Integrate Window Buffer Memory (easiest) in your LLM apps and 422+ apps and services

How it works: This project creates a personal AI assistant named Angie that operates through Telegram. Angie can summarize daily emails, look up calendar entries, remind users of upcoming tasks, and retrieve contact information. The assistant can interact with users via both voice and text inputs. Step-by-step: Telegram Trigger: The workflow starts with a Telegram trigger that listens for incoming message events. The system determines if the incoming message is voice or text. If voice, the voice file is retrieved and transcribed to text using OpenAI's API Speech to Text AI Assistant: The telegram request is passed to the AI assistant (Angie). Tools Integration: The AI assistant is equipped with several tools: Get Email: Uses Gmail API to fetch recent emails, filtering by date. Get Calendar: Retrieves calendar entries for specified dates. Get Tasks: Connects to a Baserow (open-source Airtable alternative) database to fetch to-do list items. Get Contacts: Also uses Baserow to retrieve contact information. Response Generation: The AI formulates a response based on the gathered information and sends back to the user on Telegram

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.

This n8n workflow demonstrates a simple approach to improve chat UX by staggering an AI Agent's reply for users who send in a sequence of partial messages and in short bursts. How it works Twilio webhook receives user's messages which are recorded in a message stack powered by Redis. The execution is immediately paused for 5 seconds and then another check is done against the message stack for the latest message. The purpose of this check lets use know if the user is sending more messages or if they are waiting for a reply. The execution is aborted if the latest message on the stack differs from the incoming message and continues if they are the same. For the latter, the agent receives the buffered messages up to that point and is able to respond to them in a single reply. Requirements A Twilio account and SMS-enabled phone number to receive messages. Redis instance for the messages stack. OpenAI account for the language model. Customising the workflow This workflow should work for other common messaging platforms such as Whatsapp and Telegram. 5 seconds too long or too short? Adjust the wait threshold to suit your customers.

This n8n workflow is a fun way to query and search over your credentials on your n8n instance. Good to know Your credentials should remain safe as this workflow does not decrypt or use any decrypted data. Example Usage "Which workflows are using Slack and Google Calendar?" "Which workflows have AI in their name but are not using openAI?" How it works Using the n8n API, it fetches all workflow data on the instance. Workflow data contains references to credentials used so this will be extracted. With some necessary reformatting, the workflows and their credentials metadata are stored to a SQLite database. Next, an AI agent is used with a custom SQL tool that reads the SQLite database created in the previous step. The AI agent is instructed to perform SQL queries against our workflow credential table when asked about credentials by the user. Requirements You'll need an n8n API key. Please note that only workflows will be scoped to your API key. Customising the workflow Add extra table fields to the SQLite database to answer even more complex queries such as: workflow status to differentiate between active and inactive workflows.

Who is this for This workflow is perfect for teams and individuals who manage extensive data in Notion and need a quick, AI-powered way to interact with their databases. If you're looking to streamline your knowledge management, automate searches, and get faster insights from your Notion databases, this workflow is for you. It’s ideal for support teams, project managers, or anyone who needs to query specific data across multiple records or within individual pages of their Notion setup. Check out the Notion template this Assistant is set up to use: https://www.notion.so/templates/knowledge-base-ai-assistant-with-n8n How it works The Notion Database Assistant uses an AI Agent built with Retrieval-Augmented Generation (RAG) to query this Knowledge Base style Notion database. The assistant can search across multiple properties like tags or question and retrieves content from inside individual Notion pages for additional context. Key features include: Querying the database with flexible filters. Searching within individual Notion pages and extracting relevant blocks. Providing a reference link to the exact Notion pages used to inform its responses, ensuring transparency and easy verification. This assistant uses two HTTP request tools—one for querying the Notion database and another for pulling data from within specific pages. It streamlines knowledge retrieval, offering a conversational, AI-driven way to interact with large datasets. Set up Find basic set up instructions inside the workflow itself or watch a quickstart video 👇

Are you a popular tech startup accelerator (named after a particular higher order function) overwhelmed with 1000s of pitch decks on a daily basis? Wish you could filter through them quickly using AI but the decks are unparseable through conventional means? Then you're in luck! This n8n template uses Multimodal LLMs to parse and extract valuable data from even the most overly designed pitch decks in quick fashion. Not only that, it'll also create the foundations of a RAG chatbot at the end so you or your colleagues can drill down into the details if needed. With this template, you'll scale your capacity to find interesting companies you'd otherwise miss! Requires n8n v1.62.1+ How It Works Airtable is used as the pitch deck database and PDF decks are downloaded from it. An AI Vision model is used to transcribe each page of the pitch deck into markdown. An Information Extractor is used to generate a report from the transcribed markdown and update required information back into pitch deck database. The transcribed markdown is also uploaded to a vector store to build an AI chatbot which can be used to ask questions on the pitch deck. Check out the sample Airtable here: https://airtable.com/appCkqc2jc3MoVqDO/shrS21vGqlnqzzNUc How To Use This template depends on the availability of the Airtable - make a duplicate of the airtable (link) and its columns before running the workflow. When a new pitchdeck is received, enter the company name into the Name column and upload the pdf into the File column. Leave all other columns blank. If you have the Airtable trigger active, the execution should start immediately once the file is uploaded. Otherwise, click the manual test trigger to start the workflow. When manually triggered, all "new" pitch decks will be handled by the workflow as separate executions. Requirements OpenAI for LLM Airtable For Database and Interface Qdrant for Vector Store Customising This Workflow Extend this starter template by adding more AI agents to validate claims made in the pitch deck eg. Linkedin Profiles, Page visits, Reviews etc.

Who is this for? This workflow is for everyone who wants to have easier access to their Odoo sales data without complex queries. Use Case To have a clear overview of your sales data in Odoo you typically needs to extract data from it manually to analyse it. This workflow uses OpenAI's language models to create an intelligent chatbot that provides conversational access to your Odoo sales opportunity data. How it works Creates a summary of all Odoo sales opportunities using OpenAI Uses that summary as context for the OpenAI chat model Keeps the summary up to date using a schedule trigger Set up steps: Configure the Odoo credentials Configure OpenAI credentials Toggle "Make Chat Publicly Available" from the Chat Trigger node.

This is an example of how we can build a slack bot in a few easy steps Before you can start, you need to o a few things Create a copy of this workflow Create a slack bot Create a slash command on slack and paste the webhook url to the slack command Note Make sure to configure this webhook using a https:// wrapper and don't use the default http://localhost:5678 as that will not be recognized by your slack webhook. Once the data has been sent to your webhook, the next step will be passing it via an AI Agent to process data based on the queries we pass to our agent. To have some sort of a memory, be sure to set the slack token to the memory node. This way you can refer to other chats from the history. The final message is relayed back to slack as a new message. Since we can not wait longer than 3000 ms for slack response, we will create a new message with reference to the input we passed. We can advance this using the tools or data sources for it to be more custom tailored for your company. Usage To use the slackbot, go to slack and click on your set slash command eg /Bob and send your desired message. This will send the message to your endpoint and get return the processed results as the message. If you would like help setting this up, feel free to reach out to [email protected]

This is a workflow that tries to answer user queries using the standard GPT-4 model. If it can't answer, it sends a message to Slack to ask for human help. It prompts the user to supply an email address. This workflow is used in Advanced AI examples | Ask a human in the documentation. To use this workflow: Load it into your n8n instance. Add your credentials as prompted by the notes. Configure the Slack node to use your Slack details, or swap out Slack for a different service.

This workflow connects Telegram bots with LangChain nodes in n8n. The main AI Agent Node is configured as a Conversation Agent. It has a custom System Prompt which explains the reply formatting and provides some additional instructions. The AI Agent has several connections: OpenAI GPT-4 model is called to generate the replies Window Buffer Memory stores the history of conversation with each user separately There is an additional Custom n8n Workflow tool (Dall-E 3 Tool). AI Agent uses this tool when the user requests an image generation. In the lower part of the workflow, there is a series of nodes that call Dall-E 3 model with the user Telegram ID and a prompt for a new image. Once image is ready, it is sent back to the user. Finally, there is an extra Telegram node that masks HTML syntax for improved stability in case the AI Agent replies using the unsupported format.

This n8n workflows builds another example of creating a knowledgebase assistant but demonstrates how a more deliberate and targeted approach to ingesting the data can produce much better results for your chatbot. In this example, a government tax code policy document is used. Whilst we could split the document into chunks by content length, we often lose the context of chapters and sections which may be required by the user. Our approach then is to first split the document into chapters and sections before importing into our vector store. Additionally, using metadata correctly is key to allow filtering and scoped queries. Example Human: "Tell me about what the tax code says about cargo for intentional commerce?" AI: "Section 11.25 of the Texas Property Tax Code pertains to "MARINE CARGO CONTAINERS USED EXCLUSIVELY IN INTERNATIONAL COMMERCE." In this section, a person who is a citizen of a foreign country or an en..." How it works The tax code policy document is downloaded as a zip file from the government website and its pages are extracted as separate chapters. Each chapter is then parsed and split into its sections using data manipulation expressions. Each section is then inserted into our Qdrant vector store tagged with its source, chapter and section numbers as metadata. When our AI Agent needs to retrieve data from our vector store, we use a custom workflow tool to perform the query to Qdrant. Because we're relying on Qdrant's advanced filtering capabilities, we perform the search using the Qdrant API rather than the Qdrant node. When the AI Agent, needs to pull full wording or extracts, we can use Qdrant's scroll API and metadata filtering to do so. This makes Qdrant behave like a key-value store for our document. Requirements A Qdrant instance is required for the vector store and specifically for it's filtering functionality. Mistral.ai account for Embeddings and AI models. Customising this workflow Depending on your use-case, consider returning actual PDF pages (or links) to the user for the extra confirmation and to build trust. Not using Mistral? You are able to replace but note to match the distance and dimension size of Qdrant collection to your chosen embedding model.

This workflow offers an effective way to handle a chatbot's functionality, making use of multiple tools for information retrieval, conversation context storage, and message sending. It's a setup tailored for a Slack environment, aiming to offer an interactive, AI-driven chatbot experience. Note that to use this template, you need to be on n8n version 1.19.4 or later.

This workflow is designed for dynamic and intelligent conversational capabilities. It incorporates OpenAI's GPT-4o model for natural language understanding and generation. Additional tools include SerpAPI and Wikipedia for enriched, data-driven responses. The workflow is triggered manually, and utilizes a 'Window Buffer Memory' to maintain the context of the last 20 interactions for better conversational continuity. All these components are orchestrated through n8n nodes, ensuring seamless interconnectivity. To use this template, you need to be on n8n version 1.50.0 or later.

OpenAI Assistant is a powerful tool, but at the time of writing it doesn't automatically remember past messages from a conversation. This workflow demonstrates how to get around this, by managing the chat history in n8n and passing it to the assistant when required. This makes it possible to use OpenAI Assistant for chatbot use cases. Note that to use this template, you need to be on n8n version 1.28.0 or later.

Create a recommendation tool without hallucinations based on RAG with the Qdrant Vector database. This example is based on movie recommendations on the IMDB-top1000 dataset. You can provide your wishes and your "big no's" to the chatbot, for example: "A movie about wizards but not Harry Potter", and get top-3 recommendations. How it works a video with the full design process Upload IMDB-1000 dataset to Qdrant Vector Store, embedding movie descriptions with OpenAI; Set up an AI agent with a chat. This agent will call a workflow tool to get movie recommendations based on a request written in the chat; Create a workflow which calls Qdrant's Recommendation API to retrieve top-3 recommendations of movies based on your positive and negative examples. Set Up Steps You'll need to create a free tier Qdrant Cluster (Qdrant can also be used locally; it's open-sourced) and set up API credentials You'll OpenAI credentials You'll need GitHub credentials & to upload the IMDB Kaggle dataset to your GitHub.

This workflow was presented at the AI Developers meet up in San Fransico on 24 July, 2024. AI workflows Categorize incoming Gmail emails and assign custom Gmail labels. This example uses the Text Classifier node, simplifying this usecase. Ingest a PDF into a Pinecone vector store and chat with it (RAG example) AI Agent example showcasing the HTTP Request tool. We teach the agent how to check availability on a Google Calendar and book an appointment.

Overview This workflow aims at providing data visualization to a native SQL Agent. Together, they can help with fostering data analysis and data visualization within a team. It uses the native SQL Agent that works well and adds some visualization capabilities thanks to OpenAI Structured Output and Quickchart.io. How it works The first part of the workflow is a regular SQL Agent: it connects to a Database and is able to query it and translate the response in a human format. Then, the Text Classifier is deciding if the user would benefit from a chart, supporting the SQL Agent's response. If it does, then it executes the subworkflow to dynamically generate a chart and append the chart to the response from the SQL Agent. If it doesn't, then the SQL Agent response is directly outputted. The sub-workflow calls OpenAI through the HTTP Request node to retrieve a chart definition. In the "set response" node, the chart definition is added at the end of a quickchart.io URL - the URL to the chart image. It is sent back to the AI Agent. How to use it Use an existing or create a new database. For example, I've used this Kaggle dataset and uploaded it to a Supabase DB. Add the PostgreSQL or MySQL credentials. Alternatively, you can use SQLite binary files (check this template). Activate the workflow. Start chatting with the AI SQL Agent. If the Text Classifier considers a chart would be useful, it will generate a chart in addition to the response from the SQL Agent. Notes The full Quickchart.io specifications have not been integrated, thus there are some possible glitches (e.g., due to the size of the graph, radar graphs are not displayed properly).

Who is this for? This workflow is designed for: Database administrators and developers working with MongoDB Content managers handling movie databases Organizations looking to implement AI-powered search and recommendation systems Developers interested in combining LangChain, OpenAI, and MongoDB capabilities What problem does this workflow solve? Traditional database queries can be complex and require specific MongoDB syntax knowledge. This workflow addresses: The complexity of writing MongoDB aggregation pipelines The need for natural language interaction with movie databases The challenge of maintaining user preferences and favorites The gap between AI language models and database operations What this workflow does This workflow creates an intelligent agent that: Accepts natural language queries about movies Translates user requests into MongoDB aggregation pipelines Queries a movie database containing detailed information including: Plot summaries Genre classifications Cast and director information Runtime and release dates Ratings and awards Provides contextual responses using OpenAI's language model Allows users to save favorite movies to the database Maintains conversation context using a window buffer memory Setup Required Credentials: OpenAI API credentials MongoDB connection details Node Configuration: Configure the MongoDB connection in the MongoDBAggregate node Set up the OpenAI Chat Model with your API key Ensure the webhook trigger is properly configured for receiving chat messages Database Requirements: A MongoDB collection named "movies" with the specified document structure Proper indexes for efficient querying Appropriate user permissions for read/write operations How to customize this workflow Modify the Document Structure: Update the tool description in the MongoDBAggregate node to match your collection schema Adjust the aggregation pipeline templates for your specific use case Enhance the AI Agent: Customize the prompt in the "AI Agent - Movie Recommendation" node Modify the window buffer memory size based on your context needs Add additional tools for more functionality Extend Functionality: Add more MongoDB operations beyond aggregation Implement additional workflows for different types of queries Create custom error handling and validation Add user authentication and rate limiting Integration Options: Connect to external APIs for additional movie data Add webhook endpoints for different platforms Implement caching mechanisms for frequent queries Add data transformation nodes for specific output formats This workflow serves as a foundation that can be adapted to various use cases beyond movie recommendations, such as e-commerce product search, content management systems, or any scenario requiring intelligent database interaction.

This n8n workflow demonstrates how to create an agent using LangChain and SQLite. The agent can understand natural language queries and interact with a SQLite database to provide accurate answers. 💪 🚀 Setup Run the top part of the workflow once. It downloads the example SQLite database, extracts from a ZIP file and saves locally (chinook.db). 🗣️ Chatting with Your Data Send a message in a chat window. Locally saved SQLite database loads automatically. User's chat input is combined with the binary data. The LangChain Agend node gets both data and begins to work. The AI Agent will process the user's message, perform necessary SQL queries, and generate a response based on the database information. 🗄️ 🌟 Example Queries Try these sample queries to see the AI Agent in action: "Please describe the database" - Get a high-level overview of the database structure, only one or two queries are needed. "What are the revenues by genre?" - Retrieve revenue information grouped by genre, LangChain agent iterates several time before producing the answer. The AI Agent will store the final answer in its memory, allowing for context-aware conversations. 💬 Read the full article: 👉 https://blog.n8n.io/ai-agents/

Video Demo: Click here to see a video of this workflow in action. Summary Description: The "IT Department Q&A Workflow" is designed to streamline and automate the process of handling IT-related inquiries from employees through Slack. When an employee sends a direct message (DM) to the IT department's Slack channel, the workflow is triggered. The initial step involves the "Receive DMs" node, which listens for new messages. Upon receiving a message, the workflow verifies the webhook by responding to Slack's challenge request, ensuring that the communication channel is active and secure. Once the webhook is verified, the workflow checks if the message sender is a bot using the "Check if Bot" node. If the sender is identified as a bot, the workflow terminates the process to avoid unnecessary actions. If the sender is a human, the workflow sends an acknowledgment message back to the user, confirming that their query is being processed. This is achieved through the "Send Initial Message" node, which posts a simple message like "On it!" to the user's Slack channel. The core functionality of the workflow is powered by the "AI Agent" node, which utilizes the OpenAI GPT-4 model to interpret and respond to the user's query. This AI-driven node processes the text of the received message, generating an appropriate response based on the context and information available. To maintain conversation context, the "Window Buffer Memory" node stores the last five messages from each user, ensuring that the AI agent can provide coherent and contextually relevant answers. Additionally, the workflow includes a custom Knowledge Base (KB) tool (see that tool template here) that integrates with the AI agent, allowing it to search the company's internal KB for relevant information. After generating the response, the workflow cleans up the initial acknowledgment message using the "Delete Initial Message" node to keep the conversation thread clean. Finally, the generated response is sent back to the user via the "Send Message" node, providing them with the information or assistance they requested. This workflow effectively automates the IT support process, reducing response times and improving efficiency. To quickly deploy the Knowledge Ninja app in Slack, use the app manifest below and don't forget to replace the two sample urls: { "display_information": { "name": "Knowledge Ninja", "description": "IT Department Q&A Workflow", "background_color": "#005e5e" }, "features": { "bot_user": { "display_name": "IT Ops AI SlackBot Workflow", "always_online": true } }, "oauth_config": { "redirect_urls": [ "Replace everything inside the double quotes with your slack redirect oauth url, for example: https://n8n.domain.com/rest/oauth2-credential/callback" ], "scopes": { "user": [ "search:read" ], "bot": [ "chat:write", "chat:write.customize", "groups:history", "groups:read", "groups:write", "groups:write.invites", "groups:write.topic", "im:history", "im:read", "im:write", "mpim:history", "mpim:read", "mpim:write", "mpim:write.topic", "usergroups:read", "usergroups:write", "users:write", "channels:history" ] } }, "settings": { "event_subscriptions": { "request_url": "Replace everything inside the double quotes with your workflow webhook url, for example: https://n8n.domain.com/webhook/99db3e73-57d8-4107-ab02-5b7e713894ad", "bot_events": [ "message.im" ] }, "org_deploy_enabled": false, "socket_mode_enabled": false, "token_rotation_enabled": false } }

Use n8n to bring data from any API to your AI. This workflow uses the Chat Trigger to provide the chat interface, and the Custom n8n Workflow Tool to call a second workflow that calls the API. The second workflow uses AI functionality to refine the API request based on the user's query. It then makes an API call, and returns the response to the main workflow. This workflow is used in Advanced AI examples | Call an API to fetch data in the documentation. To use this workflow: Load it into your n8n instance. Add your credentials as prompted by the notes. Requires n8n 1.28.0 or above

Purpose Use a lightweight Voice Interface, for you and your entire organization, to interact with an AI Supervisor, a personal AI Assistant, which has access to your custom workflows. You can also connect the supervisor to your already existing Agents. Demo & Explanation How it works After recording a message in the Vagent App, it gets transcribed and sent in combination with a session ID to the registered webhook The Main Agent acts as a router. I interprets the message while using the stored chat history (bound to the session ID) and chooses which tool to use to perform the required action and. Tools on this level are workflows, which contain subordinated Agents. Since the Main Agent interprets the original message, the raw input is passed to the Tools/Sub-Agents as a separate parameter Within the Sub-Agents the actual processing takes place. Each of those has it’s separate chat memory (with a suffix to the main session ID), to achieve a clear separation of concerns Depending on the required action an HTTP Request Tool is called. The result is being formatted in Markdown and returned to the Main Agent with an additional short prompt, so it does not get interpreted by the Main Agent. Drafts are separated from a short message by added indentation (angle brackets). If some information is missing, no tool is called just yet, instead a message is returned back to the user The Main Agent then outputs the result from the called Sub-Agent. If a draft is included, it gets separated from the spoken output Finally the formatted output is returned as response to the webhook. The message is split into a spoken and a text version, which enables the App to read out loud unnecessary information like drafts in this example See the full documentation of Vagent: https://vagent.io/docs Setup Import this workflow into your n8n instance Follow the instructions given in the sticky notes on the canvas Setup your credentials. OpenAI can be replaced by another LLM in the workflow, but is required for the App to work. Google Calendar and Notion are required for all scenarios to work Copy the Webhook URL from the Webhook node of the main workflow Download the Vagent App from https://vagent.io In the settings paste your OpenAI API Token, the Webhook URL and the password defined for Header Auth Now you can use the App to interact with the Multi-Agent using your Voice by tapping the Mic symbol in the App to record your message. To use the chat trigger (for testing) properly, temporarily disable the nodes after the Tools Agent.

Who is this for? This workflow is designed for businesses or developers looking to integrate voice-based chat applications with dynamic responses and conversational memory. What problem does this solve? It automates AI-powered voice conversations, maintaining context between sessions and converting speech-to-text and text-to-speech. What this workflow does: The workflow receives audio input, transcribes it using OpenAI, and processes the conversation using Google Gemini Chat Model (you can use OpenAI Chat Model). Responses are converted back to speech using ElevenLabs. Prerequisites: You'll need API keys for: OpenAI (you can obtain it from OpenAI website) ElevenLabs (you can obtain it from their website) Google Gemini (You can obtain it from Google AI Studio) Setup: Configure you API keys Ensure that the value (voice_message) in the "Path" parameter in the Webhook node is used as the name of the parameter that will contain the voice message you are sending via the HTTP Post request.