Namespace Oci.GenerativeaiinferenceService.Models
Classes
ApplyGuardrailsDetails
Details for applying guardrails to the input text.
ApplyGuardrailsResult
The result of applying guardrails to the input text.
AssistantMessage
Represents a single instance of assistant message.
Note: When responding to a tool call, set content to null (not \"\").
This ensures the model correctly processes tool call messages in multi-step interactions.
BaseChatRequest
The base class to use for the chat inference request.
BaseChatRequestModelConverter
BaseChatResponse
The base class that creates the chat response.
BaseChatResponseModelConverter
CategoryScore
A category with its score.
ChatChoice
Represents a single instance of the chat response.
ChatContent
The base class for the chat content.
ChatContentModelConverter
ChatDetails
Details of the conversation for the model to respond.
ChatResult
The response to the chat conversation.
Choice
Represents a single instance of the generated text.
Citation
A section of the generated response which cites the documents that were used for generating the response.
CohereChatBotMessage
A message that represents a single chat dialog as CHATBOT role.
CohereChatRequest
Details for the chat request for Cohere models.
CohereChatResponse
The response to the chat conversation.
CohereLlmInferenceRequest
Details for the text generation request for Cohere models.
CohereLlmInferenceResponse
The generated text result to return.
CohereMessage
A message that represents a single chat dialog.
CohereMessageModelConverter
CohereParameterDefinition
A definition of tool parameter.
CohereResponseFormat
Specify the format the model output is guaranteed to be of
CohereResponseFormatModelConverter
CohereResponseJsonFormat
The json object format for the model structured output
CohereResponseTextFormat
The text format for cohere model response
CohereSystemMessage
A message that represents a single chat dialog as SYSTEM role.
CohereTool
A definition of tool (function).
CohereToolCall
A tool call generated by the model.
CohereToolMessage
A message that represents a single chat dialog as TOOL role.
CohereToolResult
The result from invoking tools recommended by the model in the previous chat turn.
CohereUserMessage
A message that represents a single chat dialog as USER role.
CompletionTokensDetails
Breakdown of tokens used in a completion.
ContentModerationConfiguration
Configuration for content moderation.
ContentModerationResult
The result of content moderation.
DedicatedServingMode
The model's serving mode is dedicated serving and has an endpoint on a dedicated AI cluster.
Document
The input of the document to rerank.
DocumentRank
An object that contains a relevance score, an index and the text for a document.
EmbedTextDetails
Details for the request to embed texts.
EmbedTextResult
The generated embedded result to return.
FunctionCall
The function call generated by the model.
FunctionDefinition
A function the model may call.
GenerateTextDetails
Details for the request to generate text.
GenerateTextResult
The generated text result to return.
GeneratedText
The text generated during each run.
GenericChatRequest
Details for the chat request.
GenericChatResponse
The response for a chat conversation.
GuardrailConfigs
Additional configuration for each guardrail.
GuardrailsInput
The input data for applying guardrails. This can be text, image, video, or audio content.
GuardrailsInputModelConverter
GuardrailsResults
The results of applying each guardrail.
GuardrailsTextInput
Represents a single instance of text in the guardrails input.
ImageContent
Represents a single instance of chat image content.
ImageUrl
Provide a base64 encoded image.
LlamaLlmInferenceRequest
Details for the text generation request for Llama models.
LlamaLlmInferenceResponse
The generated text result to return.
LlmInferenceRequest
The base class for the inference requests.
LlmInferenceRequestModelConverter
LlmInferenceResponse
The base class for inference responses.
LlmInferenceResponseModelConverter
Logprobs
Includes the logarithmic probabilities for the most likely output tokens and the chosen tokens.
For example, if the log probability is 5, the API returns a list of the 5 most likely tokens. The API returns the log probability of the sampled token, so there might be up to logprobs+1 elements in the response.
Message
A message that represents a single chat dialog.
MessageModelConverter
OnDemandServingMode
The model's serving mode is on-demand serving on a shared infrastructure.
PersonallyIdentifiableInformationConfiguration
Configuration for personally identifiable information detection.
PersonallyIdentifiableInformationResult
An item of personally identifiable information.
PromptInjectionConfiguration
Configuration for prompt injection
PromptInjectionProtectionResult
The result of prompt injection protection.
PromptTokensDetails
Breakdown of tokens used in the prompt.
RerankTextDetails
Details required for a rerank request.
RerankTextResult
The rerank response to return to the caller.
SearchQuery
The generated search query.
ServingMode
The model's serving mode, which is either on-demand serving or dedicated serving.
ServingModeModelConverter
StreamOptions
Options for streaming response. Only set this when you set stream: true.
SummarizeTextDetails
Details for the request to summarize text.
SummarizeTextResult
Summarize text result to return to caller.
SystemMessage
Represents a single instance of system message.
TextContent
Represents a single instance of text in the chat content.
TokenLikelihood
An object that contains the returned token and its corresponding likelihood.
ToolCall
The tool call generated by the model, such as function call.
ToolCallModelConverter
ToolChoice
The tool choice for a tool.
ToolChoiceAuto
The model can pick between generating a message or calling one or more tools.
ToolChoiceFunction
The tool choice for a function.
ToolChoiceModelConverter
ToolChoiceNone
The model will not call any tool and instead generates a message.
ToolChoiceRequired
The model must call one or more tools.
ToolDefinition
A tool the model may call.
ToolDefinitionModelConverter
ToolMessage
Represents a single instance of tool message.
Usage
Usage statistics for the completion request.
UserMessage
Represents a single instance of user message.