text

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

Overview

Name	text
Type	Resource
Id	gemini.models.text

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
batch_embed_text	exec	modelsId		Generates multiple embeddings from the model given input text in a synchronous call.
generate_text	exec	modelsId		Generates a response from the model given an input message.
embed_text	exec	modelsId		Generates an embedding from the model given an input message.
count_text_tokens	exec	modelsId		Runs a model's tokenizer on a text and returns the token count.

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
modelsId	string

Lifecycle Methods

batch_embed_text

Generates multiple embeddings from the model given input text in a synchronous call.

EXEC gemini.models.text.batch_embed_text 
@modelsId='{{ modelsId }}' --required
@@json=
'{
"requests": "{{ requests }}", 
"texts": "{{ texts }}"
}'
;

generate_text

Generates a response from the model given an input message.

EXEC gemini.models.text.generate_text 
@modelsId='{{ modelsId }}' --required
@@json=
'{
"topK": {{ topK }}, 
"maxOutputTokens": {{ maxOutputTokens }}, 
"safetySettings": "{{ safetySettings }}", 
"candidateCount": {{ candidateCount }}, 
"temperature": {{ temperature }}, 
"topP": {{ topP }}, 
"stopSequences": "{{ stopSequences }}", 
"prompt": "{{ prompt }}"
}'
;

embed_text

Generates an embedding from the model given an input message.

EXEC gemini.models.text.embed_text 
@modelsId='{{ modelsId }}' --required
@@json=
'{
"model": "{{ model }}", 
"text": "{{ text }}"
}'
;

count_text_tokens

Runs a model's tokenizer on a text and returns the token count.

EXEC gemini.models.text.count_text_tokens 
@modelsId='{{ modelsId }}' --required
@@json=
'{
"prompt": "{{ prompt }}"
}'
;