Ai connect pro_05_XMP generation for image_ChatGPT
Flow
Created at 1/28/2025 8:32 AM
Ai connect pro_05_XMP generation for image_ChatGPT
191
No
35
E:/BlueWest/98-Utilitaires/Grille Switch.png
E:/BlueWest/bitBucketFolder/ai-connect-pro/Images/Ai-connect-+-gpt.png
C:/Users/tdesc/Pictures/gpt.png
No
No
00:00
00:00
No
Monday
Sunday
No
1
Start of the month
205
ProblemFilesFolder
producer
Filter
One
Problem jobs
This flow only
Default
10
10
80
224
Folder
folder
-
#automanaged#
No
Default
No
00:00
00:00
No
Monday
Sunday
No
1
Start of the month
#808080
No
No
Yes
Yes
Overwrite
1
No
No Folders
No
80
304
Folder
folder
GPT response
#automanaged#
No
Default
No
00:00
00:00
No
Monday
Sunday
No
1
Start of the month
#808080
No
No
Yes
Yes
Overwrite
1
No
No Folders
No
272
224
createLog
processor
TrafficLight
Create log
368
304
Default
Default
Yes
Unlimited
XMP
[Metadata.Text:Dataset="AIconnect",Model="JSON",Path="/0/message/content"]
####
%%%%
utf8
Folder
folder
-
#automanaged#
No
Default
No
00:00
00:00
No
Monday
Sunday
No
1
Start of the month
#808080
No
No
Yes
Yes
Overwrite
1
No
No Folders
No
464
304
TrafficLight
xmp
0
158
160
Gray
Data with log
xmp
No
Yes
Yes
Yes
Folder
folder
XMP
#automanaged#
No
Default
No
00:00
00:00
No
Monday
Sunday
No
1
Start of the month
#808080
No
No
Yes
Yes
Overwrite
1
No
No Folders
No
464
224
TrafficLight
-90
158
163
Gray
Log
Log
No
Yes
Yes
Yes
XMP inject
processor
TrafficLight
XMP inject
560
304
Yes
Unlimited
Inject XMP
xmp
Yes
Filter
0
160
165
Gray
No
All Files
No Files
Folder
folder
-
#automanaged#
No
Default
No
00:00
00:00
No
Monday
Sunday
No
1
Start of the month
#808080
No
No
Yes
Yes
Overwrite
1
No
No Folders
No
656
304
TrafficLight
0
165
167
Gray
Data
Log
No
Yes
Yes
Set hierarchy path
processor
Move
Set hierarchy path
752
304
Default
Default
0
Default
Yes
One
Replace
[Metadata.Text:Dataset="xmp",Model="XMP",Path="xmp:brand"]/[Metadata.Text:Dataset="xmp",Model="XMP",Path="custom:productLine"]
1
0
ArchiveHierarchy
processor
TrafficLight
Yes
Unlimited
Archive hierarchy is a folder-like consumer that supports one
or more levels of subfolders. It is used to archive files into
a structured hierarchy at the end of a flow.
Basics
0500000000
backing folder subfolder structure output
Archive hierarchy
#automanaged#
99
Yes
Yes
Overwrite
1
944
304
Filter
0
167
170
Gray
No
All Files
No Files
Folder
folder
-
#automanaged#
No
Default
No
00:00
00:00
No
Monday
Sunday
No
1
Start of the month
#808080
No
No
Yes
Yes
Overwrite
1
No
No Folders
No
848
304
Move
0
170
173
Gray
No
Filter
0
173
171
Gray
No
All Files
No Files
Folder
folder
Set your API key
#automanaged#
No
Default
No
00:00
00:00
No
Monday
Sunday
No
1
Start of the month
Magenta
No
No
Yes
Yes
Overwrite
1
No
No Folders
No
176
384
ai-connect-pro
processor
TrafficLight
AI connect_PRO
176
304
Default
Default
Yes
Unlimited
OpenAI
Text completion
dall-e-2
Vivid
Standard
256x256
1024x1024
a photo of a happy corgi puppy sitting and facing forward, studio light, longshot
1
gpt-4o
You are assisting with digital asset management in a creative production workflow.
Analyze the provided image and return the metadata formatted as valid **XMP** (Extensible Metadata Platform) XML.
Include:
- Title (dc:title)
- Brand (xmp:brand)
- productLine (xmp:productLine)
- Description (dc:description)
- Tags/keywords (dc:subject)
- Usage suggestion (xmp:usage)
- Color theme (xmp:colorTheme)
- Dominant mood (xmp:mood)
Respond only with the XMP block, using the appropriate namespaces. Format for embedding in image metadata or DAM systems.
Use terminology familiar to creative, marketing, and print professionals.
Output strict XMP only, no plain text or line breaks
DO NOT add markdown wrapper
Example Output (XMP format):
<x:xmpmeta xmlns:x="adobe:ns:meta/"
xmlns:dc="http://purl.org/dc/elements/1.1/"
xmlns:xmp="http://ns.adobe.com/xap/1.0/"
xmlns:photoshop="http://ns.adobe.com/photoshop/1.0/"
xmlns:xmpMM="http://ns.adobe.com/xap/1.0/mm/"
xmlns:custom="http://ns.example.com/custom/1.0/">
<rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#">
<rdf:Description rdf:about="">
<dc:title>
<rdf:Alt>
<rdf:li xml:lang="x-default">LEGO City police chase scene</rdf:li>
</rdf:Alt>
</dc:title>
<xmp:brand>LEGO</xmp:brand>
<custom:productLine>LEGO City</custom:SubBrand>productLine
<dc:description>
<rdf:Alt>
<rdf:li xml:lang="x-default">An action-packed LEGO City scene featuring a high-speed police pursuit through urban streets, appealing to children and collectors alike.</rdf:li>
</rdf:Alt>
</dc:description>
<dc:subject>
<rdf:Bag>
<rdf:li>LEGO</rdf:li>
<rdf:li>LEGO City</rdf:li>
<rdf:li>police</rdf:li>
<rdf:li>toys</rdf:li>
<rdf:li>kids</rdf:li>
<rdf:li>action</rdf:li>
</rdf:Bag>
</dc:subject>
<xmp:usage>Retail packaging, product catalog, e-commerce listing, promotional posters</xmp:Usage>
<xmp:colorTheme>primary colors</xmp:ColorTheme>
<xmp:mood>energetic</xmp:Mood>
</rdf:Description>
</rdf:RDF>
</x:xmpmeta>
0.5
1.0
alloy
mp3
Current
en
0
json
http://localhost:7869/
Text completion
Tell
gemma:2b
0
Text completion
You are an expert assistant from MyPrintingCompany.com a printing company, helping with customer communication. You will receive two input files:
- An XML file that contains all information about a printed product (e.g., paper type, size, deadlines, invoice/bill info, contact details).
- A Pitstop preflight report file that details the technical results of the PDF preflight check.
Your task is to:
- Read and understand the relevant data from both files.
- Generate an HTML email body only (no subject, no headers).
Instruction for the HTML content :
- Translate it in [Metadata.Text:Dataset="Submit",Model="XML",Path="/field-list/field[tag='Language']/value"]
- Add at the top a greeting to the customer (refer to the XML file for contact)
- Follow with a reminder of the order name and a summary block (in a table format) showing key production details from the XML.
- Summarize the preflight report using clear, non-technical language intended for someone not used to printer related terminlogy.
- Errors are critical and mean the file is not suitable for print — highlight these in red.
- Warnings are advisory and up to the customer to accept — highlight these in orange.
- If there are no errors or warnings, briefly confirm the file is ready for print.
Display the preflight results in a table format, listing:
- Type (Error or Warning)
- Description (
- Page number (if available)
- Include helpful suggestions for resolving issue
- Add a button with the review link that should lead the customer to this web page : https://www.enfocus.com/en/review
- Below the button, add a short message telling the customer to click the button to make an approval decision.
Formatting :
- Output the body of the HTML only, as a single line (no line breaks, no \n or \r).
- Do not escape characters.
- Use single quotes (') instead of double quotes (").
- Do not include any plain text explanation or mardown element — only the final body HTML output.
mistral-large-2411
0
store_name=The name of the store or merchant transaction_date=Date and time of the purchase total_amount:number=Total amount paid including tax tax_amount?:number=Tax amount applied (if shown) payment_method=Method of payment (e.g., Visa, cash) address?:string=Store address if available
Yes
Yes
No
json
No
TrafficLight
-90
187
148
Gray
Log
Log
No
Yes
Yes
Yes
Filter
0
156
187
Gray
No
All Files
No Files
Folder
folder
-
#automanaged#
No
Default
No
00:00
00:00
No
Monday
Sunday
No
1
Start of the month
#808080
No
No
Yes
Yes
Overwrite
1
No
No Folders
No
272
304
Filter
0
2
158
Gray
No
All Files
No Files
TrafficLight
0
187
2
Gray
Data with log
AIconnect
No
Yes
Yes
Yes
Filter
0
93
187
Gray
No
All Files
No Files