Marko
Workflows by Marko
Chat with Google Drive documents using GPT, Pinecone, and RAG
## 📌 Short Overview Automatically sync files from Google Drive into a searchable AI knowledge base with Pinecone, and answer user queries using GPT-4o with conversational memory. ⸻ ## 🛠️ Workflow Usage Steps ### 1. Watch Google Drive for file changes Trigger the workflow when a new file is uploaded or an existing file is updated in a specific Google Drive folder. ### 2. Download and process the file Retrieve the file, split it into smaller text chunks with a Recursive Character Text Splitter, and generate vector embeddings using OpenAI. ### 3. Store embeddings in Pinecone Save the embeddings in a Pinecone vector database to keep your knowledge base continuously updated and searchable. ### 4. Search context for chat queries When a user asks a question, query Pinecone for relevant context, combine results with conversational memory, and process them with GPT-4o. ### 5. Respond with AI-powered answers Provide a concise response (100–200 words) that blends knowledge from your documents with the conversation history. ⸻ ## ✅ Use Cases • Keep a live, AI-ready knowledge base from your Google Drive files. • Enable team members to query company documents instantly. • Build a personal assistant that stays up to date with your latest uploads. ## ⚙️ Setup Steps 1. Google Drive • Create a Google Cloud project. • Enable the Google Drive API. • Generate OAuth credentials and connect them in n8n. 2. OpenAI • Sign up at OpenAI. • Copy your API key from the dashboard. • Add it to n8n under Credentials → OpenAI API. 3. Pinecone • Create an account at Pinecone. • Create a new index (e.g., docs-embeddings). • Copy your API key and environment, then add them to n8n under Credentials → Pinecone API. 4. Workflow Configuration • Import this workflow into your n8n instance. • Select the Google Drive folder you want to monitor. • Set the Pinecone index name in the workflow. • Adjust chunk size / overlap in the text splitter if needed. 5. Test the Workflow • Upload a new document to your Google Drive folder. • Run the workflow to confirm embeddings are created and stored in Pinecone. • Ask a sample query and verify the AI returns a context-aware answer.
Generate & publish SEO articles with Claude AI, Webflow & image generation
**Content engine that ships fresh, SEO-ready articles every single day. ** Workflow: ⸻ 1. Layout Blueprint • Purpose: Define content structure before writing begins. • What’s Included: • Search intent mapping • Internal link planning • Call-to-action (CTA) placement • Benefit: Ensures consistency, SEO alignment, and content goals are baked in early. ⸻ 2. AI-Assisted Drafting • Tool: GPT generates the first draft. • Editor’s Role: • Focus on depth and accuracy • Align tone and style with existing site content • Context-Aware: Pulls insights from top-ranking articles already live on the site. ⸻ 3. SEO Validation • Automated Checks for: • Keyword coverage • Readability scoring • Schema markup • Internal/external link quality • Outcome: Each piece is validated before hitting publish. ⸻ 4. Media Production • Process: AI auto-generates relevant images. • Delivery: Visual assets are automatically added to the CMS library. ⸻ Optional Human Review: Team feedback via Slack or Teams if needed. ⸻ 5. Automated Publishing • Action: Instantly publishes content to Webflow once approved. • Result: A fully streamlined pipeline from draft to live with minimal manual steps.