HumationHuman + Automation
Back to Catalog

Build a chatbot with Reinforced Learning Human Feedback (RLHF) and RAG

NovaNodeNovaNode
6130 views
2/3/2026
Google SheetsUpdate RowWebhookAutomationData Manipulation
Official Page

Who is this for?

This template is designed for internal support teams, product specialists, and knowledge managers who want to build an AI-powered knowledge assistant with retrieval-augmented generation (RAG) and reinforcement learning from human feedback (RLHF) via Telegram.

What problem is this workflow solving?

Manual knowledge management and answering support queries can be time-consuming and error-prone. This solution automates importing and indexing official documentation into MongoDB vector search and enhances AI responses with Telegram-based user feedback to continuously improve answer quality.

What these workflows do

Workflow 1: Document ingestion & indexing

  • Manually triggered workflow imports product documentation from Google Docs.
  • Documents are split into manageable chunks and embedded using OpenAI embeddings.
  • Embedded document chunks are stored in MongoDB Atlas vector store to enable semantic search.

Workflow 2: Telegram chat with RLHF feedback loop

  • Listens for user messages via Telegram bot integration.
  • Uses vector similarity search on MongoDB to retrieve relevant documentation chunks.
  • Generates answers with OpenAI GPT-4o-mini model using retrieval-augmented generation.
  • Sends answers back via Telegram and waits for user feedback (approval or disapproval).
  • Captures feedback, maps it as positive or negative, and stores it with the conversation data for future model improvement.

Setup

Setting up vector embeddings

  1. Authenticate Google Docs and connect your Google Docs URL containing the product documentation you want to index.
  2. Authenticate MongoDB Atlas and connect the collection where you want to store the vector embeddings. Create a search index on this collection to support vector similarity queries.
  3. Ensure the index name matches the one configured in n8n (data_index).
  4. See the example MongoDB search index template below for reference.

Setting up chat with Telegram RLHF

  1. Create a bot in Telegram with @botFather using the /newbot command.
  2. Connect the MongoDB database and search index used for vector search in the previous workflow. Also create two new collections in MongoDB Atlas: one for feedback and one for chat history. Create a search index for feedback, copying the provided template.
  3. Configure the AI system prompt in the “Knowledge Base Agent” node, making sure it references all three tools connected (productDocs, feedbackPositive, feedbackNegative) as provided in the template prompt.

Make sure

  • Product documentation and feedback collections must connect to the same MongoDB database.
  • There are three distinct MongoDB collections: one for product documentation, one for feedback, and one for chat history (chat history collection can be separate).
  • Telegram API credentials are valid and webhook URLs are correctly set up.

MongoDB Search Index Templates

Documentation Collection Index

{ "mappings": { "dynamic": false, "fields": { "_id": { "type": "string" }, "text": { "type": "string" }, "embedding": { "type": "knnVector", "dimensions": 1536, "similarity": "cosine" }, "source": { "type": "string" }, "doc_id": { "type": "string" } } } }

Feedback Collection Index

{ "mappings": { "dynamic": false, "fields": { "prompt": { "type": "string" }, "response": { "type": "string" }, "text": { "type": "string" }, "embedding": { "type": "knnVector", "dimensions": 1536, "similarity": "cosine" }, "feedback": { "type": "token" } } } }

n8n Chatbot with Reinforced Learning (RLHF) and RAG

This n8n workflow demonstrates a foundational setup for building a chatbot that incorporates elements of Reinforced Learning with Human Feedback (RLHF) and Retrieval Augmented Generation (RAG). It allows for human interaction via Telegram to provide feedback and leverages Google Docs as a knowledge base.

What it does

This workflow outlines the following key steps:

  1. Triggers on Telegram Message: Listens for incoming messages from a Telegram bot, acting as the user's input to the chatbot.
  2. Loads Document from Google Docs: Retrieves information from a specified Google Docs document, which serves as the knowledge base for the RAG component.
  3. Splits Text for Processing: Divides the loaded document content into smaller, manageable chunks using a Recursive Character Text Splitter, preparing it for embedding.
  4. Generates Embeddings: Creates vector embeddings for the text chunks using OpenAI's embedding model, enabling semantic search and retrieval.
  5. Stores Embeddings in MongoDB Atlas: Persists the generated embeddings in a MongoDB Atlas Vector Store, forming the searchable knowledge base for the RAG system.
  6. Manages Chat History: Utilizes MongoDB Chat Memory to store and retrieve conversational history, allowing the AI agent to maintain context.
  7. Processes User Input with AI Agent: An AI Agent (LangChain) orchestrates the interaction, potentially using the RAG system to retrieve relevant information from the vector store and the chat memory for conversational context.
  8. Generates Chat Responses with OpenAI: Uses an OpenAI Chat Model to generate intelligent and context-aware responses based on the AI Agent's processing.
  9. Sends Response to Telegram: Delivers the AI-generated response back to the user via Telegram.
  10. Allows for Human Feedback: The "Edit Fields (Set)" node and the final Telegram node suggest a mechanism for human intervention or feedback, where the workflow could be paused or reviewed by a human before sending a final response or to record feedback for RLHF.
  11. Manual Trigger for Setup/Testing: Includes a manual trigger for easy testing and initial setup of the workflow.
  12. Sticky Note for Documentation: A sticky note is included, likely for in-workflow documentation or instructions.

Prerequisites/Requirements

To use this workflow, you will need:

  • n8n Instance: A running n8n instance.
  • Telegram Bot: A Telegram bot token and chat ID for the Telegram Trigger and Telegram nodes.
  • Google Docs Account: Access to a Google Docs document containing your knowledge base.
  • OpenAI API Key: An OpenAI API key for generating embeddings and chat responses.
  • MongoDB Atlas Account: A MongoDB Atlas cluster configured with a vector store for storing embeddings and a database for chat memory.
  • LangChain Nodes: Ensure the @n8n/n8n-nodes-langchain package is installed in your n8n instance.

Setup/Usage

  1. Import the Workflow: Download the JSON provided and import it into your n8n instance.
  2. Configure Credentials:
    • Set up a Telegram credential with your bot token.
    • Configure a Google Docs credential with access to your document.
    • Set up an OpenAI credential with your API key.
    • Configure MongoDB Atlas credentials for both the Vector Store and Chat Memory nodes.
  3. Customize Nodes:
    • Telegram Trigger: Ensure it's configured to listen to your bot.
    • Google Docs: Specify the ID of the Google Docs document you want to use as your knowledge base.
    • Recursive Character Text Splitter: Adjust chunk size and overlap as needed for your data.
    • Embeddings OpenAI: Select the appropriate embedding model.
    • MongoDB Atlas Vector Store: Configure your MongoDB Atlas connection details, database, collection, and index name.
    • MongoDB Chat Memory: Configure your MongoDB Atlas connection details, database, and collection for chat history.
    • OpenAI Chat Model: Select your desired OpenAI chat model (e.g., gpt-3.5-turbo).
    • AI Agent: Configure the agent's prompt, tools (including the vector store), and memory (MongoDB Chat Memory).
    • Edit Fields (Set): This node can be customized to format the AI's response or to inject specific data for human feedback.
    • Telegram: Configure the chat ID to send responses back to the user.
  4. Activate the Workflow: Once configured, activate the workflow to start listening for Telegram messages.
  5. Test: Send a message to your Telegram bot to test the end-to-end flow. The "Manual Trigger" can be used for initial debugging.

Related Templates

Track competitor SEO keywords with Decodo + GPT-4.1-mini + Google Sheets

This workflow automates competitor keyword research using OpenAI LLM and Decodo for intelligent web scraping. Who this is for SEO specialists, content strategists, and growth marketers who want to automate keyword research and competitive intelligence. Marketing analysts managing multiple clients or websites who need consistent SEO tracking without manual data pulls. Agencies or automation engineers using Google Sheets as an SEO data dashboard for keyword monitoring and reporting. What problem this workflow solves Tracking competitor keywords manually is slow and inconsistent. Most SEO tools provide limited API access or lack contextual keyword analysis. This workflow solves that by: Automatically scraping any competitor’s webpage with Decodo. Using OpenAI GPT-4.1-mini to interpret keyword intent, density, and semantic focus. Storing structured keyword insights directly in Google Sheets for ongoing tracking and trend analysis. What this workflow does Trigger — Manually start the workflow or schedule it to run periodically. Input Setup — Define the website URL and target country (e.g., https://dev.to, france). Data Scraping (Decodo) — Fetch competitor web content and metadata. Keyword Analysis (OpenAI GPT-4.1-mini) Extract primary and secondary keywords. Identify focus topics and semantic entities. Generate a keyword density summary and SEO strength score. Recommend optimization and internal linking opportunities. Data Structuring — Clean and convert GPT output into JSON format. Data Storage (Google Sheets) — Append structured keyword data to a Google Sheet for long-term tracking. Setup Prerequisites If you are new to Decode, please signup on this link visit.decodo.com n8n account with workflow editor access Decodo API credentials OpenAI API key Google Sheets account connected via OAuth2 Make sure to install the Decodo Community node. Create a Google Sheet Add columns for: primarykeywords, seostrengthscore, keyworddensity_summary, etc. Share with your n8n Google account. Connect Credentials Add credentials for: Decodo API credentials - You need to register, login and obtain the Basic Authentication Token via Decodo Dashboard OpenAI API (for GPT-4o-mini) Google Sheets OAuth2 Configure Input Fields Edit the “Set Input Fields” node to set your target site and region. Run the Workflow Click Execute Workflow in n8n. View structured results in your connected Google Sheet. How to customize this workflow Track Multiple Competitors → Use a Google Sheet or CSV list of URLs; loop through them using the Split In Batches node. Add Language Detection → Add a Gemini or GPT node before keyword analysis to detect content language and adjust prompts. Enhance the SEO Report → Expand the GPT prompt to include backlink insights, metadata optimization, or readability checks. Integrate Visualization → Connect your Google Sheet to Looker Studio for SEO performance dashboards. Schedule Auto-Runs → Use the Cron Node to run weekly or monthly for competitor keyword refreshes. Summary This workflow automates competitor keyword research using: Decodo for intelligent web scraping OpenAI GPT-4.1-mini for keyword and SEO analysis Google Sheets for live tracking and reporting It’s a complete AI-powered SEO intelligence pipeline ideal for teams that want actionable insights on keyword gaps, optimization opportunities, and content focus trends, without relying on expensive SEO SaaS tools.

Ranjan DailataBy Ranjan Dailata
161

Generate song lyrics and music from text prompts using OpenAI and Fal.ai Minimax

Spark your creativity instantly in any chat—turn a simple prompt like "heartbreak ballad" into original, full-length lyrics and a professional AI-generated music track, all without leaving your conversation. 📋 What This Template Does This chat-triggered workflow harnesses AI to generate detailed, genre-matched song lyrics (at least 600 characters) from user messages, then queues them for music synthesis via Fal.ai's minimax-music model. It polls asynchronously until the track is ready, delivering lyrics and audio URL back in chat. Crafts original, structured lyrics with verses, choruses, and bridges using OpenAI Submits to Fal.ai for melody, instrumentation, and vocals aligned to the style Handles long-running generations with smart looping and status checks Returns complete song package (lyrics + audio link) for seamless sharing 🔧 Prerequisites n8n account (self-hosted or cloud with chat integration enabled) OpenAI account with API access for GPT models Fal.ai account for AI music generation 🔑 Required Credentials OpenAI API Setup Go to platform.openai.com → API keys (sidebar) Click "Create new secret key" → Name it (e.g., "n8n Songwriter") Copy the key and add to n8n as "OpenAI API" credential type Test by sending a simple chat completion request Fal.ai HTTP Header Auth Setup Sign up at fal.ai → Dashboard → API Keys Generate a new API key → Copy it In n8n, create "HTTP Header Auth" credential: Name="Fal.ai", Header Name="Authorization", Header Value="Key [Your API Key]" Test with a simple GET to their queue endpoint (e.g., /status) ⚙️ Configuration Steps Import the workflow JSON into your n8n instance Assign OpenAI API credentials to the "OpenAI Chat Model" node Assign Fal.ai HTTP Header Auth to the "Generate Music Track", "Check Generation Status", and "Fetch Final Result" nodes Activate the workflow—chat trigger will appear in your n8n chat interface Test by messaging: "Create an upbeat pop song about road trips" 🎯 Use Cases Content Creators: YouTubers generating custom jingles for videos on the fly, streamlining production from idea to audio export Educators: Music teachers using chat prompts to create era-specific folk tunes for classroom discussions, fostering interactive learning Gift Personalization: Friends crafting anniversary R&B tracks from shared memories via quick chats, delivering emotional audio surprises Artist Brainstorming: Songwriters prototyping hip-hop beats in real-time during sessions, accelerating collaboration and iteration ⚠️ Troubleshooting Invalid JSON from AI Agent: Ensure the system prompt stresses valid JSON; test the agent standalone with a sample query Music Generation Fails (401/403): Verify Fal.ai API key has minimax-music access; check usage quotas in dashboard Status Polling Loops Indefinitely: Bump wait time to 45-60s for complex tracks; inspect fal.ai queue logs for bottlenecks Lyrics Under 600 Characters: Tweak agent prompt to enforce fuller structures like [V1][C][V2][B][C]; verify output length in executions

Daniel NkenchoBy Daniel Nkencho
601

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 🔗 LinkedIn – Wessel Bulte

Wessel BulteBy Wessel Bulte
247