Skip to content

Access to the multimodal LLM Perceptor.

License

Unknown, Unknown licenses found

Licenses found

Unknown
LICENSE
Unknown
LICENSE.txt
Notifications You must be signed in to change notification settings

n-1-l-s/perceptor-client-lib-py

Repository files navigation

perceptor-client-lib-py

Installing package

to be described here

Installing poppler

If you want to use pdf processing functionality, follow this instructions to install popppler on your machine. On Windows, if the poppler "bin" path is not added to PATH, you have to set the environment variable POPPLER_PATH to point to bin.

Usage

Create the client first:

import perceptor_client_lib.perceptor as perceptor

API_KEY = "your_api_key"

perceptor_client = perceptor.Client(api_key=API_KEY)

optionally, another url can be specified:

perceptor_client = perceptor.Client(api_key="your_key",request_url="another_url")

Sending instructions for text

result = perceptor_client.ask_text("text_to_process",
                                       instructions=[
                                           "Question 1?",
                                           "Question 2",
                                       ])

Sending instructions for an image

Following image formats are supported: "jpg", "png".

From image file:

result = perceptor_client.ask_image("path_to_image_file",
                                       instructions=[
                                           "Question 1?",
                                           "Question 2",
                                       ])

or from image file:

reader = open("image_path", 'rb')
with reader:
    result = perceptor_client.ask_image(reader,
                                       instructions=[
                                           "Question 1?",
                                           "Question 2",
                                       ], file_type='jpg')

or from bytes:

reader = open(_image_path, 'rb')
with reader:
    content_bytes = reader.read()
    result = perceptor_client.ask_image(content_bytes,
                                       instructions=[
                                           "Question 1?",
                                           "Question 2",
                                       ], file_type='jpg')

Table queries can be performed as following:

result = perceptor_client.ask_table_from_image("path_to_image_file",
                                       instruction="GENERATE TABLE Column1, Column2, Column3 GUIDED BY Column3",
                                               )

Sending instructions for a pdf document

From document file:

result = perceptor_client.ask_document("path_to_document_file",
                                       instructions=[
                                           "Question 1?",
                                           "Question 2",
                                       ])

About

Access to the multimodal LLM Perceptor.

Resources

License

Unknown, Unknown licenses found

Licenses found

Unknown
LICENSE
Unknown
LICENSE.txt

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published