RAG AI Agent with Milvus and Cohere
Configured with Agent, Chat Trigger, Document Default Data Loader, Embeddings Cohere, and additional nodes. Review the connections and setup before adapting this template.
Node categories in this workflow
- Files / media
- AI & models
- Trigger
- Data store
- Transform
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.
| Node | Category | Type | Operation |
|---|---|---|---|
| Default Data Loader | Files / media | Document Default Data Loader | See node parameters |
| Embeddings Cohere | AI & models | Embeddings Cohere | See node parameters |
| When chat message received | Trigger | Chat Trigger | See node parameters |
| Watch New Files | Trigger | Google Drive Trigger | See node parameters |
| Download New | Files / media | Google Drive | download |
| Insert into Milvus | Data store | Vector Store Milvus | See node parameters |
| RAG Agent | AI & models | Agent | See node parameters |
| Retrieve from Milvus | Data store | Vector Store Milvus | See node parameters |
| OpenAI 4o | AI & models | OpenAI Chat Model | See node parameters |
| Memory | Data store | Memory Buffer Window | See node parameters |
| Cohere embeddings | AI & models | Embeddings Cohere | See node parameters |
| Set Chunks | Transform | Text Splitter Recursive Character Text Splitter | See node parameters |
| Extract from File | Transform | Extract From File |
Setup
- Download the JSON and import it into an isolated n8n instance. Leave the workflow inactive.
- Connect your own credentials through n8n’s credential store. Replace
REPLACE_WITH_*values with your resource identifiers. - Inspect API destinations, Code nodes, database queries, file paths, and outbound actions.
- 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
cohereApigoogleDriveOAuth2ApimilvusApiopenAiApi
Workflow notes
Why Milvus
Why Milvus
Based on comparisons and user feedback, Milvus is often considered a more performant and scalable vector database solution compared to Supabase, particularly for demanding use cases involving large datasets, high-volume vector search operations, and multilingual support.
Requirements
- Create an account on Zilliz to generate the Milvus cluster.
- There is no need to create docker containers or your own instance, Zilliz provides the cloud infraestructure to build it easily
- Get your credentials ready from Drive, Milvus (Zilliz), and Cohere
Usage
Every time a new pdf is added into the Drive folder, it will be inserted into the Milvus Vector Store, allowing for the interaction with the RAG agent in seconds.
Calculate your company's RAG costs
Want to run Milvus on your own server on n8n? Zilliz provides a great cost calculator
Get in touch with us
Want to implement a RAG AI agent for your company? Shoot us a message
RAG AI Agent with Milvus and Cohere
RAG AI Agent with Milvus and Cohere
Purpose and structure
This folder contains the RAG AI Agent with Milvus and Cohere workflow. Its executable nodes use agent, chatTrigger, documentDefaultDataLoader, embeddingsCohere, extractFromFile, googleDrive, googleDriveTrigger, lmChatOpenAi, memoryBufferWindow, textSplitterRecursiveCharacterTextSplitter, vectorStoreMilvus. 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 chat message received, Watch New Files
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/Extractfromfile/0741_Extractfromfile_Stickynote_Automation_Triggered.json MIT; preserve source notices.