Documents Methods - UiForm Docs

In this section, we will see how to use the methods of the documents client.

Create Messages

create_messages

Function

Creates messages from a document for use with LLM models

Response

DocumentMessage Object

A DocumentMessage object with the messages created from the document.

Use doc_msg.items to have a list of [PIL.Image.Image | str] objects

Correct image orientation

correct_image_orientation

function

Corrects the orientation of an image using the UiForm API.

Response

PIL.Image.Image

The orientation-corrected image as a PIL Image object

Extractions

extractions.parse

function

Extract structured data from a document using a JSON schema

json_schema

dict[str, Any] | Path | str

required

The JSON schema defining the structure to extract. Can be a dict, file path, or string.

document

Path | str | IO[bytes]

required

The document to extract from. Can be a file path, string, or bytes IO object.

text_operations

TextOperations

Optional text operations to perform on the document:

image_operations

ImageOperations

Optional image preprocessing operations:

model

string

default:

"gpt-4o-2024-08-06"

The model to use for extraction.

temperature

float

default:

"0"

The sampling temperature to use.

messages

array[ChatCompletionUiformMessage]

default:

"[]"

Optional list of previous messages to include. Each message must have:

modality

string

default:

"native"

The modality to use for processing the document. Can be:

“native” (default) - Uses the document’s native modality based on file type
“text” - Process as text
“image” - Process as image
“audio” - Process as audio
“video” - Process as video

Response

ParsedChatCompletion

An OpenAI ParsedChatCompletion object with the extracted data.

extractions.stream

function

Extract structured data from a document using a JSON schema

json_schema

dict[str, Any] | Path | str

required

The JSON schema defining the structure to extract. Can be a dict, file path, or string.

document

Path | str | IO[bytes]

required

The document to extract from. Can be a file path, string, or bytes IO object.

text_operations

TextOperations

Optional text operations to perform on the document:

image_operations

ImageOperations

Optional image preprocessing operations:

model

string

default:

"gpt-4o-2024-08-06"

The model to use for extraction.

temperature

float

default:

"0"

The sampling temperature to use.

messages

array[ChatCompletionUiformMessage]

default:

"[]"

Optional list of previous messages to include. Each message must have:

modality

string

default:

"native"

The modality to use for processing the document. Can be:

“native” (default) - Uses the document’s native modality based on file type
“text” - Process as text
“image” - Process as image
“audio” - Process as audio
“video” - Process as video

Response

AsyncChatCompletionStreamManager[ResponseFormatT]

An OpenAI AsyncChatCompletionStreamManager[ResponseFormatT] object with the extracted data.

​Create Messages

​Correct image orientation

​Extractions

​extractions.parse

​extractions.stream

Create Messages

Correct image orientation

Extractions

extractions.parse

extractions.stream