Audit Trail: Logs all checks and deadlines to Google Sheets for compliance records How It Works Daily Trigger - Runs at 8:00 AM every morning Fetch Data - Pulls tax calendar and company configuration from Google Sheets Analyze Deadlines - Calculates days remaining, filters by jurisdiction/entity type, categorizes by priority AI Analysis - GPT-4 provides strategic insights and risk assessment on upcoming deadlines Smart Routing - Only sends alerts if overdue or critical deadlines exist Critical Alerts - HTML email to executives + Slack alert for urgent items Team Updates - Slack summary to finance channel with all upcoming deadlines Logging - Records compliance check results to Google Sheets for audit trail Requirements Google Sheets Structure Sheet 1: TaxCalendar DeadlineID | DeadlineName | DeadlineDate | Jurisdiction | Category | AssignedTo | IsActive FED-Q1 | Form 1120 Q1 | 2025-04-15 | Federal | Income | John Doe | TRUE Sheet 2: CompanyConfig (single row) Jurisdictions | EntityType | FiscalYearEnd Federal, California | Corporation | 12-31 Sheet 3: ComplianceLog (auto-populated) Date | AlertLevel | TotalUpcoming | CriticalCount | OverdueCount 2025-01-15 | HIGH | 12 | 3 | 1 Credentials Needed Google Sheets - Service Account OAuth2 OpenAI - API Key (GPT-4 access required) SMTP - Email account for sending alerts Slack - Bot Token with chat:write permission Setup Steps Import workflow JSON into n8n Add all 4 credentials Replace these placeholders: YOURTAXCALENDAR_ID - Tax calendar sheet ID YOURCONFIGID - Company config sheet ID YOURLOGID - Compliance log sheet ID C12345678 - Slack channel ID tax@company.com - Sender email cfo@company.com - Recipient email Share all sheets with Google service account email Invite Slack bot to channels Test workflow manually Activate the trigger Customizing This Workflow Change Alert Thresholds: Edit "Analyze Deadlines" node: Critical: Change <= 3 to <= 5 for 5-day warning High: Change <= 7 to <= 14 for 2-week notice Medium: Change <= 30 to <= 60 for 2-month lookout Adjust Schedule: Edit "Daily Tax Check" trigger: Change hour/minute for different run time Add multiple trigger times for tax season (8 AM, 2 PM, 6 PM) Add More Recipients: Edit "Send Email" node: To: cfo@company.com, director@company.com CC: accounting@company.com BCC: archive@company.com Customize Email Design: Edit "Format Email" node to change colors, add logo, or modify layout Add SMS Alerts: Insert Twilio node after "Is Critical" for emergency notifications Integrate Task Management: Add HTTP Request node to create tasks in Asana/Jira for critical deadlines Troubleshooting | Issue | Solution | |-------|----------| | No deadlines found | Check date format (YYYY-MM-DD) and IsActive = TRUE | | AI analysis failed | Verify OpenAI API key and account credits | | Email not sending | Test SMTP credentials and check if critical condition met | | Slack not posting | Invite bot to channel and verify channel ID format | | Permission denied | Share Google Sheets with service account email | πŸ“ž Professional Services Need help with implementation or customization? Our team offers: 🎯 Custom workflow development 🏒 Enterprise deployment support πŸŽ“ Team training sessions πŸ”§ Ongoing maintenance πŸ“Š Custom reporting & dashboards πŸ”— Additional API integrations Discover more workflows – Get in touch with us

Oneclick AI SquadBy Oneclick AI Squad
93