HumationHuman + Automation
Back to Catalog

Bitrix24 AI-Powered RAG Chatbot for Open Line Channels

Ferenc ErbFerenc Erb
6490 views
2/3/2026
AirtableCustomer ManagementSynchronizationShopifyCRM
Official Page

Overview

Transform your Bitrix24 Open Line channels with an intelligent chatbot that leverages Retrieval-Augmented Generation (RAG) technology to provide accurate, document-based responses to customer inquiries in real-time.

Use Case

This workflow is designed for organizations that want to enhance their customer support capabilities in Bitrix24 by providing automated, knowledge-based responses to customer inquiries. It's particularly useful for:

  • Customer service teams handling repetitive questions
  • Support departments with extensive documentation
  • Sales teams needing quick access to product information
  • Organizations looking to provide 24/7 customer support

What This Workflow Does

Smart Document Processing

  • Automatically processes uploaded PDF documents
  • Splits documents into manageable chunks
  • Generates vector embeddings for semantic understanding
  • Indexes content for efficient retrieval

AI-Powered Responses

  • Utilizes Google Gemini AI to generate natural language responses
  • Constructs answers based on relevant document content
  • Maintains conversation context for coherent interactions
  • Provides fallback responses when information is not available

Vector Database Integration

  • Stores document embeddings in Qdrant vector database
  • Enables semantic search beyond simple keyword matching
  • Retrieves the most relevant information for each query
  • Maintains a persistent knowledge base that grows over time

Webhook Handler

  • Processes incoming messages from Bitrix24 Open Line channels
  • Handles authentication and security validation
  • Routes different types of events to appropriate handlers
  • Manages session and conversation state

Event Routing

  • Intelligently routes different event types:
    • ONIMBOTMESSAGEADD: Processes new user messages
    • ONIMBOTJOINCHAT: Handles bot joining a conversation
    • ONAPPINSTALL: Manages application installation
    • ONIMBOTDELETE: Handles bot deletion

Document Management

  • Organizes processed documents in designated folders
  • Tracks document processing status
  • Moves indexed documents to appropriate locations
  • Maintains document metadata for reference

Interactive Menu

  • Provides menu-based options for common user requests
  • Customizable menu items and responses
  • Easy navigation for users seeking specific information
  • Fallback to operator option when needed

Technical Architecture

Components

  1. Webhook Handler: Receives and validates incoming requests from Bitrix24
  2. Credential Manager: Securely manages authentication tokens and API keys
  3. Event Router: Directs events to appropriate processing functions
  4. Document Processor: Handles document loading, chunking, and embedding
  5. Vector Store: Qdrant database for storing and retrieving document embeddings
  6. Retrieval System: Searches for relevant document chunks based on user queries
  7. LLM Integration: Google Gemini model for generating natural language responses
  8. Response Manager: Formats and sends responses back to Bitrix24

Integration Points

  • Bitrix24 API: For bot registration, message handling, and user interaction
  • Ollama API: For generating document embeddings
  • Qdrant API: For vector storage and retrieval
  • Google Gemini API: For AI-powered response generation

Setup Instructions

Prerequisites

  • Active Bitrix24 account with Open Line channels enabled
  • Access to n8n workflow system
  • Ollama API credentials
  • Qdrant vector database access
  • Google Gemini API key

Configuration Steps

  1. Initial Setup

    • Import the workflow into your n8n instance
    • Configure credentials for all services
    • Set up webhook endpoints

  2. Bitrix24 Configuration

    • Create a new Bitrix24 application
    • Configure webhook URLs
    • Set appropriate permissions
    • Install the application to your Bitrix24 account

  3. Document Storage

    • Create a designated folder in Bitrix24 for knowledge base documents
    • Configure folder paths in the workflow settings
    • Upload initial documents to be processed

  4. Bot Configuration

    • Customize bot name, avatar, and description
    • Configure welcome messages and menu options
    • Set up fallback responses

  5. Testing

    • Verify successful installation
    • Test document processing pipeline
    • Send test queries to evaluate response qu

n8n Workflow: AI-Powered RAG Chatbot for Open Line Channels

This n8n workflow provides a robust, AI-powered Retrieval Augmented Generation (RAG) chatbot solution designed to integrate with open line channels. It leverages large language models (LLMs) and vector databases to deliver intelligent, context-aware responses, enhancing customer support or information retrieval in real-time.

What it does

This workflow orchestrates several key steps to provide an AI-powered RAG chatbot:

  1. Receives Incoming Messages: It acts as a webhook listener, waiting for new messages or queries from an external "open line channel" (e.g., a messaging platform, a custom chat interface).
  2. Pre-processes Input: The incoming message is processed to extract relevant information and prepare it for the AI model.
  3. Determines Action Type: It evaluates the incoming message to decide if it's a new query requiring a RAG response or a follow-up/status update.
  4. Retrieves Relevant Information:
    • If it's a new query, the workflow takes the user's message and performs a similarity search against a Qdrant vector store. This step retrieves relevant documents or knowledge base articles that might contain the answer.
    • The retrieved documents are then split into manageable chunks using a Recursive Character Text Splitter to optimize for LLM processing.
    • These document chunks are loaded using a Default Data Loader.
  5. Generates AI Response:
    • The user's query and the retrieved context (from the vector store) are fed into a Google Gemini Chat Model.
    • The Google Gemini Chat Model, configured as a Question and Answer Chain, generates a comprehensive and contextually relevant answer.
  6. Handles No-Match Scenarios: If no relevant information is found in the vector store, the workflow can route to a fallback, potentially indicating to the user that it couldn't find an answer or escalating to a human agent.
  7. Responds to the Channel: The generated AI response (or fallback message) is sent back to the originating open line channel via the webhook.
  8. Manages Embeddings: It utilizes an Ollama Embeddings model to convert text into vector embeddings, which are crucial for the vector store's similarity search.

Prerequisites/Requirements

To use this workflow, you will need:

  • n8n Instance: A running n8n instance.
  • Webhook Integration: An external system or "open line channel" capable of sending messages to an n8n webhook.
  • Qdrant Vector Database: Access to a Qdrant instance for storing and retrieving vector embeddings of your knowledge base.
  • Google Gemini API Key: Credentials for the Google Gemini Chat Model to power the RAG responses.
  • Ollama Instance: An Ollama instance (or compatible embedding service) for generating text embeddings.

Setup/Usage

  1. Import the Workflow: Download the provided JSON and import it into your n8n instance.
  2. Configure Webhook:
    • Activate the Webhook node and copy its URL.
    • Configure your "open line channel" to send messages/queries to this webhook URL.
  3. Set up Credentials:
    • Configure your Google Gemini Chat Model credentials in the Google Gemini Chat Model node.
    • Configure your Qdrant Vector Store connection details in the Qdrant Vector Store node.
    • Configure your Ollama Embeddings connection details in the Embeddings Ollama node.
  4. Populate Qdrant: Ensure your Qdrant vector database is populated with the relevant knowledge base documents, converted into embeddings using a compatible embedding model (e.g., Ollama, as configured in this workflow).
  5. Activate Workflow: Once all credentials and configurations are set, activate the workflow.

The workflow will now listen for incoming messages, process them using the RAG pipeline, and send back AI-generated responses.

Related Templates

Auto-create TikTok videos with VEED.io AI avatars, ElevenLabs & GPT-4

💥 Viral TikTok Video Machine: Auto-Create Videos with Your AI Avatar --- 🎯 Who is this for? This workflow is for content creators, marketers, and agencies who want to use Veed.io’s AI avatar technology to produce short, engaging TikTok videos automatically. It’s ideal for creators who want to appear on camera without recording themselves, and for teams managing multiple brands who need to generate videos at scale. --- ⚙️ What problem this workflow solves Manually creating videos for TikTok can take hours — finding trends, writing scripts, recording, and editing. By combining Veed.io, ElevenLabs, and GPT-4, this workflow transforms a simple Telegram input into a ready-to-post TikTok video featuring your AI avatar powered by Veed.io — speaking naturally with your cloned voice. --- 🚀 What this workflow does This automation links Veed.io’s video-generation API with multiple AI tools: Analyzes TikTok trends via Perplexity AI Writes a 10-second viral script using GPT-4 Generates your voiceover via ElevenLabs Uses Veed.io (Fabric 1.0 via FAL.ai) to animate your avatar and sync the lips to the voice Creates an engaging caption + hashtags for TikTok virality Publishes the video automatically via Blotato TikTok API Logs all results to Google Sheets for tracking --- 🧩 Setup Telegram Bot Create your bot via @BotFather Configure it as the trigger for sending your photo and theme Connect Veed.io Create an account on Veed.io Get your FAL.ai API key (Veed Fabric 1.0 model) Use HTTPS image/audio URLs compatible with Veed Fabric Other APIs Add Perplexity, ElevenLabs, and Blotato TikTok keys Connect your Google Sheet for logging results --- 🛠️ How to customize this workflow Change your Avatar: Upload a new image through Telegram, and Veed.io will generate a new talking version automatically. Modify the Script Style: Adjust the GPT prompt for tone (educational, funny, storytelling). Adjust Voice Tone: Tweak ElevenLabs stability and similarity settings. Expand Platforms: Add Instagram, YouTube Shorts, or X (Twitter) posting nodes. Track Performance: Customize your Google Sheet to measure your most successful Veed.io-based videos. --- 🧠 Expected Outcome In just a few seconds after sending your photo and theme, this workflow — powered by Veed.io — creates a fully automated TikTok video featuring your AI avatar with natural lip-sync and voice. The result is a continuous stream of viral short videos, made without cameras, editing, or effort. --- ✅ Import the JSON file in n8n, add your API keys (including Veed.io via FAL.ai), and start generating viral TikTok videos starring your AI avatar today! 🎥 Watch This Tutorial --- 📄 Documentation: Notion Guide Need help customizing? Contact me for consulting and support : Linkedin / Youtube

Dr. FirasBy Dr. Firas
39510

Two-way property repair management system with Google Sheets & Drive

This workflow automates the repair request process between tenants and building managers, keeping all updates organized in a single spreadsheet. It is composed of two coordinated workflows, as two separate triggers are required — one for new repair submissions and another for repair updates. A Unique Unit ID that corresponds to individual units is attributed to each request, and timestamps are used to coordinate repair updates with specific requests. General use cases include: Property managers who manage multiple buildings or units. Building owners looking to centralize tenant repair communication. Automation builders who want to learn multi-trigger workflow design in n8n. --- ⚙️ How It Works Workflow 1 – New Repair Requests Behind the Scenes: A tenant fills out a Google Form (“Repair Request Form”), which automatically adds a new row to a linked Google Sheet. Steps: Trigger: Google Sheets rowAdded – runs when a new form entry appears. Extract & Format: Collects all relevant form data (address, unit, urgency, contacts). Generate Unit ID: Creates a standardized identifier (e.g., BUILDING-UNIT) for tracking. Email Notification: Sends the building manager a formatted email summarizing the repair details and including a link to a Repair Update Form (which activates Workflow 2). --- Workflow 2 – Repair Updates Behind the Scenes:\ Triggered when the building manager submits a follow-up form (“Repair Update Form”). Steps: Lookup by UUID: Uses the Unit ID from Workflow 1 to find the existing row in the Google Sheet. Conditional Logic: If photos are uploaded: Saves each image to a Google Drive folder, renames files consistently, and adds URLs to the sheet. If no photos: Skips the upload step and processes textual updates only. Merge & Update: Combines new data with existing repair info in the same spreadsheet row — enabling a full repair history in one place. --- 🧩 Requirements Google Account (for Forms, Sheets, and Drive) Gmail/email node connected for sending notifications n8n credentials configured for Google API access --- ⚡ Setup Instructions (see more detail in workflow) Import both workflows into n8n, then copy one into a second workflow. Change manual trigger in workflow 2 to a n8n Form node. Connect Google credentials to all nodes. Update spreadsheet and folder IDs in the corresponding nodes. Customize email text, sender name, and form links for your organization. Test each workflow with a sample repair request and a repair update submission. --- 🛠️ Customization Ideas Add Slack or Telegram notifications for urgent repairs. Auto-create folders per building or unit for photo uploads. Generate monthly repair summaries using Google Sheets triggers. Add an AI node to create summaries/extract relevant repair data from repair request that include long submissions.

Matt@VeraisonLabsBy Matt@VeraisonLabs
208

Automate invoice processing with OCR, GPT-4 & Salesforce opportunity creation

PDF Invoice Extractor (AI) End-to-end pipeline: Watch Drive ➜ Download PDF ➜ OCR text ➜ AI normalize to JSON ➜ Upsert Buyer (Account) ➜ Create Opportunity ➜ Map Products ➜ Create OLI via Composite API ➜ Archive to OneDrive. --- Node by node (what it does & key setup) 1) Google Drive Trigger Purpose: Fire when a new file appears in a specific Google Drive folder. Key settings: Event: fileCreated Folder ID: google drive folder id Polling: everyMinute Creds: googleDriveOAuth2Api Output: Metadata { id, name, ... } for the new file. --- 2) Download File From Google Purpose: Get the file binary for processing and archiving. Key settings: Operation: download File ID: ={{ $json.id }} Creds: googleDriveOAuth2Api Output: Binary (default key: data) and original metadata. --- 3) Extract from File Purpose: Extract text from PDF (OCR as needed) for AI parsing. Key settings: Operation: pdf OCR: enable for scanned PDFs (in options) Output: JSON with OCR text at {{ $json.text }}. --- 4) Message a model (AI JSON Extractor) Purpose: Convert OCR text into strict normalized JSON array (invoice schema). Key settings: Node: @n8n/n8n-nodes-langchain.openAi Model: gpt-4.1 (or gpt-4.1-mini) Message role: system (the strict prompt; references {{ $json.text }}) jsonOutput: true Creds: openAiApi Output (per item): $.message.content → the parsed JSON (ensure it’s an array). --- 5) Create or update an account (Salesforce) Purpose: Upsert Buyer as Account using an external ID. Key settings: Resource: account Operation: upsert External Id Field: taxid_c External Id Value: ={{ $json.message.content.buyer.tax_id }} Name: ={{ $json.message.content.buyer.name }} Creds: salesforceOAuth2Api Output: Account record (captures Id) for downstream Opportunity. --- 6) Create an opportunity (Salesforce) Purpose: Create Opportunity linked to the Buyer (Account). Key settings: Resource: opportunity Name: ={{ $('Message a model').item.json.message.content.invoice.code }} Close Date: ={{ $('Message a model').item.json.message.content.invoice.issue_date }} Stage: Closed Won Amount: ={{ $('Message a model').item.json.message.content.summary.grand_total }} AccountId: ={{ $json.id }} (from Upsert Account output) Creds: salesforceOAuth2Api Output: Opportunity Id for OLI creation. --- 7) Build SOQL (Code / JS) Purpose: Collect unique product codes from AI JSON and build a SOQL query for PricebookEntry by Pricebook2Id. Key settings: pricebook2Id (hardcoded in script): e.g., 01sxxxxxxxxxxxxxxx Source lines: $('Message a model').first().json.message.content.products Output: { soql, codes } --- 8) Query PricebookEntries (Salesforce) Purpose: Fetch PricebookEntry.Id for each Product2.ProductCode. Key settings: Resource: search Query: ={{ $json.soql }} Creds: salesforceOAuth2Api Output: Items with Id, Product2.ProductCode (used for mapping). --- 9) Code in JavaScript (Build OLI payloads) Purpose: Join lines with PBE results and Opportunity Id ➜ build OpportunityLineItem payloads. Inputs: OpportunityId: ={{ $('Create an opportunity').first().json.id }} Lines: ={{ $('Message a model').first().json.message.content.products }} PBE rows: from previous node items Output: { body: { allOrNone:false, records:[{ OpportunityLineItem... }] } } Notes: Converts discount_total ➜ per-unit if needed (currently commented for standard pricing). Throws on missing PBE mapping or empty lines. --- 10) Create Opportunity Line Items (HTTP Request) Purpose: Bulk create OLIs via Salesforce Composite API. Key settings: Method: POST URL: https://<your-instance>.my.salesforce.com/services/data/v65.0/composite/sobjects Auth: salesforceOAuth2Api (predefined credential) Body (JSON): ={{ $json.body }} Output: Composite API results (per-record statuses). --- 11) Update File to One Drive Purpose: Archive the original PDF in OneDrive. Key settings: Operation: upload File Name: ={{ $json.name }} Parent Folder ID: onedrive folder id Binary Data: true (from the Download node) Creds: microsoftOneDriveOAuth2Api Output: Uploaded file metadata. --- Data flow (wiring) Google Drive Trigger → Download File From Google Download File From Google → Extract from File → Update File to One Drive Extract from File → Message a model Message a model → Create or update an account Create or update an account → Create an opportunity Create an opportunity → Build SOQL Build SOQL → Query PricebookEntries Query PricebookEntries → Code in JavaScript Code in JavaScript → Create Opportunity Line Items --- Quick setup checklist 🔐 Credentials: Connect Google Drive, OneDrive, Salesforce, OpenAI. 📂 IDs: Drive Folder ID (watch) OneDrive Parent Folder ID (archive) Salesforce Pricebook2Id (in the JS SOQL builder) 🧠 AI Prompt: Use the strict system prompt; jsonOutput = true. 🧾 Field mappings: Buyer tax id/name → Account upsert fields Invoice code/date/amount → Opportunity fields Product name must equal your Product2.ProductCode in SF. ✅ Test: Drop a sample PDF → verify: AI returns array JSON only Account/Opportunity created OLI records created PDF archived to OneDrive --- Notes & best practices If PDFs are scans, enable OCR in Extract from File. If AI returns non-JSON, keep “Return only a JSON array” as the last line of the prompt and keep jsonOutput enabled. Consider adding validation on parsing.warnings to gate Salesforce writes. For discounts/taxes in OLI: Standard OLI fields don’t support per-line discount amounts directly; model them in UnitPrice or custom fields. Replace the Composite API URL with your org’s domain or use the Salesforce node’s Bulk Upsert for simplicity.

Le NguyenBy Le Nguyen
942