Website chatbot with Google Drive knowledge base using GPT-4 and Mistral AI
Knowledge & search workflow for n8n with 23 active steps. Starts with Chat Trigger, Manual Trigger, Webhook. Uses OpenAI, Mistral AI. Integrations include OpenAI, Qdrant, Mistral AI, Google Drive.
What it does
23 active nodes · Starts with Chat Trigger, Manual Trigger, Webhook.
Steps in the template include:
- When chat message received (Chat Trigger)
- OpenAI Chat Model (OpenAI Chat Model)
- Simple Memory (Simple Memory)
- Loop Over Items1 (Loop Over Items (Split in Batches))
Nodes and integrations
- Chat Trigger
- OpenAI Chat Model
- Simple Memory
- Loop Over Items (Split in Batches)
- Wait
- Default Data Loader
- Character Text Splitter
- If
- Qdrant Vector Store ×2
- Embeddings Mistral Cloud ×2
- Manual Trigger
- Edit Fields (Set) ×2
- HTTP Request ×3
- Google Drive ×2
- Code
- Webhook
- AI Agent
See the author’s step names
- When chat message received (Chat Trigger)
- OpenAI Chat Model (OpenAI Chat Model)
- Simple Memory (Simple Memory)
- Loop Over Items1 (Loop Over Items (Split in Batches))
- Wait (Wait)
- Default Data Loader (Default Data Loader)
- Character Text Splitter (Character Text Splitter)
- If2 (If)
- Qdrant Vector Store1 (Qdrant Vector Store)
- Embeddings Mistral Cloud (Embeddings Mistral Cloud)
- Qdrant Vector Store (Qdrant Vector Store)
- Embeddings Mistral Cloud1 (Embeddings Mistral Cloud)
- When clicking ‘Execute workflow’ (Manual Trigger)
- Set metadata (Edit Fields (Set))
- Mistral Upload (HTTP Request)
- Mistral Signed URL (HTTP Request)
- Mistral DOC OCR (HTTP Request)
- Google Drive(brand related data for chatbot) (Google Drive) — fileFolder
- Google Drive(load file) (Google Drive) — download
- Code(convert to chunks for loading into vector db) (Code)
- prepare for chunking (Edit Fields (Set))
- Webhook (Webhook)
- website chat agent (AI Agent)
Accounts and credentials
- OpenAI access
- Qdrant
- Mistral AI access
- Mistral AI
- Google Drive
Credential types in the graph: openAiApi, qdrantApi, mistralCloudApi, googleDriveOAuth2Api
Check the HTTP request steps for any additional service accounts or API keys.
AI models and swaps
OpenAI · Chat
gpt-4.1-mini in OpenAI Chat Model. Potentially swappable with a compatible n8n chat model node. Match tool calling before testing.
Mistral AI · Embeddings
Model ID not specified in the template in Embeddings Mistral Cloud. Changing the embedding model may require rebuilding the vector index and matching its dimensions.
Mistral AI · Embeddings
Model ID not specified in the template in Embeddings Mistral Cloud1. Changing the embedding model may require rebuilding the vector index and matching its dimensions.
Mistral AI · Model or API operation
Model ID not specified in the template in Mistral Upload. Provider-specific step. A different provider requires edits and testing.
Mistral AI · Model or API operation
Model ID not specified in the template in Mistral DOC OCR. Provider-specific step. A different provider requires edits and testing.
Inputs and setup options
- When chat message received: public chat is enabled in the template
- OpenAI Chat Model: temperature 0.5
- Webhook: HTTP POST
Resource information
- Credit basis
- Author listed by n8n
- Pricing
- Template access shown on n8n
- License
- Not specified
- Last record update
- Nov 5, 2026
