diff --git a/docs/source/references/python_sdk_reference/index.md b/docs/source/references/python_sdk_reference/index.md
index 8ee0375a5..74101f7aa 100644
--- a/docs/source/references/python_sdk_reference/index.md
+++ b/docs/source/references/python_sdk_reference/index.md
@@ -4,29 +4,77 @@
```python
from llama_stack_client.types import (
- Attachment,
+ AgentConfig,
BatchCompletion,
CompletionMessage,
+ ContentDelta,
+ Document,
+ InterleavedContent,
+ InterleavedContentItem,
+ Message,
+ ParamType,
+ QueryConfig,
+ QueryResult,
+ ReturnType,
+ SafetyViolation,
SamplingParams,
+ ScoringResult,
SystemMessage,
ToolCall,
+ ToolParamDefinition,
ToolResponseMessage,
+ URL,
UserMessage,
)
```
-## Telemetry
+## Toolgroups
Types:
```python
-from llama_stack_client.types import TelemetryGetTraceResponse
+from llama_stack_client.types import ListToolGroupsResponse, ToolGroup, ToolgroupListResponse
```
Methods:
-- client.telemetry.get_trace(\*\*params) -> TelemetryGetTraceResponse
-- client.telemetry.log(\*\*params) -> None
+- client.toolgroups.list() -> ToolgroupListResponse
+- client.toolgroups.get(toolgroup_id) -> ToolGroup
+- client.toolgroups.register(\*\*params) -> None
+- client.toolgroups.unregister(toolgroup_id) -> None
+
+## Tools
+
+Types:
+
+```python
+from llama_stack_client.types import ListToolsResponse, Tool, ToolListResponse
+```
+
+Methods:
+
+- client.tools.list(\*\*params) -> ToolListResponse
+- client.tools.get(tool_name) -> Tool
+
+## ToolRuntime
+
+Types:
+
+```python
+from llama_stack_client.types import ToolDef, ToolInvocationResult
+```
+
+Methods:
+
+- client.tool_runtime.invoke_tool(\*\*params) -> ToolInvocationResult
+- client.tool_runtime.list_tools(\*\*params) -> JSONLDecoder[ToolDef]
+
+### RagTool
+
+Methods:
+
+- client.tool_runtime.rag_tool.insert(\*\*params) -> None
+- client.tool_runtime.rag_tool.query(\*\*params) -> QueryResult
## Agents
@@ -36,20 +84,19 @@ Types:
from llama_stack_client.types import (
InferenceStep,
MemoryRetrievalStep,
- RestAPIExecutionConfig,
ShieldCallStep,
ToolExecutionStep,
- ToolParamDefinition,
+ ToolResponse,
AgentCreateResponse,
)
```
Methods:
-- client.agents.create(\*\*params) -> AgentCreateResponse
-- client.agents.delete(\*\*params) -> None
+- client.agents.create(\*\*params) -> AgentCreateResponse
+- client.agents.delete(agent_id) -> None
-### Sessions
+### Session
Types:
@@ -59,104 +106,106 @@ 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
+- client.agents.session.create(agent_id, \*\*params) -> SessionCreateResponse
+- client.agents.session.retrieve(session_id, \*, agent_id, \*\*params) -> Session
+- client.agents.session.delete(session_id, \*, agent_id) -> None
### Steps
Types:
```python
-from llama_stack_client.types.agents import AgentsStep
+from llama_stack_client.types.agents import StepRetrieveResponse
```
Methods:
-- client.agents.steps.retrieve(\*\*params) -> AgentsStep
+- client.agents.steps.retrieve(step_id, \*, agent_id, session_id, turn_id) -> StepRetrieveResponse
-### Turns
+### Turn
Types:
```python
-from llama_stack_client.types.agents import AgentsTurnStreamChunk, Turn, TurnStreamEvent
+from llama_stack_client.types.agents import Turn, TurnCreateResponse
```
Methods:
-- client.agents.turns.create(\*\*params) -> AgentsTurnStreamChunk
-- client.agents.turns.retrieve(\*\*params) -> Turn
+- client.agents.turn.create(session_id, \*, agent_id, \*\*params) -> TurnCreateResponse
+- client.agents.turn.retrieve(turn_id, \*, agent_id, session_id) -> Turn
+
+## BatchInference
+
+Types:
+
+```python
+from llama_stack_client.types import BatchInferenceChatCompletionResponse
+```
+
+Methods:
+
+- client.batch_inference.chat_completion(\*\*params) -> BatchInferenceChatCompletionResponse
+- client.batch_inference.completion(\*\*params) -> BatchCompletion
## Datasets
Types:
```python
-from llama_stack_client.types import TrainEvalDataset
+from llama_stack_client.types import (
+ ListDatasetsResponse,
+ DatasetRetrieveResponse,
+ DatasetListResponse,
+)
```
Methods:
-- client.datasets.create(\*\*params) -> None
-- client.datasets.delete(\*\*params) -> None
-- client.datasets.get(\*\*params) -> TrainEvalDataset
+- client.datasets.retrieve(dataset_id) -> Optional[DatasetRetrieveResponse]
+- client.datasets.list() -> DatasetListResponse
+- client.datasets.register(\*\*params) -> None
+- client.datasets.unregister(dataset_id) -> None
-## Evaluate
+## Eval
Types:
```python
-from llama_stack_client.types import EvaluationJob
+from llama_stack_client.types import EvaluateResponse, Job
```
+Methods:
+
+- client.eval.evaluate_rows(task_id, \*\*params) -> EvaluateResponse
+- client.eval.run_eval(task_id, \*\*params) -> Job
+
### Jobs
Types:
```python
-from llama_stack_client.types.evaluate import (
- EvaluationJobArtifacts,
- EvaluationJobLogStream,
- EvaluationJobStatus,
-)
+from llama_stack_client.types.eval import JobStatusResponse
```
Methods:
-- client.evaluate.jobs.list() -> EvaluationJob
-- client.evaluate.jobs.cancel(\*\*params) -> None
+- client.eval.jobs.retrieve(job_id, \*, task_id) -> EvaluateResponse
+- client.eval.jobs.cancel(job_id, \*, task_id) -> None
+- client.eval.jobs.status(job_id, \*, task_id) -> Optional[JobStatusResponse]
-#### Artifacts
+## Inspect
+
+Types:
+
+```python
+from llama_stack_client.types import HealthInfo, ProviderInfo, RouteInfo, VersionInfo
+```
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
+- client.inspect.health() -> HealthInfo
+- client.inspect.version() -> VersionInfo
## Inference
@@ -164,8 +213,8 @@ Types:
```python
from llama_stack_client.types import (
- ChatCompletionStreamChunk,
- CompletionStreamChunk,
+ CompletionResponse,
+ EmbeddingsResponse,
TokenLogProbs,
InferenceChatCompletionResponse,
InferenceCompletionResponse,
@@ -174,175 +223,232 @@ from llama_stack_client.types import (
Methods:
-- client.inference.chat_completion(\*\*params) -> InferenceChatCompletionResponse
-- client.inference.completion(\*\*params) -> InferenceCompletionResponse
+- client.inference.chat_completion(\*\*params) -> InferenceChatCompletionResponse
+- client.inference.completion(\*\*params) -> InferenceCompletionResponse
+- client.inference.embeddings(\*\*params) -> EmbeddingsResponse
-### Embeddings
+## VectorIo
Types:
```python
-from llama_stack_client.types.inference import Embeddings
+from llama_stack_client.types import QueryChunksResponse
```
Methods:
-- client.inference.embeddings.create(\*\*params) -> Embeddings
+- client.vector_io.insert(\*\*params) -> None
+- client.vector_io.query(\*\*params) -> QueryChunksResponse
-## Safety
-
-Types:
-
-```python
-from llama_stack_client.types import RunSheidResponse
-```
-
-Methods:
-
-- client.safety.run_shield(\*\*params) -> RunSheidResponse
-
-## Memory
+## VectorDBs
Types:
```python
from llama_stack_client.types import (
- QueryDocuments,
- MemoryCreateResponse,
- MemoryRetrieveResponse,
- MemoryListResponse,
- MemoryDropResponse,
+ ListVectorDBsResponse,
+ VectorDBRetrieveResponse,
+ VectorDBListResponse,
+ VectorDBRegisterResponse,
)
```
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:
-
-```python
-from llama_stack_client.types.memory import DocumentRetrieveResponse
-```
-
-Methods:
-
-- client.memory.documents.retrieve(\*\*params) -> DocumentRetrieveResponse
-- client.memory.documents.delete(\*\*params) -> None
-
-## PostTraining
-
-Types:
-
-```python
-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:
-
-```python
-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:
-
-```python
-from llama_stack_client.types import RewardScoring, ScoredDialogGenerations
-```
-
-Methods:
-
-- client.reward_scoring.score(\*\*params) -> RewardScoring
-
-## SyntheticDataGeneration
-
-Types:
-
-```python
-from llama_stack_client.types import SyntheticDataGeneration
-```
-
-Methods:
-
-- client.synthetic_data_generation.generate(\*\*params) -> SyntheticDataGeneration
-
-## BatchInference
-
-Types:
-
-```python
-from llama_stack_client.types import BatchChatCompletion
-```
-
-Methods:
-
-- client.batch_inference.chat_completion(\*\*params) -> BatchChatCompletion
-- client.batch_inference.completion(\*\*params) -> BatchCompletion
+- client.vector_dbs.retrieve(vector_db_id) -> Optional[VectorDBRetrieveResponse]
+- client.vector_dbs.list() -> VectorDBListResponse
+- client.vector_dbs.register(\*\*params) -> VectorDBRegisterResponse
+- client.vector_dbs.unregister(vector_db_id) -> None
## Models
Types:
```python
-from llama_stack_client.types import ModelServingSpec
+from llama_stack_client.types import ListModelsResponse, Model, ModelListResponse
```
Methods:
-- client.models.list() -> ModelServingSpec
-- client.models.get(\*\*params) -> Optional
+- client.models.retrieve(model_id) -> Optional[Model]
+- client.models.list() -> ModelListResponse
+- client.models.register(\*\*params) -> Model
+- client.models.unregister(model_id) -> None
-## MemoryBanks
+## PostTraining
Types:
```python
-from llama_stack_client.types import MemoryBankSpec
+from llama_stack_client.types import ListPostTrainingJobsResponse, PostTrainingJob
```
Methods:
-- client.memory_banks.list() -> MemoryBankSpec
-- client.memory_banks.get(\*\*params) -> Optional
+- client.post_training.preference_optimize(\*\*params) -> PostTrainingJob
+- client.post_training.supervised_fine_tune(\*\*params) -> PostTrainingJob
+
+### Job
+
+Types:
+
+```python
+from llama_stack_client.types.post_training import (
+ JobListResponse,
+ JobArtifactsResponse,
+ JobStatusResponse,
+)
+```
+
+Methods:
+
+- client.post_training.job.list() -> JobListResponse
+- client.post_training.job.artifacts(\*\*params) -> Optional[JobArtifactsResponse]
+- client.post_training.job.cancel(\*\*params) -> None
+- client.post_training.job.status(\*\*params) -> Optional[JobStatusResponse]
+
+## Providers
+
+Types:
+
+```python
+from llama_stack_client.types import ListProvidersResponse, ProviderListResponse
+```
+
+Methods:
+
+- client.providers.list() -> ProviderListResponse
+
+## Routes
+
+Types:
+
+```python
+from llama_stack_client.types import ListRoutesResponse, RouteListResponse
+```
+
+Methods:
+
+- client.routes.list() -> RouteListResponse
+
+## Safety
+
+Types:
+
+```python
+from llama_stack_client.types import RunShieldResponse
+```
+
+Methods:
+
+- client.safety.run_shield(\*\*params) -> RunShieldResponse
## Shields
Types:
```python
-from llama_stack_client.types import ShieldSpec
+from llama_stack_client.types import ListShieldsResponse, Shield, ShieldListResponse
```
Methods:
-- client.shields.list() -> ShieldSpec
-- client.shields.get(\*\*params) -> Optional
+- client.shields.retrieve(identifier) -> Optional[Shield]
+- client.shields.list() -> ShieldListResponse
+- client.shields.register(\*\*params) -> Shield
+
+## SyntheticDataGeneration
+
+Types:
+
+```python
+from llama_stack_client.types import SyntheticDataGenerationResponse
+```
+
+Methods:
+
+- client.synthetic_data_generation.generate(\*\*params) -> SyntheticDataGenerationResponse
+
+## Telemetry
+
+Types:
+
+```python
+from llama_stack_client.types import (
+ QuerySpansResponse,
+ SpanWithStatus,
+ Trace,
+ TelemetryGetSpanResponse,
+ TelemetryGetSpanTreeResponse,
+ TelemetryQuerySpansResponse,
+ TelemetryQueryTracesResponse,
+)
+```
+
+Methods:
+
+- client.telemetry.get_span(span_id, \*, trace_id) -> TelemetryGetSpanResponse
+- client.telemetry.get_span_tree(span_id, \*\*params) -> TelemetryGetSpanTreeResponse
+- client.telemetry.get_trace(trace_id) -> Trace
+- client.telemetry.log_event(\*\*params) -> None
+- client.telemetry.query_spans(\*\*params) -> TelemetryQuerySpansResponse
+- client.telemetry.query_traces(\*\*params) -> TelemetryQueryTracesResponse
+- client.telemetry.save_spans_to_dataset(\*\*params) -> None
+
+## Datasetio
+
+Types:
+
+```python
+from llama_stack_client.types import PaginatedRowsResult
+```
+
+Methods:
+
+- client.datasetio.append_rows(\*\*params) -> None
+- client.datasetio.get_rows_paginated(\*\*params) -> PaginatedRowsResult
+
+## Scoring
+
+Types:
+
+```python
+from llama_stack_client.types import ScoringScoreResponse, ScoringScoreBatchResponse
+```
+
+Methods:
+
+- client.scoring.score(\*\*params) -> ScoringScoreResponse
+- client.scoring.score_batch(\*\*params) -> ScoringScoreBatchResponse
+
+## ScoringFunctions
+
+Types:
+
+```python
+from llama_stack_client.types import (
+ ListScoringFunctionsResponse,
+ ScoringFn,
+ ScoringFunctionListResponse,
+)
+```
+
+Methods:
+
+- client.scoring_functions.retrieve(scoring_fn_id) -> Optional[ScoringFn]
+- client.scoring_functions.list() -> ScoringFunctionListResponse
+- client.scoring_functions.register(\*\*params) -> None
+
+## EvalTasks
+
+Types:
+
+```python
+from llama_stack_client.types import EvalTask, ListEvalTasksResponse, EvalTaskListResponse
+```
+
+Methods:
+
+- client.eval_tasks.retrieve(eval_task_id) -> Optional[EvalTask]
+- client.eval_tasks.list() -> EvalTaskListResponse
+- client.eval_tasks.register(\*\*params) -> None