Bear Brown
← All N8N workflows
AI & researchAgentChat TriggerCodeDocument Default Data LoaderEmbeddings Open Ai

🤖 AI Powered RAG Chatbot for Your Docs + Google Drive + Gemini + Qdrant

Configured with Agent, Chat Trigger, Document Default Data Loader, Embeddings Open Ai, and additional nodes. Review the connections and setup before adapting this template.

Download workflow JSONView files on GitHub ↗35 nodes · MIT
Workflow preview
Files / mediaData LoaderDocument Default Data Lo…TransformToken SplitterText Splitter Token Spli…Data storeQdrant Vector StoreVector Store QdrantRoutingLoop Over ItemsLoop Over ItemsWaitWaitWaitTriggerWhen clicking ‘Testworkflow’Manual TriggerAI & modelsGoogle Gemini ChatModelLM Chat Google GeminiTransformMergeMergeAI & modelsExtract Meta DataInformation ExtractorTransformGet File ContentsExtract From FileFiles / mediaDownload File FromGoogle DriveGoogle DriveFiles / mediaFind File Ids in GoogleDrive FolderGoogle DriveAI & modelstext-embeddings-3-largeEmbeddings Open AiTransformGoogle Folder IDEdit FieldsAI & modelsgpt-4o-mini1OpenAI Chat ModelCodeDelete Qdrant Points byFile IDCodeTransformQdrant Collection NameEdit FieldsTransformFile Id ListSummarizeTransformMerge1MergeTransformMerge2MergeMessagingConfirm Qdrant DeletePointsTelegramRoutingIfIfMessagingSend Declined MessageTelegramTriggerWebhookWebhookAI & modelsAI AgentAgentData storeWindow Buffer MemoryMemory Buffer WindowTriggerWhen chat messagereceivedChat TriggerAI & modelsGoogle Gemini ChatModel1LM Chat Google GeminiAI & modelstext-embeddings-3-large1Embeddings Open AiFiles / mediaGoogle DriveGoogle DriveTransformRespond to UserEdit FieldsFiles / mediaUpdate Chat HistoryGoogle DocsData storeQdrant Vector StoreToolVector Store QdrantAI & modelsOpenAI Chat ModelOpenAI Chat ModelMessagingSend Completed MessageTelegram

Node categories in this workflow

  • Files / media
  • Transform
  • Data store
  • Routing
  • Wait
  • Trigger
  • AI & models
  • Code
  • Messaging

Icons describe general node roles, inferred from node types. Inspect the parameters for the configured action.

Drag to pan; use + and − to zoom. Reconstructed from the exported node positions; nothing runs here. Dashed lines represent non-main connections. Full node names and notes appear below.

How it works

The exported workflow contains the following configured nodes. Their connections are shown above; inspect the JSON for the complete logic, expressions, and external actions.

Workflow node names, types, and operations
NodeCategoryTypeOperation
Data LoaderFiles / mediaDocument Default Data LoaderSee node parameters
Token SplitterTransformText Splitter Token SplitterSee node parameters
Qdrant Vector StoreData storeVector Store QdrantSee node parameters
Loop Over ItemsRoutingLoop Over ItemsSee node parameters
WaitWaitWaitSee node parameters
When clicking ‘Test workflow’TriggerManual TriggerSee node parameters
Google Gemini Chat ModelAI & modelsLM Chat Google GeminiSee node parameters
MergeTransformMergeSee node parameters
Extract Meta DataAI & modelsInformation ExtractorSee node parameters
Get File ContentsTransformExtract From Filetext
Download File From Google DriveFiles / mediaGoogle Drivedownload
Find File Ids in Google Drive FolderFiles / mediaGoogle DrivefileFolder
text-embeddings-3-largeAI & modelsEmbeddings Open AiSee node parameters
Google Folder IDTransformEdit FieldsSee node parameters
gpt-4o-mini1AI & modelsOpenAI Chat ModelSee node parameters
Delete Qdrant Points by File IDCodeCodeSee node parameters
Qdrant Collection NameTransformEdit FieldsSee node parameters
File Id ListTransformSummarizeSee node parameters
Merge1TransformMergeSee node parameters
Merge2TransformMergeSee node parameters
Confirm Qdrant Delete PointsMessagingTelegramsendAndWait
IfRoutingIfSee node parameters
Send Declined MessageMessagingTelegramSee node parameters
WebhookTriggerWebhookSee node parameters
AI AgentAI & modelsAgentSee node parameters
Window Buffer MemoryData storeMemory Buffer WindowSee node parameters
When chat message receivedTriggerChat TriggerSee node parameters
Google Gemini Chat Model1AI & modelsLM Chat Google GeminiSee node parameters
text-embeddings-3-large1AI & modelsEmbeddings Open AiSee node parameters
Google DriveFiles / mediaGoogle DrivecreateFromText
Respond to UserTransformEdit FieldsSee node parameters
Update Chat HistoryFiles / mediaGoogle Docsupdate
Qdrant Vector Store ToolData storeVector Store QdrantSee node parameters
OpenAI Chat ModelAI & modelsOpenAI Chat ModelSee node parameters
Send Completed MessageMessagingTelegramSee node parameters

Setup

  1. Download the JSON and import it into an isolated n8n instance. Leave the workflow inactive.
  2. Connect your own credentials through n8n’s credential store. Replace REPLACE_WITH_* values with your resource identifiers.
  3. Inspect API destinations, Code nodes, database queries, file paths, and outbound actions.
  4. Run with synthetic data and harmless destinations. Enable triggers only after checking the actual outputs.

Requirements

An n8n instance with the listed node types and compatible versions. Service-connected workflows may require accounts, credentials, or paid APIs.

Credential types declared in the source

  • googleDocsOAuth2Api
  • googleDriveOAuth2Api
  • googlePalmApi
  • openAiApi
  • qdrantApi
  • telegramApi

Workflow notes

🌟Workflow Config

🌟Workflow Config

  • Google Drive Folder Id
  • Qdrant Collection Name
  • List of Google Drive File Id's
Delete From Qdrant Vector Store

Delete From Qdrant Vector Store

This operation can not be undone!!!

Human In The Loop

Human In The Loop

User must verify deletion of points from Qdrant vector store

🤖 AI-Powered RAG Chatbot with Google Drive Integration

🤖 AI-Powered RAG Chatbot with Google Drive Integration

This workflow creates a powerful RAG (Retrieval-Augmented Generation) chatbot that can process, store, and interact with documents from Google Drive using Qdrant vector storage and Google's Gemini AI.

How It Works

Document Processing & Storage 📚

  • Retrieves documents from a specified Google Drive folder
  • Processes and splits documents into manageable chunks
  • Extracts metadata using AI for enhanced search capabilities
  • Stores document vectors in Qdrant for efficient retrieval

Intelligent Chat Interface 💬

  • Provides a conversational interface powered by Google Gemini
  • Uses RAG to retrieve relevant context from stored documents
  • Maintains chat history in Google Docs for reference
  • Delivers accurate, context-aware responses

Vector Store Management 🗄️

  • Features secure delete operations with human verification
  • Includes Telegram notifications for important operations
  • Maintains data integrity with proper version control
  • Supports batch processing of documents

Setup Steps

  1. Configure API Credentials:

    • Set up Google Drive & Docs access
    • Configure Gemini AI API
    • Set up Qdrant vector store connection
    • Add Telegram bot for notifications

  2. Configure Document Sources:

    • Set Google Drive folder ID
    • Define Qdrant collection name
    • Set up document processing parameters

  3. Test and Deploy:

    • Verify document processing
    • Test chat functionality
    • Confirm vector store operations
    • Check notification system

This workflow is ideal for organizations needing to create intelligent chatbots that can access and understand large document repositories while maintaining context and providing accurate responses through RAG technology.

🤖 AI Powered RAG Chatbot for Your Docs + Google Drive + Gemini + Qdrant

🤖 AI Powered RAG Chatbot for Your Docs + Google Drive + Gemini + Qdrant

Purpose and structure

This folder contains the 🤖 AI Powered RAG Chatbot for Your Docs + Google Drive + Gemini + Qdrant workflow. Its executable nodes use agent, chatTrigger, code, documentDefaultDataLoader, embeddingsOpenAi, extractFromFile, googleDocs, googleDrive, if, informationExtractor, lmChatGoogleGemini, lmChatOpenAi, manualTrigger, memoryBufferWindow, merge, set, splitInBatches, summarize, telegram, textSplitterTokenSplitter, vectorStoreQdrant, wait, webhook. The table and connection map below are derived from the JSON, not an inferred guarantee of behavior.

Setup

Import inactive. Configure your own credentials and replace REPLACE_WITH_* values. Review external destinations and Code nodes before running.

Entry points

When clicking ‘Test workflow’, Webhook, When chat message received

Verification

Sanitized source candidate; not runtime-tested. This overview is generated from node metadata. Read the folder README for the connection map, credential types, and license.

Attribution

https://github.com/Zie619/n8n-workflows/blob/94007c1445d9258a7da116646b79473e7c7c3282/workflows/Telegram/1185_Telegram_Wait_Automate_Webhook.json MIT; preserve source notices.

Canvas section labels

These name areas of the original canvas; they do not include explanatory instructions.

  • Prepare Qdrant Vector Store
  • Perform Qdrant Vector Store Operations
  • Extract Metadata for Qdrant Hybrid Search
  • Google Drive
  • ✨ Save Documents to Qdrant Vector Store
  • 👍Start Here!
  • 🤖Retrieve Content from Qdrant Vector Store
  • 🗣️ Chat with Your Documents
  • Step 1 - Save Documents to Qdrant Vector Store
  • Step 2 - Chat with Your Documents from Qdrant Vector Store
  • Save Chat History

More in AI & research

"Hey Siri, Ask Agent" workflow#️⃣Nostr #damus AI Powered Reporting + Gmail + Telegram(G) - Email Classification