This topic lists the functions available for Polar_AI.
Model management
Function | Description |
Creates a model and registers it in a metadata table. | |
Modifies the information of a model. | |
Sets token information for one or more models. | |
Calls a model to execute machine learning and natural language processing (NLP) tasks such as sentiment analysis, question-answering, translation, summarization, and text generation. | |
Deletes a model. |
Model services
General-purpose text embedding.
Function
Description
Calls an existing general-purpose text embedding model to convert text into vectors online. If you do not specify a model, the function calls the built-in model
_dashscope/text_embedding/text_embedding_v2.Open-domain text understanding.
Function
Description
Calls a text comprehension model for tasks such as sentiment classification, topic classification, or information extraction. If you do not specify a model, the function calls the built-in model
_dashscope/text-classfication/opennlu-v1.Text conversation.
Function name
Description
Calls a text generation model for tasks such as text conversation and Q&A pairs. If a model is not specified, the function uses the default built-in model
_dashscope/text-generation/deepseek-r1.
GUC settings
Parameter | Description |
Specifies whether to enable persistent HTTP connections. | |
The timeout duration for HTTP connections. Unit: milliseconds. | |
The maximum number of retry attempts for failed HTTP requests. | |
The interval between retry attempts for failed HTTP requests. Unit: milliseconds. | |
The size of the model metadata cache in the database. |
Helper functions
Function | Description |
Resizes an image. | |
Converts an image into a Base64-encoded string. | |
Converts a Base64-encoded string into an image. | |
Loads a file from Object Storage Service (OSS). | |
Returns a list of currently cached models. |