Telegram node
Telegram Trigger node
+11

Self-Learning AI Assistant with Permanent Memory | GPT,Telegram & Pinecone RAG

Published 5 days ago

Created by

muzi
Tianyi

Categories

Template description

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.

Share Template

More AI workflow templates

OpenAI Chat Model node
SerpApi (Google Search) node

AI agent chat

This workflow employs OpenAI's language models and SerpAPI to create a responsive, intelligent conversational agent. It comes equipped with manual chat triggers and memory buffer capabilities to ensure seamless interactions. To use this template, you need to be on n8n version 1.50.0 or later.
n8n-team
n8n Team
HTTP Request node
Merge node
+7

Scrape and summarize webpages with AI

This workflow integrates both web scraping and NLP functionalities. It uses HTML parsing to extract links, HTTP requests to fetch essay content, and AI-based summarization using GPT-4o. It's an excellent example of an end-to-end automated task that is not only efficient but also provides real value by summarizing valuable content. Note that to use this template, you need to be on n8n version 1.50.0 or later.
n8n-team
n8n Team
HTTP Request node
WhatsApp Business Cloud node
+10

Building Your First WhatsApp Chatbot

This n8n template builds a simple WhatsApp chabot acting as a Sales Agent. The Agent is backed by a product catalog vector store to better answer user's questions. This template is intended to help introduce n8n users interested in building with WhatsApp. How it works This template is in 2 parts: creating the product catalog vector store and building the WhatsApp AI chatbot. A product brochure is imported via HTTP request node and its text contents extracted. The text contents are then uploaded to the in-memory vector store to build a knowledgebase for the chatbot. A WhatsApp trigger is used to capture messages from customers where non-text messages are filtered out. The customer's message is sent to the AI Agent which queries the product catalogue using the vector store tool. The Agent's response is sent back to the user via the WhatsApp node. How to use Once you've setup and configured your WhatsApp account and credentials First, populate the vector store by clicking the "Test Workflow" button. Next, activate the workflow to enable the WhatsApp chatbot. Message your designated WhatsApp number and you should receive a message from the AI sales agent. Tweak datasource and behaviour as required. Requirements WhatsApp Business Account OpenAI for LLM Customising this workflow Upgrade the vector store to Qdrant for persistance and production use-cases. Handle different WhatsApp message types for a more rich and engaging experience for customers.
jimleuk
Jimleuk
HTTP Request node
Markdown node
+5

AI agent that can scrape webpages

⚙️🛠️🚀🤖🦾 This template is a PoC of a ReAct AI Agent capable of fetching random pages (not only Wikipedia or Google search results). On the top part there's a manual chat node connected to a LangChain ReAct Agent. The agent has access to a workflow tool for getting page content. The page content extraction starts with converting query parameters into a JSON object. There are 3 pre-defined parameters: url** – an address of the page to fetch method** = full / simplified maxlimit** - maximum length for the final page. For longer pages an error message is returned back to the agent Page content fetching is a multistep process: An HTTP Request mode tries to get the page content. If the page content was successfuly retrieved, a series of post-processing begin: Extract HTML BODY; content Remove all unnecessary tags to recude the page size Further eliminate external URLs and IMG scr values (based on the method query parameter) Remaining HTML is converted to Markdown, thus recuding the page lengh even more while preserving the basic page structure The remaining content is sent back to an Agent if it's not too long (maxlimit = 70000 by default, see CONFIG node). NB: You can isolate the HTTP Request part into a separate workflow. Check the Workflow Tool description, it guides the agent to provide a query string with several parameters instead of a JSON object. Please reach out to Eduard is you need further assistance with you n8n workflows and automations! Note that to use this template, you need to be on n8n version 1.19.4 or later.
eduard
Eduard
Merge node
Telegram node
Telegram Trigger node
+2

Telegram AI Chatbot

The workflow starts by listening for messages from Telegram users. The message is then processed, and based on its content, different actions are taken. If it's a regular chat message, the workflow generates a response using the OpenAI API and sends it back to the user. If it's a command to create an image, the workflow generates an image using the OpenAI API and sends the image to the user. If the command is unsupported, an error message is sent. Throughout the workflow, there are additional nodes for displaying notes and simulating typing actions.
eduard
Eduard
Google Drive node
Binary Input Loader node
Embeddings OpenAI node
OpenAI Chat Model node
+5

Ask questions about a PDF using AI

The workflow first populates a Pinecone index with vectors from a Bitcoin whitepaper. Then, it waits for a manual chat message. When received, the chat message is turned into a vector and compared to the vectors in Pinecone. The most similar vectors are retrieved and passed to OpenAI for generating a chat response. Note that to use this template, you need to be on n8n version 1.19.4 or later.
davidn8n
David Roberts

Implement complex processes faster with n8n

red icon yellow icon red icon yellow icon