llmwhisperer-client 0.1.0

Client library for LLM Whisperer

LLMWhisperer Python Client

This Python client provides a simple and efficient way to interact with the LLMWhisperer API. LLMWhisperer is a technology that presents data from complex documents (different designs and formats) to LLMs in a way that they can best understand.

Refer to the API documentation for more information: LLMWhisperer API Documentation

Features

• Easy to use Pythonic interface.
• Handles all the HTTP requests and responses for you.
• Raises Python exceptions for API errors.

Installation

You can install the LLMWhisperer Python Client using pip:

pip install llmwhisperer-client

Usage

First, import the LLMWhispererClient from the client module:

from llmwhisperer.client import LLMWhispererClient

Then, create an instance of the LLMWhispererClient:

client = LLMWhispererClient(base_url="https://llmwhisperer-api.unstract.com/v1", api_key="your_api_key")

Now, you can use the client to interact with the LLMWhisperer API:

# Get usage info
usage_info = client.get_usage_info()

# Process a document
# Extracted text is available in the 'extracted_text' field of the result
whisper = client.whisper(file_path="path_to_your_file")

# Get the status of a whisper operation
# whisper_hash is available in the 'whisper_hash' field of the result of the whisper operation
status = client.whisper_status(whisper_hash)

# Retrieve the result of a whisper operation
# whisper_hash is available in the 'whisper_hash' field of the result of the whisper operation
whisper = client.whisper_retrieve(whisper_hash)

Error Handling

The client raises LLMWhispererClientException for API errors:

try:
    result = client.whisper_retrieve("invalid_hash")
except LLMWhispererClientException as e:
    print(f"Error: {e.message}, Status Code: {e.status_code}")

Simple use case with defaults

client = LLMWhispererClient()
try:
    result = client.whisper(file_path="sample_files/restaurant_invoice_photo.pdf")
    extracted_text = result["extracted_text"]
    print(extracted_text)
except LLMWhispererClientException as e:
    print(e)

Simple use case with more options set

We are forcing text processing and extracting text from the first two pages only.

client = LLMWhispererClient()
try:
    result = client.whisper(
        file_path="sample_files/credit_card.pdf",
        processing_mode="text",
        force_text_processing=True,
        pages_to_extract="1,2",
    )
    extracted_text = result["extracted_text"]
    print(extracted_text)
except LLMWhispererClientException as e:
    print(e)

Extraction with timeout set

The platform has a hard timeout of 200 seconds. If the document takes more than 200 seconds to convert (large documents), the platform will switch to async extraction and return a hash. The client can be used to check the status of the extraction and retrieve the result. Also note that the timeout is in seconds and can be set by the caller too.

client = LLMWhispererClient()
try:
    result = client.whisper(
        file_path="sample_files/credit_card.pdf",
        pages_to_extract="1,2",
        timeout=2,
    )
    if result["statusCode"] == 202:
        print("Timeout occured. Whisper request accepted.")
        print(f"Whisper hash: {result['whisper-hash']}")
        while True:
            print("Polling for whisper status...")
            status = client.whisper_status(whisper_hash=result["whisper-hash"])
            if status["status"] == "processing":
                print("STATUS: processing...")
            elif status["status"] == "delivered":
                print("STATUS: Already delivered!")
                break
            elif status["status"] == "unknown":
                print("STATUS: unknown...")
                break
            elif status["status"] == "processed":
                print("STATUS: processed!")
                print("Let's retrieve the result of the extraction...")
                resultx = client.whisper_retrieve(
                    whisper_hash=result["whisper-hash"]
                )
                print(resultx["extracted_text"])
                break
            time.sleep(2)
except LLMWhispererClientException as e:
    print(e)

Questions and Feedback

On Slack, join great conversations around LLMs, their ecosystem and leveraging them to automate the previously unautomatable!

LLMWhisperer Playground: Test drive LLMWhisperer with your own documents. No sign up needed!

LLMWhisperer developer documentation and playground: Learn more about LLMWhisperer and its API.