Integrate LangChain Question and Answer Chain in your LLM apps and 422+ apps and services

What this template does This template serves as a Chatbot that enables you to ask questions about the content of a PDF directly in Telegream. It checks incoming Telegram messages if they contain a document. If they do, it stores the PDF in a Pinecone Vector store. If there's no document, it will search the Vector Store for information and try to answer your question. Setup Open the Telegram app and search for the BotFather user (@BotFather) Start a chat with the BotFather Type /newbot to create a new bot Follow the prompts to name your bot and get a unique API token Save your access token and username Once you set your bot, you can send the pdf, and then ask questions about the content. How to adjust it to your needs You can exchange the Groq chat model with any model that you like Exchange Pinecone with any other vector store tool you like (e.g. Supabase, Postgres or QDrant) #Telegram, #Pinecone, #Openai, #GroQ

This is a demo workflow to showcase how to use Supabase to embed a document, retrieve information from the vector store via chat and update the database. Setup steps: set your credentials for Supabase set your credentials for an AI model of your choice set credentials for any service you want to use to upload documents please follow the guidelines in the workflow itself (Sticky Notes) Feedback & Questions If you have any questions or feedback about this workflow - Feel free to get in touch at ria@n8n.io

Purpose This workflow adds the capability to build a RAG on living data. In this case Notion is used as a Knowledge Base. Whenever a page is updated, the embeddings get upserted in a Supabase Vector Store. It can also be fairly easily adapted to PGVector, Pinecone, or Qdrant by using a custom HTTP request for the latter two. Demo How it works A trigger checks every minute for changes in the Notion Database. The manual polling approach improves accuracy and prevents changes from being lost between cached polling intervals. Afterwards every updated page is processed sequentially The Vector Database is searched using the Notion Page ID stored in the metadata of each embedding. If old entries exist, they are deleted. All blocks of the Notion Database Page are retrieved and combined into a single string The content is embedded and split into chunks if necessary. Metadata, including the Notion Page ID, is added during storage for future reference. A simple Question and Answer Chain enables users to ask questions about the embedded content through the integrated chat function Prerequisites To setup a new Vector Store in Supabase, follow this guide Prepare a simple Database in Notion with each Database Page containing at least a title and some content in the blocks section. You can of course also connect this to an existing Database of your choice. Setup Select your credentials in the nodes which require those If you are on an n8n cloud plan, switch to the native Notion Trigger by activating it and deactivating the Schedule Trigger along with its subsequent Notion Node Choose your Notion Database in the first Node related to Notion Adjust the chunk size and overlap in the Token Splitter to your preference Activate the workflow How to use Populate your Notion Database with useful information and use the chat mode of this workflow to ask questions about it. Updates to a Notion Page should quickly reflect in future conversations.

Check Online Version ! [https://n8n-tools.streamlit.app/](https://n8n-tools.streamlit.app/ ) Who is it for? This workflow is perfect for n8n users who want to maintain clean and organized workflows without manually repositioning nodes. Whether you're building complex workflows or sharing them with a team, maintaining visual clarity is essential for efficiency and collaboration. This template automates the positioning process, saving time and ensuring consistent layout standards. How does it work? The template is divided into two parts: Positioning Engine: A webhook node kicks off the process by receiving a workflow ID. Using the provided workflow ID, an n8n API node fetches the workflow details. The fetched workflow is sent to a processing webhook that calculates optimized positions for the nodes. Finally, an n8n API node updates the workflow with the newly positioned nodes, ensuring a clean and professional layout. Reusable Positioning Block: This is an HTTP Request node that can be seamlessly integrated into any workflow you create. When triggered, it sends the current workflow for automatic positioning via the first part of this template. How to set it up? Enable n8n API Access: Ensure that your n8n instance has API access enabled with the appropriate credentials. Input Your n8n API URL and Credentials: Open the template, locate the n8n API nodes, and update them with your instance API key. Update the URL of the 'Magic Positioning' Http Request node to point to your n8n instance webhook URL. Embed the Reusable Block: Add the provided HTTP Request node to any of your workflows to instantly connect to the auto-positioning engine.

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 Webhook Handler: Receives and validates incoming requests from Bitrix24 Credential Manager: Securely manages authentication tokens and API keys Event Router: Directs events to appropriate processing functions Document Processor: Handles document loading, chunking, and embedding Vector Store: Qdrant database for storing and retrieving document embeddings Retrieval System: Searches for relevant document chunks based on user queries LLM Integration: Google Gemini model for generating natural language responses 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 Initial Setup Import the workflow into your n8n instance Configure credentials for all services Set up webhook endpoints Bitrix24 Configuration Create a new Bitrix24 application Configure webhook URLs Set appropriate permissions Install the application to your Bitrix24 account 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 Bot Configuration Customize bot name, avatar, and description Configure welcome messages and menu options Set up fallback responses Testing Verify successful installation Test document processing pipeline Send test queries to evaluate response qu