api.md

Shared Types

from llama_stack_client.types import (
    Attachment,
    BatchCompletion,
    CompletionMessage,
    SamplingParams,
    SystemMessage,
    ToolCall,
    ToolResponseMessage,
    UserMessage,
)

Telemetry

Types:

from llama_stack_client.types import TelemetryGetTraceResponse

Methods:

• client.telemetry.get_trace(**params) -> TelemetryGetTraceResponse
• client.telemetry.log(**params) -> None

Agents

Types:

from llama_stack_client.types import (
    InferenceStep,
    MemoryRetrievalStep,
    RestAPIExecutionConfig,
    ShieldCallStep,
    ToolExecutionStep,
    ToolParamDefinition,
    AgentCreateResponse,
)

Methods:

• client.agents.create(**params) -> AgentCreateResponse
• client.agents.delete(**params) -> None

Sessions

Types:

from llama_stack_client.types.agents import Session, SessionCreateResponse

Methods:

• client.agents.sessions.create(**params) -> SessionCreateResponse
• client.agents.sessions.retrieve(**params) -> Session
• client.agents.sessions.delete(**params) -> None

Steps

Types:

from llama_stack_client.types.agents import AgentsStep

Methods:

• client.agents.steps.retrieve(**params) -> AgentsStep

Turns

Types:

from llama_stack_client.types.agents import AgentsTurnStreamChunk, Turn, TurnStreamEvent

Methods:

• client.agents.turns.create(**params) -> AgentsTurnStreamChunk
• client.agents.turns.retrieve(**params) -> Turn

Datasets

Types:

from llama_stack_client.types import TrainEvalDataset

Methods:

• client.datasets.create(**params) -> None
• client.datasets.delete(**params) -> None
• client.datasets.get(**params) -> TrainEvalDataset

Evaluate

Types:

from llama_stack_client.types import EvaluationJob

Jobs

Types:

from llama_stack_client.types.evaluate import (
    EvaluationJobArtifacts,
    EvaluationJobLogStream,
    EvaluationJobStatus,
)

Methods:

• client.evaluate.jobs.list() -> EvaluationJob
• client.evaluate.jobs.cancel(**params) -> None

Artifacts

Methods:

• client.evaluate.jobs.artifacts.list(**params) -> EvaluationJobArtifacts

Logs

Methods:

• client.evaluate.jobs.logs.list(**params) -> EvaluationJobLogStream

Status

Methods:

• client.evaluate.jobs.status.list(**params) -> EvaluationJobStatus

QuestionAnswering

Methods:

• client.evaluate.question_answering.create(**params) -> EvaluationJob

Evaluations

Methods:

• client.evaluations.summarization(**params) -> EvaluationJob
• client.evaluations.text_generation(**params) -> EvaluationJob

Inference

Types:

from llama_stack_client.types import (
    ChatCompletionStreamChunk,
    CompletionStreamChunk,
    TokenLogProbs,
    InferenceChatCompletionResponse,
    InferenceCompletionResponse,
)

Methods:

• client.inference.chat_completion(**params) -> InferenceChatCompletionResponse
• client.inference.completion(**params) -> InferenceCompletionResponse

Embeddings

Types:

from llama_stack_client.types.inference import Embeddings

Methods:

• client.inference.embeddings.create(**params) -> Embeddings

Safety

Types:

from llama_stack_client.types import RunSheidResponse

Methods:

• client.safety.run_shield(**params) -> RunSheidResponse

Memory

Types:

from llama_stack_client.types import (
    QueryDocuments,
    MemoryCreateResponse,
    MemoryRetrieveResponse,
    MemoryListResponse,
    MemoryDropResponse,
)

Methods:

• client.memory.create(**params) -> object
• client.memory.retrieve(**params) -> object
• client.memory.update(**params) -> None
• client.memory.list() -> object
• client.memory.drop(**params) -> str
• client.memory.insert(**params) -> None
• client.memory.query(**params) -> QueryDocuments

Documents

Types:

from llama_stack_client.types.memory import DocumentRetrieveResponse

Methods:

• client.memory.documents.retrieve(**params) -> DocumentRetrieveResponse
• client.memory.documents.delete(**params) -> None

PostTraining

Types:

from llama_stack_client.types import PostTrainingJob

Methods:

• client.post_training.preference_optimize(**params) -> PostTrainingJob
• client.post_training.supervised_fine_tune(**params) -> PostTrainingJob

Jobs

Types:

from llama_stack_client.types.post_training import (
    PostTrainingJobArtifacts,
    PostTrainingJobLogStream,
    PostTrainingJobStatus,
)

Methods:

• client.post_training.jobs.list() -> PostTrainingJob
• client.post_training.jobs.artifacts(**params) -> PostTrainingJobArtifacts
• client.post_training.jobs.cancel(**params) -> None
• client.post_training.jobs.logs(**params) -> PostTrainingJobLogStream
• client.post_training.jobs.status(**params) -> PostTrainingJobStatus

RewardScoring

Types:

from llama_stack_client.types import RewardScoring, ScoredDialogGenerations

Methods:

• client.reward_scoring.score(**params) -> RewardScoring

SyntheticDataGeneration

Types:

from llama_stack_client.types import SyntheticDataGeneration

Methods:

• client.synthetic_data_generation.generate(**params) -> SyntheticDataGeneration

BatchInference

Types:

from llama_stack_client.types import BatchChatCompletion

Methods:

• client.batch_inference.chat_completion(**params) -> BatchChatCompletion
• client.batch_inference.completion(**params) -> BatchCompletion

Models

Types:

from llama_stack_client.types import ModelServingSpec

Methods:

• client.models.list() -> ModelServingSpec
• client.models.get(**params) -> Optional

MemoryBanks

Types:

from llama_stack_client.types import MemoryBankSpec

Methods:

• client.memory_banks.list() -> MemoryBankSpec
• client.memory_banks.get(**params) -> Optional

Shields

Types:

from llama_stack_client.types import ShieldSpec

Methods:

• client.shields.list() -> ShieldSpec
• client.shields.get(**params) -> Optional