Resize, sharpen, and compress an image to fit email platform size limits in a single pipeline.
中文简介正在准备中。当前显示原文说明。
iterationlayer/skills42026年6月9日 更新
免费在 GitHub 公开
extract-property-appraisal
Extract appraised value, property details, and comparable sales from a property appraisal report into structured JSON.
中文简介正在准备中。当前显示原文说明。
集成工具n8n
查看安装方法包含的文件（1）
- SKILL.md18.1 KB
SKILL.md（原文）
安装前可以查看交给 AI 代理的指令内容。
Extract Property Appraisal
Mortgage lenders, real estate platforms, and appraisal management companies use this recipe to digitize appraisal reports. Upload an appraisal PDF and receive structured JSON with the appraised value, property details, and comparable sales — ready to feed into your loan origination system or valuation database.
APIs Used
Document Extraction (1 credit per page)
Prerequisites
You need an Iteration Layer API key. Get one at platform.iterationlayer.com during the 7-day trial.
For full integration guidance (SDKs, auth, MCP, error handling), see the Iteration Layer Integration Guide.
Implementation
curl -X POST https://api.iterationlayer.com/document-extraction/v1/extract \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"files": [
{
"type": "url",
"name": "appraisal.pdf",
"url": "https://example.com/appraisals/2026-0042.pdf"
}
],
"schema": {
"fields": [
{
"name": "subject_address",
"type": "ADDRESS",
"description": "Address of the subject property being appraised"
},
{
"name": "appraised_value",
"type": "CURRENCY_AMOUNT",
"description": "Final appraised market value of the property"
},
{
"name": "effective_date",
"type": "DATE",
"description": "Date of the appraisal"
},
{
"name": "property_type",
"type": "ENUM",
"description": "Type of property",
"values": ["single_family", "condo", "multi_family", "commercial", "land"],
"max_selected": 1
},
{
"name": "gross_living_area_sqft",
"type": "INTEGER",
"description": "Gross living area in square feet"
},
{
"name": "year_built",
"type": "INTEGER",
"description": "Year the property was built"
},
{
"name": "bedrooms",
"type": "INTEGER",
"description": "Number of bedrooms"
},
{
"name": "bathrooms",
"type": "DECIMAL",
"description": "Number of bathrooms",
"decimal_points": 1
},
{
"name": "comparable_sales",
"type": "ARRAY",
"description": "Comparable sales used in the appraisal",
"fields": [
{
"name": "address",
"type": "ADDRESS",
"description": "Address of the comparable property"
},
{
"name": "sale_price",
"type": "CURRENCY_AMOUNT",
"description": "Sale price of the comparable"
},
{
"name": "sale_date",
"type": "DATE",
"description": "Date of the comparable sale"
},
{
"name": "gross_living_area_sqft",
"type": "INTEGER",
"description": "Gross living area of the comparable in square feet"
}
]
}
]
}
}'
import { IterationLayer } from "iterationlayer";
const client = new IterationLayer({ apiKey: "YOUR_API_KEY" });
const result = await client.extractDocument({
files: [
{
type: "url",
name: "appraisal.pdf",
url: "https://example.com/appraisals/2026-0042.pdf",
},
],
schema: {
fields: [
{
name: "subject_address",
type: "ADDRESS",
description: "Address of the subject property being appraised",
},
{
name: "appraised_value",
type: "CURRENCY_AMOUNT",
description: "Final appraised market value of the property",
},
{
name: "effective_date",
type: "DATE",
description: "Date of the appraisal",
},
{
name: "property_type",
type: "ENUM",
description: "Type of property",
values: [
"single_family",
"condo",
"multi_family",
"commercial",
"land",
],
max_selected: 1,
},
{
name: "gross_living_area_sqft",
type: "INTEGER",
description: "Gross living area in square feet",
},
{
name: "year_built",
type: "INTEGER",
description: "Year the property was built",
},
{
name: "bedrooms",
type: "INTEGER",
description: "Number of bedrooms",
},
{
name: "bathrooms",
type: "DECIMAL",
description: "Number of bathrooms",
decimal_points: 1,
},
{
name: "comparable_sales",
type: "ARRAY",
description: "Comparable sales used in the appraisal",
fields: [
{
name: "address",
type: "ADDRESS",
description: "Address of the comparable property",
},
{
name: "sale_price",
type: "CURRENCY_AMOUNT",
description: "Sale price of the comparable",
},
{
name: "sale_date",
type: "DATE",
description: "Date of the comparable sale",
},
{
name: "gross_living_area_sqft",
type: "INTEGER",
description: "Gross living area of the comparable in square feet",
},
],
},
],
},
});
from iterationlayer import IterationLayer
client = IterationLayer(api_key="YOUR_API_KEY")
result = client.extract_document(
files=[
{
"type": "url",
"name": "appraisal.pdf",
"url": "https://example.com/appraisals/2026-0042.pdf",
}
],
schema={
"fields": [
{
"name": "subject_address",
"type": "ADDRESS",
"description": "Address of the subject property being appraised",
},
{
"name": "appraised_value",
"type": "CURRENCY_AMOUNT",
"description": "Final appraised market value of the property",
},
{
"name": "effective_date",
"type": "DATE",
"description": "Date of the appraisal",
},
{
"name": "property_type",
"type": "ENUM",
"description": "Type of property",
"values": ["single_family", "condo", "multi_family", "commercial", "land"],
"max_selected": 1,
},
{
"name": "gross_living_area_sqft",
"type": "INTEGER",
"description": "Gross living area in square feet",
},
{
"name": "year_built",
"type": "INTEGER",
"description": "Year the property was built",
},
{
"name": "bedrooms",
"type": "INTEGER",
"description": "Number of bedrooms",
},
{
"name": "bathrooms",
"type": "DECIMAL",
"description": "Number of bathrooms",
"decimal_points": 1,
},
{
"name": "comparable_sales",
"type": "ARRAY",
"description": "Comparable sales used in the appraisal",
"fields": [
{
"name": "address",
"type": "ADDRESS",
"description": "Address of the comparable property",
},
{
"name": "sale_price",
"type": "CURRENCY_AMOUNT",
"description": "Sale price of the comparable",
},
{
"name": "sale_date",
"type": "DATE",
"description": "Date of the comparable sale",
},
{
"name": "gross_living_area_sqft",
"type": "INTEGER",
"description": "Gross living area of the comparable in square feet",
},
],
},
]
},
)
package main
import il "github.com/iterationlayer/sdk-go"
func main() {
client := il.NewClient("YOUR_API_KEY")
result, err := client.ExtractDocument(il.ExtractDocumentRequest{
Files: []il.FileInput{
il.FileInput{
Type: "url",
Name: "appraisal.pdf",
Url: "https://example.com/appraisals/2026-0042.pdf",
},
},
Schema: il.ExtractionSchema{
Fields: []any{
il.AddressFieldConfig{
Name: "subject_address",
Type: "ADDRESS",
Description: "Address of the subject property being appraised",
},
il.CurrencyAmountFieldConfig{
Name: "appraised_value",
Type: "CURRENCY_AMOUNT",
Description: "Final appraised market value of the property",
},
il.DateFieldConfig{
Name: "effective_date",
Type: "DATE",
Description: "Date of the appraisal",
},
il.EnumFieldConfig{
Name: "property_type",
Type: "ENUM",
Description: "Type of property",
Values: []string{"single_family", "condo", "multi_family", "commercial", "land"},
MaxSelected: 1,
},
il.IntegerFieldConfig{
Name: "gross_living_area_sqft",
Type: "INTEGER",
Description: "Gross living area in square feet",
},
il.IntegerFieldConfig{
Name: "year_built",
Type: "INTEGER",
Description: "Year the property was built",
},
il.IntegerFieldConfig{
Name: "bedrooms",
Type: "INTEGER",
Description: "Number of bedrooms",
},
il.DecimalFieldConfig{
Name: "bathrooms",
Type: "DECIMAL",
Description: "Number of bathrooms",
},
il.ArrayFieldConfig{
Name: "comparable_sales",
Type: "ARRAY",
Description: "Comparable sales used in the appraisal",
Fields: []any{
il.AddressFieldConfig{
Name: "address",
Type: "ADDRESS",
Description: "Address of the comparable property",
},
il.CurrencyAmountFieldConfig{
Name: "sale_price",
Type: "CURRENCY_AMOUNT",
Description: "Sale price of the comparable",
},
il.DateFieldConfig{
Name: "sale_date",
Type: "DATE",
Description: "Date of the comparable sale",
},
il.IntegerFieldConfig{
Name: "gross_living_area_sqft",
Type: "INTEGER",
Description: "Gross living area of the comparable in square feet",
},
},
},
},
},
})
if err != nil {
panic(err)
}
_ = result
}
{
"name": "Extract Property Appraisal",
"nodes": [
{
"parameters": {
"content": "## Extract Property Appraisal\n\nMortgage lenders, real estate platforms, and appraisal management companies use this recipe to digitize appraisal reports. Upload an appraisal PDF and receive structured JSON with the appraised value, property details, and comparable sales \u2014 ready to feed into your loan origination system or valuation database.\n\n**Note:** This workflow uses the Iteration Layer community node (`n8n-nodes-iterationlayer`). Install it via Settings > Community Nodes on self-hosted n8n, or add it directly on n8n Cloud with Verified Community Nodes enabled.",
"height": 280,
"width": 500,
"color": 2
},
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
200,
40
],
"id": "18c9143e-4361-4a50-952b-dda14da53749",
"name": "Overview"
},
{
"parameters": {
"content": "### Step 1: Extract Data\nResource: **Document Extraction**\n\nConfigure the Document Extraction parameters below, then connect your credentials.",
"height": 160,
"width": 300,
"color": 6
},
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
475,
100
],
"id": "163e4817-e901-4199-b290-9f0674a62a3d",
"name": "Step 1 Note"
},
{
"parameters": {},
"type": "n8n-nodes-base.manualTrigger",
"typeVersion": 1,
"position": [
250,
300
],
"id": "e7f8a9b0-c1d2-3456-efab-567890123efa",
"name": "Manual Trigger"
},
{
"parameters": {
"resource": "documentExtraction",
"schemaInputMode": "rawJson",
"schemaJson": "{\"fields\":[{\"name\":\"subject_address\",\"type\":\"ADDRESS\",\"description\":\"Address of the subject property being appraised\"},{\"name\":\"appraised_value\",\"type\":\"CURRENCY_AMOUNT\",\"description\":\"Final appraised market value of the property\"},{\"name\":\"effective_date\",\"type\":\"DATE\",\"description\":\"Date of the appraisal\"},{\"name\":\"property_type\",\"type\":\"ENUM\",\"description\":\"Type of property\",\"values\":[\"single_family\",\"condo\",\"multi_family\",\"commercial\",\"land\"],\"max_selected\":1},{\"name\":\"gross_living_area_sqft\",\"type\":\"INTEGER\",\"description\":\"Gross living area in square feet\"},{\"name\":\"year_built\",\"type\":\"INTEGER\",\"description\":\"Year the property was built\"},{\"name\":\"bedrooms\",\"type\":\"INTEGER\",\"description\":\"Number of bedrooms\"},{\"name\":\"bathrooms\",\"type\":\"DECIMAL\",\"description\":\"Number of bathrooms\",\"decimal_points\":1},{\"name\":\"comparable_sales\",\"type\":\"ARRAY\",\"description\":\"Comparable sales used in the appraisal\",\"fields\":[{\"name\":\"address\",\"type\":\"ADDRESS\",\"description\":\"Address of the comparable property\"},{\"name\":\"sale_price\",\"type\":\"CURRENCY_AMOUNT\",\"description\":\"Sale price of the comparable\"},{\"name\":\"sale_date\",\"type\":\"DATE\",\"description\":\"Date of the comparable sale\"},{\"name\":\"gross_living_area_sqft\",\"type\":\"INTEGER\",\"description\":\"Gross living area of the comparable in square feet\"}]}]}",
"files": {
"fileValues": [
{
"fileInputMode": "url",
"fileName": "appraisal.pdf",
"fileUrl": "https://example.com/appraisals/2026-0042.pdf"
}
]
}
},
"type": "n8n-nodes-iterationlayer.iterationLayer",
"typeVersion": 1,
"position": [
500,
300
],
"id": "f8a9b0c1-d2e3-4567-fabc-678901234fab",
"name": "Extract Data",
"credentials": {
"iterationLayerApi": {
"id": "1",
"name": "Iteration Layer API"
}
}
}
],
"connections": {
"Manual Trigger": {
"main": [
[
{
"node": "Extract Data",
"type": "main",
"index": 0
}
]
]
}
},
"settings": {
"executionOrder": "v1"
}
}
Extract property appraisal data from the file at [file URL]. Use the extract_document tool with these fields:
- subject_address (ADDRESS): Address of the subject property being appraised
- appraised_value (CURRENCY_AMOUNT): Final appraised market value
- effective_date (DATE): Date of the appraisal
- property_type (ENUM): Type of property (single_family, condo, multi_family, commercial, land)
- gross_living_area_sqft (INTEGER): Gross living area in square feet
- year_built (INTEGER): Year the property was built
- bedrooms (INTEGER): Number of bedrooms
- bathrooms (DECIMAL): Number of bathrooms
- comparable_sales (ARRAY): Each with address (ADDRESS), sale_price (CURRENCY_AMOUNT), sale_date (DATE), gross_living_area_sqft (INTEGER)
Response
{
"success": true,
"data": {
"subject_address": {
"value": {
"street": "412 Ridgewood Lane",
"city": "Denver",
"region": "CO",
"postal_code": "80203",
"country": "US"
},
"confidence": 0.98,
"citations": ["412 Ridgewood Lane, Denver, CO 80203"]
},
"appraised_value": {
"value": { "amount": "685000.00", "currency": "USD" },
"confidence": 0.97,
"citations": ["Market Value Opinion: $685,000"]
},
"effective_date": {
"value": "2026-03-15",
"confidence": 0.99,
"citations": ["Effective Date: March 15, 2026"]
},
"property_type": {
"value": ["single_family"],
"confidence": 0.99,
"citations": ["Single Family Residence"]
},
"gross_living_area_sqft": {
"value": 2140,
"confidence": 0.97,
"citations": ["GLA: 2,140 sq ft"]
},
"year_built": {
"value": 1998,
"confidence": 0.99,
"citations": ["Year Built: 1998"]
},
"bedrooms": {
"value": 4,
"confidence": 0.99,
"citations": ["Bedrooms: 4"]
},
"bathrooms": {
"value": 2.5,
"confidence": 0.98,
"citations": ["Bathrooms: 2.5"]
},
"comparable_sales": {
"value": [
{
"address": {
"value": {
"street": "388 Ridgewood Lane",
"city": "Denver",
"region": "CO",
"postal_code": "80203",
"country": "US"
},
"confidence": 0.96,
"citations": ["388 Ridgewood Lane, Denver, CO 80203"]
},
"sale_price": {
"value": { "amount": "672000.00", "currency": "USD" },
"confidence": 0.97,
"citations": ["Sale Price: $672,000"]
},
"sale_date": {
"value": "2026-01-20",
"confidence": 0.98,
"citations": ["Date of Sale: 01/20/2026"]
},
"gross_living_area_sqft": {
"value": 2090,
"confidence": 0.96,
"citations": ["GLA: 2,090"]
}
}
],
"confidence": 0.96,
"citations": []
}
}
}
Links
评价
还没有评价。欢迎分享你的使用感受。
评论
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
同一仓库的技能
Compress an image to fit within a specific file size in bytes using quality-first compression.
中文简介正在准备中。当前显示原文说明。
iterationlayer/skills42026年6月9日 更新
Convert a contract PDF to clean markdown for clause extraction or LLM analysis.
中文简介正在准备中。当前显示原文说明。
iterationlayer/skills42026年6月9日 更新
Convert external documents — specs, contracts, reports — to markdown for knowledge base ingestion.
中文简介正在准备中。当前显示原文说明。
iterationlayer/skills42026年6月9日 更新
Convert a document to clean markdown suitable for chunking and embedding in a RAG pipeline.
中文简介正在准备中。当前显示原文说明。
iterationlayer/skills42026年6月9日 更新
Convert an image between PNG, JPEG, and WebP formats with quality control for web optimization.
中文简介正在准备中。当前显示原文说明。
iterationlayer/skills42026年6月9日 更新