Fine-tuning with OpenAI models
Configured with Agent, Chat Trigger, Google Drive, HTTP Request, and additional nodes. Review the connections and setup before adapting this template.
Node categories in this workflow
- Trigger
- Files / media
- AI & models
- Web / API
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 |
|---|---|---|---|
| When clicking ‘Test workflow’ | Trigger | Manual Trigger | See node parameters |
| Google Drive | Files / media | Google Drive | download |
| AI Agent | AI & models | Agent | See node parameters |
| When chat message received | Trigger | Chat Trigger | See node parameters |
| OpenAI Chat Model | AI & models | OpenAI Chat Model | See node parameters |
| Upload File | AI & models | Open Ai | file |
| Create Fine-tuning Job | Web / API | HTTP Request | POST |
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
googleDriveOAuth2ApihttpHeaderAuthopenAiApi
Workflow notes
Step 2
Step 2
Once the .jsonl file for training is uploaded (See the entire process here.: https://platform.openai.com/finetune/), a "new model" will be created and made available via your API. OpenAI will automatically train it based on the uploaded .jsonl file. If the training is successful, the new model will be accessible via API.
eg. ft:gpt-4o-mini-2024-07-18:n3w-italia::XXXXX7B
Step 1
Step 1
Create the training file .jsonl with the following syntax and upload it to Drive.
{"messages": [{"role": "system", "content": "You are an experienced and helpful travel assistant."}, {"role": "user", "content": "What documents are needed to travel to the United States?"}, {"role": "assistant", "content": "To travel to the United States, you will need a valid passport and an ESTA authorization, which you can apply for online. Make sure to check the specific requirements based on your nationality."}]} ....
The file will be uploaded here: https://platform.openai.com/storage/files
Fine-tuning with OpenAI models
Fine-tuning with OpenAI models
Purpose and structure
This folder contains the Fine-tuning with OpenAI models workflow. Its executable nodes use agent, chatTrigger, googleDrive, httpRequest, lmChatOpenAi, manualTrigger, openAi. 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’, 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/Manual/1863_Manual_HTTP_Automation_Webhook.json MIT; preserve source notices.