Document RAG & chat agent: Google Drive to Qdrant with Mistral OCR
Knowledge RAG & AI Chat Agent: Google Drive to Qdrant Description This workflow transforms a Google Drive folder into an intelligent, searchable knowledge base and provides a chat agent to query it. It’s composed of two distinct flows: An ingestion pipeline to process documents. A live chat agent that uses RAG (Retrieval-Augmented Generation) and optional web search to answer user questions. This system fully automates the creation of a “Chat with your docs” solution and enhances it with external web-searching capabilities. --- Quick Implementation Steps Import the workflow JSON into your n8n instance. Set up credentials for Google Drive, Mistral AI, OpenAI, and Qdrant. Open the Web Search node and add your Tavily AI API key to the Authorization header. In the Google Drive (List Files) node, set the Folder ID you want to ingest. Run the workflow manually once to populate your Qdrant database (Flow 1). Activate the workflow to enable the chat trigger (Flow 2). Copy the public webhook URL from the When chat message received node and open it in a new tab to start chatting. --- What It Does The workflow is divided into two primary functions: Knowledge Base Ingestion (Manual Trigger) This flow populates your vector database. Scans Google Drive: Lists all files from a specified folder. Processes Files Individually: Downloads each file. Extracts Text via OCR: Uses Mistral AI OCR API for text extraction from PDFs, images, etc. Generates Smart Metadata: A Mistral LLM assigns metadata like documenttype, project, and assignedto. Chunks & Embeds: Text is cleaned, chunked, and embedded via OpenAI’s text-embedding-3-small model. Stores in Qdrant: Text chunks, embeddings, and metadata are stored in a Qdrant collection (docaiauto). AI Chat Agent (Chat Trigger) This flow powers the conversational interface. Handles User Queries: Triggered when a user sends a chat message. Internal RAG Retrieval: Searches Qdrant Vector Store first for answers. Web Search Fallback: If unavailable internally, the agent offers to perform a Tavily AI web search. Contextual Responses: Combines internal and external info for comprehensive answers. --- Who's It For Ideal for: Teams building internal AI knowledge bases from Google Drive. Developers creating AI-powered support, research, or onboarding bots. Organizations implementing RAG pipelines. Anyone making unstructured Google Drive documents searchable via chat. --- Requirements n8n instance (self-hosted or cloud). Google Drive Credentials (to list and download files). Mistral AI API Key (for OCR & metadata extraction). OpenAI API Key (for embeddings and chat LLM). Qdrant instance (cloud or self-hosted). Tavily AI API Key (for web search). --- How It Works The workflow runs two independent flows in parallel: Flow 1: Ingestion Pipeline (Manual Trigger) List Files: Fetch files from Google Drive using the Folder ID. Loop & Download: Each file is processed one by one. OCR Processing: Upload file to Mistral Retrieve signed URL Extract text using Mistral DOC OCR Metadata Extraction: Analyze text using a Mistral LLM. Text Cleaning & Chunking: Split into 1000-character chunks. Embeddings Creation: Use OpenAI embeddings. Vector Insertion: Push chunks + metadata into Qdrant. Flow 2: AI Chat Agent (Chat Trigger) Chat Trigger: Starts when a chat message is received. AI Agent: Uses OpenAI + Simple Memory to process context. RAG Retrieval: Queries Qdrant for related data. Decision Logic: Found → Form answer. Not found → Ask if user wants web search. Web Search: Performs Tavily web lookup. Final Response: Synthesizes internal + external info. --- How To Set Up Import the Workflow Upload the provided JSON into your n8n instance. Configure Credentials Create and assign: Google Drive → Google Drive nodes Mistral AI → Upload, Signed URL, DOC OCR, Cloud Chat Model OpenAI → Embeddings + Chat Model nodes Qdrant → Vector Store nodes Add Tavily API Key Open Web Search node → Parameters → Headers Add your key under Authorization (e.g., tvly-xxxx). Node Configuration Google Drive (List Files): Set Folder ID. Qdrant Nodes: Ensure same collection name (docaiauto). Run Ingestion (Flow 1) Click Test workflow to populate Qdrant with your Drive documents. Activate Chat (Flow 2) Toggle the workflow ON to enable real-time chat. Test Open the webhook URL and start chatting! --- How To Customize Change LLMs: Swap models in OpenAI or Mistral nodes (e.g., GPT-4o, Claude 3). Modify Prompts: Edit the system message in ai chat agent to alter tone or logic. Chunking Strategy: Adjust chunkSize and chunkOverlap in the Code node. Different Sources: Replace Google Drive with AWS S3, Local Folder, etc. Automate Updates: Add a Cron node for scheduled ingestion. Validation: Add post-processing steps after metadata extraction. Expand Tools: Add more functional nodes like Google Calendar or Calculator. --- Use Case Examples Internal HR Bot: Answer HR-related queries from stored policy docs. Tech Support Assistant: Retrieve troubleshooting steps for products. Research Assistant: Summarize and compare market reports. Project Management Bot: Query document ownership or project status. --- Troubleshooting Guide | Issue | Possible Solution | |------------|------------------------| | Chat agent doesn’t respond | Check OpenAI API key and model availability (e.g., gpt-4.1-mini). | | Known documents not found | Ensure ingestion flow ran and both Qdrant nodes use same collection name. | | OCR node fails | Verify Mistral API key and input file integrity. | | Web search not triggered | Re-check Tavily API key in Web Search node headers. | | Incorrect metadata | Tune Information Extractor prompt or use a stronger Mistral model. | --- 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. We can help you set it up for free — from connecting credentials to deploying it live. Contact: shilpa.raju@digitalbiz.tech Website: https://www.digitalbiz.tech LinkedIn: https://www.linkedin.com/company/digital-biz-tech/ You can also DM us on LinkedIn for any help. ---
By DIGITAL BIZ TECHAI-powered ServiceNow chat triage with GPT-4 — incident & request manager
Automated Incident and Request Management in ServiceNow Who’s it for This workflow is designed for IT teams, service desk agents, and operations managers who use ServiceNow. It reduces manual effort by automatically classifying chat messages as Incidents or Requests, creating/updating them in ServiceNow, and summarizing ticket updates. --- What it does Receives incoming chat messages. Classifies the message as one of: Incident (something broken, unavailable, or a complaint) Request (access, provisioning, product/order related) Follow-ups (incident or request update checks) Update action (user wants to add info to an existing ticket) Everything else (knowledge search / general query). Creates Incidents in ServiceNow via the ServiceNow node. Creates Requests in ServiceNow using the Service Catalog API. Updates existing Incidents with new work notes when the user provides an update. Pulls existing incident/request work notes for summaries. Optionally uses SerpAPI for general queries (if enabled). Returns a concise summary back to the user through the webhook. --- Requirements ServiceNow account with API access (Basic Auth) OpenAI API key (used by the classifier and summarizer) SerpAPI key (optional – for general web lookups)* --- Credentials needed You will need to set up the following credentials in n8n: ServiceNow Basic Auth (username, password, instance URL). OpenAI API (API key). SerpAPI (optional – only if you want web search enabled). --- How to set up Import the workflow JSON into your n8n instance. Create the credentials mentioned above and assign them to the corresponding nodes: Create an incident → ServiceNow Basic Auth HTTP Request1 (for Service Catalog requests) → ServiceNow Basic Auth OpenAI Chat Model / OpenAI Chat Model1 / OpenAI Chat Model2 / OpenAI Chat Model3 → OpenAI API SerpAPI node (optional) → SerpAPI key Adjust the ServiceNow instance URL in the HTTP Request node to match your environment. Deploy the workflow. Send a test chat message to trigger the workflow. --- How to customize Update the classification rules in the Text Classifier node if your organization uses different definitions for incidents vs. requests. Edit the summary prompt in the Summarization Chain to include or exclude specific fields. Add additional notification nodes (Slack, Teams, or Email) if you want updates pushed to other channels. --- Notes & Limitations This workflow creates general requests in ServiceNow using the catalog API. For production, update the Service Catalog item ID to match your environment. “Everything else” category uses SerpAPI. If not configured, those queries will not return results. This workflow requires OpenAI GPT-4.1 mini (or another supported model) for classification and summarization. ---
By Ritesh