Basic LLM Chain workflows
205 results — all source-linked n8n references
BAnswer HR policy and benefits questions with BambooHR, OpenAI and Supabase
Quick Overview This workflow ingests company policy PDFs from BambooHR into a Supabase vector database and provides an employee chat interface that answers policy and benefits questions using OpenAI, with an additional employee/department lookup powered by BambooHR employee data. How it works Starts a manual run to fetch files from BambooHR and keep only PDFs in the “Company Files” category. Downloads each selected PDF, splits it into chunks, generates OpenAI embeddings, and inserts the content into a Supabase vector table for retrieval. Exposes a chat trigger where employees submit questions to an HR assistant. Uses OpenAI with conversation memory and retrieves relevant policy content from the Supabase vector store to ground responses. When a question requires a contact person, looks up employee details in BambooHR by exact name or finds the most senior person in a requested department using an OpenAI-assisted department extraction and ranking step. Returns the final answer to the chat, including policy-based guidance and any retrieved employee contact details. Setup Add BambooHR credentials and ensure your policies/benefits PDFs are available in the BambooHR file category named “
Create blog drafts, images, and LinkedIn posts with Tavily, Gemini, and OpenAI
Quick overview This workflow receives a blog request via webhook, researches the topic with Tavily, generates a long-form HTML article using Google Gemini, creates two images via the kie.ai API, stores assets in Google Drive, updates a Google Sheets tracker, and notifies a Slack user with links. How it works Receives a POST webhook request containing a Google Sheets row payload with an “AI Blog Title” and related metadata. Searches the web for supporting sources using Tavily and passes the research plus the title to Google Gemini to generate the full article as HTML. Converts the generated content to HTML, creates a temporary HTML file in Google Drive, downloads it to set the correct text/html MIME type, re-uploads it as the final Drive file, and deletes the temporary file. Sends the finished article to OpenAI to generate a short LinkedIn post, then updates the matching row in Google Sheets with a Done flag, the article folder/link value, and the LinkedIn post text. Creates a cover image and an in-article infographic by submitting two text-to-image jobs to the kie.ai API, polling until each job succeeds, downloading each resulting image, and uploading both images to Google Drive. W
Generate digital product launch content with OpenAI GPT-4o-mini and Google Sheets
Quick overview This workflow generates a multi-channel digital product launch content pack from product details, using OpenAI to create a blog intro, LinkedIn post, X post, Instagram caption, and launch email, and can optionally append the results to Google Sheets. How it works Runs manually when you execute the workflow. Loads sample product details such as name, tagline, price, URL, target audience, and brand tone. Sends the product details to OpenAI (GPT-4o-mini) with instructions to return a JSON content pack for blog, LinkedIn, X, Instagram, and email. Normalizes and validates the returned JSON, ensuring all five content fields are present and formatted as plain text. Optionally appends the generated content fields as a new row in Google Sheets (when the Google Sheets step is enabled). Setup Add an OpenAI API credential and select it in the OpenAI Chat Model configuration. Replace the sample product fields (especially productURL and brandTone) with your own product data or connect a real data source. (Optional) Enable the Google Sheets step, add Google Sheets OAuth2 credentials, and set the target spreadsheet ID and sheet name. Requirements n8n instance (cloud or self-hosted)
Generate workflow audit docs from JSON with Claude Sonnet and Notion
Quick overview This workflow collects an exported n8n workflow JSON via an n8n Form, audits it for common reliability and security issues, uses Anthropic Claude to draft a business summary and technical report, and then creates a formatted documentation page in Notion. How it works Receives a form submission with a workflow JSON file, client name, and a Notion parent page ID. Parses and validates the uploaded JSON to confirm it contains nodes and connections and extracts the workflow metadata. Analyzes the workflow graph to determine execution order, detect cycles and unreachable nodes, and generate a scored list of audit findings. Sends the audit context to Anthropic Claude (Sonnet) to generate a business-facing workflow summary and a developer-facing audit report. Converts the generated text into Notion blocks, including an audit score callout and optional warnings for cycles or unreachable nodes. Creates a new Notion page under the provided parent page and appends the blocks in batches with a short wait to avoid Notion rate limits. Setup Import the workflow and connect your Anthropic account credential to the Claude Sonnet node. No additional configuration is needed on the Anthr
Create SEO blog posts from YouTube videos with Gemini and Google Docs
Quick overview Submit a YouTube URL and get a publish-ready SEO blog post. Three Gemini agents research the video, write the article, and score it. Articles scoring 7+ auto-publish to Google Docs. Lower scores route to Telegram for review. How it works The workflow starts when a POST request hits the webhook with a YouTube URL, optional target keyword, and tone. A Code node extracts the video ID and validates the URL format, then an HTTP Request node calls YouTube Data API v3 to pull the video title, description, channel name, and tags. Three Basic LLM Chain nodes run in sequence, each powered by a Google Gemini Flash sub-node connected via the native ai_languageModel port. The first chain (Research Agent) receives the video context and returns a structured JSON brief containing an SEO title, four H2 headings, primary keyword, secondary keywords, key insights, target audience, and a content angle. A Code node parses this output with a JSON fallback in case Gemini adds unexpected formatting. The second chain (Writer Agent) takes the research brief and writes a complete 1,000–1,400 word blog post following strict rules: flowing paragraphs over bullet lists, primary keyword used 3–5 t
Classify workflow errors with Claude and deduplicate Jira and Slack alerts
Quick overview This global error-handling workflow classifies n8n execution failures with Anthropic Claude, deduplicates incidents in Jira using a hash label, and posts a detailed alert to Slack with links to the affected execution and Jira issue. How it works Triggers whenever any n8n workflow execution or trigger fails (when set as the instance Error Workflow). Normalizes the error event into a consistent payload that includes workflow details, error message, truncated stack trace, and an execution log URL. Sends the normalized payload to Anthropic Claude to return a structured JSON classification (category, severity, root cause, recommended action, and transient flag). Parses the classification, falls back to an UNKNOWN classification if the LLM response is invalid, and generates a deduplication hash used to group similar errors. Searches Jira for an open issue in the configured project that already has the matching deduplication label. If an open issue exists, appends a recurrence comment with the latest execution details; otherwise, creates a new Jira Bug with labels, priority, and a full incident description. Builds a Slack Block Kit message summarizing the incident and sends
BCWScrape Hacker News hiring threads with OpenAI GPT-4o-mini and Airtable
Quick overview This workflow manually runs a scraper that finds the latest Hacker News “Ask HN: Who is hiring?” thread via the Algolia HN Search API, pulls each job comment from the Hacker News Firebase API, uses OpenAI to structure postings into fields, and saves the results to Airtable. How it works Starts when you manually execute the workflow. Queries the Algolia Hacker News Search API for recent “Ask HN: Who is hiring?” stories and keeps only the relevant thread metadata. Filters the results to the most recent thread (created within the last 30 days) and fetches the full thread from the Hacker News Firebase API. Iterates through the thread’s comment IDs, fetching each individual job comment from the Hacker News Firebase API. Extracts and cleans the job text to remove HTML/entities and normalize links and whitespace. Sends the cleaned text to OpenAI (GPT-4o-mini) to extract a structured JSON record (company, title, location, type, salary, description, and URLs). Creates a new record in Airtable for each structured job posting. Setup Add an Airtable credential and set the target base and table in the Airtable create step. Add an OpenAI credential for the GPT-4o-mini chat model.
Detect visual regressions with Apify, Google Gemini, Sheets and Linear
Quick overview This workflow generates baseline website screenshots with Apify, stores them in Google Drive, and logs the file IDs in Google Sheets, then runs scheduled visual regression checks by comparing new screenshots against the baselines with Google Gemini Vision and creating a consolidated Linear issue when changes are detected. How it works Manually starts to backfill missing baselines by reading URLs from Google Sheets that do not yet have a stored base image. For each missing baseline URL, calls Apify’s screenshot actor, downloads the rendered image, uploads it to Google Drive, and updates the matching Google Sheets row with the Drive file ID. Runs weekly on a schedule and reads the list of webpages to test from Google Sheets. For each webpage, downloads the baseline image from Google Drive and captures a fresh screenshot via Apify. Sends both images to Google Gemini (vision) to detect visual differences and returns a structured list of regressions (text, number, image, color, or position). Filters out pages with no detected changes, aggregates the remaining results, and creates a Linear issue containing the regression report. Setup Add an Apify API token as HTTP Query A
Draft Gmail reply drafts automatically with Google Gemini
Quick overview This workflow watches for new Gmail messages, uses Google Gemini to draft a concise reply based on the email content, and saves the response as a Gmail draft in the original thread for you to review before sending. How it works Triggers every minute when a new email is received in Gmail. Sends the email subject, sender, and snippet to Google Gemini with instructions to write a professional reply under 100 words matching the sender’s tone. Creates a Gmail draft containing the generated reply and sets the subject to “Re:” while attaching it to the original email thread. Setup Connect a Gmail OAuth2 credential and ensure the trigger has access to the inbox you want to monitor. Add a Google Gemini (PaLM) API credential for the Gemini chat model. Review the reply prompt and the Gmail trigger polling interval, then activate the workflow. No additional setup is required the workflow is ready to run as soon as both credentials are connected.
Track expenses from phone notifications with Google Gemini and Google Sheets
Quick overview This workflow receives phone push notification through FlowTrigger mobile app, extracts the transaction amount and date, uses Google Gemini to categorize the expense and adds it to a Google Sheets transactions log. How it works Receives a POST webhook request containing a captured notification payload from FlowTrigger mobile app. Parses the notification data and skips the flow if no amount is detected in the notification payload. Sends the notification title and body to Google Gemini and parses a structured response with cleaned merchant name, expense category, reasoning, and ISO currency code. Appends the date, amount, category, currency, and merchant to a selected Google Sheets tab. Returns a success response with the saved fields, or an error response if the AI categorization or Google Sheets write fails. Setup Create and connect a Google Gemini API key credential for the Google Gemini Chat Model. Create and connect a Google Sheets OAuth2 credential, then set the Google Sheets Document ID and Sheet Tab Name in the Google Sheets append step. Activate the workflow, copy the Webhook production URL from the Webhook trigger, and paste it into FlowTrigger’s Notification
Enrich and route inbound leads using You.com, Groq, Notion, and Slack
Quick overview This workflow receives inbound lead details via webhook, enriches the company using You.com search and website content extraction, generates a one-page profile and fit score with Groq, then routes hot leads to Slack, logs all leads to Notion, and returns the enriched result in the webhook response. How it works Receives a POST webhook request containing a company name and/or domain and normalizes the input into consistent fields. Rejects the request with a 400 response if neither a company name nor a domain is provided. Uses You.com Web Search to gather recent company signals (for example funding, news, and leadership changes) and resolves a best-guess company URL. Uses You.com Content Extraction to pull website content and combines the search signals and site content into a single enrichment context. Uses Groq (Llama 3.3 70B) to generate a concise one-page company profile and then scores the lead against the defined fit criteria with structured output. If the fit score meets or exceeds the hot-lead threshold, posts an alert message to a selected Slack channel with an @mention. Logs the lead, fit score, tier, and profile summary to a Notion database and returns the f
Classify LinkedIn posts as quality or slop with OpenAI and Qdrant
Purpose This workflow is the official backend for the StopSlopIn Chrome extension – it classifies LinkedIn posts as quality or slop using a strict LLM quality gate and learns from user votes over time via a Qdrant vector store. What this is for This runs the webhook that powers the StopSlopIn Chrome extension on the Chrome Web Store. The extension sends LinkedIn posts here for analysis and user votes here for training – everything stays on your own n8n instance. Setup Add your OpenAI credentials to the chat model and embeddings nodes Add your Qdrant credentials to both vector store nodes, pointing to a collection named stopslopin Activate the workflow, copy the webhook URL, and paste it into the StopSlopIn Chrome extension settings Follow the instructions on the yellow sticky notes for anything else How it works A single webhook exposes two actions, selected via a ?action= query parameter: analyze for classification, vote for training. A Switch node routes incoming requests based on the action parameter On analyze: each post is enriched with similar prior-rated posts pulled from Qdrant (RAG), batched together, and sent to the LLM with a strict quality-gate system prompt The LLM ret
Monitor news sentiment trends with GPT-4o-mini, MrScraper, Slack and Notion
Description This n8n template automatically monitors news sources daily, analyzes article sentiment using AI, and delivers structured intelligence reports to your team — all without any manual reading. It uses MrScraper to discover and extract articles, GPT-4o-mini to score sentiment and flag urgent issues, and delivers results to both Notion (for archiving) and Slack (for real-time alerts and daily digests). Whether you're tracking brand reputation, monitoring a competitor, or staying on top of industry trends, this workflow turns the open web into a fully automated radar system that runs every morning before your team starts their day. How It Works Phase 1 – Trigger & Config:** A Schedule Trigger fires daily at 8AM. The workflow reads your list of target news source URLs from a Google Sheet, then loops through each source one by one. Phase 2 – URL Discovery:** For each news source, the Map Agent crawls the page and extracts individual article URLs. URLs are filtered using include patterns to keep only actual article links, deduplicated, and capped at your configured maxArticles limit. Phase 3 – Article Extraction:** Each article URL is processed by the General Agent, which extrac
Enrich and score Japanese B2B leads with gBizINFO, web scraping, and Gemini AI
Enrich and score Japanese company leads with government APIs, web scraping, and Gemini AI What this workflow does This workflow automates B2B lead research for Japanese companies. Submit a company name through a web form, and the workflow queries two free Japanese government APIs for corporate registry and business data, checks Google Maps for reputation, scrapes the company website for contact details and tech stack, and uses Gemini AI to score the lead and write a personalized outreach message in Japanese. Results are saved to Google Sheets, and high-scoring leads trigger a Slack alert. How it works Lead input form — A sales rep submits a company name along with industry, prefecture, priority, and notes National Tax Agency API — Retrieves the official corporate number, registered name, address, and entity type using the free 法人番号 API gBizINFO API — Enriches the lead with employee count, capital, establishment date, representative, subsidies, certifications, patents, and business summary using the free Ministry of Economy API Google Maps Places API — Fetches the company's star rating, review count, and business status for reputation assessment Website scraping — Fetches the compan
Automate Gmail Organization with AI-Powered Email Classification and Smart Labeling
📧 AI-Powered Gmail Auto-Labeling with Smart Classification This n8n workflow automatically organizes your Gmail inbox by intelligently categorizing incoming emails and applying custom labels using AI-powered sentiment analysis. Say goodbye to manual email sorting and hello to an organized inbox! Use Cases Business Email Management**: Automatically sort partnership inquiries, meeting requests, and promotional emails Sales Team Automation**: Identify and label cold outreach and high-priority leads Executive Assistants**: Filter important meetings and urgent matters for busy professionals Marketing Teams**: Separate promotional content from genuine business communications Good to Know The workflow runs every minute to check for new emails Each email is processed only once - already labeled emails are automatically skipped Uses OpenAI's GPT model for accurate email classification (API costs apply) Processes emails in batches to handle multiple incoming messages efficiently How It Works Gmail Trigger continuously monitors your inbox for new emails every minute Switch Node checks if emails already have labels (Other, Promotion, or Meeting) to avoid duplicate processing Loop Node process
Summarize YouTube Videos with Gemini AI and Send via Telegram
This automated TLDW (Too Long; Didn't Watch) generator using Decodo's scraping API to extract complete video transcripts and metadata, then uses Google Gemini 3 to create intelligent summaries with key points, chapters breakdown, tools mentioned, and actionable takeaways—eliminating hours of manual note-taking and video watching. Why Use This Workflow? Time Savings: Convert a 2-hour video into a readable 5-minute summary, reducing research time by 95% Comprehensive Coverage: Captures key points, chapters, tools, quotes, and actionable steps that manual notes often miss Instant Accessibility: Receive structured summaries directly in Telegram within 30-60 seconds of sharing a link Multi-Language Support: Process transcripts in multiple languages supported by YouTube's auto-caption system Ideal For Content Creators & Researchers:** Quickly extract insights from competitor videos, educational content, or industry talks without watching hours of footage Students & Educators:** Generate study notes from lecture recordings, online courses, or tutorial videos with chapter-based breakdowns Marketing Teams:** Analyze competitor content strategies, extract tools and techniques mentioned, and
WAutomatically Scrape Make.com Job Board with GPT-5-mini Summaries & Email Digest
Automatically Scrape Make.com Job Board with GPT-5-mini Summaries & Email Digest Overview Who is this for? Make.com consultants, automation specialists, and freelancers who want to catch new client opportunities without manually checking the forum. What problem does it solve? Scrolling through forum posts to find jobs wastes time. This automation finds new postings, uses AI to summarize what clients need, and emails you a clean digest. How it works: Runs on schedule → scrapes the Make.com professional services forum → filters jobs from last 7 days → AI summarizes each posting → sends formatted email digest. Use Cases Freelancers: Get daily job alerts without forum browsing, respond to opportunities faster Agencies: Keep sales teams informed of potential clients needing Make.com expertise Job Seekers: Track contract and full-time positions requiring Make.com skills Detailed Workflow Scraping: HTTP module pulls HTML from the Make.com forum job board Parsing: Extracts job titles, dates, authors, and thread links Filtering: Only jobs posted within last 7 days pass through (configurable) AI Processing: GPT-5-mini analyzes each post to extract: Project type Key requirements Complexity le
Create & Upload AI Videos to YouTube with Kling 2.5 & Auto-SEO
++What it is++ An automated workflow for creating Kling 2.5 videos and posting them to YouTube. The workflow is divided into three main phases: Create Kling 2.5 Video Wait for Video Processing Post to YouTube ++Create Kling 2.5 Video++ This phase handles the initial video creation based on user input. Type Prompt: A form trigger allows the user to input details for the video, including: Prompt: A simple scenario for the video. Video Style: (e.g., Dialogue, Monologue, Advertisement, Documentary) Aspect Ratio: (e.g., 16:9, 9:16, 1:1) Videography (AI Refinement): Refines the user’s prompt into a detailed “script-to-screen” format suitable for video generation. FAL.AI Request: The refined prompt is sent to the Fal.ai Kling 2.5 model via an HTTP request to generate the video. Store Data: Details of the video request, including the date requested, the refined prompt, and the request URL, are stored in a Google Sheet. ++Wait for Video Processing++ Wait 5 mins: The workflow pauses for 5 minutes. This waiting period is necessary as it typically takes 3–5 minutes for the video to be ready after the generation request. ++Post to YouTube++ This phase focuses on generating YouTube SEO details a
Extract and Analyze Web Data with Bright Data & Google Gemini
This workflow performs structured data extraction and data mining from a web page by combining the capabilities of Bright Data and Google Gemini. How it Works This workflow focuses on extracting structured data from a web page using Bright Data's Web Unlocker Product. It then uses n8n's AI capabilities, specifically Google Gemini Flash Exp, for information extraction and custom sentiment analysis. The results are sent to webhooks and saved as local files. Use Cases Data Mining**: Automating the process of extracting and analyzing data from websites. Web Scraping**: Gathering structured data for market research, competitive analysis, or content aggregation. Sentiment Analysis**: Performing custom sentiment analysis on unstructured text. Setup Instructions Bright Data Credentials: You need to have an account and a Web Unlocker zone with Bright Data. Update the Header Auth account credentials in the Perform Bright Data Web Request node. Google Gemini Credentials: Provide your Google Gemini(PaLM) Api account credentials for the AI-related nodes. Configure URL and Zone: In the Set URL and Bright Data Zone node, set the web URL you want to scrape and your Bright Data zone. Update Webhook
Create Research-Backed Articles with AI Planning, Linkup Search & GPT-5
Go beyond basic AI-generated text and create articles that are well-researched, comprehensive, and credible. This template automates an advanced content creation process that mimics a professional writing team: it plans, researches, and then writes. Instead of just giving an AI a topic, this workflow first uses an AI "planner" to break the topic down into logical sub-questions. Then, it deploys an AI "researcher" powered by Linkup to search the web for relevant insights and sources for each question. Finally, this complete, sourced research brief is handed to a powerful AI "writer" to compose a high-quality article, complete with hyperlinks back to the original sources. Who is this for? Content marketers & SEO specialists:** Scale the production of well-researched, link-rich articles that are built for authority and performance. Bloggers & thought leaders:** Quickly generate high-quality first drafts on any topic, complete with a list of sources for easy fact-checking and validation. Marketing agencies:** Dramatically improve your content turnaround time by automating the entire research and first-draft process for clients. What problem does this solve? Adds credibility with source
Create Fact-Based Articles from Your Knowledge Sources with Super RAG and GPT-5
Move beyond generic AI-generated content and create articles that are high-quality, factually reliable, and aligned with your unique expertise. This template orchestrates a sophisticated "research-first" content creation process. Instead of simply asking an AI to write an article from scratch, it first uses an AI planner to break your topic down into logical sub-questions. It then queries a Super assistant—which you've connected to your own trusted knowledge sources like Notion, Google Drive, or PDFs—to build a comprehensive research brief. Only then is this fact-checked brief handed to a powerful AI writer to compose the final article, complete with source links. This is the ultimate workflow for scaling expert-level content creation. Who is this for? Content marketers & SEO specialists:** Scale the creation of authoritative, expert-level blog posts that are grounded in factual, source-based information. Technical writers & subject matter experts:** Transform your complex internal documentation into accessible public-facing articles, tutorials, and guides. Marketing agencies:** Quickly generate high-quality, well-researched drafts for clients by connecting the workflow to their pr
BLinkedIn Profile Scraper & Personalized Outreach using PhantomBuster + GPT-4
Description This plug-and-play n8n workflow template helps you automate LinkedIn profile data extraction and transform it into structured, enriched outputs using PhantomBuster and GPT-4. Perfect for lead generation, recruiting, or growth marketing teams, this pipeline handles scraping, structuring, and messaging—all in one flow. Requirements PhantomBuster Setup Create a PhantomBuster account. Use the LinkedIn Profile Scraper Phantom (or your custom one). Get your API Key and Agent ID from PhantomBuster dashboard. Configure your LinkedIn Phantom with an active LinkedIn session cookie (available from your browser’s developer tools). OpenAI or Azure OpenAI Provide your GPT-4 / GPT-4o API Key. You can use OpenAI or Azure's hosted model. (Optional) Google Sheets Use Sheets for batch profile inputs or output logging. What This Template Does Step-by-Step Flow: 🔁 Manual Trigger / Google Sheets input – Accepts LinkedIn profile URLs. 🚀 Launch PhantomBuster Agent – Starts the scraping job with provided LinkedIn URLs. ⏳ Wait Node (45 sec) – Allows PhantomBuster to finish execution. 📥 Download Scraped Output – Fetches the download URL for JSON/CSV from the container. 📂 Temp File Management
BCWCreate AI Videos with Scripts, Images & HeyGen Avatars (🔥 LIMITED-TIME OFFER)
Short Content Automation 🎬 (AI Video System with Bulk Gen, Avatar & Music Customization) 🔥 LIMITED-TIME OFFER: AI Video Automation (Previously \$59) Previously Template 🚀 Transform Your Content Game in Minutes – Save Hours of Work! Introducing a powerful AI Video System to automate short video creation — from scriptwriting to avatar + image generation, music, and assembly — all with n8n. This is not a basic template. It's a complete, customizable system with step-by-step videos and my personal enhancements. 🎁 Why $10 Now? (Regular Price: \$59) ✅ Over 4000 people viewed my original automation — see it here — and I receive many messages from people who want it. ✅ I learned n8n from free templates and I want to give back. ✅ People asking for a more accessible price — this is my answer. ⏳ Limited-Time Deal: 7 Days Only! After that, this price goes away and the blueprint will be unlisted. 📦 What You Get ✅ Full n8n Workflow: From text prompt → ready-to-publish short video ✅ AI Tools Integration: OpenAI, Leonardo.AI, HeyGen, etc. ✅ Customization Options: Avatar, Voice, Music, Style ✅ Video Setup Guide: Step-by-step walkthrough ✅ Clean UI, easy-to-use, even if you're not a developer �
Extract Details from Receipts via Telegram with Tesseract and Llama
Tesseract - Money Mate Workflow Description Disclaimer: This template requires the n8n-nodes-tesseractjs community node, which is only available on self-hosted n8n instances. You’ll need a self-hosted n8n setup to use this workflow. Who is this for? This workflow is designed for individuals, freelancers, or small business owners who want an easy way to track expenses using Telegram. It’s ideal for anyone looking to digitize receipts—whether from photos or text messages—using free tools, without needing advanced technical skills. What problem does this workflow solve? Manually entering receipt details into a spreadsheet or app is time-consuming and prone to mistakes. This workflow automates the process by extracting information from receipt images or text messages sent via Telegram, categorizing expenses, and sending back a clear, formatted summary. It saves time, reduces errors, and makes expense tracking effortless. What this workflow does The workflow listens for messages sent to a Telegram bot, which can be either text descriptions of expenses or photos of receipts. If a photo is sent, Tesseract (an open-source text recognition tool) extracts the text. If text is sent, it’s proc