api.md

Shared Params Types

• llamastackclient.InterleavedContentUnionParam
• llamastackclient.InterleavedContentItemUnionParam
• llamastackclient.SamplingParams
• llamastackclient.SystemMessageParam

Shared Response Types

• llamastackclient.InterleavedContentUnion
• llamastackclient.InterleavedContentItemUnion
• llamastackclient.SafetyViolation
• llamastackclient.ScoringResult

Toolgroups

Response Types:

• llamastackclient.ListToolGroupsResponse
• llamastackclient.ToolGroup

Methods:

• client.Toolgroups.List(ctx context.Context) ([]llamastackclient.ToolGroup, error)
• client.Toolgroups.Get(ctx context.Context, toolgroupID string) (llamastackclient.ToolGroup, error)
• client.Toolgroups.Register(ctx context.Context, body llamastackclient.ToolgroupRegisterParams) error
• client.Toolgroups.Unregister(ctx context.Context, toolgroupID string) error

Tools

Methods:

• client.Tools.List(ctx context.Context, query llamastackclient.ToolListParams) ([]llamastackclient.ToolDef, error)
• client.Tools.Get(ctx context.Context, toolName string) (llamastackclient.ToolDef, error)

ToolRuntime

Response Types:

• llamastackclient.ToolDef
• llamastackclient.ToolInvocationResult

Methods:

• client.ToolRuntime.InvokeTool(ctx context.Context, body llamastackclient.ToolRuntimeInvokeToolParams) (llamastackclient.ToolInvocationResult, error)
• client.ToolRuntime.ListTools(ctx context.Context, query llamastackclient.ToolRuntimeListToolsParams) ([]llamastackclient.ToolDef, error)

RagTool

Responses

Response Types:

• llamastackclient.ResponseObject
• llamastackclient.ResponseObjectStreamUnion
• llamastackclient.ResponseListResponse
• llamastackclient.ResponseDeleteResponse

Methods:

• client.Responses.New(ctx context.Context, body llamastackclient.ResponseNewParams) (llamastackclient.ResponseObject, error)
• client.Responses.Get(ctx context.Context, responseID string) (llamastackclient.ResponseObject, error)
• client.Responses.List(ctx context.Context, query llamastackclient.ResponseListParams) (pagination.OpenAICursorPage[llamastackclient.ResponseListResponse], error)
• client.Responses.Delete(ctx context.Context, responseID string) (llamastackclient.ResponseDeleteResponse, error)

InputItems

Response Types:

• llamastackclient.ResponseInputItemListResponse

Methods:

• client.Responses.InputItems.List(ctx context.Context, responseID string, query llamastackclient.ResponseInputItemListParams) (llamastackclient.ResponseInputItemListResponse, error)

Prompts

Response Types:

• llamastackclient.ListPromptsResponse
• llamastackclient.Prompt

Methods:

• client.Prompts.New(ctx context.Context, body llamastackclient.PromptNewParams) (llamastackclient.Prompt, error)
• client.Prompts.Get(ctx context.Context, promptID string, query llamastackclient.PromptGetParams) (llamastackclient.Prompt, error)
• client.Prompts.Update(ctx context.Context, promptID string, body llamastackclient.PromptUpdateParams) (llamastackclient.Prompt, error)
• client.Prompts.List(ctx context.Context) ([]llamastackclient.Prompt, error)
• client.Prompts.Delete(ctx context.Context, promptID string) error
• client.Prompts.SetDefaultVersion(ctx context.Context, promptID string, body llamastackclient.PromptSetDefaultVersionParams) (llamastackclient.Prompt, error)

Versions

Methods:

• client.Prompts.Versions.List(ctx context.Context, promptID string) ([]llamastackclient.Prompt, error)

Conversations

Response Types:

• llamastackclient.ConversationObject
• llamastackclient.ConversationDeleteResponse

Methods:

• client.Conversations.New(ctx context.Context, body llamastackclient.ConversationNewParams) (llamastackclient.ConversationObject, error)
• client.Conversations.Get(ctx context.Context, conversationID string) (llamastackclient.ConversationObject, error)
• client.Conversations.Update(ctx context.Context, conversationID string, body llamastackclient.ConversationUpdateParams) (llamastackclient.ConversationObject, error)
• client.Conversations.Delete(ctx context.Context, conversationID string) (llamastackclient.ConversationDeleteResponse, error)

Items

Response Types:

• llamastackclient.ConversationItemNewResponse
• llamastackclient.ConversationItemListResponseUnion
• llamastackclient.ConversationItemGetResponseUnion

Methods:

• client.Conversations.Items.New(ctx context.Context, conversationID string, body llamastackclient.ConversationItemNewParams) (llamastackclient.ConversationItemNewResponse, error)
• client.Conversations.Items.List(ctx context.Context, conversationID string, query llamastackclient.ConversationItemListParams) (pagination.OpenAICursorPage[llamastackclient.ConversationItemListResponseUnion], error)
• client.Conversations.Items.Get(ctx context.Context, itemID string, query llamastackclient.ConversationItemGetParams) (llamastackclient.ConversationItemGetResponseUnion, error)

Inspect

Response Types:

• llamastackclient.HealthInfo
• llamastackclient.ProviderInfo
• llamastackclient.RouteInfo
• llamastackclient.VersionInfo

Methods:

• client.Inspect.Health(ctx context.Context) (llamastackclient.HealthInfo, error)
• client.Inspect.Version(ctx context.Context) (llamastackclient.VersionInfo, error)

Embeddings

Response Types:

• llamastackclient.CreateEmbeddingsResponse

Methods:

• client.Embeddings.New(ctx context.Context, body llamastackclient.EmbeddingNewParams) (llamastackclient.CreateEmbeddingsResponse, error)

Chat

Response Types:

• llamastackclient.ChatCompletionChunk

Completions

Response Types:

• llamastackclient.ChatCompletionNewResponseUnion
• llamastackclient.ChatCompletionGetResponse
• llamastackclient.ChatCompletionListResponse

Methods:

• client.Chat.Completions.New(ctx context.Context, body llamastackclient.ChatCompletionNewParams) (llamastackclient.ChatCompletionNewResponseUnion, error)
• client.Chat.Completions.Get(ctx context.Context, completionID string) (llamastackclient.ChatCompletionGetResponse, error)
• client.Chat.Completions.List(ctx context.Context, query llamastackclient.ChatCompletionListParams) (pagination.OpenAICursorPage[llamastackclient.ChatCompletionListResponse], error)

Completions

Response Types:

• llamastackclient.CompletionNewResponse

Methods:

• client.Completions.New(ctx context.Context, body llamastackclient.CompletionNewParams) (llamastackclient.CompletionNewResponse, error)

VectorIo

Response Types:

• llamastackclient.QueryChunksResponse

Methods:

• client.VectorIo.Insert(ctx context.Context, body llamastackclient.VectorIoInsertParams) error
• client.VectorIo.Query(ctx context.Context, body llamastackclient.VectorIoQueryParams) (llamastackclient.QueryChunksResponse, error)

VectorStores

Response Types:

• llamastackclient.ListVectorStoresResponse
• llamastackclient.VectorStore
• llamastackclient.VectorStoreDeleteResponse
• llamastackclient.VectorStoreSearchResponse

Methods:

• client.VectorStores.New(ctx context.Context, body llamastackclient.VectorStoreNewParams) (llamastackclient.VectorStore, error)
• client.VectorStores.Get(ctx context.Context, vectorStoreID string) (llamastackclient.VectorStore, error)
• client.VectorStores.Update(ctx context.Context, vectorStoreID string, body llamastackclient.VectorStoreUpdateParams) (llamastackclient.VectorStore, error)
• client.VectorStores.List(ctx context.Context, query llamastackclient.VectorStoreListParams) (pagination.OpenAICursorPage[llamastackclient.VectorStore], error)
• client.VectorStores.Delete(ctx context.Context, vectorStoreID string) (llamastackclient.VectorStoreDeleteResponse, error)
• client.VectorStores.Search(ctx context.Context, vectorStoreID string, body llamastackclient.VectorStoreSearchParams) (llamastackclient.VectorStoreSearchResponse, error)

Files

Response Types:

• llamastackclient.VectorStoreFile
• llamastackclient.VectorStoreFileDeleteResponse
• llamastackclient.VectorStoreFileContentResponse

Methods:

• client.VectorStores.Files.New(ctx context.Context, vectorStoreID string, body llamastackclient.VectorStoreFileNewParams) (llamastackclient.VectorStoreFile, error)
• client.VectorStores.Files.Get(ctx context.Context, fileID string, query llamastackclient.VectorStoreFileGetParams) (llamastackclient.VectorStoreFile, error)
• client.VectorStores.Files.Update(ctx context.Context, fileID string, params llamastackclient.VectorStoreFileUpdateParams) (llamastackclient.VectorStoreFile, error)
• client.VectorStores.Files.List(ctx context.Context, vectorStoreID string, query llamastackclient.VectorStoreFileListParams) (pagination.OpenAICursorPage[llamastackclient.VectorStoreFile], error)
• client.VectorStores.Files.Delete(ctx context.Context, fileID string, body llamastackclient.VectorStoreFileDeleteParams) (llamastackclient.VectorStoreFileDeleteResponse, error)
• client.VectorStores.Files.Content(ctx context.Context, fileID string, params llamastackclient.VectorStoreFileContentParams) (llamastackclient.VectorStoreFileContentResponse, error)

FileBatches

Response Types:

• llamastackclient.ListVectorStoreFilesInBatchResponse
• llamastackclient.VectorStoreFileBatches

Methods:

• client.VectorStores.FileBatches.New(ctx context.Context, vectorStoreID string, body llamastackclient.VectorStoreFileBatchNewParams) (llamastackclient.VectorStoreFileBatches, error)
• client.VectorStores.FileBatches.Get(ctx context.Context, batchID string, query llamastackclient.VectorStoreFileBatchGetParams) (llamastackclient.VectorStoreFileBatches, error)
• client.VectorStores.FileBatches.Cancel(ctx context.Context, batchID string, body llamastackclient.VectorStoreFileBatchCancelParams) (llamastackclient.VectorStoreFileBatches, error)
• client.VectorStores.FileBatches.ListFiles(ctx context.Context, batchID string, params llamastackclient.VectorStoreFileBatchListFilesParams) (pagination.OpenAICursorPage[llamastackclient.VectorStoreFile], error)

Models

Response Types:

• llamastackclient.ListModelsResponse
• llamastackclient.Model
• llamastackclient.ModelGetResponse
• llamastackclient.ModelRegisterResponse

Methods:

• client.Models.Get(ctx context.Context, modelID string) (llamastackclient.ModelGetResponse, error)
• client.Models.List(ctx context.Context) ([]llamastackclient.Model, error)
• client.Models.Register(ctx context.Context, body llamastackclient.ModelRegisterParams) (llamastackclient.ModelRegisterResponse, error)
• client.Models.Unregister(ctx context.Context, modelID string) error

OpenAI

Methods:

• client.Models.OpenAI.List(ctx context.Context) ([]llamastackclient.Model, error)

Providers

Response Types:

• llamastackclient.ListProvidersResponse

Methods:

• client.Providers.Get(ctx context.Context, providerID string) (llamastackclient.ProviderInfo, error)
• client.Providers.List(ctx context.Context) ([]llamastackclient.ProviderInfo, error)

Routes

Response Types:

• llamastackclient.ListRoutesResponse

Methods:

• client.Routes.List(ctx context.Context, query llamastackclient.RouteListParams) ([]llamastackclient.RouteInfo, error)

Moderations

Response Types:

• llamastackclient.CreateResponse

Methods:

• client.Moderations.New(ctx context.Context, body llamastackclient.ModerationNewParams) (llamastackclient.CreateResponse, error)

Safety

Response Types:

• llamastackclient.RunShieldResponse

Methods:

• client.Safety.RunShield(ctx context.Context, body llamastackclient.SafetyRunShieldParams) (llamastackclient.RunShieldResponse, error)

Shields

Response Types:

• llamastackclient.ListShieldsResponse
• llamastackclient.Shield

Methods:

• client.Shields.Get(ctx context.Context, identifier string) (llamastackclient.Shield, error)
• client.Shields.List(ctx context.Context) ([]llamastackclient.Shield, error)
• client.Shields.Delete(ctx context.Context, identifier string) error
• client.Shields.Register(ctx context.Context, body llamastackclient.ShieldRegisterParams) (llamastackclient.Shield, error)

Scoring

Response Types:

• llamastackclient.ScoringScoreResponse
• llamastackclient.ScoringScoreBatchResponse

Methods:

• client.Scoring.Score(ctx context.Context, body llamastackclient.ScoringScoreParams) (llamastackclient.ScoringScoreResponse, error)
• client.Scoring.ScoreBatch(ctx context.Context, body llamastackclient.ScoringScoreBatchParams) (llamastackclient.ScoringScoreBatchResponse, error)

ScoringFunctions

Params Types:

• llamastackclient.ScoringFnParamsUnion

Response Types:

• llamastackclient.ListScoringFunctionsResponse
• llamastackclient.ScoringFn
• llamastackclient.ScoringFnParamsUnionResp

Methods:

• client.ScoringFunctions.Get(ctx context.Context, scoringFnID string) (llamastackclient.ScoringFn, error)
• client.ScoringFunctions.List(ctx context.Context) ([]llamastackclient.ScoringFn, error)
• client.ScoringFunctions.Register(ctx context.Context, body llamastackclient.ScoringFunctionRegisterParams) error

Files

Response Types:

• llamastackclient.DeleteFileResponse
• llamastackclient.File
• llamastackclient.ListFilesResponse
• llamastackclient.FileContentResponse

Methods:

• client.Files.New(ctx context.Context, body llamastackclient.FileNewParams) (llamastackclient.File, error)
• client.Files.Get(ctx context.Context, fileID string) (llamastackclient.File, error)
• client.Files.List(ctx context.Context, query llamastackclient.FileListParams) (pagination.OpenAICursorPage[llamastackclient.File], error)
• client.Files.Delete(ctx context.Context, fileID string) (llamastackclient.DeleteFileResponse, error)
• client.Files.Content(ctx context.Context, fileID string) (llamastackclient.FileContentResponse, error)

Alpha

Inference

Response Types:

• llamastackclient.AlphaInferenceRerankResponse

Methods:

• client.Alpha.Inference.Rerank(ctx context.Context, body llamastackclient.AlphaInferenceRerankParams) ([]llamastackclient.AlphaInferenceRerankResponse, error)

PostTraining

Params Types:

• llamastackclient.AlgorithmConfigUnionParam

Response Types:

• llamastackclient.ListPostTrainingJobsResponse
• llamastackclient.PostTrainingJob

Methods:

• client.Alpha.PostTraining.PreferenceOptimize(ctx context.Context, body llamastackclient.AlphaPostTrainingPreferenceOptimizeParams) (llamastackclient.PostTrainingJob, error)
• client.Alpha.PostTraining.SupervisedFineTune(ctx context.Context, body llamastackclient.AlphaPostTrainingSupervisedFineTuneParams) (llamastackclient.PostTrainingJob, error)

Job

Response Types:

• llamastackclient.AlphaPostTrainingJobArtifactsResponse
• llamastackclient.AlphaPostTrainingJobStatusResponse

Methods:

• client.Alpha.PostTraining.Job.List(ctx context.Context) ([]llamastackclient.ListPostTrainingJobsResponseData, error)
• client.Alpha.PostTraining.Job.Artifacts(ctx context.Context, query llamastackclient.AlphaPostTrainingJobArtifactsParams) (llamastackclient.AlphaPostTrainingJobArtifactsResponse, error)
• client.Alpha.PostTraining.Job.Cancel(ctx context.Context, body llamastackclient.AlphaPostTrainingJobCancelParams) error
• client.Alpha.PostTraining.Job.Status(ctx context.Context, query llamastackclient.AlphaPostTrainingJobStatusParams) (llamastackclient.AlphaPostTrainingJobStatusResponse, error)

Benchmarks

Response Types:

• llamastackclient.Benchmark
• llamastackclient.ListBenchmarksResponse

Methods:

• client.Alpha.Benchmarks.Get(ctx context.Context, benchmarkID string) (llamastackclient.Benchmark, error)
• client.Alpha.Benchmarks.List(ctx context.Context) ([]llamastackclient.Benchmark, error)
• client.Alpha.Benchmarks.Register(ctx context.Context, body llamastackclient.AlphaBenchmarkRegisterParams) error

Eval

Params Types:

• llamastackclient.BenchmarkConfigParam

Response Types:

• llamastackclient.EvaluateResponse
• llamastackclient.Job

Methods:

• client.Alpha.Eval.EvaluateRows(ctx context.Context, benchmarkID string, body llamastackclient.AlphaEvalEvaluateRowsParams) (llamastackclient.EvaluateResponse, error)
• client.Alpha.Eval.EvaluateRowsAlpha(ctx context.Context, benchmarkID string, body llamastackclient.AlphaEvalEvaluateRowsAlphaParams) (llamastackclient.EvaluateResponse, error)
• client.Alpha.Eval.RunEval(ctx context.Context, benchmarkID string, body llamastackclient.AlphaEvalRunEvalParams) (llamastackclient.Job, error)
• client.Alpha.Eval.RunEvalAlpha(ctx context.Context, benchmarkID string, body llamastackclient.AlphaEvalRunEvalAlphaParams) (llamastackclient.Job, error)

Jobs

Methods:

• client.Alpha.Eval.Jobs.Get(ctx context.Context, jobID string, query llamastackclient.AlphaEvalJobGetParams) (llamastackclient.EvaluateResponse, error)
• client.Alpha.Eval.Jobs.Cancel(ctx context.Context, jobID string, body llamastackclient.AlphaEvalJobCancelParams) error
• client.Alpha.Eval.Jobs.Status(ctx context.Context, jobID string, query llamastackclient.AlphaEvalJobStatusParams) (llamastackclient.Job, error)

Beta

Datasets

Response Types:

• llamastackclient.ListDatasetsResponse
• llamastackclient.BetaDatasetGetResponse
• llamastackclient.BetaDatasetIterrowsResponse
• llamastackclient.BetaDatasetRegisterResponse

Methods:

• client.Beta.Datasets.Get(ctx context.Context, datasetID string) (llamastackclient.BetaDatasetGetResponse, error)
• client.Beta.Datasets.List(ctx context.Context) ([]llamastackclient.ListDatasetsResponseData, error)
• client.Beta.Datasets.Appendrows(ctx context.Context, datasetID string, body llamastackclient.BetaDatasetAppendrowsParams) error
• client.Beta.Datasets.Iterrows(ctx context.Context, datasetID string, query llamastackclient.BetaDatasetIterrowsParams) (llamastackclient.BetaDatasetIterrowsResponse, error)
• client.Beta.Datasets.Register(ctx context.Context, body llamastackclient.BetaDatasetRegisterParams) (llamastackclient.BetaDatasetRegisterResponse, error)
• client.Beta.Datasets.Unregister(ctx context.Context, datasetID string) error