oa.openai_specs

Tools to extract specs from the openai interface

See raw schemas by doing

>>> from oa.openai_specs import schemas
>>> sorted(schemas)
['AssistantFileObject', 'AssistantObject', 'AssistantToolsCode', 'AssistantToolsFunction', 'AssistantToolsRetrieval', 'ChatCompletionFunctionCallOption',
'ChatCompletionFunctions', 'ChatCompletionMessageToolCall', 'ChatCompletionMessageToolCallChunk', 'ChatCompletionMessageToolCalls',
'ChatCompletionNamedToolChoice', 'ChatCompletionRequestAssistantMessage', 'ChatCompletionRequestFunctionMessage', 'ChatCompletionRequestMessage',
'ChatCompletionRequestMessageContentPart', 'ChatCompletionRequestMessageContentPartImage', 'ChatCompletionRequestMessageContentPartText',
'ChatCompletionRequestSystemMessage', 'ChatCompletionRequestToolMessage', 'ChatCompletionRequestUserMessage', 'ChatCompletionResponseMessage',
'ChatCompletionRole', 'ChatCompletionStreamResponseDelta', 'ChatCompletionTool', 'ChatCompletionToolChoiceOption', 'CompletionUsage',
'CreateAssistantFileRequest', 'CreateAssistantRequest', 'CreateChatCompletionFunctionResponse', 'CreateChatCompletionImageResponse',
'CreateChatCompletionRequest', 'CreateChatCompletionResponse', 'CreateChatCompletionStreamResponse', 'CreateCompletionRequest',
'CreateCompletionResponse', 'CreateEditRequest', 'CreateEditResponse', 'CreateEmbeddingRequest', 'CreateEmbeddingResponse', 'CreateFileRequest',
'CreateFineTuneRequest', 'CreateFineTuningJobRequest', 'CreateImageEditRequest', 'CreateImageRequest', 'CreateImageVariationRequest', 'CreateMessageRequest',
'CreateModerationRequest', 'CreateModerationResponse', 'CreateRunRequest', 'CreateSpeechRequest', 'CreateThreadAndRunRequest', 'CreateThreadRequest',
'CreateTranscriptionRequest', 'CreateTranscriptionResponse', 'CreateTranslationRequest', 'CreateTranslationResponse', 'DeleteAssistantFileResponse',
'DeleteAssistantResponse', 'DeleteFileResponse', 'DeleteMessageResponse', 'DeleteModelResponse', 'DeleteThreadResponse', 'Embedding', 'Error',
'ErrorResponse', 'FineTune', 'FineTuneEvent', 'FineTuningJob', 'FineTuningJobEvent', 'FunctionObject', 'FunctionParameters', 'Image',
'ImagesResponse', 'ListAssistantFilesResponse', 'ListAssistantsResponse', 'ListFilesResponse', 'ListFineTuneEventsResponse', 'ListFineTunesResponse',
'ListFineTuningJobEventsResponse', 'ListMessageFilesResponse', 'ListMessagesResponse', 'ListModelsResponse', 'ListPaginatedFineTuningJobsResponse',
'ListRunStepsResponse', 'ListRunsResponse', 'ListThreadsResponse', 'MessageContentImageFileObject', 'MessageContentTextAnnotationsFileCitationObject',
'MessageContentTextAnnotationsFilePathObject', 'MessageContentTextObject', 'MessageFileObject', 'MessageObject', 'Model', 'ModifyAssistantRequest',
'ModifyMessageRequest', 'ModifyRunRequest', 'ModifyThreadRequest', 'OpenAIFile', 'RunObject', 'RunStepDetailsMessageCreationObject', 'RunStepDetailsToolCallsCodeObject',
'RunStepDetailsToolCallsCodeOutputImageObject', 'RunStepDetailsToolCallsCodeOutputLogsObject', 'RunStepDetailsToolCallsFunctionObject', 'RunStepDetailsToolCallsObject',
'RunStepDetailsToolCallsRetrievalObject', 'RunStepObject', 'RunToolCallObject', 'SubmitToolOutputsRunRequest', 'ThreadObject']
>>> schema = schemas['CreateCompletionRequest']
>>> schema['properties']
 {'model': {'description': 'ID of the model to use...

Get resulting signatures by doing.

>>> from oa.openai_specs import sig
>>> sig.CreateCompletionRequest)
<Sig (model: str, prompt='<|endoftext|>', *, seed: int, best_of: int = 1, echo: bool = False,
frequency_penalty: float = 0, logit_bias: dict = None, logprobs: int = None, max_tokens: int = None,
n: int = 1, presence_penalty: float = 0, stop=None, stream: bool = False, suffix: str = None,
temperature: float = 1, top_p: float = 1, user: str = None)>

Or see argument descriptions in rst format by doing:

>>> from oa.openai_specs import schema_to_rst_argument_descriptions, schemas
>>> schema_to_rst_argument_descriptions(schemas['CreateCompletionRequest'])

Functions

get_openapi_spec_dict([openapi_spec_url, ...])

Get the dict of the openapi spec

merge_keys_to_values(d[, key_name])

Merge the keys of a dict into the values of the dict.

normalized_file_name(prompt)

Convert prompt to a normalized valid file/folder name

prompt_path(prompt[, prefix])

properties_to_annotation(name, props)

Get annotations from a schema

properties_to_param_dict(name, props)

Get all but kind fields of a Parameter object

schema_to_docs(name, schema[, prefix, ...])

Get the docs for a schema

schema_to_rst_argument_descriptions(schema)

Yield rst-formatted argument descriptions for a schema

schema_to_signature(schema)

Get a signature from a schema

schemas_df(schema)

Classes

Message

SpecNames()

class oa.openai_specs.Message[source]

Bases: TypedDict

oa.openai_specs.get_openapi_spec_dict(openapi_spec_url='https://raw.githubusercontent.com/thorwhalen/oa/main/misc/openapi.yaml', *, refresh=False, expand_refs=True)[source]

Get the dict of the openapi spec

oa.openai_specs.merge_keys_to_values(d, key_name='key')[source]

Merge the keys of a dict into the values of the dict.

>>> d = {'a': {'b': 1}, 'c': {'d': 2, 'e': 3}}
>>> dict(merge_keys_to_values(d))
{'a': {'key': 'a', 'b': 1}, 'c': {'key': 'c', 'd': 2, 'e': 3}}

Useful when, for example, you want to make a table containing both keys and values.

oa.openai_specs.normalized_file_name(prompt)[source]

Convert prompt to a normalized valid file/folder name

Return type:

str

>>> normalized_file_name("This is a prompt")
'this is a prompt'
>>> normalized_file_name("This is: a PROMPT!  (with punctuation)")
'this is a prompt with punctuation'
oa.openai_specs.properties_to_annotation(name, props)[source]

Get annotations from a schema

oa.openai_specs.properties_to_param_dict(name, props)[source]

Get all but kind fields of a Parameter object

oa.openai_specs.schema_to_docs(name, schema, prefix='', line_prefix='\\t')[source]

Get the docs for a schema

>>> from oa.openai_specs import specs
>>> schema = specs['components']['schemas']['CreateChatCompletionRequest']
>>> print(schema_to_docs('chatcompletion', schema))
chatcompletion(...
Parameters:

model – ID of the model to use. Currently, only …

oa.openai_specs.schema_to_rst_argument_descriptions(schema, process_description=<function _clean_up_whitespace>)[source]

Yield rst-formatted argument descriptions for a schema

>>> from oa.openai_specs import specs
>>> schema = specs['components']['schemas']['CreateChatCompletionRequest']
>>> print(*schema_to_rst_argument_descriptions(schema), '\n')
:param model: ID of the model to use. Currently, only ...

process_description is a function that will be applied to each schema description (so you can clean it up, or add links, etc.). By default, it will replace all whitespaces with single space, and strip.

oa.openai_specs.schema_to_signature(schema)[source]

Get a signature from a schema

>>> from oa.openai_specs import specs
>>> schema = specs['components']['schemas']['CreateChatCompletionRequest']
>>> print(str(schema_to_signature(schema)))
(model: str, messages: List[openai_specs.Message], *, temperature: float = 1, ...