completions

Creates, updates, deletes, gets or lists a completions resource.

Overview

Name	completions
Type	Resource
Id	snowflake.cortex_inference.completions

Fields

The following fields are returned by SELECT queries:

SELECT not supported for this resource, use SHOW METHODS to view available operations for the resource.

Methods

The following methods are available for this resource:

Name	Accessible by	Required Params	Optional Params	Description
cortex_llm_inference_complete	insert	endpoint		Perform LLM text completion inference, similar to snowflake.cortex.Complete.

Parameters

Parameters can be passed in the WHERE clause of a query. Check the Methods section to see which parameters are required or optional for each operation.

Name	Datatype	Description
endpoint	string	Organization and Account Name (default: orgid-acctid)

INSERT examples

cortex_llm_inference_complete

Perform LLM text completion inference, similar to snowflake.cortex.Complete.

INSERT INTO snowflake.cortex_inference.completions (
data__model,
data__messages,
data__temperature,
data__top_p,
data__max_tokens,
data__max_output_tokens,
data__response_format,
data__guardrails,
data__tools,
data__tool_choice,
data__provisioned_throughput_id,
data__sf-ml-xp-inflight-prompt-action,
data__sf-ml-xp-inflight-prompt-client-id,
data__sf-ml-xp-inflight-prompt-public-key,
data__stream,
endpoint
)
SELECT 
'{{ model }}' --required,
'{{ messages }}' --required,
{{ temperature }},
{{ top_p }},
{{ max_tokens }},
{{ max_output_tokens }},
'{{ response_format }}',
'{{ guardrails }}',
'{{ tools }}',
'{{ tool_choice }}',
'{{ provisioned_throughput_id }}',
'{{ sf-ml-xp-inflight-prompt-action }}',
'{{ sf-ml-xp-inflight-prompt-client-id }}',
'{{ sf-ml-xp-inflight-prompt-public-key }}',
{{ stream }},
'{{ endpoint }}'
;

Manifest

# Description fields are for documentation purposes
- name: completions
  props:
    - name: endpoint
      value: string
      description: Required parameter for the completions resource.
    - name: model
      value: string
      description: >
        The model name. See documentation for possible values.
        
    - name: messages
      value: array
    - name: temperature
      value: number
      description: >
        Temperature controls the amount of randomness used in response generation. A higher temperature corresponds to more randomness.
        
    - name: top_p
      value: number
      description: >
        Threshold probability for nucleus sampling. A higher top-p value increases the diversity of tokens that the model considers, while a lower value results in more predictable output.
        
      default: 1
    - name: max_tokens
      value: integer
      description: >
        The maximum number of output tokens to produce. The default value is model-dependent.
        
      default: 4096
    - name: max_output_tokens
      value: integer
      description: >
        Deprecated in favor of "max_tokens", which has identical behavior.
        
    - name: response_format
      value: object
      description: >
        An object describing response format config for structured-output mode.
        
    - name: guardrails
      value: object
      description: >
        Guardrails configuration
        
    - name: tools
      value: array
      description: >
        List of tools to be used during tool calling
        
    - name: tool_choice
      value: object
    - name: provisioned_throughput_id
      value: string
      description: >
        The provisioned throughput ID to be used with the request.
        
    - name: sf-ml-xp-inflight-prompt-action
      value: string
      description: >
        Reserved
        
    - name: sf-ml-xp-inflight-prompt-client-id
      value: string
      description: >
        Reserved
        
    - name: sf-ml-xp-inflight-prompt-public-key
      value: string
      description: >
        Reserved
        
    - name: stream
      value: boolean
      description: >
        Reserved
        
      default: true