| external help file | Module Name | online version | schema |
|---|---|---|---|
PSOpenAI-help.xml |
PSOpenAI |
2.0.0 |
Create an assistant with a model and instructions.
New-Assistant
[-Name <String>]
[-Model <String>]
[-Description <String>]
[-Instructions <String>]
[-UseCodeInterpreter]
[-UseFileSearch]
[-Functions <IDictionary[]>]
[-FileIdsForCodeInterpreter <Object[]>]
[-VectorStoresForFileSearch <Object[]>]
[-MaxNumberOfFileSearchResults <UInt16>]
[-RankerForFileSearch <String>]
[-ScoreThresholdForFileSearch <Double>]
[-FileIdsForFileSearch <Object[]>]
[-Temperature <Double>]
[-TopP <Double>]
[-MetaData <IDictionary>]
[-Format <Object>]
[-JsonSchema <String>]
[-TimeoutSec <Int32>]
[-MaxRetryCount <Int32>]
[-ApiBase <Uri>]
[-ApiKey <SecureString>]
[-Organization <String>]
[<CommonParameters>]
Create an assistant with a model and instructions. An Assistant represents an entity that can be configured to respond to users’ Messages using several parameters.
PS C:\> $Assistant = New-Assistant -Model gpt-4 -Instructions "You are a math teacher." -UseCodeInterpreter $trueCreate an assitant with a model and instructions and enable to use code interpreter.
The name of the assistant. The maximum length is 256 characters.
Type: String
Required: False
Position: NamedID of the model to use. The default value is gpt-3.5-turbo.
Type: String
Required: False
Position: Named
Default value: gpt-3.5-turboThe description of the assistant. The maximum length is 512 characters.
Type: String
Required: False
Position: NamedThe system instructions that the assistant uses. The maximum length is 256,000 characters.
Type: String
Required: False
Position: NamedSpecifies Whether the code interpreter tool enable or not. The default is $false.
Type: SwitchParameter
Required: False
Position: Named
Default value: $falseSpecifies Whether the file_search tool enable or not. The default is $false.
Type: SwitchParameter
Required: False
Position: Named
Default value: $falseA list of functions the model may call. Use this to provide a list of functions the model may generate JSON inputs for.
Type: IDictionary[]
Required: False
Position: NamedA list of file IDs made available to the code_interpreter tool. There can be a maximum of 20 files associated with the tool.
Type: Object[]
Required: False
Position: NamedThe vector store attached to this assistant. There can be a maximum of 1 vector store attached to the assistant.
Type: Object[]
Required: False
Position: NamedA list of file IDs to add to the vector store. There can be a maximum of 10000 files in a vector store.
Type: Object[]
Required: False
Position: NamedThe maximum number of results the file search tool should output. This number should be between 1 and 50 inclusive.
Type: UInt16
Required: False
Position: NamedThe ranker to use for the file search. If not specified will use the auto ranker.
Type: String
Required: False
Position: NamedThe score threshold for the file search. All values must be a floating point number between 0 and 1.
Type: double
Required: False
Position: NamedWhat sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.
Type: double
Required: False
Position: NamedAn alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.
Type: double
Aliases: top_p
Required: False
Position: NamedSet of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format.
Type: IDictionary
Required: False
Position: NamedSpecifies the format that the model must output.
autois default.json_objectenables JSON mode, which ensures the message the model generates is valid JSON.json_schemaenables Structured Outputs which ensures the model will match your supplied JSON schema.raw_responsereturns raw response content from API.
Type: Object
Aliases: response_format
Required: False
Position: NamedSpecifies an object or data structure to represent the JSON Schema that the model should be constrained to follow.
Required if json_schema is specified for -Format. Otherwise, it is ignored.
Type: String
Required: False
Position: NamedSpecifies how long the request can be pending before it times out.
The default value is 0 (infinite).
Type: Int32
Required: False
Position: Named
Default value: 0Number between 0 and 100.
Specifies the maximum number of retries if the request fails.
The default value is 0 (No retry).
Note : Retries will only be performed if the request fails with a 429 (Rate limit reached) or 5xx (Server side errors) error. Other errors (e.g., authentication failure) will not be performed.
Type: Int32
Required: False
Position: Named
Default value: 0Specifies an API endpoint URL such like: https://your-api-endpoint.test/v1
If not specified, it will use https://api.openai.com/v1
Type: System.Uri
Required: False
Position: Named
Default value: https://api.openai.com/v1Specifies API key for authentication.
The type of data should [string] or [securestring].
If not specified, it will try to use $global:OPENAI_API_KEY or $env:OPENAI_API_KEY
Type: Object
Required: False
Position: NamedSpecifies Organization ID which used for an API request.
If not specified, it will try to use $global:OPENAI_ORGANIZATION or $env:OPENAI_ORGANIZATION
Type: string
Aliases: OrgId
Required: False
Position: Namedhttps://platform.openai.com/docs/api-reference/assistants/createAssistant https://platform.openai.com/docs/assistants/overview/