Quickstart

import json
from landingai_ade import LandingAIADE

# Initialize the client
client = LandingAIADE()

##### Parse the document #####

# Parse the document
parse_response = client.parse(
    document_url="https://docs.landing.ai/examples/bank-statement.pdf",
    model="dpt-2-latest"
)

# Print the parsing results
print("Parse Markdown:")
print(parse_response.markdown)

print("Parse Chunks:")
print(parse_response.chunks)

print("Grounding Information:")
print(parse_response.grounding)

print("Parse API Metadata:")
print(parse_response.metadata)

# Save Markdown to a file (optional, useful for later reference)
if parse_response.markdown:
    with open('markdown-bank-statement.md', 'w', encoding='utf-8') as f:
        f.write(parse_response.markdown)
    print("\nMarkdown content saved to a Markdown file.")
else:
    print("No 'markdown' field found in the response")

##### Extract fields from the parsed document #####

# Define your extraction schema
schema_dict = {
    "type": "object",
    "properties": {
        "name": {
            "type": "string",
            "description": "Account holder name"
        },
        "number_deposits": {
            "type": "integer",
            "description": "The number of deposits"
        }
    },
    "required": ["name", "number_deposits"]
}

# Convert schema dictionary to JSON string
schema_json = json.dumps(schema_dict)

# Extract fields using the parsed markdown
extract_response = client.extract(
    schema=schema_json,
    markdown=parse_response.markdown,  # Use the markdown from the parse response
    model="extract-latest"
)

# Print the extracted fields
print("\nExtracted fields:")
print(extract_response.extraction)

import LandingAIADE, { toFile } from "landingai-ade";
import fs from "fs";

const client = new LandingAIADE();

///// Parse the document /////

// Parse the document
const parseResponse = await client.parse({
  document: await fetch("https://docs.landing.ai/examples/bank-statement.pdf"),
  model: "dpt-2-latest"
});

// Print the parsing results
console.log("Parse Markdown:");
console.log(parseResponse.markdown);

console.log("Parse Chunks:");
console.log(parseResponse.chunks);

console.log("Grounding Information:");
console.log(parseResponse.grounding);

console.log("Parse API Metadata:");
console.log(parseResponse.metadata);

// Save Markdown to a file (optional, useful for later reference)
if (parseResponse.markdown) {
  fs.writeFileSync("markdown-bank-statement.md", parseResponse.markdown, "utf-8");
  console.log("\nMarkdown content saved to a Markdown file.");
} else {
  console.log("No 'markdown' field found in the response");
}

///// Extract fields from the parsed document /////

// Define your extraction schema
const schemaDict = {
  type: "object",
  properties: {
    name: {
      type: "string",
      description: "Account holder name"
    },
    number_deposits: {
      type: "integer",
      description: "The number of deposits"
    }
  },
  required: ["name", "number_deposits"]
};

const schemaJson = JSON.stringify(schemaDict);

// Extract fields using the parsed markdown
const extractResponse = await client.extract({
  schema: schemaJson,
  markdown: await toFile(Buffer.from(parseResponse.markdown), "document.md"), // Use the markdown from the parse response
  model: "extract-latest"
});

// Print the extracted fields
console.log("\nExtracted fields:");
console.log(extractResponse.extraction);