Best n8n Recursive Character Text Splitter Node & Integration: Workflows & Templates

Documentation Expert Chatbot with RAG and Gemini

Build a custom RAG chatbot using an n8n workflow, Gemini, and Supabase. Index n8n documentation to create an AI expert that answers questions about any n8n node or feature accurately.

Automated Book Summarization with DeepSeek AI, Qdrant Vector DB & Google Drive

Automate RAG pipelines using n8n to summarize long documents uploaded to Google Drive. This n8n workflow uses DeepSeek, Cohere embeddings, and Qdrant storage.

AI Travel Planning Agent with Gemini and MongoDB Atlas

Build a robust, knowledge-enhanced AI travel assistant using this powerful n8n workflow template. Leverage the Gemini LLM, MongoDB Atlas Vector Search for RAG, and persistent conversation memory.

Documentation Expert Chatbot with RAG and Gemini

Build a custom RAG chatbot using an n8n workflow, Gemini, and Supabase. Index n8n documentation to create an AI expert that answers questions about any n8n node or feature accurately.

AI Omnichannel Restaurant Assistant (WhatsApp, Instagram, Messenger)

Automate your restaurant's customer service across WhatsApp, Instagram, and Messenger using this robust n8n workflow. Integrates LangChain AI, OpenAI, Supabase, and handles RAG, payments, and lead management.

YouTube Transcript Processing and Pinecone Vector Upsert for RAG

Use this powerful n8n workflow to automatically scrape YouTube transcripts via Apify, process the text, and upsert the data into Pinecone using OpenAI embeddings for RAG applications.

Google Drive to PGVector Knowledge Base Builder

Automate loading files (PDF, JSON, text) from Google Drive into a PGVector database using n8n. This powerful n8n workflow creates a RAG knowledge base using OpenAI embeddings.

Multi-Channel AI Pet Shop Assistant with GPT-4o, Supabase & Payment Integration

A robust n8n workflow for a Pet Shop AI assistant automating multi-channel customer service (WhatsApp, Instagram, Facebook), lead management, payment processing, delivery calculation, and RAG knowledge base updates using GPT-4o.

Youtube Video RAG Search Engine with Qdrant and AI

Build a powerful RAG search engine using this n8n workflow. Scrape YouTube transcripts with Apify, vectorise with OpenAI, and search Qdrant for precise, timestamped results, served via an n8n hosted frontend.

Voice AI Chatbot with Document Retrieval and Guardrails for WordPress

Deploy a powerful Voice AI Chatbot using this n8n workflow. Integrates OpenAI STT/TTS, Qdrant RAG, and guardrails for safe, context-aware, real-time voice responses on your WordPress site.

AI Travel Planning Agent with Gemini and MongoDB Atlas

Build a robust, knowledge-enhanced AI travel assistant using this powerful n8n workflow template. Leverage the Gemini LLM, MongoDB Atlas Vector Search for RAG, and persistent conversation memory.

Documentation Expert Chatbot with RAG and Gemini

Build a custom RAG chatbot using an n8n workflow, Gemini, and Supabase. Index n8n documentation to create an AI expert that answers questions about any n8n node or feature accurately.

AI Travel Planning Agent with RAG and Couchbase Vector Search

Deploy a cutting-edge RAG travel planning solution using this advanced n8n workflow. It integrates Google Gemini, OpenAI embeddings, and Couchbase vector search for highly accurate trip advice.

RAG Chatbot for PDF Documents via Telegram

Use this comprehensive n8n workflow to create a Retrieval-Augmented Generation (RAG) chatbot on Telegram. Index PDFs into Pinecone and answer queries using Groq LLMs.

Advanced RAG Pipeline: Document Ingestion, Structured Extraction, and Knowledge Base Sync

Use this advanced n8n workflow to monitor Google Drive, extract structured data using AI Agents (Azure OpenAI), update Google Sheets, and build a Pinecone vector knowledge base.

Glassdoor Data Extraction and Gemini AI Summarization

Automate Glassdoor company data scraping using Bright Data and summarize key findings instantly with the Google Gemini LLM. Deploy this advanced n8n workflow.

AI Assistant with RAG, Google Sheets Context, and Pinecone Memory

Deploy a powerful n8n workflow for an AI chat assistant using Pinecone RAG and Google Sheets logging. This n8n template features auto-indexing, weekly reports, and GPT-5 integration.

Search & Summarize Web Data using Bright Data, Perplexity, and Gemini

Automate deep web searches and content summarization using this powerful n8n workflow. Integrate Bright Data, Perplexity, and Gemini AI for efficient, asynchronous data processing and reporting.

Semantic Caching for LLMs using Redis and HuggingFace

Reduce large language model costs and improve latency using this advanced n8n workflow. It implements a semantic cache with Redis and HuggingFace embeddings.

Recipe Recommendation Engine with Mistral AI and Qdrant

Build a sophisticated AI recipe recommendation engine using this advanced n8n workflow. Scrape menu data, generate embeddings with Mistral, store in Qdrant, and use an n8n AI Agent for dynamic, personalized suggestions.

Context-Aware RAG Indexing from Google Drive to Pinecone

Use this advanced n8n workflow to automate RAG data preparation. It pulls documents from Google Drive, uses an AI agent (via OpenRouter/Gemini) for context-aware chunking, and indexes the enriched vectors in Pinecone. Leverage powerful n8n templates for superior vector search.

RAG Chatbot for Multi-Format Documents (PDF, CSV, JSON)

Use this powerful n8n workflow to create a conversational AI agent capable of reading and answering questions based on complex multi-format file uploads (PDF, CSV, images, JSON). Leverage OpenAI and Gemini for advanced RAG capabilities.

Business Data Query Agent with RAG and Text-to-SQL

Deploy an advanced AI assistant using this n8n workflow. It combines Retrieval-Augmented Generation (RAG) via Supabase and Text-to-SQL via Peliqan to query internal documents and quantitative business data effectively. This n8n template accelerates BI.

Document Ingestion, RAG Chatbot, and Qdrant Vector Storage

Use this comprehensive n8n workflow to automate document processing. It integrates Google Drive or a file upload form with OpenAI embeddings and Qdrant, forming a powerful RAG knowledge base queryable via a Gemini-powered chatbot. This n8n template enhances document searchability.

Personalized AI Tech Newsletter Generator

Generate a custom, weekly tech newsletter using an n8n workflow. This automation utilizes OpenAI, RSS feeds, and vector storage to deliver personalized summaries to your Gmail.

Personal Portfolio CV RAG Chatbot with Conversation History and Email Reporting

Build a powerful RAG chatbot for your resume or portfolio using an n8n workflow, Pinecone, Google Gemini, and NocoDB. This n8n templates includes conversation history logging and daily Gmail summary reports.

Automated RAG Chatbot Setup with Google Drive and Gemini

Implement a powerful RAG chatbot using this comprehensive n8n workflow. Automatically ingest Google Drive files, embed content using Gemini, store in Pinecone, and answer queries via an AI Agent.

HR & IT Helpdesk Chatbot with RAG and Audio Transcription

Build a comprehensive internal HR/IT helpdesk chatbot using an n8n workflow. This solution integrates RAG, PostgreSQL vector storage, and OpenAI for policy knowledge lookup and voice message transcription.

Generate YouTube Video Summaries from Transcripts

Automate YouTube video summarization using this powerful n8n workflow. Fetches transcripts via SearchAPI, processes text, and generates summaries using an LLM integration (OpenRouter). Discover new n8n templates.

AI Powered SEO Blog Content Generator using Gemini and Pinecone RAG

A robust n8n workflow for generating SEO-optimized blog content. It scrapes web data, analyzes SERP using Scrapeless, and leverages a Pinecone RAG knowledge base via n8n templates.

Automated AI Quiz Video Generation for YouTube Shorts

Generate engaging YouTube Shorts automatically using an n8n workflow leveraging Anthropic AI, Pinecone memory, Creatomate rendering, and Google Sheets for tracking. This n8n template streamlines content creation.