HumationHuman + Automation
Back to Catalog

AI-powered document search with Oracle and ONNX embeddings for recruiting

sudarshansudarshan
211 views
2/3/2026
Google SheetsSpreadsheetData TransformationAPIETL
Official Page

How it works

  1. Create a user for doing Hybrid Search.
  2. Clear Existing Data, if present.
  3. Add Documents into the table.
  4. Create a hybrid index.
  5. Run Semantic search on the Documents table for "prioritize teamwork and leadership experience".
  6. Run Hybrid search for the text input in the Chat interface on the Documents table.

Setup Steps

Download the ONNX model

all_MiniLM_L12_v2_augmented.zip

Extract the ZIP file on the database server into a directory, for example /opt/oracle/onnx. After extraction, the folder contents should look like:

bash-4.4$ pwd
/opt/oracle/onnx
bash-4.4$ ls
all_MiniLM_L12_v2.onnx

Connect as SYSDBA and create the DBA user

-- Create DBA user
CREATE USER app_admin IDENTIFIED BY "StrongPassword123"
  DEFAULT TABLESPACE users 
  TEMPORARY TABLESPACE temp 
  QUOTA UNLIMITED ON users;


-- Grant privileges
GRANT DBA TO app_admin;
GRANT CREATE TABLESPACE, ALTER TABLESPACE, DROP TABLESPACE TO app_admin;

Create n8n Oracle DB credentials

  • hybridsearchuser → for hybrid search operations
  • dbadocuser → for DBA setup (user and tablespace creation)

Run the workflow

Click the manual Trigger

  • It displays Pure semantic search results.

Enter search text in Chat interface

  • It displays results for vector and keyword search.

Note

  • The workflow currently creates the hybrid search user, docuser with the password visible in plain text inside the n8n Execute SQL node.
  • For better security, consider performing the user creation manually outside n8n.
  • Oracle 23ai or 26ai Database has to be used.

Reference

Hybrid Search End-End Example

AI-Powered Document Search with Oracle and ONNX Embeddings for Recruiting

This n8n workflow demonstrates a foundational structure for an AI-powered document search system, specifically tailored for recruiting. It outlines the initial steps for receiving a chat message, processing it, and preparing to interact with an Oracle Database, likely for retrieving relevant candidate documents or information based on the chat input.

What it does

This workflow sets up the initial components for a conversational AI search system:

  1. Triggers on Chat Message: It starts by listening for incoming chat messages, indicating a user query.
  2. Manual Trigger Option: Provides an alternative manual trigger for testing and development purposes.
  3. Code Execution: Includes a "Code" node, which is typically used for custom JavaScript logic. In a full implementation, this node would likely handle:
    • Extracting the user's query from the chat message.
    • Generating embeddings for the query using an ONNX model (as hinted by the directory name).
    • Preparing the query for an Oracle Database search.
  4. Oracle Database Interaction: Features an "Oracle Database" node, which would be configured to:
    • Connect to an Oracle database.
    • Execute a query to find relevant documents or candidate profiles based on the generated embeddings.
    • Retrieve the search results.

Prerequisites/Requirements

To fully implement and run this workflow, you would need:

  • n8n Instance: A running n8n instance.
  • Chat Platform Integration: Integration with a chat platform (e.g., Slack, Microsoft Teams, custom chat interface) that can send messages to the n8n "Chat Trigger" webhook.
  • Oracle Database: Access to an Oracle Database instance.
  • Oracle Database Credentials: Necessary credentials (hostname, port, service name/SID, username, password) to connect to the Oracle Database.
  • ONNX Embedding Model: While not explicitly configured in the provided JSON, the "Code" node would require logic to interact with an ONNX model for generating embeddings. This might involve an external service or a local ONNX runtime setup.
  • JavaScript Knowledge: To customize the "Code" node for embedding generation and query preparation.

Setup/Usage

  1. Import the Workflow:
    • Download the provided JSON.
    • In your n8n instance, go to "Workflows" and click "New".
    • Click the three dots menu (...) in the top right and select "Import from JSON".
    • Paste the JSON content and click "Import".
  2. Configure Credentials:
    • Locate the "Oracle Database" node.
    • Click on it and configure your Oracle Database credentials. You will likely need to create a new credential for Oracle Database if you haven't already.
  3. Customize the Code Node:
    • Open the "Code" node.
    • Write or paste your JavaScript code to:
      • Process the incoming chat message.
      • Call an embedding service (e.g., an ONNX runtime, an external API) to generate vector embeddings for the user's query.
      • Construct an SQL query (or a procedure call) for your Oracle Database that uses these embeddings for similarity search.
  4. Connect Chat Trigger:
    • Configure the "Chat Trigger" node to listen for messages from your desired chat platform. This typically involves setting up a webhook URL in your chat platform's integration settings.
  5. Expand the Workflow:
    • After the "Oracle Database" node, you would add further nodes to process the search results (e.g., format them, summarize them using an LLM, send them back to the chat platform).
  6. Activate the Workflow:
    • Once configured, activate the workflow by toggling the "Active" switch in the top right corner of the workflow editor.

This workflow provides a robust starting point for building sophisticated AI-driven search capabilities within n8n.

Related Templates

AI-powered code review with linting, red-marked corrections in Google Sheets & Slack

Advanced Code Review Automation (AI + Lint + Slack) Who’s it for For software engineers, QA teams, and tech leads who want to automate intelligent code reviews with both AI-driven suggestions and rule-based linting — all managed in Google Sheets with instant Slack summaries. How it works This workflow performs a two-layer review system: Lint Check: Runs a lightweight static analysis to find common issues (e.g., use of var, console.log, unbalanced braces). AI Review: Sends valid code to Gemini AI, which provides human-like review feedback with severity classification (Critical, Major, Minor) and visual highlights (red/orange tags). Formatter: Combines lint and AI results, calculating an overall score (0–10). Aggregator: Summarizes results for quick comparison. Google Sheets Writer: Appends results to your review log. Slack Notification: Posts a concise summary (e.g., number of issues and average score) to your team’s channel. How to set up Connect Google Sheets and Slack credentials in n8n. Replace placeholders (<YOURSPREADSHEETID>, <YOURSHEETGIDORNAME>, <YOURSLACKCHANNEL_ID>). Adjust the AI review prompt or lint rules as needed. Activate the workflow — reviews will start automatically whenever new code is added to the sheet. Requirements Google Sheets and Slack integrations enabled A configured AI node (Gemini, OpenAI, or compatible) Proper permissions to write to your target Google Sheet How to customize Add more linting rules (naming conventions, spacing, forbidden APIs) Extend the AI prompt for project-specific guidelines Customize the Slack message formatting Export analytics to a dashboard (e.g., Notion or Data Studio) Why it’s valuable This workflow brings realistic, team-oriented AI-assisted code review to n8n — combining the speed of automated linting with the nuance of human-style feedback. It saves time, improves code quality, and keeps your team’s review history transparent and centralized.

higashiyama By higashiyama
90

Automate RSS to social media pipeline with AI, Airtable & GetLate for multiple platforms

Overview Automates your complete social media content pipeline: sources articles from Wallabag RSS, generates platform-specific posts with AI, creates contextual images, and publishes via GetLate API. Built with 63 nodes across two workflows to handle LinkedIn, Instagram, and Bluesky—with easy expansion to more platforms. Ideal for: Content marketers, solo creators, agencies, and community managers maintaining a consistent multi-platform presence with minimal manual effort. How It Works Two-Workflow Architecture: Content Aggregation Workflow Monitors Wallabag RSS feeds for tagged articles (to-share-linkedin, to-share-instagram, etc.) Extracts and converts content from HTML to Markdown Stores structured data in Airtable with platform assignment AI Generation & Publishing Workflow Scheduled trigger queries Airtable for unpublished content Routes to platform-specific sub-workflows (LinkedIn, Instagram, Bluesky) LLM generates optimized post text and image prompts based on custom brand parameters Optionally generates AI images and hosts them on Imgbb CDN Publishes via GetLate API (immediate or draft mode) Updates Airtable with publication status and metadata Key Features: Tag-based content routing using Wallabag's native system Swappable AI providers (Groq, OpenAI, Anthropic) Platform-specific optimization (tone, length, hashtags, CTAs) Modular design—duplicate sub-workflows to add new platforms in \~30 minutes Centralized Airtable tracking with 17 data points per post Set Up Steps Setup time: \~45-60 minutes for initial configuration Create accounts and get API keys (\~15 min) Wallabag (with RSS feeds enabled) GetLate (social media publishing) Airtable (create base with provided schema—see sticky notes) LLM provider (Groq, OpenAI, or Anthropic) Image service (Hugging Face, Fal.ai, or Stability AI) Imgbb (image hosting) Configure n8n credentials (\~10 min) Add all API keys in n8n's credential manager Detailed credential setup instructions in workflow sticky notes Set up Airtable database (\~10 min) Create "RSS Feed - Content Store" base Add 19 required fields (schema provided in workflow sticky notes) Get Airtable base ID and API key Customize brand prompts (\~15 min) Edit "Set Custom SMCG Prompt" node for each platform Define brand voice, tone, goals, audience, and image preferences Platform-specific examples provided in sticky notes Configure platform settings (\~10 min) Set GetLate account IDs for each platform Enable/disable image generation per platform Choose immediate publish vs. draft mode Adjust schedule trigger frequency Test and deploy Tag test articles in Wallabag Monitor the first few executions in draft mode Activate workflows when satisfied with the output Important: This is a proof-of-concept template. Test thoroughly with draft mode before production use. Detailed setup instructions, troubleshooting tips, and customization guidance are in the workflow's sticky notes. Technical Details 63 nodes: 9 Airtable operations, 8 HTTP requests, 7 code nodes, 3 LangChain LLM chains, 3 RSS triggers, 3 GetLate publishers Supports: Multiple LLM providers, multiple image generation services, unlimited platforms via modular architecture Tracking: 17 metadata fields per post, including publish status, applied parameters, character counts, hashtags, image URLs Prerequisites n8n instance (self-hosted or cloud) Accounts: Wallabag, GetLate, Airtable, LLM provider, image generation service, Imgbb Basic understanding of n8n workflows and credential configuration Time to customize prompts for your brand voice Detailed documentation, Airtable schema, prompt examples, and troubleshooting guides are in the workflow's sticky notes. Category Tags social-media-automation, ai-content-generation, rss-to-social, multi-platform-posting, getlate-api, airtable-database, langchain, workflow-automation, content-marketing

Mikal Hayden-GatesBy Mikal Hayden-Gates
188

Ai website scraper & company intelligence

AI Website Scraper & Company Intelligence Description This workflow automates the process of transforming any website URL into a structured, intelligent company profile. It's triggered by a form, allowing a user to submit a website and choose between a "basic" or "deep" scrape. The workflow extracts key information (mission, services, contacts, SEO keywords), stores it in a structured Supabase database, and archives a full JSON backup to Google Drive. It also features a secondary AI agent that automatically finds and saves competitors for each company, building a rich, interconnected database of company intelligence. --- Quick Implementation Steps Import the Workflow: Import the provided JSON file into your n8n instance. Install Custom Community Node: You must install the community node from: https://www.npmjs.com/package/n8n-nodes-crawl-and-scrape FIRECRAWL N8N Documentation https://docs.firecrawl.dev/developer-guides/workflow-automation/n8n Install Additional Nodes: n8n-nodes-crawl-and-scrape and n8n-nodes-mcp fire crawl mcp . Set up Credentials: Create credentials in n8n for FIRE CRAWL API,Supabase, Mistral AI, and Google Drive. Configure API Key (CRITICAL): Open the Web Search tool node. Go to Parameters → Headers and replace the hardcoded Tavily AI API key with your own. Configure Supabase Nodes: Assign your Supabase credential to all Supabase nodes. Ensure table names (e.g., companies, competitors) match your schema. Configure Google Drive Nodes: Assign your Google Drive credential to the Google Drive2 and save to Google Drive1 nodes. Select the correct Folder ID. Activate Workflow: Turn on the workflow and open the Webhook URL in the “On form submission” node to access the form. --- What It Does Form Trigger Captures user input: “Website URL” and “Scraping Type” (basic or deep). Scraping Router A Switch node routes the flow: Deep Scraping → AI-based MCP Firecrawler agent. Basic Scraping → Crawlee node. Deep Scraping (Firecrawl AI Agent) Uses Firecrawl and Tavily Web Search. Extracts a detailed JSON profile: mission, services, contacts, SEO keywords, etc. Basic Scraping (Crawlee) Uses Crawl and Scrape node to collect raw text. A Mistral-based AI extractor structures the data into JSON. Data Storage Stores structured data in Supabase tables (companies, company_basicprofiles). Archives a full JSON backup to Google Drive. Automated Competitor Analysis Runs after a deep scrape. Uses Tavily web search to find competitors (e.g., from Crunchbase). Saves competitor data to Supabase, linked by company_id. --- Who's It For Sales & Marketing Teams: Enrich leads with deep company info. Market Researchers: Build structured, searchable company databases. B2B Data Providers: Automate company intelligence collection. Developers: Use as a base for RAG or enrichment pipelines. --- Requirements n8n instance (self-hosted or cloud) Supabase Account: With tables like companies, competitors, social_links, etc. Mistral AI API Key Google Drive Credentials Tavily AI API Key (Optional) Custom Nodes: n8n-nodes-crawl-and-scrape --- How It Works Flow Summary Form Trigger: Captures “Website URL” and “Scraping Type”. Switch Node: deep → MCP Firecrawler (AI Agent). basic → Crawl and Scrape node. Scraping & Extraction: Deep path: Firecrawler → JSON structure. Basic path: Crawlee → Mistral extractor → JSON. Storage: Save JSON to Supabase. Archive in Google Drive. Competitor Analysis (Deep Only): Finds competitors via Tavily. Saves to Supabase competitors table. End: Finishes with a No Operation node. --- How To Set Up Import workflow JSON. Install community nodes (especially n8n-nodes-crawl-and-scrape from npm). Configure credentials (Supabase, Mistral AI, Google Drive). Add your Tavily API key. Connect Supabase and Drive nodes properly. Fix disconnected “basic” path if needed. Activate workflow. Test via the webhook form URL. --- How To Customize Change LLMs: Swap Mistral for OpenAI or Claude. Edit Scraper Prompts: Modify system prompts in AI agent nodes. Change Extraction Schema: Update JSON Schema in extractor nodes. Fix Relational Tables: Add Items node before Supabase inserts for arrays (social links, keywords). Enhance Automation: Add email/slack notifications, or replace form trigger with a Google Sheets trigger. --- Add-ons Automated Trigger: Run on new sheet rows. Notifications: Email or Slack alerts after completion. RAG Integration: Use the Supabase database as a chatbot knowledge source. --- Use Case Examples Sales Lead Enrichment: Instantly get company + competitor data from a URL. Market Research: Collect and compare companies in a niche. B2B Database Creation: Build a proprietary company dataset. --- WORKFLOW IMAGE --- Troubleshooting Guide | Issue | Possible Cause | Solution | |-------|----------------|-----------| | Form Trigger 404 | Workflow not active | Activate the workflow | | Web Search Tool fails | Missing Tavily API key | Replace the placeholder key | | FIRECRAWLER / find competitor fails | Missing MCP node | Install n8n-nodes-mcp | | Basic scrape does nothing | Switch node path disconnected | Reconnect “basic” output | | Supabase node error | Wrong table/column names | Match schema exactly | --- Need Help or More Workflows? Want to customize this workflow for your business or integrate it with your existing tools? Our team at Digital Biz Tech can tailor it precisely to your use case from automation logic to AI-powered enhancements. Contact: shilpa.raju@digitalbiz.tech For more such offerings, visit us: https://www.digitalbiz.tech ---

DIGITAL BIZ TECHBy DIGITAL BIZ TECH
923