graph TD %%{init: {'theme': 'mc','layout': 'elk'}}%% TextInput-7a156[<div><img alt="logo" src="/_astro/type.Dy26vmDy.svg" style="height: 20px !important;width: 20px !important"/></div>Instructions] style TextInput-7a156 stroke:#a170ff ChatOutput-ol8bm[<div><img alt="logo" src="/_astro/messages-square.BaSDmT6g.svg" style="height: 20px !important;width: 20px !important"/></div>Chat Output] style ChatOutput-ol8bm stroke:#a170ff OpenAIModel-d3ck8[<div><img alt="logo" src="/_astro/openAI.BhmuxEs3.svg" style="height: 20px !important;width: 20px !important"/></div>OpenAI] style OpenAIModel-d3ck8 stroke:#a170ff TextInput-cv9yq[<div><img alt="logo" src="/_astro/type.Dy26vmDy.svg" style="height: 20px !important;width: 20px !important"/></div>ImageURL] style TextInput-cv9yq stroke:#a170ff DescribeImage-kmqoa[<div><img alt="logo" src="/_astro/image.segxnpQg.svg" style="height: 20px !important;width: 20px !important"/></div>Describe Image] style DescribeImage-kmqoa stroke:#a170ff ParseData-7m4sd[<div><img alt="logo" src="/_astro/braces.Djq0PW4_.svg" style="height: 20px !important;width: 20px !important"/></div>DescriptionExtraction] style ParseData-7m4sd stroke:#a170ff OpenAIModel-d3ck8 -.- DescribeImage-kmqoa linkStyle 0 stroke:#a170ff TextInput-7a156 -.- DescribeImage-kmqoa linkStyle 1 stroke:#a170ff DescribeImage-kmqoa -.- ParseData-7m4sd linkStyle 2 stroke:#a170ff ParseData-7m4sd -.- ChatOutput-ol8bm linkStyle 3 stroke:#a170ff TextInput-cv9yq -.- DescribeImage-kmqoa linkStyle 4 stroke:#a170ff

Ticket to JSON Converter

🧩 Overview

The Ticket to JSON Converter automates the extraction of structured information from a visual ticket. By leveraging an AI model to interpret the image and transform the results into a JSON object, the workflow eliminates manual data entry and reduces error risk.

⚙️ Main Features

Accepts a text prompt defining extraction rules and an image URL in a single flow.
Uses a configurable OpenAI model to generate a natural‑language description of the ticket contents.
Parses the model output into a clean JSON structure following the provided schema.
Returns the final JSON via a chat‑style output for immediate display or downstream consumption.
Supports modular configuration of model parameters, prompt wording, and output formatting.

🔄 Workflow Steps

Component Name	Role in the Workflow	Key Inputs	Key Outputs
Text Input (Instructions)	Provides the extraction prompt that guides the AI.	Instruction text describing ticket format and required fields.	Prompt text for the next component.
Text Input (Image URL)	Supplies the image to be processed.	URL pointing to the ticket image.	Image reference passed to the image‑analysis step.
OpenAI Model	Generates a natural‑language description of the ticket using the configured LLM.	Model name, prompt text, and image reference.	Structured description of the image content.
Describe Image	Feeds the image and prompt to the AI model, producing a descriptive text.	Image data, prompt, and LLM reference.	Data object containing the image description.
Parse Data	Formats the description into a plain‑text message using a template.	Image description, template string, and separator.	Text representation of the parsed information.
Chat Output	Presents the final JSON to the user or downstream system.	Parsed text (JSON string).	Displayed message containing the structured data.

🧠 Notes

The OpenAI model requires a valid API key and may incur usage costs depending on token consumption.
The image URL must be publicly accessible; otherwise, the describe image component will fail to fetch the content.
The prompt supplied in the first Text Input must explicitly include the JSON structure expected in the final output; otherwise, the AI may produce non‑JSON text.
The workflow assumes the ticket image contains clear, legible text; heavily distorted or low‑resolution images may lead to incomplete extraction.
The Chat Output component displays the result as a simple chat message; additional post‑processing steps can be added if integration with other systems is required.