AI-Powered Claim Verification with Ollama
detail.loadingPreview
Automate the crucial task of fact-checking and claim verification using AI. This n8n workflow intelligently breaks down text into individual claims, then leverages a local Ollama LLM to verify each claim against a provided set of factual documents, highlighting any unsupported statements.
About This Workflow
This powerful n8n workflow revolutionizes your content verification process by integrating advanced AI capabilities. It efficiently dissects an input text into its constituent sentences, treating each as a distinct claim. These claims are then meticulously cross-referenced against a comprehensive reference document (your 'facts') using a customizable Large Language Model powered by Ollama. The workflow is designed to automatically identify and filter out any claims that lack factual support from your provided context. Ideal for ensuring accuracy in reports, articles, or any content requiring rigorous verification, this solution brings robust fact-checking directly into your automated workflows.
Key Features
- Intelligent Sentence Segmentation: Precisely splits complex texts into individual sentences, preserving critical elements like dates and list items for accurate claim isolation.
- Local LLM Integration (Ollama): Utilizes your self-hosted Ollama instance and a specialized
bespoke-minicheckmodel for secure and private claim verification. - Contextual Fact-Checking: Compares each isolated claim against a provided 'facts' document to determine its veracity or support.
- Automated Unverified Claim Identification: Automatically filters and outputs only the claims that are not supported by the reference material.
- Scalable Verification: Process documents of varying lengths, ensuring consistent and automated accuracy checks.
How To Use
- Configure Ollama: Ensure you have Ollama installed and a model named
bespoke-minicheck:latestavailable. You might need to pull or create this custom model. - Set Ollama Credentials: In the 'Ollama Chat Model' node, update the 'Ollama account' credential with your Ollama API endpoint.
- Provide Input Data:
- If triggered manually (for testing): Update the 'Edit Fields' node with your
facts(the reference document) andtext(the content to be verified). - If triggered by another workflow: Ensure the triggering workflow passes
factsandtextas inputs to this workflow.
- If triggered manually (for testing): Update the 'Edit Fields' node with your
- Review LLM Chain: The 'Basic LLM Chain' node defines the prompt for the LLM. You might adjust the prompt based on your specific verification needs if the
bespoke-minicheckmodel expects a different input format or if you're using a generic model. - Adjust Filter (Optional): The 'Filter' node is set to identify claims where the LLM's response contains "No". If your LLM returns a different indicator for unsupported claims, update the filter condition accordingly.
Apps Used
Workflow JSON
{
"id": "daef0c57-7a2d-4256-ae82-c7a02f86799c",
"name": "AI-Powered Claim Verification with Ollama",
"nodes": 9,
"category": "Operations",
"status": "active",
"version": "1.0.0"
}Note: This is a sample preview. The full workflow JSON contains node configurations, credentials placeholders, and execution logic.
Get This Workflow
ID: daef0c57-7a2d...
About the Author
SaaS_Connector
Integration Guru
Connecting CRM, Notion, and Slack to automate your life.
Statistics
Related Workflows
Discover more workflows you might like
Google Sheets to Icypeas: Automated Bulk Domain Scanning
This workflow streamlines the process of performing bulk domain scans by integrating your Google Sheets data directly with the Icypeas platform. Automate the submission of company names from your spreadsheet to Icypeas for comprehensive domain information, saving valuable time and effort.
Instant WooCommerce Order Notifications via Telegram
When a new order is placed on your WooCommerce store, instantly receive detailed notifications directly to your Telegram chat. Stay on top of your e-commerce operations with real-time alerts, including order specifics and a direct link to view the order.
On-Demand Microsoft SQL Query Execution
This workflow allows you to manually trigger and execute any SQL query against your Microsoft SQL Server database. Perfect for ad-hoc data lookups, administrative tasks, or quick tests, giving you direct control over your database operations.