RPA.OpenAI

Authorize To Openai

Keyword for authorize to OpenAI with your API key obtained from your account.

Arguments

Argument	Type	Default value	Description
api_key	str	null	Your OpenAI API key

param api_key:	Your OpenAI API key

Robot Framework example:

${secrets}   Get Secret   secret_name=OpenAI
Authorize To OpenAI   api_key=${secrets}[key]

Python example:

secrets = Vault().get_secret("OpenAI")
baselib = OpenAI()
baselib.authorize_to_openai(secrets["key"])

Chat Completion Create

Keyword for creating ChatGPT text completions in OpenAI. Keyword returns a list containing the response as a string and the message history as a list.

Arguments

Argument	Type	Default value	Description
user_content	str, None	None	Text submitted to ChatGPT to generate completions.
conversation	List, None	None	List containing the conversation to be continued. Leave empty for a new conversation.
model	str, None	gpt-3.5-turbo	ID of the model to use. Currently, only gpt-3.5-turbo and gpt-3.5-turbo-0301 are supported.
system_content	str, None	None	The system message helps set the behavior of the assistant.
temperature	int, None	1	What sampling temperature to use between 0 to 2. Higher values means the model will take more risks.
top_probability	int, None	1	An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass.
frequency_penalty	int, None	0	Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far.
presence_penalty	int, None	0	Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far.

param user_content:
	Text submitted to ChatGPT to generate completions.
param conversation:
	List containing the conversation to be continued. Leave empty for a new conversation.
param model:	ID of the model to use. Currently, only gpt-3.5-turbo and gpt-3.5-turbo-0301 are supported.
param system_content:
	The system message helps set the behavior of the assistant.
param temperature:
	What sampling temperature to use between 0 to 2. Higher values means the model will take more risks.
param top_probability:
	An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass.
param frequency_penalty:
	Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far.
param presence_penalty:
	Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far.

Robot Framework example:

# Create a new conversation without conversation history.
${response}   @{chatgpt_conversation}=     Chat Completion Create
...    user_content=What is the biggest mammal?
Log    ${response}

# Continue the conversation by using the "conversation" argument.
${response}   @{chatgpt_conversation}=     Chat Completion Create
...    conversation=${chatgpt_conversation}
...    user_content=How old can it live?
Log    ${response}

Completion Create

Keyword for creating text completions in OpenAI. Keyword returns a text string.

Arguments

Argument	Type	Default value	Description
prompt	str	null	Text submitted to OpenAI for creating natural language.
model	str, None	text-davinci-003	OpenAI's model to use in the completion.
temperature	int, None	0.7	What sampling temperature to use. Higher values means the model will take more risks..
max_tokens	int, None	256	The maximum number of tokens to generate in the completion..
top_probability	int, None	1	Controls diversity via nucleus sampling. 0.5 means half of all likelihood-weighted options are considered.
frequency_penalty	int, None	0	Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far.
presence_penalty	int, None	0	Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far.
result_format	str, None	string	Result format (string / json). Return just a string or the default JSON response.

param temperature:
param prompt:	Text submitted to OpenAI for creating natural language.
param model:	OpenAI's model to use in the completion.
	What sampling temperature to use. Higher values means the model will take more risks..
param max_tokens:
	The maximum number of tokens to generate in the completion..
param top_probability:
	Controls diversity via nucleus sampling. 0.5 means half of all likelihood-weighted options are considered.
param frequency_penalty:
	Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far.
param presence_penalty:
	Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far.
param result_format:
	Result format (string / json). Return just a string or the default JSON response.

Robot Framework example:

${response}  Completion Create
...     Write a tagline for an icecream shop.
...     temperature=0.6
Log     ${response}

Python example:

result = baselib.completion_create(
    'Create a tagline for icecream shop',
    temperature=0.6,
)
print(result)

Image Create

Keyword for creating one or more images in OpenAI. Keyword returns a list of urls for the images created.

Arguments

Argument	Type	Default value	Description
prompt	str	null	A text description of the desired image(s). The maximum length is 1000 characters.
size	str, None	512x512	Size of the files to be created. 256x256, 512x512, 1024x1024
num_images	int, None	1	The number of images to generate. Must be between 1 and 10.
result_format	str, None	list	Result format (list / json).

param num_images:
param prompt:	A text description of the desired image(s). The maximum length is 1000 characters.
param size:	Size of the files to be created. 256x256, 512x512, 1024x1024
	The number of images to generate. Must be between 1 and 10.
param result_format:
	Result format (list / json).

Robot Framework example:

${images}    Image Create
...   Cartoon style picture of a cute monkey skateboarding.
...   size=256x256
...   num_images=2
FOR    ${url}    IN    @{images}
    Log    ${url}
END

Python example:

images = baselib.image_create(
    'Cartoon style picture of a cute monkey skateboarding',
    size='256x256',
    num_images=2,
)
for url in images:
    print(url)

Image Create Variation

Keyword for creating one or more variations of a image. Keyword returns a list of urls for the images created. Source file must be a valid PNG file, less than 4MB, and square.

Arguments

Argument	Type	Default value	Description
src_image	str	null	The image to use as the basis for the variation(s). Must be a valid PNG file, less than 4MB, and square.
size	str, None	512x512	The size of the generated images. Must be one of 256x256, 512x512, or 1024x1024.
num_images	int, None	1	The number of images to generate. Must be between 1 and 10
result_format	str, None	list	Result format (list / json).

param src_image:
	The image to use as the basis for the variation(s). Must be a valid PNG file, less than 4MB, and square.
param size:	The size of the generated images. Must be one of 256x256, 512x512, or 1024x1024.
param num_images:
	The number of images to generate. Must be between 1 and 10
param result_format:
	Result format (list / json).

Robot Framework example:

${variations}   Image Create Variation
...     source_image.png
...     size=256x256
...     num_images=2
FOR    ${url}    IN    @{variations}
    Log    ${url}
END

Python example:

variations = baselib.image_create_variation(
    'source_image.png',
    size='256x256',
    num_images=2,
)
for url in variations:
    print(url)