pdf extract from file and create airtable and text classifier
Configured with Airtable, Chain LLM, Extract From File, Form, and additional nodes. Review the connections and setup before adapting this template.
Node categories in this workflow
- Transform
- Data store
- AI & models
- Web / API
- Integration
- Trigger
- Code
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 |
|---|---|---|---|
| Extract from File | Transform | Extract From File | |
| Structured Output Parser | Transform | Output Parser Structured | See node parameters |
| Save to Airtable | Data store | Airtable | create |
| Classify Document | AI & models | Text Classifier | See node parameters |
| Upload File to Record | Web / API | HTTP Request | POST |
| Application Suitability Agent | AI & models | Chain LLM | See node parameters |
| File Upload Retry | Integration | Form | See node parameters |
| Google Gemini Chat Model1 | AI & models | LM Chat Google Gemini | See node parameters |
| Google Gemini Chat Model | AI & models | LM Chat Google Gemini | See node parameters |
| Step 1 of 2 - Upload Document | Trigger | Form Trigger | See node parameters |
| Split Files | Code | Function | See node parameters |
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
airtableTokenApigooglePalmApi
Workflow notes
1. Application Form To Upload Documents
1. Application Form To Upload Documents
Learn more the Form Trigger node
Our application process starts with a simple file upload to get the applicant's files for processing.
2. Document Classifier and ReUpload Form
2. Document Classifier and ReUpload Form
Read more about the Text Classifier
Form validation remains a critical step and before the introduction of LLMs, classifying document types was a relatively troublesome process. Today, n8n's text classifier node does an excellent job at this task.
Contextual validation powered by AI means invalid, unrelevant docs can be rejected as a quality check. When this happens in our workflow, we present the user again with the file upload form to retry.
3. Smarter Application Pre-fill with Relevant Context
3. Smarter Application Pre-fill with Relevant Context
Read more about the Basic LLM node
Information extraction is a logical next step once we have our PDF contents but we can extend further by only extracting data which is relevant.
To achieve this for this demo, we've give a detailed prompt to the LLM to compare the docs against. The provides the AI enough context to complete the task successfully.
4. Save to Applicant Tracking System
4. Save to Applicant Tracking System
Read more about the Airtable node
Next, we can complete our simple data capture by integrating and pushing data to our Applicant Tracking System.
Here, we're using Airtable because we can also store PDF files in our rows.
See our example Airtable here: https://airtable.com/appIhhPcGtnOr5YkL/tblb5tYXk4E2Ev4nO
pdf extract from file and create airtable and text classifier
pdf extract from file and create airtable and text classifier
Purpose and structure
This folder contains the pdf extract from file and create airtable and text classifier workflow. Its executable nodes use airtable, chainLlm, extractFromFile, form, formTrigger, function, httpRequest, lmChatGoogleGemini, outputParserStructured, textClassifier. 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
Step 1 of 2 - Upload Document
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/BikramMondal5/MagicFill/blob/3037cd5390c2e64e5d8414df6d9d413d57fa6625/resume.json MIT; preserve source notices.