Generative Ai Inference

oci.generative_ai_inference.GenerativeAiInferenceClient	OCI Generative AI is a fully managed service that provides a set of state-of-the-art, customizable large language models (LLMs) that cover a wide range of use cases for text generation, summarization, and text embeddings.
oci.generative_ai_inference.GenerativeAiInferenceClientCompositeOperations	This class provides a wrapper around GenerativeAiInferenceClient and offers convenience methods for operations that would otherwise need to be chained together.

Models

oci.generative_ai_inference.models.Annotation	An annotation attached to the assistant’s message, used to represent additional metadata such as citations.
oci.generative_ai_inference.models.ApplyGuardrailsDetails	Details for applying guardrails to the input text.
oci.generative_ai_inference.models.ApplyGuardrailsResult	The result of applying guardrails to the input text.
oci.generative_ai_inference.models.ApproximateLocation	To refine search results based on geography, you can specify an approximate user location using any of the following: - city and region are free-text strings, like “Minneapolis” and “Minnesota”.
oci.generative_ai_inference.models.AssistantMessage	Represents a single instance of assistant message.
oci.generative_ai_inference.models.AudioContent	Represents a single instance of chat audio content.
oci.generative_ai_inference.models.AudioUrl	Provide a base64 encoded audio or an audio uri if it’s supported.
oci.generative_ai_inference.models.BaseChatRequest	The base class to use for the chat inference request.
oci.generative_ai_inference.models.BaseChatResponse	The base class that creates the chat response.
oci.generative_ai_inference.models.CategoryScore	A category with its score.
oci.generative_ai_inference.models.ChatChoice	Represents a single instance of the chat response.
oci.generative_ai_inference.models.ChatContent	The base class for the chat content.
oci.generative_ai_inference.models.ChatDetails	Details of the conversation for the model to respond.
oci.generative_ai_inference.models.ChatResult	The response to the chat conversation.
oci.generative_ai_inference.models.Choice	Represents a single instance of the generated text.
oci.generative_ai_inference.models.Citation	A section of the generated response which cites the documents that were used for generating the response.
oci.generative_ai_inference.models.CohereChatBotMessage	A message that represents a single chat dialog as CHATBOT role.
oci.generative_ai_inference.models.CohereChatRequest	Details for the chat request for Cohere models.
oci.generative_ai_inference.models.CohereChatResponse	The response to the chat conversation.
oci.generative_ai_inference.models.CohereLlmInferenceRequest	Details for the text generation request for Cohere models.
oci.generative_ai_inference.models.CohereLlmInferenceResponse	The generated text result to return.
oci.generative_ai_inference.models.CohereMessage	A message that represents a single chat dialog.
oci.generative_ai_inference.models.CohereParameterDefinition	A definition of tool parameter.
oci.generative_ai_inference.models.CohereResponseFormat	Specify the format the model output is guaranteed to be of
oci.generative_ai_inference.models.CohereResponseJsonFormat	The json object format for the model structured output
oci.generative_ai_inference.models.CohereResponseTextFormat	The text format for cohere model response
oci.generative_ai_inference.models.CohereSystemMessage	A message that represents a single chat dialog as SYSTEM role.
oci.generative_ai_inference.models.CohereTool	A definition of tool (function).
oci.generative_ai_inference.models.CohereToolCall	A tool call generated by the model.
oci.generative_ai_inference.models.CohereToolMessage	A message that represents a single chat dialog as TOOL role.
oci.generative_ai_inference.models.CohereToolResult	The result from invoking tools recommended by the model in the previous chat turn.
oci.generative_ai_inference.models.CohereUserMessage	A message that represents a single chat dialog as USER role.
oci.generative_ai_inference.models.CompletionTokensDetails	Breakdown of tokens used in a completion.
oci.generative_ai_inference.models.ContentModerationConfiguration	Configuration for content moderation.
oci.generative_ai_inference.models.ContentModerationResult	The result of content moderation.
oci.generative_ai_inference.models.DedicatedServingMode	The model’s serving mode is dedicated serving and has an endpoint on a dedicated AI cluster.
oci.generative_ai_inference.models.DeveloperMessage	Developer-provided instructions that the model should follow, regardless of messages sent by the user.
oci.generative_ai_inference.models.Document	The input of the document to rerank.
oci.generative_ai_inference.models.DocumentRank	An object that contains a relevance score, an index and the text for a document.
oci.generative_ai_inference.models.EmbedTextDetails	Details for the request to embed texts.
oci.generative_ai_inference.models.EmbedTextResult	The generated embedded result to return.
oci.generative_ai_inference.models.FunctionCall	The function call generated by the model.
oci.generative_ai_inference.models.FunctionDefinition	A function the model may call.
oci.generative_ai_inference.models.GenerateTextDetails	Details for the request to generate text.
oci.generative_ai_inference.models.GenerateTextResult	The generated text result to return.
oci.generative_ai_inference.models.GeneratedText	The text generated during each run.
oci.generative_ai_inference.models.GenericChatRequest	Details for the chat request.
oci.generative_ai_inference.models.GenericChatResponse	The response for a chat conversation.
oci.generative_ai_inference.models.GroundingChunk	object containing the source.
oci.generative_ai_inference.models.GroundingMetadata	Grounding metadata.
oci.generative_ai_inference.models.GroundingSupport	chunk to connect model response text to the source in groundingChunk
oci.generative_ai_inference.models.GroundingSupportSegment	segment within groundingSupport.
oci.generative_ai_inference.models.GroundingWebChunk	object containing the web source.
oci.generative_ai_inference.models.GuardrailConfigs	Additional configuration for each guardrail.
oci.generative_ai_inference.models.GuardrailsInput	The input data for applying guardrails.
oci.generative_ai_inference.models.GuardrailsResults	The results of applying each guardrail.
oci.generative_ai_inference.models.GuardrailsTextInput	Represents a single instance of text in the guardrails input.
oci.generative_ai_inference.models.ImageContent	Represents a single instance of chat image content.
oci.generative_ai_inference.models.ImageUrl	Provide a base64 encoded image or an image uri if it’s supported.
oci.generative_ai_inference.models.JsonObjectResponseFormat	Enables JSON mode, which ensures the message the model generates is valid JSON.
oci.generative_ai_inference.models.JsonSchemaResponseFormat	Enables Structured Outputs which ensures the model will match your supplied JSON schema.
oci.generative_ai_inference.models.LlamaLlmInferenceRequest	Details for the text generation request for Llama models.
oci.generative_ai_inference.models.LlamaLlmInferenceResponse	The generated text result to return.
oci.generative_ai_inference.models.LlmInferenceRequest	The base class for the inference requests.
oci.generative_ai_inference.models.LlmInferenceResponse	The base class for inference responses.
oci.generative_ai_inference.models.Logprobs	Includes the logarithmic probabilities for the most likely output tokens and the chosen tokens.
oci.generative_ai_inference.models.Message	A message that represents a single chat dialog.
oci.generative_ai_inference.models.OnDemandServingMode	The model’s serving mode is on-demand serving on a shared infrastructure.
oci.generative_ai_inference.models.PersonallyIdentifiableInformationConfiguration	Configuration for personally identifiable information detection.
oci.generative_ai_inference.models.PersonallyIdentifiableInformationResult	An item of personally identifiable information.
oci.generative_ai_inference.models.Prediction	Configuration for a Predicted Output, which can greatly improve response times when large parts of the model response are known ahead of time.
oci.generative_ai_inference.models.PromptInjectionConfiguration	Configuration for prompt injection
oci.generative_ai_inference.models.PromptInjectionProtectionResult	The result of prompt injection protection.
oci.generative_ai_inference.models.PromptTokensDetails	Breakdown of tokens used in the prompt.
oci.generative_ai_inference.models.RerankTextDetails	Details required for a rerank request.
oci.generative_ai_inference.models.RerankTextResult	The rerank response to return to the caller.
oci.generative_ai_inference.models.ResponseFormat	An object specifying the format that the model must output.
oci.generative_ai_inference.models.ResponseJsonSchema	The JSON schema definition to be used in JSON_SCHEMA response format.
oci.generative_ai_inference.models.SearchEntryPoint	Contains the HTML and CSS to render the required Search Suggestions.
oci.generative_ai_inference.models.SearchQuery	The generated search query.
oci.generative_ai_inference.models.ServingMode	The model’s serving mode, which is either on-demand serving or dedicated serving.
oci.generative_ai_inference.models.StaticContent	Static predicted output content, such as the content of a text file that is being regenerated.
oci.generative_ai_inference.models.StreamOptions	Options for streaming response.
oci.generative_ai_inference.models.SummarizeTextDetails	Details for the request to summarize text.
oci.generative_ai_inference.models.SummarizeTextResult	Summarize text result to return to caller.
oci.generative_ai_inference.models.SystemMessage	Represents a single instance of system message.
oci.generative_ai_inference.models.TextContent	Represents a single instance of text in the chat content.
oci.generative_ai_inference.models.TextResponseFormat	Enables TEXT mode.
oci.generative_ai_inference.models.TokenLikelihood	An object that contains the returned token and its corresponding likelihood.
oci.generative_ai_inference.models.ToolCall	The tool call generated by the model, such as function call.
oci.generative_ai_inference.models.ToolChoice	The tool choice for a tool.
oci.generative_ai_inference.models.ToolChoiceAuto	The model can pick between generating a message or calling one or more tools.
oci.generative_ai_inference.models.ToolChoiceFunction	The tool choice for a function.
oci.generative_ai_inference.models.ToolChoiceNone	The model will not call any tool and instead generates a message.
oci.generative_ai_inference.models.ToolChoiceRequired	The model must call one or more tools.
oci.generative_ai_inference.models.ToolDefinition	A tool the model may call.
oci.generative_ai_inference.models.ToolMessage	Represents a single instance of tool message.
oci.generative_ai_inference.models.UrlCitation	Contains metadata for a cited URL included in the assistant’s response.
oci.generative_ai_inference.models.Usage	Usage statistics for the completion request.
oci.generative_ai_inference.models.UserMessage	Represents a single instance of user message.
oci.generative_ai_inference.models.VideoContent	Represents a single instance of chat video content.
oci.generative_ai_inference.models.VideoUrl	The base64 encoded video data or a video uri if it’s supported.
oci.generative_ai_inference.models.WebSearchOptions	Options for performing a web search to augment the response.