Identifier for the source contributing to this attribution.
Request to batch create Chunk
s.
Response from BatchCreateChunks
containing a list of created Chunk
s.
Request to batch delete Chunk
s.
Batch request to get embeddings from the model for a list of prompts.
The response to a BatchEmbedContentsRequest
.
Batch request to get a text embedding from the model.
The response to a EmbedTextRequest.
Request to batch update Chunk
s.
Response from BatchUpdateChunks
containing a list of updated Chunk
s.
Raw media bytes.
A response candidate generated from the model.
A Chunk
is a subpart of a Document
that is treated as an independent unit
for the purposes of vector representation and storage.
A Corpus
can have a maximum of 1 million Chunk
s.
Extracted data that represents the Chunk
content.
A collection of source attributions for a piece of content.
A citation to a source for a portion of a specific response.
Filter condition applicable to a single key.
The base structured datatype containing multi-part content of a message.
A list of floats representing an embedding.
Content filtering metadata associated with processing a single request.
A Corpus
is a collection of Document
s.
A project can create up to 5 corpora.
Counts the number of tokens in the prompt
sent to a model.
A response from CountMessageTokens
.
Counts the number of tokens in the prompt
sent to a model.
A response from CountTextTokens
.
Counts the number of tokens in the prompt
sent to a model.
A response from CountTokens
.
Request to create a Chunk
.
Request to create a Corpus
.
Request to create a Document
.
Request for CreateFile
.
Response for CreateFile
.
Request to create a Permission
.
Metadata about the state and progress of creating a tuned model returned from
the long-running operation
Request to create a TunedModel.
User provided metadata stored as key-value pairs.
Dataset for training or validation.
Request to delete a Chunk
.
Request to delete a Corpus
.
Request to delete a Document
.
Request for DeleteFile
.
Request to delete the Permission
.
Request to delete a TunedModel.
A Document
is a collection of Chunk
s.
A Corpus
can have a maximum of 10,000 Document
s.
Request containing the Content
for the model to embed.
The response to an EmbedContentRequest
.
Request to get a text embedding from the model.
The response to a EmbedTextRequest.
A list of floats representing the embedding.
An input/output example used to instruct the Model.
A file uploaded to the API.
URI based data.
A predicted FunctionCall
returned from the model that contains
a string representing the FunctionDeclaration.name
with the
arguments and their values.
Configuration for specifying function calling behavior.
Structured representation of a function declaration as defined by the
OpenAPI 3.03 specification. Included
in this declaration are the function name and parameters. This
FunctionDeclaration is a representation of a block of code that can be used
as a
Tool
by the model and executed by the client.
The result output from a FunctionCall
that contains a string
representing the FunctionDeclaration.name
and a structured JSON
object containing any output from the function is used as context to
the model. This should contain the result of aFunctionCall
made
based on model prediction.
Request to generate a grounded answer from the model.
Response from the model for a grounded answer.
Request to generate a completion from the model.
Response from the model supporting multiple candidates.
Request to generate a message response from the model.
The response from the model.
Request to generate a text completion response from the model.
The response from the model, including candidate completions.
Configuration options for model generation and outputs. Not all parameters
may be configurable for every model.
Request for getting information about a specific Chunk
.
Request for getting information about a specific Corpus
.
Request for getting information about a specific Document
.
Request for GetFile
.
Request for getting information about a specific Model.
Request for getting information about a specific Permission
.
Request for getting information about a specific Model.
Attribution for a source that contributed to an answer.
Passage included inline with a grounding configuration.
A repeated list of passages.
Request for listing Chunk
s.
Response from ListChunks
containing a paginated list of Chunk
s.
The Chunk
s are sorted by ascending chunk.create_time
.
Request for listing Corpora
.
Response from ListCorpora
containing a paginated list of Corpora
.
The results are sorted by ascending corpus.create_time
.
Request for listing Document
s.
Response from ListDocuments
containing a paginated list of Document
s.
The Document
s are sorted by ascending document.create_time
.
Request for ListFiles
.
Response for ListFiles
.
Request for listing all Models.
Response from ListModel
containing a paginated list of Models.
Request for listing permissions.
Response from ListPermissions
containing a paginated list of
permissions.
Request for listing TunedModels.
Response from ListTunedModels
containing a paginated list of Models.
The base unit of structured text.
All of the structured input text passed to the model as a prompt.
User provided filter to limit retrieval based on Chunk
or Document
level
metadata values.
Example (genre = drama OR genre = action):
key = “document.custom_metadata.genre”
conditions = [{string_value = “drama”, operation = EQUAL},
{string_value = “action”, operation = EQUAL}]
Information about a Generative Language Model.
A datatype containing media that is part of a multi-part Content
message.
Permission resource grants user, group or the rest of the world access to the
PaLM API resource (e.g. a tuned model, corpus).
Request for querying a Corpus
.
Response from QueryCorpus
containing a list of relevant chunks.
Request for querying a Document
.
Response from QueryDocument
containing a list of relevant chunks.
The information for a chunk relevant to a query.
Safety feedback for an entire request.
Safety rating for a piece of content.
Safety setting, affecting the safety-blocking behavior.
The
Schema
object allows the definition of input and output data types.
These types can be objects, but also primitives and arrays.
Represents a select subset of an
OpenAPI 3.0 schema
object.
Configuration for retrieving grounding content from a Corpus
or
Document
created using the Semantic Retriever API.
User provided string values assigned to a single metadata key.
Output text returned from a model.
Text given to the model as a prompt.
Tool details that the model may use to generate response.
The Tool configuration containing parameters for specifying Tool
use
in the request.
Request to transfer the ownership of the tuned model.
Response from TransferOwnership
.
A fine-tuned model created using ModelService.CreateTunedModel.
Tuned model as a source for training a new model.
A single example for tuning.
A set of tuning examples. Can be training or validation data.
Record for a single tuning step.
Tuning tasks that create tuned models.
Request to update a Chunk
.
Request to update a Corpus
.
Request to update a Document
.
Request to update the Permission
.
Request to update a TunedModel.
Metadata for a video File
.