The PaLM API allows developers to build generative AI applications using the PaLM model. Large Language Models (LLMs) are a powerful, versatile type of machine learning model that enables computers to comprehend and generate natural language through a series of prompts. The PaLM API is based on Google's next generation LLM, PaLM. It excels at a variety of different tasks like code generation, reasoning, and writing. You can use the PaLM API to build generative AI applications for use cases like content generation, dialogue agents, summarization and classification systems, and more.
- REST Resource: v1beta3.models
- REST Resource: v1beta3.tunedModels
- REST Resource: v1beta3.tunedModels.permissions
Service: generativelanguage.googleapis.com
To call this service, we recommend that you use the Google-provided client libraries. If your application needs to use your own libraries to call this service, use the following information when you make the API requests.
Service endpoint
A service endpoint is a base URL that specifies the network address of an API service. One service might have multiple service endpoints. This service has the following service endpoint and all URIs below are relative to this service endpoint:
https://generativelanguage.googleapis.com
REST Resource: v1beta3.models
Methods | |
---|---|
batchEmbedText |
POST /v1beta3/{model=models/*}:batchEmbedText Generates multiple embeddings from the model given input text in a synchronous call. |
countMessageTokens |
POST /v1beta3/{model=models/*}:countMessageTokens Runs a model's tokenizer on a string and returns the token count. |
countTextTokens |
POST /v1beta3/{model=models/*}:countTextTokens Runs a model's tokenizer on a text and returns the token count. |
embedText |
POST /v1beta3/{model=models/*}:embedText Generates an embedding from the model given an input message. |
generateMessage |
POST /v1beta3/{model=models/*}:generateMessage Generates a response from the model given an input MessagePrompt . |
generateText |
POST /v1beta3/{model=models/*}:generateText Generates a response from the model given an input message. |
get |
GET /v1beta3/{name=models/*} Gets information about a specific Model. |
list |
GET /v1beta3/models Lists models available through the API. |
REST Resource: v1beta3.tunedModels
Methods | |
---|---|
create |
POST /v1beta3/tunedModels Creates a tuned model. |
delete |
DELETE /v1beta3/{name=tunedModels/*} Deletes a tuned model. |
generateText |
POST /v1beta3/{model=tunedModels/*}:generateText Generates a response from the model given an input message. |
get |
GET /v1beta3/{name=tunedModels/*} Gets information about a specific TunedModel. |
list |
GET /v1beta3/tunedModels Lists tuned models owned by the user. |
patch |
PATCH /v1beta3/{tunedModel.name=tunedModels/*} Updates a tuned model. |
transferOwnership |
POST /v1beta3/{name=tunedModels/*}:transferOwnership Transfers ownership of the tuned model. |
REST Resource: v1beta3.tunedModels.permissions
Methods | |
---|---|
create |
POST /v1beta3/{parent=tunedModels/*}/permissions Create a permission to a specific resource. |
delete |
DELETE /v1beta3/{name=tunedModels/*/permissions/*} Deletes the permission. |
get |
GET /v1beta3/{name=tunedModels/*/permissions/*} Gets information about a specific Permission. |
list |
GET /v1beta3/{parent=tunedModels/*}/permissions Lists permissions for the specific resource. |
patch |
PATCH /v1beta3/{permission.name=tunedModels/*/permissions/*} Updates the permission. |