This workflow automates the creation and management of a Retrieval-Augmented Generation (RAG) system using Qdrant as a vector store and Google Drive as the document source. It enables full or incremental updates to documents in the Qdrant vector database and integrates with a chatbot using Google Gemini for question answering. Here is a clear and professional description in English of the n8n workflow “Create a RAG with Qdrant and update single files”, including its benefits: ---

This workflow automates the creation and management of a Retrieval-Augmented Generation (RAG) system using Qdrant as a vector store and Google Drive as the document source. It enables full or incremental updates to documents in the Qdrant vector database and integrates with a chatbot using Google Gemini for question answering. Here is a clear and professional description in English of the n8n workflow “Create a RAG with Qdrant and update single files”, including its benefits: --- Benefits Efficient RAG Setup Seamlessly integrates OpenAI, Qdrant, and Google Drive to create a scalable RAG pipeline. Single File Update You can replace the vector representation of a single file without reprocessing the entire collection—ideal for maintaining document freshness. Flexible File Source Works with Google Drive, allowing document management and updates from a familiar interface. --- How It Works This workflow is designed to create a Retrieval-Augmented Generation (RAG) system using Qdrant as a vector store and Google Drive as a document source. It consists of four main phases: - Collection Setup: - Creates or clears a Qdrant collection to store vectorized documents. - Configures the collection with cosine distance metrics and other parameters. - Document Processing: - Retrieves files from a specified Google Drive folder. - Downloads and processes each file (text extraction, chunking, and embedding using OpenAI). - Stores the embeddings in Qdrant for vector search. - Single-File Update: - Allows updating or deleting a specific file in the Qdrant collection by referencing its Google Drive ID. - Re-embeds the file and updates the vector store. - RAG Querying: - Uses a chat trigger to receive user questions. - Retrieves relevant documents from Qdrant using vector similarity. - Generates answers using Google Gemini as the language model. --- Set Up Steps 1. Configure Qdrant: - Replace QDRANTURL and COLLECTION in the "Create collection" and "Clear collection" HTTP nodes. - Ensure Qdrant API credentials are correctly set in the credentials section. 2. Google Drive Integration: - Specify the Google Drive folder ID in the "Get files" node. - Ensure Google Drive OAuth credentials are configured. 3. OpenAI and Gemini Keys: - Add OpenAI API credentials for embeddings (used in "Embeddings OpenAI" nodes). - Configure Google Gemini credentials for the chat model. 4. Single-File Update: - Set the fileid in the "Edit Fields3" node to target a specific Google Drive file for updates. 5. Testing: - Trigger the workflow manually to populate the Qdrant collection. - Use the chat interface to test RAG responses. --- Need help customizing? Contact me for consulting and support or add me on Linkedin.
Download the workflow JSON file after purchase.
Open n8n → click the menu → Import from File.
Select the downloaded JSON and import.
Set up credentials for each node that requires them.
Click Execute Workflow to test, then activate.
Setup guide included
Purchase to unlock the full step-by-step guide
No reviews yet
Be the first to buy and share your experience.
Leave a review
Sign in to share your experience with this workflow.
Create a free account to purchase workflows.
Need help setting this up?
Book a 3-hour live setup session with an Agility consultant.