From 00c59b7e399ef126f16e8aeccf1ede3f841ac69f Mon Sep 17 00:00:00 2001 From: Ashwin Bharambe Date: Fri, 22 Nov 2024 18:27:16 -0800 Subject: [PATCH] Add Python SDK reference --- docs/source/references/index.md | 6 +- ...md => llama_stack_client_cli_reference.md} | 0 .../references/python_sdk_reference/index.md | 348 ++++++++++++++++++ 3 files changed, 352 insertions(+), 2 deletions(-) rename docs/source/references/{llama_stack_client_cli_reference/index.md => llama_stack_client_cli_reference.md} (100%) create mode 100644 docs/source/references/python_sdk_reference/index.md diff --git a/docs/source/references/index.md b/docs/source/references/index.md index 85b1ad75a..2a5b0889e 100644 --- a/docs/source/references/index.md +++ b/docs/source/references/index.md @@ -1,15 +1,17 @@ # References - [API Reference](api_reference/index) for the Llama Stack API specification +- [Python SDK Reference](python_sdk_reference/index) - [Llama CLI](llama_cli_reference/index) for building and running your Llama Stack server - [Llama Stack Client CLI](llama_stack_client_cli_reference/index) for interacting with your Llama Stack server ```{toctree} -:maxdepth: 2 +:maxdepth: 1 :hidden: api_reference/index +python_sdk_reference/index llama_cli_reference/index -llama_stack_client_cli_reference/index +llama_stack_client_cli_reference llama_cli_reference/download_models ``` diff --git a/docs/source/references/llama_stack_client_cli_reference/index.md b/docs/source/references/llama_stack_client_cli_reference.md similarity index 100% rename from docs/source/references/llama_stack_client_cli_reference/index.md rename to docs/source/references/llama_stack_client_cli_reference.md diff --git a/docs/source/references/python_sdk_reference/index.md b/docs/source/references/python_sdk_reference/index.md new file mode 100644 index 000000000..8ee0375a5 --- /dev/null +++ b/docs/source/references/python_sdk_reference/index.md @@ -0,0 +1,348 @@ +# Python SDK Reference + +## Shared Types + +```python +from llama_stack_client.types import ( + Attachment, + BatchCompletion, + CompletionMessage, + SamplingParams, + SystemMessage, + ToolCall, + ToolResponseMessage, + UserMessage, +) +``` + +## Telemetry + +Types: + +```python +from llama_stack_client.types import TelemetryGetTraceResponse +``` + +Methods: + +- client.telemetry.get_trace(\*\*params) -> TelemetryGetTraceResponse +- client.telemetry.log(\*\*params) -> None + +## Agents + +Types: + +```python +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: + +```python +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: + +```python +from llama_stack_client.types.agents import AgentsStep +``` + +Methods: + +- client.agents.steps.retrieve(\*\*params) -> AgentsStep + +### Turns + +Types: + +```python +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: + +```python +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: + +```python +from llama_stack_client.types import EvaluationJob +``` + +### Jobs + +Types: + +```python +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: + +```python +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: + +```python +from llama_stack_client.types.inference import Embeddings +``` + +Methods: + +- client.inference.embeddings.create(\*\*params) -> Embeddings + +## Safety + +Types: + +```python +from llama_stack_client.types import RunSheidResponse +``` + +Methods: + +- client.safety.run_shield(\*\*params) -> RunSheidResponse + +## Memory + +Types: + +```python +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: + +```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 + +## Models + +Types: + +```python +from llama_stack_client.types import ModelServingSpec +``` + +Methods: + +- client.models.list() -> ModelServingSpec +- client.models.get(\*\*params) -> Optional + +## MemoryBanks + +Types: + +```python +from llama_stack_client.types import MemoryBankSpec +``` + +Methods: + +- client.memory_banks.list() -> MemoryBankSpec +- client.memory_banks.get(\*\*params) -> Optional + +## Shields + +Types: + +```python +from llama_stack_client.types import ShieldSpec +``` + +Methods: + +- client.shields.list() -> ShieldSpec +- client.shields.get(\*\*params) -> Optional