Icon

Car Insurance Claims

<p>This workflow demonstrates how to <strong>prompt an LLM using both text and images.</strong></p><p>Textual data from insurance claims and corresponding accident images are imported, combined into row-wise multimodal prompts, and sent to a connected LLM. The model then returns a severity assessment for each accident based on both the text and image inputs.</p>

Set up the OpenAI API key, authenticate, and select the LLM

For each claim, sendthe multimodal prompt to an LLM to assess severity

多模态- 汽车保险评估

这项工作流程展示了如何使用文本和图像同时向大型语言模型（LLM）发出提示，以评估车祸的严重程度。

来自保险理赔的文本数据与相应的事故图像被导入，并组合成按行排列的多模态提示，随后发送至连接的语言模型。模型根据文本和图像输入，为每起事故返回相应的严重程度评估

Import textual data (car accident insurance claims) and images (accident images)and combine them into a multimodal prompt

证明 LLM 是从图片中获得的信息，而不是文字提示

LLM 直接描述 图片中的信息

Path to URI
Combine insuranceclaims and accidentimages into a messagefor the prompt
Message Creator
Insurance claims& accident imagepaths
Table Reader
OpenAI Authenticator
View the resultsof the LLM analysis
Table View
Prompt an LLM withboth text and images
LLM Prompter
Import imagesfrom paths tothe table
Read Images
Table View
OpenAI LLM Selector
only the pictures
Message Creator
Credentials Configuration
only the pictures
Message Creator
Prompt an LLM withboth text and images
LLM Prompter
Prompt an LLM withboth text and images
LLM Prompter
View the resultsof the LLM analysis
Table View

Nodes

Extensions

Links

Download

To use this workflow in KNIME, download it from the below URL and open it in KNIME:

Download Workflow
Created by: Keerthan M Shetty
Created at: 2025-06-18
On NodePit since: 2025-09-30
Last update: 2025-09-30
Created with KNIME version: v5.7.0
Tags: AIGenAILLMeducationmultimodal prompt

Deploy, schedule, execute, and monitor your KNIME workflows locally, in the cloud or on-premises – with our brand new NodePit Runner.

Try NodePit Runner!