-
Notifications
You must be signed in to change notification settings - Fork 17
/
Copy pathcatalog.yaml
124 lines (112 loc) · 8.7 KB
/
catalog.yaml
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
apiVersion: v1
schemas:
# document
- domain: document.bank-statement
schema: vlmrun.hub.schemas.document.bank_statement.BankStatement
prompt: "You are a diligent bank statement analyzer. Extract all the relevant information from the statement as accurately as possible."
description: "Bank statement data extraction system that processes bank statements to extract structured financial transaction information including account details, balances, and transaction history."
sample_data: "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/document.bank-statement/lending_bankstatement.pdf"
metadata:
supported_inputs: ["image", "document"]
tags: ["finance", "banking", "work"]
- domain: document.invoice
schema: vlmrun.hub.schemas.document.invoice.Invoice
prompt: "You are a detail-oriented invoice analyst. Extract all the relevant information from the candidate's invoice as accurately as possible."
description: "Comprehensive invoice data extraction system that processes invoice images to extract structured information including invoice metadata, customer details, line items, and financial totals."
sample_data: "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/document.invoice/invoice_1.jpg"
metadata:
supported_inputs: ["image", "document"]
tags: ["finance", "work"]
- domain: document.receipt
schema: vlmrun.hub.schemas.document.receipt.Receipt
prompt: "You are a detail-oriented receipt analyst. Extract all the relevant information from the receipt as accurately as possible."
description: "Receipt data extraction system that processes receipt images to extract structured information including transaction details, merchant information, and financial totals."
sample_data: "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/document.receipt/sample_receipt.webp"
metadata:
supported_inputs: ["image", "document"]
tags: ["finance", "work"]
- domain: document.resume
schema: vlmrun.hub.schemas.document.resume.Resume
prompt: "You are a detail-oriented technical resume analyst. Extract all the relevant information from the candidate's resume as accurately as possible."
description: "Resume data extraction system that processes resume images to extract structured information including contact details, education, work experience, skills, and additional sections."
sample_data: "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/document.resume/fake-resume.webp"
metadata:
supported_inputs: ["image", "document"]
tags: ["work", "hr"]
- domain: document.us-drivers-license
schema: vlmrun.hub.schemas.document.us_drivers_license.USDriversLicense
prompt: "You are a detail-oriented document analyst. Extract all the relevant information from the candidate's driver's license as accurately as possible."
description: "Driver's license information extraction system that processes driver's license images to extract structured information including name, address, date of birth, and license details."
sample_data: "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/document.us-drivers-license/dl3.jpg"
metadata:
supported_inputs: ["image", "document"]
tags: ["work", "identity"]
- domain: document.utility-bill
schema: vlmrun.hub.schemas.document.utility_bill.UtilityBill
prompt: "You are a detail-oriented utility bill analyst. Extract all the relevant information from the utility bill as accurately as possible."
description: "Utility bill data extraction system that processes utility bill images to extract structured information including account details, billing period, charges, and payment information."
sample_data: "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/document.utility-bill/utility-bill-example.webp"
metadata:
supported_inputs: ["image", "document"]
tags: ["energy"]
- domain: document.w2-form
schema: vlmrun.hub.schemas.document.w2_form.W2Form
prompt: "You are a detail-oriented tax document analyst. Extract all the relevant information from the W-2 form as accurately as possible."
description: "W-2 form data extraction system that processes Form W-2 (Wage and Tax Statement) to extract structured information including employee details, employer information, wages, and tax withholding data."
sample_data: "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/document.w2-form/w2-form.jpg"
metadata:
supported_inputs: ["image", "document"]
tags: ["finance", "work", "hr"]
# industry: aerospace
- domain: aerospace.remote-sensing
schema: vlmrun.hub.schemas.aerospace.remote_sensing.RemoteSensing
prompt: "You are a detail-oriented remote sensing analyst. Analyze this satellite image to identify and categorize land features, infrastructure, and environmental elements. Note any significant objects and assess visibility conditions as accurately as possible."
description: "Satellite image analysis system for identifying and categorizing geographical features, infrastructure, and environmental elements from aerial imagery."
sample_data: "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/aerospace.remote-sensing/planet_labs_port.jpg"
metadata:
supported_inputs: ["image", "video"]
tags: ["aerospace"]
# industry: healthcare
- domain: healthcare.medical-insurance-card
schema: vlmrun.hub.schemas.healthcare.medical_insurance_card.MedicalInsuranceCard
prompt: "You are a detail-oriented document analyst. Extract all the relevant information from the candidate's medical insurance card as accurately as possible."
description: "Medical insurance card information extraction system that processes insurance card images to extract comprehensive coverage details, member information, and provider data."
sample_data: "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/healthcare.medical-insurance-card/blue_cross_example.jpg"
metadata:
supported_inputs: ["image", "document"]
tags: ["healthcare", "work"]
# industry: retail
- domain: retail.ecommerce-product-caption
schema: vlmrun.hub.schemas.retail.ecommerce_product_caption.RetailEcommerceProductCaption
prompt: "You are a detail-oriented product analyst. Extract all the relevant product information from the image as accurately as possible."
description: "Product data extraction system that processes product images to extract structured information including visual description, product details, and delivery information."
sample_data: "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/retail.ecommerce-product-caption/Electronics%20-%20Kindle.webp"
metadata:
supported_inputs: ["image"]
tags: ["retail", "ecommerce"]
# industry: media
- domain: media.tv-news
schema: vlmrun.hub.schemas.media.tv_news.TVNews
prompt: "You are a detail-oriented TV news analyst. Extract relevant news broadcast information as accurately as possible."
description: "TV news data extraction system that processes news footage or screenshots to extract structured information such as headlines, anchors, and on-screen text."
sample_data: "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/media.tv-news/bbc_news_ukraine_screenshot.jpg"
metadata:
supported_inputs: ["image", "video"]
tags: ["media", "news"]
# document: us-passport
- domain: document.us-passport
schema: vlmrun.hub.schemas.contrib.document.us_passport.USPassport
prompt: "You are a detail-oriented passport document analyst. Extract all the relevant information from the US passport as accurately as possible."
description: "US passport data extraction system that processes passport images to extract structured information including personal details, document identifiers, and biometric data."
sample_data: "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/document.us-passport/2020-Next-Gen-US-Passport.png"
metadata:
supported_inputs: ["image", "document"]
tags: ["identity", "travel", "document"]
- domain: retail.product-catalog
schema: vlmrun.hub.schemas.retail.product_catalog.ProductCatalog
prompt: You are a detail-oriented product catalog agent. Extract all the relevant fields in this image as accurately as possible.
description: "Gain a competitive edge with real-time analytics from product catalog, helping you track trending topics, public sentiment, and influential quotes that shape audience perspectives.."
sample_data: "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/retail.product-catalog/fashion_small.jpg"
metadata:
supported_inputs: ["image"]
tags: ["retail", "product-catalog"]