Issue with LlamaParse ...

[krtarunsingh]

Describe the bug
Write a concise description of what the bug is.

Files
If possible, please provide the PDF file causing the issue.

**Job ID-ada0e2fd-799d-4a2a-ba43-8a67ce4577fc

Client:
Please remove untested options:

• Python Library
• API
• Frontend (cloud.llamaindex.ai)
• Typescript Library
• Notebook

Additional context
Add any additional context about the problem here.
What options did you use? Premium mode, multimodal, fast mode, parsing instructions, etc.
Screenshots, code snippets, etc.

[apostolos-geyer]

@krtarunsingh You should provide more information about the bug you are facing,

• Stack traces, if any, from the Python library
• Error message from the LlamaCloud UI
• Your source code, your expected result, and the result you're seeing instead.

Otherwise, there is not much anyone can do for you here.

[krtarunsingh]

below is the code

import os
from dotenv import load_dotenv
from rich import print
from llama_extract import LlamaExtract
import llama_cloud.core.api_error

Load the API key from .env file

load_dotenv()
api_key = os.getenv("LLAMA_CLOUD_API_KEY")

if not api_key:
raise ValueError("LLAMA_CLOUD_API_KEY is not set in the .env file. Please add it before proceeding.")

Initialize LlamaExtract with the API key

extractor = LlamaExtract(api_key=api_key)

Define schema for the bank statement

bank_statement_data_config = {
"type": "object",
"title": "BankStatementData",
"required": [
"account_holder_name", "account_number", "bank_name", "transactions"
],
"properties": {
"account_holder_name": {"type": "string", "title": "Account Holder Name"},
"account_number": {"type": "string", "title": "Account Number"},
"bank_name": {"type": "string", "title": "Bank Name"},
"statement_date": {"type": "string", "format": "date", "title": "Statement Date"},
"transactions": {
"type": "array",
"items": {
"type": "object",
"properties": {
"date": {"type": "string", "format": "date", "title": "Transaction Date"},
"description": {"type": "string", "title": "Transaction Description"},
"transaction_type": {"type": "string", "title": "Transaction Type (Credit/Debit)"},
"amount": {"type": "number", "title": "Transaction Amount"},
"balance": {"type": "number", "title": "Balance After Transaction"}
},
"required": ["date", "description", "transaction_type", "amount", "balance"]
}
}
}
}

try:
# Create schema in LlamaExtract
extraction_schema = extractor.create_schema("InvoiceData Schema", bank_statement_data_config)
print("[green]Schema Created Successfully:[/green]", extraction_schema)

# Extract data using the created schema
results = extractor.extract(
    schema_id="652d91d5-cf0b-4ff4-bc23-98e6743b28c9",  # Use schema ID from creation
    file_input=[r"C:\Users\user\Downloads\Account_stmt_XX4259_27092024.pdf"]  # Updated to use the uploaded file path
)
print("[green]Extraction Successful! Results:[/green]")
print(results)

except llama_cloud.core.api_error.ApiError as e:
# Handle API-specific errors
print("[red]API Error Occurred:[/red]", e)
if e.body:
print("[red]Error Details:[/red]", e.body)

except Exception as e:
# Handle any other exceptions
print("[red]An unexpected error occurred:[/red]", e)