AWS S3 and Slack integration

Salesforce to S3 File Migration & Cleanup Automate archiving old Salesforce files to Amazon S3, log them back in Salesforce, and free up org storage — all from a scheduled n8n workflow. 🔧 How It Works (High-Level) Schedule Trigger kicks off (e.g., daily). Query Salesforce for ContentDocument records older than 365 days. Loop Each File → download binary via REST. Upload to S3 with the original filename. Lookup Links (ContentDocumentLink) to keep the parent record reference. Filter Out Users (ignore LinkedEntityId starting with 005). Create S3_File__c record in Salesforce for traceability. Delete Original File from Salesforce to reclaim storage. Notify via Slack when the batch is done. 🚀 Set Up Steps (Time: ~45–90 mins) Import n8n Workflow JSON and wire up credentials (Salesforce OAuth2, AWS S3, Slack). Install Salesforce Unmanaged Package (Custom Object S3_File__c, Apex controller, LWC, settings). Fill S3Settings__c (bucket, region, keys, expiry) or swap to Named Credentials. Test with a Sandbox Batch (e.g., small date range) and verify upload/delete. Schedule & Monitor (tweak interval, Slack channel). 💖 Why you’ll love it 💸 Slash storage costs — offload gigabytes to S3 🔍 Full traceability — every file still tracked in Salesforce 🧰 Plug & play — import JSON, install package, plug in creds 🧱 Modular & extensible — swap S3, add approvals, build an uploader UI ⏱ Set it & forget it — scheduled automation + Slack alerts 📦 What’s Included n8n JSON Flow** – ready to import. Salesforce Unmanaged Package** – Apex (S3FilesController.cls), LWC (s3FilesViewer), S3_File__c, S3Settings__c. S3 + Salesforce Setup Guide** – quick reference for configuring keys, permissions, and the LWC. All components are editable — extend, replace, or integrate with your own processes. 🧱 Requirements n8n instance (self-hosted or Cloud) with HTTP Request, AWS S3, Slack, and Salesforce nodes. Salesforce org with API access & permission to install unmanaged packages. You have to have Query All Files permission. Setup-> Permission Sets / Profile -> App Permission -> Content -> Query All Files. Allows View All Data users to SOQL query all files in the org. AWS S3 bucket + IAM user/role with GetObject/PutObject (and optional ListBucket).

This workflow exports every table in a base as its own CSV, saves the files in a time-stamped folder in Amazon S3, pings you on Slack, and optionally prunes older copies. You get an automated weekly backup that is easy to inspect or re-import as needed. You can easily swap the S3 node for the storage provider of your choice. ++How it works++ Weekly Backup Schedule trigger fires weekly Sets and formats the week ex. [2025-W12] Create a folder in S3 bucket with the week Loops through all tables in Airtable base creating CSVs and uploading to the new path Slack message is sent on completion Monthly Prune Schedule trigger fires weekly Sets a cut-off date 4 weeks in the past Lists folders in S3 Deletes all folders > 4 weeks old ++Setup Steps++ Clone workflow Swap credentials for Airtable, AWS, and Slack Ensure AWS credential has appropriate IAM policy to manage bucket & objects Set workflow to "Active"

Who’s it for This workflow is built for finance teams, operations managers, founders, and businesses that process invoices regularly and want to eliminate manual document handling. It’s especially useful for teams that need quick, structured invoice insights delivered directly to their communication tools. What it does / How it works This workflow automates the entire invoice-processing pipeline from upload to notification. A user uploads an invoice file through an n8n form trigger. The uploaded file is securely stored in AWS S3. AWS Textract analyzes the invoice and extracts text and structured data such as vendor name, totals, and line items. The extracted data is sent to AI Agent, which summarizes the invoice and highlights key financial details. The AI-generated summary is sent as a direct message to a selected user in Slack. All steps run automatically after the form submission. Requirements AWS credentials with access to: Amazon S3 AWS Textract Google Gemini (PaLM) API credentials Slack API credentials An existing S3 bucket to store uploaded invoice files How to set up Connect your AWS credentials in n8n with permissions for S3 and Textract. Specify the S3 bucket name where invoice files should be uploaded. Add and authenticate your Google Gemini API credentials. Connect your Slack account and choose the user or channel for notifications. Test the workflow by submitting an invoice through the n8n form. How to customize the workflow Update the Gemini prompt to extract specific fields such as tax, due date, or invoice number. Route invoices differently based on total amount or vendor. Send Slack messages to a channel instead of a direct message. Store extracted invoice data in a database or spreadsheet. Add approval or alert steps for high-value invoices.

HR Chatbot with RAG: Retrieve Company Policies via Slack, Amazon S3, and OpenAI Overview Answer HR and company policy questions via Slack, powered by a Knowledge Base of internal documents stored in S3. The assistant uses vector search and an OpenAI Chat Model to retrieve accurate answers. The HR Assistant is an AI-powered Slack bot that allows employees to ask questions in natural language and get accurate answers from company documentation. Documents are managed through an ingestion workflow that retrieves files from S3, transforms them into embeddings, and stores them in a vector database. On Slack, the assistant interprets questions, searches the Knowledge Base, and responds with concise and reliable answers, or clearly states when information isn’t available. How it works Normal interaction An employee asks a question in Slack (e.g., “How many vacation days do I have?”). The assistant checks the Knowledge Base (vector store). If relevant information is found, the assistant provides a clear answer. If not, it responds with: “That answer doesn’t appear to be covered in the materials I have access to.” Standardized process of Knowledge Base ingestion Trigger – The ingestion workflow is manually executed. S3 Download – Files are pulled from the company’s S3 bucket. Data Loader – Documents are pre-processed and split into chunks. Embeddings – Each chunk is converted into an embedding via OpenAI. Vector Store – Embeddings are stored in the Knowledge Base (vector DB). Chatbot Workflow – When questions arrive via Slack, the assistant queries the vector store to find the most relevant context before generating a response. Required Connections To use the HR Assistant effectively, you need: A Slack workspace, where the bot is installed and invited to relevant channels. An S3 bucket containing company documents (e.g., HR policies, procedures). Access to OpenAI API keys for both embeddings and chat models. Proper permissions to fetch documents from S3 and write to the vector store. A configured n8n instance with both ingestion and chatbot workflows. Setup Time ≈ 20–30 minutes (depending on number of documents and Slack integration). Customising this workflow Add more document sources (e.g., Google Drive, Confluence) in the ingestion pipeline. Expand the Slack integration to allow commands like /askHR or to restrict the bot to only respond when @mentioned. Add scheduled ingestion (instead of manual trigger) to automatically refresh the Knowledge Base from S3. Connect analytics nodes to monitor which HR topics employees ask most often.