This is my playground for OpenAI API. I use this repo to study openai api.
['APIError', 'Completion', 'ContextVar', 'Customer', 'Deployment', 'Edit', 'Embedding', 'Engine', 'ErrorObject', 'File', 'FineTune', 'Image', 'InvalidRequestError', 'Model', 'Moderation', 'OpenAIError', 'Optional', 'TYPE_CHECKING', '__all__', '__annotations__', '__builtins__', '__cached__', '__doc__', '__file__', '__loader__', '__name__', '__package__', '__path__', '__spec__', 'aiosession', 'api_base', 'api_key', 'api_key_path', 'api_requestor', 'api_resources', 'api_type', 'api_version', 'app_info', 'ca_bundle_path', 'datalib', 'debug', 'enable_telemetry', 'error', 'log', 'openai_object', 'openai_response', 'organization', 'os', 'proxy', 'util', 'verify_ssl_certs', 'version']
This is the script to Generate Yune's picture
chatgpt 背后的有多个 GPT-3 模型。They are good at difference tasks. The first two is pretty important
-
Davinci: Good at: Complex intent, cause and effect, summarization for audience
-
Curie: Language translation, complex classification, text sentiment, summarization
-
- Key points list out key points from the text.
-
- Report generation read an email from a customer and provide answers to a preset list of questions.
-
Babbage: Moderate classification, semantic search classification
-
Ada: Parsing text, simple classification, address correction, keywords
While Davinci is more capable when it comes to comprehending text and generating responses that are more nuanced like summarizing for a child or emulating human speaking patterns, Curie is highly capable of analyzing text, answering direct questions, and providing key points
- Use a low temperature when extracting data