diff --git a/llama_toolchain/agentic_system/api/api.py b/llama_toolchain/agentic_system/api/api.py
index b8be54861..95af3727b 100644
--- a/llama_toolchain/agentic_system/api/api.py
+++ b/llama_toolchain/agentic_system/api/api.py
@@ -416,7 +416,16 @@ class AgenticSystem(Protocol):
@webmethod(route="/agentic_system/turn/create")
async def create_agentic_system_turn(
self,
- request: AgenticSystemTurnCreateRequest,
+ agent_id: str,
+ session_id: str,
+ messages: List[
+ Union[
+ UserMessage,
+ ToolResponseMessage,
+ ]
+ ],
+ attachments: Optional[List[Attachment]] = None,
+ stream: Optional[bool] = False,
) -> AgenticSystemTurnResponseStreamChunk: ...
@webmethod(route="/agentic_system/turn/get")
diff --git a/llama_toolchain/agentic_system/client.py b/llama_toolchain/agentic_system/client.py
index e30e90376..52cf0dee2 100644
--- a/llama_toolchain/agentic_system/client.py
+++ b/llama_toolchain/agentic_system/client.py
@@ -73,9 +73,7 @@ class AgenticSystemClient(AgenticSystem):
async with client.stream(
"POST",
f"{self.base_url}/agentic_system/turn/create",
- json={
- "request": encodable_dict(request),
- },
+ json=encodable_dict(request),
headers={"Content-Type": "application/json"},
timeout=20,
) as response:
diff --git a/llama_toolchain/agentic_system/meta_reference/agent_instance.py b/llama_toolchain/agentic_system/meta_reference/agent_instance.py
index 36c3d19e8..202f42a3c 100644
--- a/llama_toolchain/agentic_system/meta_reference/agent_instance.py
+++ b/llama_toolchain/agentic_system/meta_reference/agent_instance.py
@@ -388,19 +388,17 @@ class ChatAgent(ShieldRunnerMixin):
)
)
- req = ChatCompletionRequest(
- model=self.agent_config.model,
- messages=input_messages,
+ tool_calls = []
+ content = ""
+ stop_reason = None
+ async for chunk in self.inference_api.chat_completion(
+ self.agent_config.model,
+ input_messages,
tools=self._get_tools(),
tool_prompt_format=self.agent_config.tool_prompt_format,
stream=True,
sampling_params=sampling_params,
- )
-
- tool_calls = []
- content = ""
- stop_reason = None
- async for chunk in self.inference_api.chat_completion(req):
+ ):
event = chunk.event
if event.event_type == ChatCompletionResponseEventType.start:
continue
diff --git a/llama_toolchain/agentic_system/meta_reference/agentic_system.py b/llama_toolchain/agentic_system/meta_reference/agentic_system.py
index 9caa3a75b..3990ab58a 100644
--- a/llama_toolchain/agentic_system/meta_reference/agentic_system.py
+++ b/llama_toolchain/agentic_system/meta_reference/agentic_system.py
@@ -114,8 +114,26 @@ class MetaReferenceAgenticSystemImpl(AgenticSystem):
async def create_agentic_system_turn(
self,
- request: AgenticSystemTurnCreateRequest,
+ agent_id: str,
+ session_id: str,
+ messages: List[
+ Union[
+ UserMessage,
+ ToolResponseMessage,
+ ]
+ ],
+ attachments: Optional[List[Attachment]] = None,
+ stream: Optional[bool] = False,
) -> AsyncGenerator:
+ # wrapper request to make it easier to pass around (internal only, not exposed to API)
+ request = AgenticSystemTurnCreateRequest(
+ agent_id=agent_id,
+ session_id=session_id,
+ messages=messages,
+ attachments=attachments,
+ stream=stream,
+ )
+
agent_id = request.agent_id
assert agent_id in AGENT_INSTANCES_BY_ID, f"System {agent_id} not found"
agent = AGENT_INSTANCES_BY_ID[agent_id]
diff --git a/llama_toolchain/batch_inference/api/api.py b/llama_toolchain/batch_inference/api/api.py
index a02815388..3d67120dd 100644
--- a/llama_toolchain/batch_inference/api/api.py
+++ b/llama_toolchain/batch_inference/api/api.py
@@ -51,11 +51,21 @@ class BatchInference(Protocol):
@webmethod(route="/batch_inference/completion")
async def batch_completion(
self,
- request: BatchCompletionRequest,
+ model: str,
+ content_batch: List[InterleavedTextMedia],
+ sampling_params: Optional[SamplingParams] = SamplingParams(),
+ logprobs: Optional[LogProbConfig] = None,
) -> BatchCompletionResponse: ...
@webmethod(route="/batch_inference/chat_completion")
async def batch_chat_completion(
self,
- request: BatchChatCompletionRequest,
+ model: str,
+ messages_batch: List[List[Message]],
+ sampling_params: Optional[SamplingParams] = SamplingParams(),
+ # zero-shot tool definitions as input to the model
+ tools: Optional[List[ToolDefinition]] = list,
+ tool_choice: Optional[ToolChoice] = ToolChoice.auto,
+ tool_prompt_format: Optional[ToolPromptFormat] = ToolPromptFormat.json,
+ logprobs: Optional[LogProbConfig] = None,
) -> BatchChatCompletionResponse: ...
diff --git a/llama_toolchain/dataset/api/api.py b/llama_toolchain/dataset/api/api.py
index c22fc01b0..2fa8bb4e5 100644
--- a/llama_toolchain/dataset/api/api.py
+++ b/llama_toolchain/dataset/api/api.py
@@ -46,7 +46,8 @@ class Datasets(Protocol):
@webmethod(route="/datasets/create")
def create_dataset(
self,
- request: CreateDatasetRequest,
+ uuid: str,
+ dataset: TrainEvalDataset,
) -> None: ...
@webmethod(route="/datasets/get")
diff --git a/llama_toolchain/evaluations/api/api.py b/llama_toolchain/evaluations/api/api.py
index b8f3fa825..898dc2822 100644
--- a/llama_toolchain/evaluations/api/api.py
+++ b/llama_toolchain/evaluations/api/api.py
@@ -86,19 +86,19 @@ class Evaluations(Protocol):
@webmethod(route="/evaluate/text_generation/")
def evaluate_text_generation(
self,
- request: EvaluateTextGenerationRequest,
+ metrics: List[TextGenerationMetric],
) -> EvaluationJob: ...
@webmethod(route="/evaluate/question_answering/")
def evaluate_question_answering(
self,
- request: EvaluateQuestionAnsweringRequest,
+ metrics: List[QuestionAnsweringMetric],
) -> EvaluationJob: ...
@webmethod(route="/evaluate/summarization/")
def evaluate_summarization(
self,
- request: EvaluateSummarizationRequest,
+ metrics: List[SummarizationMetric],
) -> EvaluationJob: ...
@webmethod(route="/evaluate/jobs")
diff --git a/llama_toolchain/inference/adapters/fireworks/fireworks.py b/llama_toolchain/inference/adapters/fireworks/fireworks.py
index b0eb41017..e51a730de 100644
--- a/llama_toolchain/inference/adapters/fireworks/fireworks.py
+++ b/llama_toolchain/inference/adapters/fireworks/fireworks.py
@@ -76,7 +76,28 @@ class FireworksInferenceAdapter(Inference):
return options
- async def chat_completion(self, request: ChatCompletionRequest) -> AsyncGenerator:
+ async def chat_completion(
+ self,
+ model: str,
+ messages: List[Message],
+ sampling_params: Optional[SamplingParams] = SamplingParams(),
+ tools: Optional[List[ToolDefinition]] = list(),
+ tool_choice: Optional[ToolChoice] = ToolChoice.auto,
+ tool_prompt_format: Optional[ToolPromptFormat] = ToolPromptFormat.json,
+ stream: Optional[bool] = False,
+ logprobs: Optional[LogProbConfig] = None,
+ ) -> AsyncGenerator:
+ request = ChatCompletionRequest(
+ model=model,
+ messages=messages,
+ sampling_params=sampling_params,
+ tools=tools,
+ tool_choice=tool_choice,
+ tool_prompt_format=tool_prompt_format,
+ stream=stream,
+ logprobs=logprobs,
+ )
+
messages = prepare_messages(request)
# accumulate sampling params and other options to pass to fireworks
diff --git a/llama_toolchain/inference/adapters/ollama/ollama.py b/llama_toolchain/inference/adapters/ollama/ollama.py
index 375257ea9..92fbf7585 100644
--- a/llama_toolchain/inference/adapters/ollama/ollama.py
+++ b/llama_toolchain/inference/adapters/ollama/ollama.py
@@ -84,7 +84,28 @@ class OllamaInferenceAdapter(Inference):
return options
- async def chat_completion(self, request: ChatCompletionRequest) -> AsyncGenerator:
+ async def chat_completion(
+ self,
+ model: str,
+ messages: List[Message],
+ sampling_params: Optional[SamplingParams] = SamplingParams(),
+ tools: Optional[List[ToolDefinition]] = list(),
+ tool_choice: Optional[ToolChoice] = ToolChoice.auto,
+ tool_prompt_format: Optional[ToolPromptFormat] = ToolPromptFormat.json,
+ stream: Optional[bool] = False,
+ logprobs: Optional[LogProbConfig] = None,
+ ) -> AsyncGenerator:
+ request = ChatCompletionRequest(
+ model=model,
+ messages=messages,
+ sampling_params=sampling_params,
+ tools=tools,
+ tool_choice=tool_choice,
+ tool_prompt_format=tool_prompt_format,
+ stream=stream,
+ logprobs=logprobs,
+ )
+
messages = prepare_messages(request)
# accumulate sampling params and other options to pass to ollama
options = self.get_ollama_chat_options(request)
diff --git a/llama_toolchain/inference/adapters/tgi/tgi.py b/llama_toolchain/inference/adapters/tgi/tgi.py
index bb7b99d02..7b1028817 100644
--- a/llama_toolchain/inference/adapters/tgi/tgi.py
+++ b/llama_toolchain/inference/adapters/tgi/tgi.py
@@ -82,7 +82,28 @@ class TGIAdapter(Inference):
return options
- async def chat_completion(self, request: ChatCompletionRequest) -> AsyncGenerator:
+ async def chat_completion(
+ self,
+ model: str,
+ messages: List[Message],
+ sampling_params: Optional[SamplingParams] = SamplingParams(),
+ tools: Optional[List[ToolDefinition]] = list(),
+ tool_choice: Optional[ToolChoice] = ToolChoice.auto,
+ tool_prompt_format: Optional[ToolPromptFormat] = ToolPromptFormat.json,
+ stream: Optional[bool] = False,
+ logprobs: Optional[LogProbConfig] = None,
+ ) -> AsyncGenerator:
+ request = ChatCompletionRequest(
+ model=model,
+ messages=messages,
+ sampling_params=sampling_params,
+ tools=tools,
+ tool_choice=tool_choice,
+ tool_prompt_format=tool_prompt_format,
+ stream=stream,
+ logprobs=logprobs,
+ )
+
messages = prepare_messages(request)
model_input = self.formatter.encode_dialog_prompt(messages)
prompt = self.tokenizer.decode(model_input.tokens)
diff --git a/llama_toolchain/inference/adapters/together/together.py b/llama_toolchain/inference/adapters/together/together.py
index 4800de6ad..76403a85b 100644
--- a/llama_toolchain/inference/adapters/together/together.py
+++ b/llama_toolchain/inference/adapters/together/together.py
@@ -76,7 +76,29 @@ class TogetherInferenceAdapter(Inference):
return options
- async def chat_completion(self, request: ChatCompletionRequest) -> AsyncGenerator:
+ async def chat_completion(
+ self,
+ model: str,
+ messages: List[Message],
+ sampling_params: Optional[SamplingParams] = SamplingParams(),
+ tools: Optional[List[ToolDefinition]] = list(),
+ tool_choice: Optional[ToolChoice] = ToolChoice.auto,
+ tool_prompt_format: Optional[ToolPromptFormat] = ToolPromptFormat.json,
+ stream: Optional[bool] = False,
+ logprobs: Optional[LogProbConfig] = None,
+ ) -> AsyncGenerator:
+ # wrapper request to make it easier to pass around (internal only, not exposed to API)
+ request = ChatCompletionRequest(
+ model=model,
+ messages=messages,
+ sampling_params=sampling_params,
+ tools=tools,
+ tool_choice=tool_choice,
+ tool_prompt_format=tool_prompt_format,
+ stream=stream,
+ logprobs=logprobs,
+ )
+
# accumulate sampling params and other options to pass to together
options = self.get_together_chat_options(request)
together_model = self.resolve_together_model(request.model)
diff --git a/llama_toolchain/inference/api/api.py b/llama_toolchain/inference/api/api.py
index 7298cb27b..8887d312f 100644
--- a/llama_toolchain/inference/api/api.py
+++ b/llama_toolchain/inference/api/api.py
@@ -85,6 +85,8 @@ class CompletionRequest(BaseModel):
@json_schema_type
class CompletionResponse(BaseModel):
+ """Completion response."""
+
completion_message: CompletionMessage
logprobs: Optional[List[TokenLogProbs]] = None
@@ -108,6 +110,8 @@ class BatchCompletionRequest(BaseModel):
@json_schema_type
class BatchCompletionResponse(BaseModel):
+ """Batch completion response."""
+
completion_message_batch: List[CompletionMessage]
@@ -137,6 +141,8 @@ class ChatCompletionResponseStreamChunk(BaseModel):
@json_schema_type
class ChatCompletionResponse(BaseModel):
+ """Chat completion response."""
+
completion_message: CompletionMessage
logprobs: Optional[List[TokenLogProbs]] = None
@@ -170,13 +176,25 @@ class Inference(Protocol):
@webmethod(route="/inference/completion")
async def completion(
self,
- request: CompletionRequest,
+ model: str,
+ content: InterleavedTextMedia,
+ sampling_params: Optional[SamplingParams] = SamplingParams(),
+ stream: Optional[bool] = False,
+ logprobs: Optional[LogProbConfig] = None,
) -> Union[CompletionResponse, CompletionResponseStreamChunk]: ...
@webmethod(route="/inference/chat_completion")
async def chat_completion(
self,
- request: ChatCompletionRequest,
+ model: str,
+ messages: List[Message],
+ sampling_params: Optional[SamplingParams] = SamplingParams(),
+ # zero-shot tool definitions as input to the model
+ tools: Optional[List[ToolDefinition]] = list,
+ tool_choice: Optional[ToolChoice] = ToolChoice.auto,
+ tool_prompt_format: Optional[ToolPromptFormat] = ToolPromptFormat.json,
+ stream: Optional[bool] = False,
+ logprobs: Optional[LogProbConfig] = None,
) -> Union[ChatCompletionResponse, ChatCompletionResponseStreamChunk]: ...
@webmethod(route="/inference/embeddings")
diff --git a/llama_toolchain/inference/client.py b/llama_toolchain/inference/client.py
index 5ba9314bc..c57433a8f 100644
--- a/llama_toolchain/inference/client.py
+++ b/llama_toolchain/inference/client.py
@@ -10,10 +10,10 @@ from typing import Any, AsyncGenerator
import fire
import httpx
-from pydantic import BaseModel
-from termcolor import cprint
from llama_toolchain.core.datatypes import RemoteProviderConfig
+from pydantic import BaseModel
+from termcolor import cprint
from .api import (
ChatCompletionRequest,
@@ -52,9 +52,7 @@ class InferenceClient(Inference):
async with client.stream(
"POST",
f"{self.base_url}/inference/chat_completion",
- json={
- "request": encodable_dict(request),
- },
+ json=encodable_dict(request),
headers={"Content-Type": "application/json"},
timeout=20,
) as response:
diff --git a/llama_toolchain/inference/meta_reference/inference.py b/llama_toolchain/inference/meta_reference/inference.py
index 187d5baae..247c08f23 100644
--- a/llama_toolchain/inference/meta_reference/inference.py
+++ b/llama_toolchain/inference/meta_reference/inference.py
@@ -22,9 +22,12 @@ from llama_toolchain.inference.api import (
ToolCallParseStatus,
)
from llama_toolchain.inference.prepare_messages import prepare_messages
+
from .config import MetaReferenceImplConfig
from .model_parallel import LlamaModelParallelGenerator
+from llama_models.llama3.api.datatypes import * # noqa: F403
+from llama_toolchain.inference.api import * # noqa: F403
# there's a single model parallel process running serving the model. for now,
# we don't support multiple concurrent requests to this process.
@@ -50,10 +53,30 @@ class MetaReferenceInferenceImpl(Inference):
# hm, when stream=False, we should not be doing SSE :/ which is what the
# top-level server is going to do. make the typing more specific here
async def chat_completion(
- self, request: ChatCompletionRequest
+ self,
+ model: str,
+ messages: List[Message],
+ sampling_params: Optional[SamplingParams] = SamplingParams(),
+ tools: Optional[List[ToolDefinition]] = list(),
+ tool_choice: Optional[ToolChoice] = ToolChoice.auto,
+ tool_prompt_format: Optional[ToolPromptFormat] = ToolPromptFormat.json,
+ stream: Optional[bool] = False,
+ logprobs: Optional[LogProbConfig] = None,
) -> AsyncIterator[
Union[ChatCompletionResponseStreamChunk, ChatCompletionResponse]
]:
+ # wrapper request to make it easier to pass around (internal only, not exposed to API)
+ request = ChatCompletionRequest(
+ model=model,
+ messages=messages,
+ sampling_params=sampling_params,
+ tools=tools,
+ tool_choice=tool_choice,
+ tool_prompt_format=tool_prompt_format,
+ stream=stream,
+ logprobs=logprobs,
+ )
+
messages = prepare_messages(request)
model = resolve_model(request.model)
if model is None:
diff --git a/llama_toolchain/post_training/api/api.py b/llama_toolchain/post_training/api/api.py
index 447a729fb..378515f83 100644
--- a/llama_toolchain/post_training/api/api.py
+++ b/llama_toolchain/post_training/api/api.py
@@ -179,13 +179,33 @@ class PostTraining(Protocol):
@webmethod(route="/post_training/supervised_fine_tune")
def supervised_fine_tune(
self,
- request: PostTrainingSFTRequest,
+ job_uuid: str,
+ model: str,
+ dataset: TrainEvalDataset,
+ validation_dataset: TrainEvalDataset,
+ algorithm: FinetuningAlgorithm,
+ algorithm_config: Union[
+ LoraFinetuningConfig, QLoraFinetuningConfig, DoraFinetuningConfig
+ ],
+ optimizer_config: OptimizerConfig,
+ training_config: TrainingConfig,
+ hyperparam_search_config: Dict[str, Any],
+ logger_config: Dict[str, Any],
) -> PostTrainingJob: ...
@webmethod(route="/post_training/preference_optimize")
def preference_optimize(
self,
- request: PostTrainingRLHFRequest,
+ job_uuid: str,
+ finetuned_model: URL,
+ dataset: TrainEvalDataset,
+ validation_dataset: TrainEvalDataset,
+ algorithm: RLHFAlgorithm,
+ algorithm_config: Union[DPOAlignmentConfig],
+ optimizer_config: OptimizerConfig,
+ training_config: TrainingConfig,
+ hyperparam_search_config: Dict[str, Any],
+ logger_config: Dict[str, Any],
) -> PostTrainingJob: ...
@webmethod(route="/post_training/jobs")
diff --git a/llama_toolchain/reward_scoring/api/api.py b/llama_toolchain/reward_scoring/api/api.py
index c91931f09..9d689f232 100644
--- a/llama_toolchain/reward_scoring/api/api.py
+++ b/llama_toolchain/reward_scoring/api/api.py
@@ -50,5 +50,6 @@ class RewardScoring(Protocol):
@webmethod(route="/reward_scoring/score")
def reward_score(
self,
- request: RewardScoringRequest,
+ dialog_generations: List[DialogGenerations],
+ model: str,
) -> Union[RewardScoringResponse]: ...
diff --git a/llama_toolchain/safety/api/api.py b/llama_toolchain/safety/api/api.py
index 96682d172..631cfa992 100644
--- a/llama_toolchain/safety/api/api.py
+++ b/llama_toolchain/safety/api/api.py
@@ -86,5 +86,6 @@ class Safety(Protocol):
@webmethod(route="/safety/run_shields")
async def run_shields(
self,
- request: RunShieldRequest,
+ messages: List[Message],
+ shields: List[ShieldDefinition],
) -> RunShieldResponse: ...
diff --git a/llama_toolchain/safety/client.py b/llama_toolchain/safety/client.py
index 0cf7deae8..26a9813b3 100644
--- a/llama_toolchain/safety/client.py
+++ b/llama_toolchain/safety/client.py
@@ -13,10 +13,10 @@ import fire
import httpx
from llama_models.llama3.api.datatypes import UserMessage
-from pydantic import BaseModel
-from termcolor import cprint
from llama_toolchain.core.datatypes import RemoteProviderConfig
+from pydantic import BaseModel
+from termcolor import cprint
from .api import * # noqa: F403
@@ -43,9 +43,7 @@ class SafetyClient(Safety):
async with httpx.AsyncClient() as client:
response = await client.post(
f"{self.base_url}/safety/run_shields",
- json={
- "request": encodable_dict(request),
- },
+ json=encodable_dict(request),
headers={"Content-Type": "application/json"},
timeout=20,
)
diff --git a/llama_toolchain/safety/meta_reference/safety.py b/llama_toolchain/safety/meta_reference/safety.py
index e71ac09a2..6c75e74e8 100644
--- a/llama_toolchain/safety/meta_reference/safety.py
+++ b/llama_toolchain/safety/meta_reference/safety.py
@@ -52,13 +52,12 @@ class MetaReferenceSafetyImpl(Safety):
async def run_shields(
self,
- request: RunShieldRequest,
+ messages: List[Message],
+ shields: List[ShieldDefinition],
) -> RunShieldResponse:
- shields = [shield_config_to_shield(c, self.config) for c in request.shields]
+ shields = [shield_config_to_shield(c, self.config) for c in shields]
- responses = await asyncio.gather(
- *[shield.run(request.messages) for shield in shields]
- )
+ responses = await asyncio.gather(*[shield.run(messages) for shield in shields])
return RunShieldResponse(responses=responses)
diff --git a/llama_toolchain/synthetic_data_generation/api/api.py b/llama_toolchain/synthetic_data_generation/api/api.py
index 44b8327a9..9a6c487af 100644
--- a/llama_toolchain/synthetic_data_generation/api/api.py
+++ b/llama_toolchain/synthetic_data_generation/api/api.py
@@ -48,5 +48,7 @@ class SyntheticDataGeneration(Protocol):
@webmethod(route="/synthetic_data_generation/generate")
def synthetic_data_generate(
self,
- request: SyntheticDataGenerationRequest,
+ dialogs: List[Message],
+ filtering_function: FilteringFunction = FilteringFunction.none,
+ model: Optional[str] = None,
) -> Union[SyntheticDataGenerationResponse]: ...
diff --git a/llama_toolchain/telemetry/api/api.py b/llama_toolchain/telemetry/api/api.py
index 100836b46..2546c1ede 100644
--- a/llama_toolchain/telemetry/api/api.py
+++ b/llama_toolchain/telemetry/api/api.py
@@ -125,7 +125,7 @@ Event = Annotated[
class Telemetry(Protocol):
@webmethod(route="/telemetry/log_event")
- async def log_event(self, event: Event): ...
+ async def log_event(self, event: Event) -> None: ...
@webmethod(route="/telemetry/get_trace", method="GET")
async def get_trace(self, trace_id: str) -> Trace: ...
diff --git a/rfcs/RFC-0001-llama-stack-assets/llama-stack-spec.html b/rfcs/RFC-0001-llama-stack-assets/llama-stack-spec.html
index 211290ce1..6e7fe287f 100644
--- a/rfcs/RFC-0001-llama-stack-assets/llama-stack-spec.html
+++ b/rfcs/RFC-0001-llama-stack-assets/llama-stack-spec.html
@@ -21,7 +21,7 @@
"info": {
"title": "[DRAFT] Llama Stack Specification",
"version": "0.0.1",
- "description": "This is the specification of the llama stack that provides\n a set of endpoints and their corresponding interfaces that are tailored to\n best leverage Llama Models. The specification is still in draft and subject to change.\n Generated at 2024-09-10 16:42:15.870336"
+ "description": "This is the specification of the llama stack that provides\n a set of endpoints and their corresponding interfaces that are tailored to\n best leverage Llama Models. The specification is still in draft and subject to change.\n Generated at 2024-09-11 16:05:23.016090"
},
"servers": [
{
@@ -51,7 +51,7 @@
"content": {
"application/json": {
"schema": {
- "$ref": "#/components/schemas/BatchChatCompletionRequestWrapper"
+ "$ref": "#/components/schemas/BatchChatCompletionRequest"
}
}
},
@@ -81,7 +81,7 @@
"content": {
"application/json": {
"schema": {
- "$ref": "#/components/schemas/BatchCompletionRequestWrapper"
+ "$ref": "#/components/schemas/BatchCompletionRequest"
}
}
},
@@ -139,11 +139,18 @@
"post": {
"responses": {
"200": {
- "description": "SSE-stream of these events.",
+ "description": "Chat completion response. **OR** SSE-stream of these events.",
"content": {
"text/event-stream": {
"schema": {
- "$ref": "#/components/schemas/ChatCompletionResponseStreamChunk"
+ "oneOf": [
+ {
+ "$ref": "#/components/schemas/ChatCompletionResponse"
+ },
+ {
+ "$ref": "#/components/schemas/ChatCompletionResponseStreamChunk"
+ }
+ ]
}
}
}
@@ -157,7 +164,7 @@
"content": {
"application/json": {
"schema": {
- "$ref": "#/components/schemas/ChatCompletionRequestWrapper"
+ "$ref": "#/components/schemas/ChatCompletionRequest"
}
}
},
@@ -169,11 +176,18 @@
"post": {
"responses": {
"200": {
- "description": "streamed completion response.",
+ "description": "Completion response. **OR** streamed completion response.",
"content": {
"application/json": {
"schema": {
- "$ref": "#/components/schemas/CompletionResponseStreamChunk"
+ "oneOf": [
+ {
+ "$ref": "#/components/schemas/CompletionResponse"
+ },
+ {
+ "$ref": "#/components/schemas/CompletionResponseStreamChunk"
+ }
+ ]
}
}
}
@@ -187,7 +201,7 @@
"content": {
"application/json": {
"schema": {
- "$ref": "#/components/schemas/CompletionRequestWrapper"
+ "$ref": "#/components/schemas/CompletionRequest"
}
}
},
@@ -277,7 +291,7 @@
"content": {
"application/json": {
"schema": {
- "$ref": "#/components/schemas/AgenticSystemTurnCreateRequestWrapper"
+ "$ref": "#/components/schemas/CreateAgenticSystemTurnRequest"
}
}
},
@@ -300,37 +314,7 @@
"content": {
"application/json": {
"schema": {
- "$ref": "#/components/schemas/CreateDatasetRequestWrapper"
- }
- }
- },
- "required": true
- }
- }
- },
- "/experiments/create": {
- "post": {
- "responses": {
- "200": {
- "description": "OK",
- "content": {
- "application/json": {
- "schema": {
- "$ref": "#/components/schemas/Experiment"
- }
- }
- }
- }
- },
- "tags": [
- "Telemetry"
- ],
- "parameters": [],
- "requestBody": {
- "content": {
- "application/json": {
- "schema": {
- "$ref": "#/components/schemas/CreateExperimentRequestWrapper"
+ "$ref": "#/components/schemas/CreateDatasetRequest"
}
}
},
@@ -368,36 +352,6 @@
}
}
},
- "/experiments/create_run": {
- "post": {
- "responses": {
- "200": {
- "description": "OK",
- "content": {
- "application/json": {
- "schema": {
- "$ref": "#/components/schemas/Run"
- }
- }
- }
- }
- },
- "tags": [
- "Telemetry"
- ],
- "parameters": [],
- "requestBody": {
- "content": {
- "application/json": {
- "schema": {
- "$ref": "#/components/schemas/CreateRunRequestWrapper"
- }
- }
- },
- "required": true
- }
- }
- },
"/agentic_system/delete": {
"post": {
"responses": {
@@ -572,7 +526,7 @@
"content": {
"application/json": {
"schema": {
- "$ref": "#/components/schemas/EvaluateQuestionAnsweringRequestWrapper"
+ "$ref": "#/components/schemas/EvaluateQuestionAnsweringRequest"
}
}
},
@@ -602,7 +556,7 @@
"content": {
"application/json": {
"schema": {
- "$ref": "#/components/schemas/EvaluateSummarizationRequestWrapper"
+ "$ref": "#/components/schemas/EvaluateSummarizationRequest"
}
}
},
@@ -632,7 +586,7 @@
"content": {
"application/json": {
"schema": {
- "$ref": "#/components/schemas/EvaluateTextGenerationRequestWrapper"
+ "$ref": "#/components/schemas/EvaluateTextGenerationRequest"
}
}
},
@@ -769,35 +723,6 @@
]
}
},
- "/artifacts/get": {
- "get": {
- "responses": {
- "200": {
- "description": "OK",
- "content": {
- "application/json": {
- "schema": {
- "$ref": "#/components/schemas/Artifact"
- }
- }
- }
- }
- },
- "tags": [
- "Telemetry"
- ],
- "parameters": [
- {
- "name": "artifact_id",
- "in": "query",
- "required": true,
- "schema": {
- "type": "string"
- }
- }
- ]
- }
- },
"/datasets/get": {
"get": {
"responses": {
@@ -973,65 +898,6 @@
"parameters": []
}
},
- "/experiments/get": {
- "get": {
- "responses": {
- "200": {
- "description": "OK",
- "content": {
- "application/json": {
- "schema": {
- "$ref": "#/components/schemas/Experiment"
- }
- }
- }
- }
- },
- "tags": [
- "Telemetry"
- ],
- "parameters": [
- {
- "name": "experiment_id",
- "in": "query",
- "required": true,
- "schema": {
- "type": "string"
- }
- }
- ]
- }
- },
- "/logging/get_logs": {
- "post": {
- "responses": {
- "200": {
- "description": "OK",
- "content": {
- "application/jsonl": {
- "schema": {
- "$ref": "#/components/schemas/Log"
- }
- }
- }
- }
- },
- "tags": [
- "Telemetry"
- ],
- "parameters": [],
- "requestBody": {
- "content": {
- "application/json": {
- "schema": {
- "$ref": "#/components/schemas/LogSearchRequestWrapper"
- }
- }
- },
- "required": true
- }
- }
- },
"/memory_banks/get": {
"get": {
"responses": {
@@ -1068,15 +934,15 @@
]
}
},
- "/runs/metrics": {
+ "/telemetry/get_trace": {
"get": {
"responses": {
"200": {
"description": "OK",
"content": {
- "application/jsonl": {
+ "application/json": {
"schema": {
- "$ref": "#/components/schemas/Metric"
+ "$ref": "#/components/schemas/Trace"
}
}
}
@@ -1087,7 +953,7 @@
],
"parameters": [
{
- "name": "run_id",
+ "name": "trace_id",
"in": "query",
"required": true,
"schema": {
@@ -1227,56 +1093,6 @@
}
}
},
- "/experiments/artifacts/get": {
- "post": {
- "responses": {
- "200": {
- "description": "OK",
- "content": {
- "application/jsonl": {
- "schema": {
- "$ref": "#/components/schemas/Artifact"
- }
- }
- }
- }
- },
- "tags": [
- "Telemetry"
- ],
- "parameters": [],
- "requestBody": {
- "content": {
- "application/json": {
- "schema": {
- "$ref": "#/components/schemas/ListArtifactsRequest"
- }
- }
- },
- "required": true
- }
- }
- },
- "/experiments/list": {
- "get": {
- "responses": {
- "200": {
- "description": "OK",
- "content": {
- "application/jsonl": {
- "schema": {
- "$ref": "#/components/schemas/Experiment"
- }
- }
- }
- }
- },
- "tags": [
- "Telemetry"
- ],
- "parameters": []
- }
- },
"/memory_banks/list": {
"get": {
"responses": {
@@ -1297,7 +1113,7 @@
"parameters": []
}
},
- "/logging/log_messages": {
+ "/telemetry/log_event": {
"post": {
"responses": {
"200": {
@@ -1312,30 +1128,7 @@
"content": {
"application/json": {
"schema": {
- "$ref": "#/components/schemas/LogMessagesRequestWrapper"
- }
- }
- },
- "required": true
- }
- }
- },
- "/runs/log_metrics": {
- "post": {
- "responses": {
- "200": {
- "description": "OK"
- }
- },
- "tags": [
- "Telemetry"
- ],
- "parameters": [],
- "requestBody": {
- "content": {
- "application/json": {
- "schema": {
- "$ref": "#/components/schemas/LogMetricsRequestWrapper"
+ "$ref": "#/components/schemas/LogEventRequest"
}
}
},
@@ -1365,7 +1158,7 @@
"content": {
"application/json": {
"schema": {
- "$ref": "#/components/schemas/PostTrainingRLHFRequestWrapper"
+ "$ref": "#/components/schemas/PreferenceOptimizeRequest"
}
}
},
@@ -1425,7 +1218,7 @@
"content": {
"application/json": {
"schema": {
- "$ref": "#/components/schemas/RewardScoringRequestWrapper"
+ "$ref": "#/components/schemas/RewardScoreRequest"
}
}
},
@@ -1455,7 +1248,7 @@
"content": {
"application/json": {
"schema": {
- "$ref": "#/components/schemas/RunShieldRequestWrapper"
+ "$ref": "#/components/schemas/RunShieldsRequest"
}
}
},
@@ -1485,7 +1278,7 @@
"content": {
"application/json": {
"schema": {
- "$ref": "#/components/schemas/PostTrainingSFTRequestWrapper"
+ "$ref": "#/components/schemas/SupervisedFineTuneRequest"
}
}
},
@@ -1515,7 +1308,7 @@
"content": {
"application/json": {
"schema": {
- "$ref": "#/components/schemas/SyntheticDataGenerationRequestWrapper"
+ "$ref": "#/components/schemas/SyntheticDataGenerateRequest"
}
}
},
@@ -1545,160 +1338,11 @@
"required": true
}
}
- },
- "/experiments/update": {
- "post": {
- "responses": {
- "200": {
- "description": "OK",
- "content": {
- "application/json": {
- "schema": {
- "$ref": "#/components/schemas/Experiment"
- }
- }
- }
- }
- },
- "tags": [
- "Telemetry"
- ],
- "parameters": [],
- "requestBody": {
- "content": {
- "application/json": {
- "schema": {
- "$ref": "#/components/schemas/UpdateExperimentRequestWrapper"
- }
- }
- },
- "required": true
- }
- }
- },
- "/runs/update": {
- "post": {
- "responses": {
- "200": {
- "description": "OK",
- "content": {
- "application/json": {
- "schema": {
- "$ref": "#/components/schemas/Run"
- }
- }
- }
- }
- },
- "tags": [
- "Telemetry"
- ],
- "parameters": [],
- "requestBody": {
- "content": {
- "application/json": {
- "schema": {
- "$ref": "#/components/schemas/UpdateRunRequestWrapper"
- }
- }
- },
- "required": true
- }
- }
- },
- "/experiments/artifacts/upload": {
- "post": {
- "responses": {
- "200": {
- "description": "OK",
- "content": {
- "application/json": {
- "schema": {
- "$ref": "#/components/schemas/Artifact"
- }
- }
- }
- }
- },
- "tags": [
- "Telemetry"
- ],
- "parameters": [],
- "requestBody": {
- "content": {
- "application/json": {
- "schema": {
- "$ref": "#/components/schemas/UploadArtifactRequestWrapper"
- }
- }
- },
- "required": true
- }
- }
}
},
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
"components": {
"schemas": {
- "BatchChatCompletionRequest": {
- "type": "object",
- "properties": {
- "model": {
- "type": "string"
- },
- "messages_batch": {
- "type": "array",
- "items": {
- "type": "array",
- "items": {
- "oneOf": [
- {
- "$ref": "#/components/schemas/UserMessage"
- },
- {
- "$ref": "#/components/schemas/SystemMessage"
- },
- {
- "$ref": "#/components/schemas/ToolResponseMessage"
- },
- {
- "$ref": "#/components/schemas/CompletionMessage"
- }
- ]
- }
- }
- },
- "sampling_params": {
- "$ref": "#/components/schemas/SamplingParams"
- },
- "tools": {
- "type": "array",
- "items": {
- "$ref": "#/components/schemas/ToolDefinition"
- }
- },
- "tool_choice": {
- "$ref": "#/components/schemas/ToolChoice"
- },
- "tool_prompt_format": {
- "$ref": "#/components/schemas/ToolPromptFormat"
- },
- "logprobs": {
- "type": "object",
- "properties": {
- "top_k": {
- "type": "integer"
- }
- },
- "additionalProperties": false
- }
- },
- "additionalProperties": false,
- "required": [
- "model",
- "messages_batch"
- ]
- },
"BuiltinTool": {
"type": "string",
"enum": [
@@ -2050,16 +1694,63 @@
"content"
]
},
- "BatchChatCompletionRequestWrapper": {
+ "BatchChatCompletionRequest": {
"type": "object",
"properties": {
- "request": {
- "$ref": "#/components/schemas/BatchChatCompletionRequest"
+ "model": {
+ "type": "string"
+ },
+ "messages_batch": {
+ "type": "array",
+ "items": {
+ "type": "array",
+ "items": {
+ "oneOf": [
+ {
+ "$ref": "#/components/schemas/UserMessage"
+ },
+ {
+ "$ref": "#/components/schemas/SystemMessage"
+ },
+ {
+ "$ref": "#/components/schemas/ToolResponseMessage"
+ },
+ {
+ "$ref": "#/components/schemas/CompletionMessage"
+ }
+ ]
+ }
+ }
+ },
+ "sampling_params": {
+ "$ref": "#/components/schemas/SamplingParams"
+ },
+ "tools": {
+ "type": "array",
+ "items": {
+ "$ref": "#/components/schemas/ToolDefinition"
+ }
+ },
+ "tool_choice": {
+ "$ref": "#/components/schemas/ToolChoice"
+ },
+ "tool_prompt_format": {
+ "$ref": "#/components/schemas/ToolPromptFormat"
+ },
+ "logprobs": {
+ "type": "object",
+ "properties": {
+ "top_k": {
+ "type": "integer"
+ }
+ },
+ "additionalProperties": false
}
},
"additionalProperties": false,
"required": [
- "request"
+ "model",
+ "messages_batch"
]
},
"BatchChatCompletionResponse": {
@@ -2118,18 +1809,6 @@
"content_batch"
]
},
- "BatchCompletionRequestWrapper": {
- "type": "object",
- "properties": {
- "request": {
- "$ref": "#/components/schemas/BatchCompletionRequest"
- }
- },
- "additionalProperties": false,
- "required": [
- "request"
- ]
- },
"BatchCompletionResponse": {
"type": "object",
"properties": {
@@ -2228,17 +1907,24 @@
"messages"
]
},
- "ChatCompletionRequestWrapper": {
+ "ChatCompletionResponse": {
"type": "object",
"properties": {
- "request": {
- "$ref": "#/components/schemas/ChatCompletionRequest"
+ "completion_message": {
+ "$ref": "#/components/schemas/CompletionMessage"
+ },
+ "logprobs": {
+ "type": "array",
+ "items": {
+ "$ref": "#/components/schemas/TokenLogProbs"
+ }
}
},
"additionalProperties": false,
"required": [
- "request"
- ]
+ "completion_message"
+ ],
+ "title": "Chat completion response."
},
"ChatCompletionResponseEvent": {
"type": "object",
@@ -2382,17 +2068,24 @@
"content"
]
},
- "CompletionRequestWrapper": {
+ "CompletionResponse": {
"type": "object",
"properties": {
- "request": {
- "$ref": "#/components/schemas/CompletionRequest"
+ "completion_message": {
+ "$ref": "#/components/schemas/CompletionMessage"
+ },
+ "logprobs": {
+ "type": "array",
+ "items": {
+ "$ref": "#/components/schemas/TokenLogProbs"
+ }
}
},
"additionalProperties": false,
"required": [
- "request"
- ]
+ "completion_message"
+ ],
+ "title": "Completion response."
},
"CompletionResponseStreamChunk": {
"type": "object",
@@ -3031,234 +2724,38 @@
"session_id"
]
},
- "AgenticSystemTurnCreateRequest": {
+ "Attachment": {
"type": "object",
"properties": {
- "sampling_params": {
- "$ref": "#/components/schemas/SamplingParams"
- },
- "input_shields": {
- "type": "array",
- "items": {
- "$ref": "#/components/schemas/ShieldDefinition"
- }
- },
- "output_shields": {
- "type": "array",
- "items": {
- "$ref": "#/components/schemas/ShieldDefinition"
- }
- },
- "tools": {
- "type": "array",
- "items": {
- "oneOf": [
- {
- "$ref": "#/components/schemas/SearchToolDefinition"
- },
- {
- "$ref": "#/components/schemas/WolframAlphaToolDefinition"
- },
- {
- "$ref": "#/components/schemas/PhotogenToolDefinition"
- },
- {
- "$ref": "#/components/schemas/CodeInterpreterToolDefinition"
- },
- {
- "$ref": "#/components/schemas/FunctionCallToolDefinition"
- },
- {
- "type": "object",
- "properties": {
- "input_shields": {
- "type": "array",
- "items": {
- "$ref": "#/components/schemas/ShieldDefinition"
- }
- },
- "output_shields": {
- "type": "array",
- "items": {
- "$ref": "#/components/schemas/ShieldDefinition"
- }
- },
- "type": {
- "type": "string",
- "const": "memory"
- },
- "memory_bank_configs": {
- "type": "array",
- "items": {
- "oneOf": [
- {
- "type": "object",
- "properties": {
- "bank_id": {
- "type": "string"
- },
- "type": {
- "type": "string",
- "const": "vector"
- }
- },
- "additionalProperties": false,
- "required": [
- "bank_id",
- "type"
- ]
- },
- {
- "type": "object",
- "properties": {
- "bank_id": {
- "type": "string"
- },
- "type": {
- "type": "string",
- "const": "keyvalue"
- },
- "keys": {
- "type": "array",
- "items": {
- "type": "string"
- }
- }
- },
- "additionalProperties": false,
- "required": [
- "bank_id",
- "type",
- "keys"
- ]
- },
- {
- "type": "object",
- "properties": {
- "bank_id": {
- "type": "string"
- },
- "type": {
- "type": "string",
- "const": "keyword"
- }
- },
- "additionalProperties": false,
- "required": [
- "bank_id",
- "type"
- ]
- },
- {
- "type": "object",
- "properties": {
- "bank_id": {
- "type": "string"
- },
- "type": {
- "type": "string",
- "const": "graph"
- },
- "entities": {
- "type": "array",
- "items": {
- "type": "string"
- }
- }
- },
- "additionalProperties": false,
- "required": [
- "bank_id",
- "type",
- "entities"
- ]
- }
- ]
- }
- },
- "query_generator_config": {
- "oneOf": [
- {
- "type": "object",
- "properties": {
- "type": {
- "type": "string",
- "const": "default"
- },
- "sep": {
- "type": "string"
- }
- },
- "additionalProperties": false,
- "required": [
- "type",
- "sep"
- ]
- },
- {
- "type": "object",
- "properties": {
- "type": {
- "type": "string",
- "const": "llm"
- },
- "model": {
- "type": "string"
- },
- "template": {
- "type": "string"
- }
- },
- "additionalProperties": false,
- "required": [
- "type",
- "model",
- "template"
- ]
- },
- {
- "type": "object",
- "properties": {
- "type": {
- "type": "string",
- "const": "custom"
- }
- },
- "additionalProperties": false,
- "required": [
- "type"
- ]
- }
- ]
- },
- "max_tokens_in_context": {
- "type": "integer"
- },
- "max_chunks": {
- "type": "integer"
- }
- },
- "additionalProperties": false,
- "required": [
- "type",
- "memory_bank_configs",
- "query_generator_config",
- "max_tokens_in_context",
- "max_chunks"
- ]
+ "content": {
+ "oneOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "array",
+ "items": {
+ "type": "string"
}
- ]
- }
+ },
+ {
+ "$ref": "#/components/schemas/URL"
+ }
+ ]
},
- "tool_choice": {
- "$ref": "#/components/schemas/ToolChoice"
- },
- "tool_prompt_format": {
- "$ref": "#/components/schemas/ToolPromptFormat"
- },
- "instructions": {
+ "mime_type": {
"type": "string"
- },
+ }
+ },
+ "additionalProperties": false,
+ "required": [
+ "content",
+ "mime_type"
+ ]
+ },
+ "CreateAgenticSystemTurnRequest": {
+ "type": "object",
+ "properties": {
"agent_id": {
"type": "string"
},
@@ -3295,47 +2792,6 @@
"messages"
]
},
- "Attachment": {
- "type": "object",
- "properties": {
- "content": {
- "oneOf": [
- {
- "type": "string"
- },
- {
- "type": "array",
- "items": {
- "type": "string"
- }
- },
- {
- "$ref": "#/components/schemas/URL"
- }
- ]
- },
- "mime_type": {
- "type": "string"
- }
- },
- "additionalProperties": false,
- "required": [
- "content",
- "mime_type"
- ]
- },
- "AgenticSystemTurnCreateRequestWrapper": {
- "type": "object",
- "properties": {
- "request": {
- "$ref": "#/components/schemas/AgenticSystemTurnCreateRequest"
- }
- },
- "additionalProperties": false,
- "required": [
- "request"
- ]
- },
"AgenticSystemTurnResponseEvent": {
"type": "object",
"properties": {
@@ -3835,23 +3291,6 @@
],
"title": "A single turn in an interaction with an Agentic System."
},
- "CreateDatasetRequest": {
- "type": "object",
- "properties": {
- "uuid": {
- "type": "string"
- },
- "dataset": {
- "$ref": "#/components/schemas/TrainEvalDataset"
- }
- },
- "additionalProperties": false,
- "required": [
- "uuid",
- "dataset"
- ],
- "title": "Request to create a dataset."
- },
"TrainEvalDataset": {
"type": "object",
"properties": {
@@ -3907,130 +3346,20 @@
"json"
]
},
- "CreateDatasetRequestWrapper": {
+ "CreateDatasetRequest": {
"type": "object",
"properties": {
- "request": {
- "$ref": "#/components/schemas/CreateDatasetRequest"
- }
- },
- "additionalProperties": false,
- "required": [
- "request"
- ]
- },
- "CreateExperimentRequest": {
- "type": "object",
- "properties": {
- "name": {
+ "uuid": {
"type": "string"
},
- "metadata": {
- "type": "object",
- "additionalProperties": {
- "oneOf": [
- {
- "type": "null"
- },
- {
- "type": "boolean"
- },
- {
- "type": "number"
- },
- {
- "type": "string"
- },
- {
- "type": "array"
- },
- {
- "type": "object"
- }
- ]
- }
+ "dataset": {
+ "$ref": "#/components/schemas/TrainEvalDataset"
}
},
"additionalProperties": false,
"required": [
- "name"
- ]
- },
- "CreateExperimentRequestWrapper": {
- "type": "object",
- "properties": {
- "request": {
- "$ref": "#/components/schemas/CreateExperimentRequest"
- }
- },
- "additionalProperties": false,
- "required": [
- "request"
- ]
- },
- "Experiment": {
- "type": "object",
- "properties": {
- "id": {
- "type": "string"
- },
- "name": {
- "type": "string"
- },
- "status": {
- "$ref": "#/components/schemas/ExperimentStatus"
- },
- "created_at": {
- "type": "string",
- "format": "date-time"
- },
- "updated_at": {
- "type": "string",
- "format": "date-time"
- },
- "metadata": {
- "type": "object",
- "additionalProperties": {
- "oneOf": [
- {
- "type": "null"
- },
- {
- "type": "boolean"
- },
- {
- "type": "number"
- },
- {
- "type": "string"
- },
- {
- "type": "array"
- },
- {
- "type": "object"
- }
- ]
- }
- }
- },
- "additionalProperties": false,
- "required": [
- "id",
- "name",
- "status",
- "created_at",
- "updated_at",
- "metadata"
- ]
- },
- "ExperimentStatus": {
- "type": "string",
- "enum": [
- "not_started",
- "running",
- "completed",
- "failed"
+ "uuid",
+ "dataset"
]
},
"CreateMemoryBankRequest": {
@@ -4203,110 +3532,6 @@
"config"
]
},
- "CreateRunRequest": {
- "type": "object",
- "properties": {
- "experiment_id": {
- "type": "string"
- },
- "metadata": {
- "type": "object",
- "additionalProperties": {
- "oneOf": [
- {
- "type": "null"
- },
- {
- "type": "boolean"
- },
- {
- "type": "number"
- },
- {
- "type": "string"
- },
- {
- "type": "array"
- },
- {
- "type": "object"
- }
- ]
- }
- }
- },
- "additionalProperties": false,
- "required": [
- "experiment_id"
- ]
- },
- "CreateRunRequestWrapper": {
- "type": "object",
- "properties": {
- "request": {
- "$ref": "#/components/schemas/CreateRunRequest"
- }
- },
- "additionalProperties": false,
- "required": [
- "request"
- ]
- },
- "Run": {
- "type": "object",
- "properties": {
- "id": {
- "type": "string"
- },
- "experiment_id": {
- "type": "string"
- },
- "status": {
- "type": "string"
- },
- "started_at": {
- "type": "string",
- "format": "date-time"
- },
- "ended_at": {
- "type": "string",
- "format": "date-time"
- },
- "metadata": {
- "type": "object",
- "additionalProperties": {
- "oneOf": [
- {
- "type": "null"
- },
- {
- "type": "boolean"
- },
- {
- "type": "number"
- },
- {
- "type": "string"
- },
- {
- "type": "array"
- },
- {
- "type": "object"
- }
- ]
- }
- }
- },
- "additionalProperties": false,
- "required": [
- "id",
- "experiment_id",
- "status",
- "started_at",
- "metadata"
- ]
- },
"DeleteAgenticSystemRequest": {
"type": "object",
"properties": {
@@ -4425,24 +3650,9 @@
"embeddings"
]
},
- "Checkpoint": {
- "description": "Checkpoint created during training runs"
- },
"EvaluateQuestionAnsweringRequest": {
"type": "object",
"properties": {
- "job_uuid": {
- "type": "string"
- },
- "dataset": {
- "$ref": "#/components/schemas/TrainEvalDataset"
- },
- "checkpoint": {
- "$ref": "#/components/schemas/Checkpoint"
- },
- "sampling_params": {
- "$ref": "#/components/schemas/SamplingParams"
- },
"metrics": {
"type": "array",
"items": {
@@ -4456,24 +3666,7 @@
},
"additionalProperties": false,
"required": [
- "job_uuid",
- "dataset",
- "checkpoint",
- "sampling_params",
"metrics"
- ],
- "title": "Request to evaluate question answering."
- },
- "EvaluateQuestionAnsweringRequestWrapper": {
- "type": "object",
- "properties": {
- "request": {
- "$ref": "#/components/schemas/EvaluateQuestionAnsweringRequest"
- }
- },
- "additionalProperties": false,
- "required": [
- "request"
]
},
"EvaluationJob": {
@@ -4491,18 +3684,6 @@
"EvaluateSummarizationRequest": {
"type": "object",
"properties": {
- "job_uuid": {
- "type": "string"
- },
- "dataset": {
- "$ref": "#/components/schemas/TrainEvalDataset"
- },
- "checkpoint": {
- "$ref": "#/components/schemas/Checkpoint"
- },
- "sampling_params": {
- "$ref": "#/components/schemas/SamplingParams"
- },
"metrics": {
"type": "array",
"items": {
@@ -4516,41 +3697,12 @@
},
"additionalProperties": false,
"required": [
- "job_uuid",
- "dataset",
- "checkpoint",
- "sampling_params",
"metrics"
- ],
- "title": "Request to evaluate summarization."
- },
- "EvaluateSummarizationRequestWrapper": {
- "type": "object",
- "properties": {
- "request": {
- "$ref": "#/components/schemas/EvaluateSummarizationRequest"
- }
- },
- "additionalProperties": false,
- "required": [
- "request"
]
},
"EvaluateTextGenerationRequest": {
"type": "object",
"properties": {
- "job_uuid": {
- "type": "string"
- },
- "dataset": {
- "$ref": "#/components/schemas/TrainEvalDataset"
- },
- "checkpoint": {
- "$ref": "#/components/schemas/Checkpoint"
- },
- "sampling_params": {
- "$ref": "#/components/schemas/SamplingParams"
- },
"metrics": {
"type": "array",
"items": {
@@ -4565,24 +3717,7 @@
},
"additionalProperties": false,
"required": [
- "job_uuid",
- "dataset",
- "checkpoint",
- "sampling_params",
"metrics"
- ],
- "title": "Request to evaluate text generation."
- },
- "EvaluateTextGenerationRequestWrapper": {
- "type": "object",
- "properties": {
- "request": {
- "$ref": "#/components/schemas/EvaluateTextGenerationRequest"
- }
- },
- "additionalProperties": false,
- "required": [
- "request"
]
},
"GetAgenticSystemSessionRequest": {
@@ -4654,74 +3789,6 @@
"step"
]
},
- "Artifact": {
- "type": "object",
- "properties": {
- "id": {
- "type": "string"
- },
- "name": {
- "type": "string"
- },
- "type": {
- "$ref": "#/components/schemas/ArtifactType"
- },
- "size": {
- "type": "integer"
- },
- "created_at": {
- "type": "string",
- "format": "date-time"
- },
- "metadata": {
- "type": "object",
- "additionalProperties": {
- "oneOf": [
- {
- "type": "null"
- },
- {
- "type": "boolean"
- },
- {
- "type": "number"
- },
- {
- "type": "string"
- },
- {
- "type": "array"
- },
- {
- "type": "object"
- }
- ]
- }
- }
- },
- "additionalProperties": false,
- "required": [
- "id",
- "name",
- "type",
- "size",
- "created_at",
- "metadata"
- ]
- },
- "ArtifactType": {
- "type": "string",
- "enum": [
- "model",
- "dataset",
- "checkpoint",
- "plot",
- "metric",
- "config",
- "code",
- "other"
- ]
- },
"GetDocumentsRequest": {
"type": "object",
"properties": {
@@ -4833,140 +3900,34 @@
"job_uuid"
]
},
- "LogSearchRequest": {
+ "Trace": {
"type": "object",
"properties": {
- "query": {
+ "trace_id": {
"type": "string"
},
- "filters": {
- "type": "object",
- "additionalProperties": {
- "oneOf": [
- {
- "type": "null"
- },
- {
- "type": "boolean"
- },
- {
- "type": "number"
- },
- {
- "type": "string"
- },
- {
- "type": "array"
- },
- {
- "type": "object"
- }
- ]
- }
- }
- },
- "additionalProperties": false,
- "required": [
- "query"
- ]
- },
- "LogSearchRequestWrapper": {
- "type": "object",
- "properties": {
- "request": {
- "$ref": "#/components/schemas/LogSearchRequest"
- }
- },
- "additionalProperties": false,
- "required": [
- "request"
- ]
- },
- "Log": {
- "type": "object",
- "properties": {
- "message": {
+ "root_span_id": {
"type": "string"
},
- "level": {
- "type": "string"
- },
- "timestamp": {
+ "start_time": {
"type": "string",
"format": "date-time"
},
- "additional_info": {
- "type": "object",
- "additionalProperties": {
- "oneOf": [
- {
- "type": "null"
- },
- {
- "type": "boolean"
- },
- {
- "type": "number"
- },
- {
- "type": "string"
- },
- {
- "type": "array"
- },
- {
- "type": "object"
- }
- ]
- }
- }
- },
- "additionalProperties": false,
- "required": [
- "message",
- "level",
- "timestamp",
- "additional_info"
- ]
- },
- "Metric": {
- "type": "object",
- "properties": {
- "name": {
- "type": "string"
- },
- "value": {
- "oneOf": [
- {
- "type": "number"
- },
- {
- "type": "integer"
- },
- {
- "type": "string"
- },
- {
- "type": "boolean"
- }
- ]
- },
- "timestamp": {
+ "end_time": {
"type": "string",
"format": "date-time"
- },
- "run_id": {
- "type": "string"
}
},
"additionalProperties": false,
"required": [
- "name",
- "value",
- "timestamp",
- "run_id"
+ "trace_id",
+ "root_span_id",
+ "start_time"
]
},
+ "Checkpoint": {
+ "description": "Checkpoint created during training runs"
+ },
"PostTrainingJobArtifactsResponse": {
"type": "object",
"properties": {
@@ -5111,77 +4072,272 @@
"documents"
]
},
- "ListArtifactsRequest": {
- "type": "object",
- "properties": {
- "experiment_id": {
- "type": "string"
- }
- },
- "additionalProperties": false,
- "required": [
- "experiment_id"
+ "LogSeverity": {
+ "type": "string",
+ "enum": [
+ "verbose",
+ "debug",
+ "info",
+ "warn",
+ "error",
+ "critical"
]
},
- "LogMessagesRequest": {
+ "MetricEvent": {
"type": "object",
"properties": {
- "logs": {
- "type": "array",
- "items": {
- "$ref": "#/components/schemas/Log"
- }
- },
- "run_id": {
- "type": "string"
- }
- },
- "additionalProperties": false,
- "required": [
- "logs"
- ]
- },
- "LogMessagesRequestWrapper": {
- "type": "object",
- "properties": {
- "request": {
- "$ref": "#/components/schemas/LogMessagesRequest"
- }
- },
- "additionalProperties": false,
- "required": [
- "request"
- ]
- },
- "LogMetricsRequest": {
- "type": "object",
- "properties": {
- "run_id": {
+ "trace_id": {
"type": "string"
},
- "metrics": {
- "type": "array",
- "items": {
- "$ref": "#/components/schemas/Metric"
+ "span_id": {
+ "type": "string"
+ },
+ "timestamp": {
+ "type": "string",
+ "format": "date-time"
+ },
+ "attributes": {
+ "type": "object",
+ "additionalProperties": {
+ "oneOf": [
+ {
+ "type": "null"
+ },
+ {
+ "type": "boolean"
+ },
+ {
+ "type": "number"
+ },
+ {
+ "type": "string"
+ },
+ {
+ "type": "array"
+ },
+ {
+ "type": "object"
+ }
+ ]
}
+ },
+ "type": {
+ "type": "string",
+ "const": "metric"
+ },
+ "metric": {
+ "type": "string"
+ },
+ "value": {
+ "oneOf": [
+ {
+ "type": "integer"
+ },
+ {
+ "type": "number"
+ }
+ ]
+ },
+ "unit": {
+ "type": "string"
}
},
"additionalProperties": false,
"required": [
- "run_id",
- "metrics"
+ "trace_id",
+ "span_id",
+ "timestamp",
+ "type",
+ "metric",
+ "value",
+ "unit"
]
},
- "LogMetricsRequestWrapper": {
+ "SpanEndPayload": {
"type": "object",
"properties": {
- "request": {
- "$ref": "#/components/schemas/LogMetricsRequest"
+ "type": {
+ "type": "string",
+ "const": "span_end"
+ },
+ "status": {
+ "$ref": "#/components/schemas/SpanStatus"
}
},
"additionalProperties": false,
"required": [
- "request"
+ "type",
+ "status"
+ ]
+ },
+ "SpanStartPayload": {
+ "type": "object",
+ "properties": {
+ "type": {
+ "type": "string",
+ "const": "span_start"
+ },
+ "name": {
+ "type": "string"
+ },
+ "parent_span_id": {
+ "type": "string"
+ }
+ },
+ "additionalProperties": false,
+ "required": [
+ "type",
+ "name"
+ ]
+ },
+ "SpanStatus": {
+ "type": "string",
+ "enum": [
+ "ok",
+ "error"
+ ]
+ },
+ "StructuredLogEvent": {
+ "type": "object",
+ "properties": {
+ "trace_id": {
+ "type": "string"
+ },
+ "span_id": {
+ "type": "string"
+ },
+ "timestamp": {
+ "type": "string",
+ "format": "date-time"
+ },
+ "attributes": {
+ "type": "object",
+ "additionalProperties": {
+ "oneOf": [
+ {
+ "type": "null"
+ },
+ {
+ "type": "boolean"
+ },
+ {
+ "type": "number"
+ },
+ {
+ "type": "string"
+ },
+ {
+ "type": "array"
+ },
+ {
+ "type": "object"
+ }
+ ]
+ }
+ },
+ "type": {
+ "type": "string",
+ "const": "structured_log"
+ },
+ "payload": {
+ "oneOf": [
+ {
+ "$ref": "#/components/schemas/SpanStartPayload"
+ },
+ {
+ "$ref": "#/components/schemas/SpanEndPayload"
+ }
+ ]
+ }
+ },
+ "additionalProperties": false,
+ "required": [
+ "trace_id",
+ "span_id",
+ "timestamp",
+ "type",
+ "payload"
+ ]
+ },
+ "UnstructuredLogEvent": {
+ "type": "object",
+ "properties": {
+ "trace_id": {
+ "type": "string"
+ },
+ "span_id": {
+ "type": "string"
+ },
+ "timestamp": {
+ "type": "string",
+ "format": "date-time"
+ },
+ "attributes": {
+ "type": "object",
+ "additionalProperties": {
+ "oneOf": [
+ {
+ "type": "null"
+ },
+ {
+ "type": "boolean"
+ },
+ {
+ "type": "number"
+ },
+ {
+ "type": "string"
+ },
+ {
+ "type": "array"
+ },
+ {
+ "type": "object"
+ }
+ ]
+ }
+ },
+ "type": {
+ "type": "string",
+ "const": "unstructured_log"
+ },
+ "message": {
+ "type": "string"
+ },
+ "severity": {
+ "$ref": "#/components/schemas/LogSeverity"
+ }
+ },
+ "additionalProperties": false,
+ "required": [
+ "trace_id",
+ "span_id",
+ "timestamp",
+ "type",
+ "message",
+ "severity"
+ ]
+ },
+ "LogEventRequest": {
+ "type": "object",
+ "properties": {
+ "event": {
+ "oneOf": [
+ {
+ "$ref": "#/components/schemas/UnstructuredLogEvent"
+ },
+ {
+ "$ref": "#/components/schemas/MetricEvent"
+ },
+ {
+ "$ref": "#/components/schemas/StructuredLogEvent"
+ }
+ ]
+ }
+ },
+ "additionalProperties": false,
+ "required": [
+ "event"
]
},
"DPOAlignmentConfig": {
@@ -5237,7 +4393,49 @@
"weight_decay"
]
},
- "PostTrainingRLHFRequest": {
+ "RLHFAlgorithm": {
+ "type": "string",
+ "enum": [
+ "dpo"
+ ]
+ },
+ "TrainingConfig": {
+ "type": "object",
+ "properties": {
+ "n_epochs": {
+ "type": "integer"
+ },
+ "batch_size": {
+ "type": "integer"
+ },
+ "shuffle": {
+ "type": "boolean"
+ },
+ "n_iters": {
+ "type": "integer"
+ },
+ "enable_activation_checkpointing": {
+ "type": "boolean"
+ },
+ "memory_efficient_fsdp_wrap": {
+ "type": "boolean"
+ },
+ "fsdp_cpu_offload": {
+ "type": "boolean"
+ }
+ },
+ "additionalProperties": false,
+ "required": [
+ "n_epochs",
+ "batch_size",
+ "shuffle",
+ "n_iters",
+ "enable_activation_checkpointing",
+ "memory_efficient_fsdp_wrap",
+ "fsdp_cpu_offload"
+ ]
+ },
+ "PreferenceOptimizeRequest": {
"type": "object",
"properties": {
"job_uuid": {
@@ -5327,61 +4525,6 @@
"training_config",
"hyperparam_search_config",
"logger_config"
- ],
- "title": "Request to finetune a model."
- },
- "RLHFAlgorithm": {
- "type": "string",
- "enum": [
- "dpo"
- ]
- },
- "TrainingConfig": {
- "type": "object",
- "properties": {
- "n_epochs": {
- "type": "integer"
- },
- "batch_size": {
- "type": "integer"
- },
- "shuffle": {
- "type": "boolean"
- },
- "n_iters": {
- "type": "integer"
- },
- "enable_activation_checkpointing": {
- "type": "boolean"
- },
- "memory_efficient_fsdp_wrap": {
- "type": "boolean"
- },
- "fsdp_cpu_offload": {
- "type": "boolean"
- }
- },
- "additionalProperties": false,
- "required": [
- "n_epochs",
- "batch_size",
- "shuffle",
- "n_iters",
- "enable_activation_checkpointing",
- "memory_efficient_fsdp_wrap",
- "fsdp_cpu_offload"
- ]
- },
- "PostTrainingRLHFRequestWrapper": {
- "type": "object",
- "properties": {
- "request": {
- "$ref": "#/components/schemas/PostTrainingRLHFRequest"
- }
- },
- "additionalProperties": false,
- "required": [
- "request"
]
},
"QueryDocumentsRequest": {
@@ -5532,7 +4675,7 @@
"sampled_generations"
]
},
- "RewardScoringRequest": {
+ "RewardScoreRequest": {
"type": "object",
"properties": {
"dialog_generations": {
@@ -5549,19 +4692,6 @@
"required": [
"dialog_generations",
"model"
- ],
- "title": "Request to score a reward function. A list of prompts and a list of responses per prompt."
- },
- "RewardScoringRequestWrapper": {
- "type": "object",
- "properties": {
- "request": {
- "$ref": "#/components/schemas/RewardScoringRequest"
- }
- },
- "additionalProperties": false,
- "required": [
- "request"
]
},
"RewardScoringResponse": {
@@ -5644,7 +4774,7 @@
"score"
]
},
- "RunShieldRequest": {
+ "RunShieldsRequest": {
"type": "object",
"properties": {
"messages": {
@@ -5679,18 +4809,6 @@
"shields"
]
},
- "RunShieldRequestWrapper": {
- "type": "object",
- "properties": {
- "request": {
- "$ref": "#/components/schemas/RunShieldRequest"
- }
- },
- "additionalProperties": false,
- "required": [
- "request"
- ]
- },
"RunShieldResponse": {
"type": "object",
"properties": {
@@ -5777,7 +4895,38 @@
"alpha"
]
},
- "PostTrainingSFTRequest": {
+ "QLoraFinetuningConfig": {
+ "type": "object",
+ "properties": {
+ "lora_attn_modules": {
+ "type": "array",
+ "items": {
+ "type": "string"
+ }
+ },
+ "apply_lora_to_mlp": {
+ "type": "boolean"
+ },
+ "apply_lora_to_output": {
+ "type": "boolean"
+ },
+ "rank": {
+ "type": "integer"
+ },
+ "alpha": {
+ "type": "integer"
+ }
+ },
+ "additionalProperties": false,
+ "required": [
+ "lora_attn_modules",
+ "apply_lora_to_mlp",
+ "apply_lora_to_output",
+ "rank",
+ "alpha"
+ ]
+ },
+ "SupervisedFineTuneRequest": {
"type": "object",
"properties": {
"job_uuid": {
@@ -5877,53 +5026,9 @@
"training_config",
"hyperparam_search_config",
"logger_config"
- ],
- "title": "Request to finetune a model."
- },
- "QLoraFinetuningConfig": {
- "type": "object",
- "properties": {
- "lora_attn_modules": {
- "type": "array",
- "items": {
- "type": "string"
- }
- },
- "apply_lora_to_mlp": {
- "type": "boolean"
- },
- "apply_lora_to_output": {
- "type": "boolean"
- },
- "rank": {
- "type": "integer"
- },
- "alpha": {
- "type": "integer"
- }
- },
- "additionalProperties": false,
- "required": [
- "lora_attn_modules",
- "apply_lora_to_mlp",
- "apply_lora_to_output",
- "rank",
- "alpha"
]
},
- "PostTrainingSFTRequestWrapper": {
- "type": "object",
- "properties": {
- "request": {
- "$ref": "#/components/schemas/PostTrainingSFTRequest"
- }
- },
- "additionalProperties": false,
- "required": [
- "request"
- ]
- },
- "SyntheticDataGenerationRequest": {
+ "SyntheticDataGenerateRequest": {
"type": "object",
"properties": {
"dialogs": {
@@ -5965,19 +5070,6 @@
"required": [
"dialogs",
"filtering_function"
- ],
- "title": "Request to generate synthetic data. A small batch of prompts and a filtering function"
- },
- "SyntheticDataGenerationRequestWrapper": {
- "type": "object",
- "properties": {
- "request": {
- "$ref": "#/components/schemas/SyntheticDataGenerationRequest"
- }
- },
- "additionalProperties": false,
- "required": [
- "request"
]
},
"SyntheticDataGenerationResponse": {
@@ -6039,176 +5131,6 @@
"bank_id",
"documents"
]
- },
- "UpdateExperimentRequest": {
- "type": "object",
- "properties": {
- "experiment_id": {
- "type": "string"
- },
- "status": {
- "$ref": "#/components/schemas/ExperimentStatus"
- },
- "metadata": {
- "type": "object",
- "additionalProperties": {
- "oneOf": [
- {
- "type": "null"
- },
- {
- "type": "boolean"
- },
- {
- "type": "number"
- },
- {
- "type": "string"
- },
- {
- "type": "array"
- },
- {
- "type": "object"
- }
- ]
- }
- }
- },
- "additionalProperties": false,
- "required": [
- "experiment_id"
- ]
- },
- "UpdateExperimentRequestWrapper": {
- "type": "object",
- "properties": {
- "request": {
- "$ref": "#/components/schemas/UpdateExperimentRequest"
- }
- },
- "additionalProperties": false,
- "required": [
- "request"
- ]
- },
- "UpdateRunRequest": {
- "type": "object",
- "properties": {
- "run_id": {
- "type": "string"
- },
- "status": {
- "type": "string"
- },
- "ended_at": {
- "type": "string",
- "format": "date-time"
- },
- "metadata": {
- "type": "object",
- "additionalProperties": {
- "oneOf": [
- {
- "type": "null"
- },
- {
- "type": "boolean"
- },
- {
- "type": "number"
- },
- {
- "type": "string"
- },
- {
- "type": "array"
- },
- {
- "type": "object"
- }
- ]
- }
- }
- },
- "additionalProperties": false,
- "required": [
- "run_id"
- ]
- },
- "UpdateRunRequestWrapper": {
- "type": "object",
- "properties": {
- "request": {
- "$ref": "#/components/schemas/UpdateRunRequest"
- }
- },
- "additionalProperties": false,
- "required": [
- "request"
- ]
- },
- "UploadArtifactRequest": {
- "type": "object",
- "properties": {
- "experiment_id": {
- "type": "string"
- },
- "name": {
- "type": "string"
- },
- "artifact_type": {
- "type": "string"
- },
- "content": {
- "type": "string",
- "contentEncoding": "base64"
- },
- "metadata": {
- "type": "object",
- "additionalProperties": {
- "oneOf": [
- {
- "type": "null"
- },
- {
- "type": "boolean"
- },
- {
- "type": "number"
- },
- {
- "type": "string"
- },
- {
- "type": "array"
- },
- {
- "type": "object"
- }
- ]
- }
- }
- },
- "additionalProperties": false,
- "required": [
- "experiment_id",
- "name",
- "artifact_type",
- "content"
- ]
- },
- "UploadArtifactRequestWrapper": {
- "type": "object",
- "properties": {
- "request": {
- "$ref": "#/components/schemas/UploadArtifactRequest"
- }
- },
- "additionalProperties": false,
- "required": [
- "request"
- ]
}
},
"responses": {}
@@ -6219,42 +5141,38 @@
}
],
"tags": [
- {
- "name": "BatchInference"
- },
- {
- "name": "Safety"
- },
- {
- "name": "Telemetry"
- },
- {
- "name": "RewardScoring"
- },
- {
- "name": "Memory"
- },
{
"name": "SyntheticDataGeneration"
},
- {
- "name": "Inference"
- },
- {
- "name": "Evaluations"
- },
- {
- "name": "PostTraining"
- },
{
"name": "Datasets"
},
{
- "name": "AgenticSystem"
+ "name": "Evaluations"
},
{
- "name": "BatchChatCompletionRequest",
- "description": ""
+ "name": "Safety"
+ },
+ {
+ "name": "Inference"
+ },
+ {
+ "name": "Telemetry"
+ },
+ {
+ "name": "PostTraining"
+ },
+ {
+ "name": "Memory"
+ },
+ {
+ "name": "RewardScoring"
+ },
+ {
+ "name": "BatchInference"
+ },
+ {
+ "name": "AgenticSystem"
},
{
"name": "BuiltinTool",
@@ -6309,8 +5227,8 @@
"description": ""
},
{
- "name": "BatchChatCompletionRequestWrapper",
- "description": ""
+ "name": "BatchChatCompletionRequest",
+ "description": ""
},
{
"name": "BatchChatCompletionResponse",
@@ -6320,10 +5238,6 @@
"name": "BatchCompletionRequest",
"description": ""
},
- {
- "name": "BatchCompletionRequestWrapper",
- "description": ""
- },
{
"name": "BatchCompletionResponse",
"description": ""
@@ -6341,8 +5255,8 @@
"description": ""
},
{
- "name": "ChatCompletionRequestWrapper",
- "description": ""
+ "name": "ChatCompletionResponse",
+ "description": "Chat completion response.\n\n"
},
{
"name": "ChatCompletionResponseEvent",
@@ -6373,8 +5287,8 @@
"description": ""
},
{
- "name": "CompletionRequestWrapper",
- "description": ""
+ "name": "CompletionResponse",
+ "description": "Completion response.\n\n"
},
{
"name": "CompletionResponseStreamChunk",
@@ -6444,17 +5358,13 @@
"name": "AgenticSystemSessionCreateResponse",
"description": ""
},
- {
- "name": "AgenticSystemTurnCreateRequest",
- "description": ""
- },
{
"name": "Attachment",
"description": ""
},
{
- "name": "AgenticSystemTurnCreateRequestWrapper",
- "description": ""
+ "name": "CreateAgenticSystemTurnRequest",
+ "description": ""
},
{
"name": "AgenticSystemTurnResponseEvent",
@@ -6512,10 +5422,6 @@
"name": "Turn",
"description": "A single turn in an interaction with an Agentic System.\n\n"
},
- {
- "name": "CreateDatasetRequest",
- "description": "Request to create a dataset.\n\n"
- },
{
"name": "TrainEvalDataset",
"description": "Dataset to be used for training or evaluating language models.\n\n"
@@ -6525,24 +5431,8 @@
"description": ""
},
{
- "name": "CreateDatasetRequestWrapper",
- "description": ""
- },
- {
- "name": "CreateExperimentRequest",
- "description": ""
- },
- {
- "name": "CreateExperimentRequestWrapper",
- "description": ""
- },
- {
- "name": "Experiment",
- "description": ""
- },
- {
- "name": "ExperimentStatus",
- "description": ""
+ "name": "CreateDatasetRequest",
+ "description": ""
},
{
"name": "CreateMemoryBankRequest",
@@ -6552,18 +5442,6 @@
"name": "MemoryBank",
"description": ""
},
- {
- "name": "CreateRunRequest",
- "description": ""
- },
- {
- "name": "CreateRunRequestWrapper",
- "description": ""
- },
- {
- "name": "Run",
- "description": ""
- },
{
"name": "DeleteAgenticSystemRequest",
"description": ""
@@ -6592,17 +5470,9 @@
"name": "EmbeddingsResponse",
"description": ""
},
- {
- "name": "Checkpoint",
- "description": "Checkpoint created during training runs\n\n"
- },
{
"name": "EvaluateQuestionAnsweringRequest",
- "description": "Request to evaluate question answering.\n\n"
- },
- {
- "name": "EvaluateQuestionAnsweringRequestWrapper",
- "description": ""
+ "description": ""
},
{
"name": "EvaluationJob",
@@ -6610,19 +5480,11 @@
},
{
"name": "EvaluateSummarizationRequest",
- "description": "Request to evaluate summarization.\n\n"
- },
- {
- "name": "EvaluateSummarizationRequestWrapper",
- "description": ""
+ "description": ""
},
{
"name": "EvaluateTextGenerationRequest",
- "description": "Request to evaluate text generation.\n\n"
- },
- {
- "name": "EvaluateTextGenerationRequestWrapper",
- "description": ""
+ "description": ""
},
{
"name": "GetAgenticSystemSessionRequest",
@@ -6636,14 +5498,6 @@
"name": "AgenticSystemStepResponse",
"description": ""
},
- {
- "name": "Artifact",
- "description": ""
- },
- {
- "name": "ArtifactType",
- "description": ""
- },
{
"name": "GetDocumentsRequest",
"description": ""
@@ -6665,20 +5519,12 @@
"description": ""
},
{
- "name": "LogSearchRequest",
- "description": ""
+ "name": "Trace",
+ "description": ""
},
{
- "name": "LogSearchRequestWrapper",
- "description": ""
- },
- {
- "name": "Log",
- "description": ""
- },
- {
- "name": "Metric",
- "description": ""
+ "name": "Checkpoint",
+ "description": "Checkpoint created during training runs\n\n"
},
{
"name": "PostTrainingJobArtifactsResponse",
@@ -6705,24 +5551,36 @@
"description": ""
},
{
- "name": "ListArtifactsRequest",
- "description": ""
+ "name": "LogSeverity",
+ "description": ""
},
{
- "name": "LogMessagesRequest",
- "description": ""
+ "name": "MetricEvent",
+ "description": ""
},
{
- "name": "LogMessagesRequestWrapper",
- "description": ""
+ "name": "SpanEndPayload",
+ "description": ""
},
{
- "name": "LogMetricsRequest",
- "description": ""
+ "name": "SpanStartPayload",
+ "description": ""
},
{
- "name": "LogMetricsRequestWrapper",
- "description": ""
+ "name": "SpanStatus",
+ "description": ""
+ },
+ {
+ "name": "StructuredLogEvent",
+ "description": ""
+ },
+ {
+ "name": "UnstructuredLogEvent",
+ "description": ""
+ },
+ {
+ "name": "LogEventRequest",
+ "description": ""
},
{
"name": "DPOAlignmentConfig",
@@ -6732,10 +5590,6 @@
"name": "OptimizerConfig",
"description": ""
},
- {
- "name": "PostTrainingRLHFRequest",
- "description": "Request to finetune a model.\n\n"
- },
{
"name": "RLHFAlgorithm",
"description": ""
@@ -6745,8 +5599,8 @@
"description": ""
},
{
- "name": "PostTrainingRLHFRequestWrapper",
- "description": ""
+ "name": "PreferenceOptimizeRequest",
+ "description": ""
},
{
"name": "QueryDocumentsRequest",
@@ -6761,12 +5615,8 @@
"description": ""
},
{
- "name": "RewardScoringRequest",
- "description": "Request to score a reward function. A list of prompts and a list of responses per prompt.\n\n"
- },
- {
- "name": "RewardScoringRequestWrapper",
- "description": ""
+ "name": "RewardScoreRequest",
+ "description": ""
},
{
"name": "RewardScoringResponse",
@@ -6781,12 +5631,8 @@
"description": ""
},
{
- "name": "RunShieldRequest",
- "description": ""
- },
- {
- "name": "RunShieldRequestWrapper",
- "description": ""
+ "name": "RunShieldsRequest",
+ "description": ""
},
{
"name": "RunShieldResponse",
@@ -6804,25 +5650,17 @@
"name": "LoraFinetuningConfig",
"description": ""
},
- {
- "name": "PostTrainingSFTRequest",
- "description": "Request to finetune a model.\n\n"
- },
{
"name": "QLoraFinetuningConfig",
"description": ""
},
{
- "name": "PostTrainingSFTRequestWrapper",
- "description": ""
+ "name": "SupervisedFineTuneRequest",
+ "description": ""
},
{
- "name": "SyntheticDataGenerationRequest",
- "description": "Request to generate synthetic data. A small batch of prompts and a filtering function\n\n"
- },
- {
- "name": "SyntheticDataGenerationRequestWrapper",
- "description": ""
+ "name": "SyntheticDataGenerateRequest",
+ "description": ""
},
{
"name": "SyntheticDataGenerationResponse",
@@ -6831,30 +5669,6 @@
{
"name": "UpdateDocumentsRequest",
"description": ""
- },
- {
- "name": "UpdateExperimentRequest",
- "description": ""
- },
- {
- "name": "UpdateExperimentRequestWrapper",
- "description": ""
- },
- {
- "name": "UpdateRunRequest",
- "description": ""
- },
- {
- "name": "UpdateRunRequestWrapper",
- "description": ""
- },
- {
- "name": "UploadArtifactRequest",
- "description": ""
- },
- {
- "name": "UploadArtifactRequestWrapper",
- "description": ""
}
],
"x-tagGroups": [
@@ -6881,8 +5695,6 @@
"AgenticSystemCreateResponse",
"AgenticSystemSessionCreateResponse",
"AgenticSystemStepResponse",
- "AgenticSystemTurnCreateRequest",
- "AgenticSystemTurnCreateRequestWrapper",
"AgenticSystemTurnResponseEvent",
"AgenticSystemTurnResponseStepCompletePayload",
"AgenticSystemTurnResponseStepProgressPayload",
@@ -6890,21 +5702,17 @@
"AgenticSystemTurnResponseStreamChunk",
"AgenticSystemTurnResponseTurnCompletePayload",
"AgenticSystemTurnResponseTurnStartPayload",
- "Artifact",
- "ArtifactType",
"Attachment",
"BatchChatCompletionRequest",
- "BatchChatCompletionRequestWrapper",
"BatchChatCompletionResponse",
"BatchCompletionRequest",
- "BatchCompletionRequestWrapper",
"BatchCompletionResponse",
"BuiltinShield",
"BuiltinTool",
"CancelEvaluationJobRequest",
"CancelTrainingJobRequest",
"ChatCompletionRequest",
- "ChatCompletionRequestWrapper",
+ "ChatCompletionResponse",
"ChatCompletionResponseEvent",
"ChatCompletionResponseEventType",
"ChatCompletionResponseStreamChunk",
@@ -6912,17 +5720,13 @@
"CodeInterpreterToolDefinition",
"CompletionMessage",
"CompletionRequest",
- "CompletionRequestWrapper",
+ "CompletionResponse",
"CompletionResponseStreamChunk",
"CreateAgenticSystemRequest",
"CreateAgenticSystemSessionRequest",
+ "CreateAgenticSystemTurnRequest",
"CreateDatasetRequest",
- "CreateDatasetRequestWrapper",
- "CreateExperimentRequest",
- "CreateExperimentRequestWrapper",
"CreateMemoryBankRequest",
- "CreateRunRequest",
- "CreateRunRequestWrapper",
"DPOAlignmentConfig",
"DeleteAgenticSystemRequest",
"DeleteAgenticSystemSessionRequest",
@@ -6934,36 +5738,25 @@
"EmbeddingsRequest",
"EmbeddingsResponse",
"EvaluateQuestionAnsweringRequest",
- "EvaluateQuestionAnsweringRequestWrapper",
"EvaluateSummarizationRequest",
- "EvaluateSummarizationRequestWrapper",
"EvaluateTextGenerationRequest",
- "EvaluateTextGenerationRequestWrapper",
"EvaluationJob",
"EvaluationJobArtifactsResponse",
"EvaluationJobLogStream",
"EvaluationJobStatusResponse",
- "Experiment",
- "ExperimentStatus",
"FinetuningAlgorithm",
"FunctionCallToolDefinition",
"GetAgenticSystemSessionRequest",
"GetDocumentsRequest",
"InferenceStep",
"InsertDocumentsRequest",
- "ListArtifactsRequest",
- "Log",
- "LogMessagesRequest",
- "LogMessagesRequestWrapper",
- "LogMetricsRequest",
- "LogMetricsRequestWrapper",
- "LogSearchRequest",
- "LogSearchRequestWrapper",
+ "LogEventRequest",
+ "LogSeverity",
"LoraFinetuningConfig",
"MemoryBank",
"MemoryBankDocument",
"MemoryRetrievalStep",
- "Metric",
+ "MetricEvent",
"OnViolationAction",
"OptimizerConfig",
"PhotogenToolDefinition",
@@ -6972,23 +5765,17 @@
"PostTrainingJobLogStream",
"PostTrainingJobStatus",
"PostTrainingJobStatusResponse",
- "PostTrainingRLHFRequest",
- "PostTrainingRLHFRequestWrapper",
- "PostTrainingSFTRequest",
- "PostTrainingSFTRequestWrapper",
+ "PreferenceOptimizeRequest",
"QLoraFinetuningConfig",
"QueryDocumentsRequest",
"QueryDocumentsResponse",
"RLHFAlgorithm",
"RestAPIExecutionConfig",
"RestAPIMethod",
- "RewardScoringRequest",
- "RewardScoringRequestWrapper",
+ "RewardScoreRequest",
"RewardScoringResponse",
- "Run",
- "RunShieldRequest",
- "RunShieldRequestWrapper",
"RunShieldResponse",
+ "RunShieldsRequest",
"SamplingParams",
"SamplingStrategy",
"ScoredDialogGenerations",
@@ -6998,9 +5785,13 @@
"ShieldCallStep",
"ShieldDefinition",
"ShieldResponse",
+ "SpanEndPayload",
+ "SpanStartPayload",
+ "SpanStatus",
"StopReason",
- "SyntheticDataGenerationRequest",
- "SyntheticDataGenerationRequestWrapper",
+ "StructuredLogEvent",
+ "SupervisedFineTuneRequest",
+ "SyntheticDataGenerateRequest",
"SyntheticDataGenerationResponse",
"SystemMessage",
"TokenLogProbs",
@@ -7014,18 +5805,14 @@
"ToolPromptFormat",
"ToolResponse",
"ToolResponseMessage",
+ "Trace",
"TrainEvalDataset",
"TrainEvalDatasetColumnType",
"TrainingConfig",
"Turn",
"URL",
+ "UnstructuredLogEvent",
"UpdateDocumentsRequest",
- "UpdateExperimentRequest",
- "UpdateExperimentRequestWrapper",
- "UpdateRunRequest",
- "UpdateRunRequestWrapper",
- "UploadArtifactRequest",
- "UploadArtifactRequestWrapper",
"UserMessage",
"WolframAlphaToolDefinition"
]
diff --git a/rfcs/RFC-0001-llama-stack-assets/llama-stack-spec.yaml b/rfcs/RFC-0001-llama-stack-assets/llama-stack-spec.yaml
index 322645813..4d1b27bb7 100644
--- a/rfcs/RFC-0001-llama-stack-assets/llama-stack-spec.yaml
+++ b/rfcs/RFC-0001-llama-stack-assets/llama-stack-spec.yaml
@@ -180,180 +180,6 @@ components:
required:
- step
type: object
- AgenticSystemTurnCreateRequest:
- additionalProperties: false
- properties:
- agent_id:
- type: string
- attachments:
- items:
- $ref: '#/components/schemas/Attachment'
- type: array
- input_shields:
- items:
- $ref: '#/components/schemas/ShieldDefinition'
- type: array
- instructions:
- type: string
- messages:
- items:
- oneOf:
- - $ref: '#/components/schemas/UserMessage'
- - $ref: '#/components/schemas/ToolResponseMessage'
- type: array
- output_shields:
- items:
- $ref: '#/components/schemas/ShieldDefinition'
- type: array
- sampling_params:
- $ref: '#/components/schemas/SamplingParams'
- session_id:
- type: string
- stream:
- type: boolean
- tool_choice:
- $ref: '#/components/schemas/ToolChoice'
- tool_prompt_format:
- $ref: '#/components/schemas/ToolPromptFormat'
- tools:
- items:
- oneOf:
- - $ref: '#/components/schemas/SearchToolDefinition'
- - $ref: '#/components/schemas/WolframAlphaToolDefinition'
- - $ref: '#/components/schemas/PhotogenToolDefinition'
- - $ref: '#/components/schemas/CodeInterpreterToolDefinition'
- - $ref: '#/components/schemas/FunctionCallToolDefinition'
- - additionalProperties: false
- properties:
- input_shields:
- items:
- $ref: '#/components/schemas/ShieldDefinition'
- type: array
- max_chunks:
- type: integer
- max_tokens_in_context:
- type: integer
- memory_bank_configs:
- items:
- oneOf:
- - additionalProperties: false
- properties:
- bank_id:
- type: string
- type:
- const: vector
- type: string
- required:
- - bank_id
- - type
- type: object
- - additionalProperties: false
- properties:
- bank_id:
- type: string
- keys:
- items:
- type: string
- type: array
- type:
- const: keyvalue
- type: string
- required:
- - bank_id
- - type
- - keys
- type: object
- - additionalProperties: false
- properties:
- bank_id:
- type: string
- type:
- const: keyword
- type: string
- required:
- - bank_id
- - type
- type: object
- - additionalProperties: false
- properties:
- bank_id:
- type: string
- entities:
- items:
- type: string
- type: array
- type:
- const: graph
- type: string
- required:
- - bank_id
- - type
- - entities
- type: object
- type: array
- output_shields:
- items:
- $ref: '#/components/schemas/ShieldDefinition'
- type: array
- query_generator_config:
- oneOf:
- - additionalProperties: false
- properties:
- sep:
- type: string
- type:
- const: default
- type: string
- required:
- - type
- - sep
- type: object
- - additionalProperties: false
- properties:
- model:
- type: string
- template:
- type: string
- type:
- const: llm
- type: string
- required:
- - type
- - model
- - template
- type: object
- - additionalProperties: false
- properties:
- type:
- const: custom
- type: string
- required:
- - type
- type: object
- type:
- const: memory
- type: string
- required:
- - type
- - memory_bank_configs
- - query_generator_config
- - max_tokens_in_context
- - max_chunks
- type: object
- type: array
- required:
- - agent_id
- - session_id
- - messages
- type: object
- AgenticSystemTurnCreateRequestWrapper:
- additionalProperties: false
- properties:
- request:
- $ref: '#/components/schemas/AgenticSystemTurnCreateRequest'
- required:
- - request
- type: object
AgenticSystemTurnResponseEvent:
additionalProperties: false
properties:
@@ -480,49 +306,6 @@ components:
- event_type
- turn_id
type: object
- Artifact:
- additionalProperties: false
- properties:
- created_at:
- format: date-time
- type: string
- id:
- type: string
- metadata:
- additionalProperties:
- oneOf:
- - type: 'null'
- - type: boolean
- - type: number
- - type: string
- - type: array
- - type: object
- type: object
- name:
- type: string
- size:
- type: integer
- type:
- $ref: '#/components/schemas/ArtifactType'
- required:
- - id
- - name
- - type
- - size
- - created_at
- - metadata
- type: object
- ArtifactType:
- enum:
- - model
- - dataset
- - checkpoint
- - plot
- - metric
- - config
- - code
- - other
- type: string
Attachment:
additionalProperties: false
properties:
@@ -574,14 +357,6 @@ components:
- model
- messages_batch
type: object
- BatchChatCompletionRequestWrapper:
- additionalProperties: false
- properties:
- request:
- $ref: '#/components/schemas/BatchChatCompletionRequest'
- required:
- - request
- type: object
BatchChatCompletionResponse:
additionalProperties: false
properties:
@@ -617,14 +392,6 @@ components:
- model
- content_batch
type: object
- BatchCompletionRequestWrapper:
- additionalProperties: false
- properties:
- request:
- $ref: '#/components/schemas/BatchCompletionRequest'
- required:
- - request
- type: object
BatchCompletionResponse:
additionalProperties: false
properties:
@@ -701,13 +468,18 @@ components:
- model
- messages
type: object
- ChatCompletionRequestWrapper:
+ ChatCompletionResponse:
additionalProperties: false
properties:
- request:
- $ref: '#/components/schemas/ChatCompletionRequest'
+ completion_message:
+ $ref: '#/components/schemas/CompletionMessage'
+ logprobs:
+ items:
+ $ref: '#/components/schemas/TokenLogProbs'
+ type: array
required:
- - request
+ - completion_message
+ title: Chat completion response.
type: object
ChatCompletionResponseEvent:
additionalProperties: false
@@ -817,13 +589,18 @@ components:
- model
- content
type: object
- CompletionRequestWrapper:
+ CompletionResponse:
additionalProperties: false
properties:
- request:
- $ref: '#/components/schemas/CompletionRequest'
+ completion_message:
+ $ref: '#/components/schemas/CompletionMessage'
+ logprobs:
+ items:
+ $ref: '#/components/schemas/TokenLogProbs'
+ type: array
required:
- - request
+ - completion_message
+ title: Completion response.
type: object
CompletionResponseStreamChunk:
additionalProperties: false
@@ -859,6 +636,30 @@ components:
- agent_id
- session_name
type: object
+ CreateAgenticSystemTurnRequest:
+ additionalProperties: false
+ properties:
+ agent_id:
+ type: string
+ attachments:
+ items:
+ $ref: '#/components/schemas/Attachment'
+ type: array
+ messages:
+ items:
+ oneOf:
+ - $ref: '#/components/schemas/UserMessage'
+ - $ref: '#/components/schemas/ToolResponseMessage'
+ type: array
+ session_id:
+ type: string
+ stream:
+ type: boolean
+ required:
+ - agent_id
+ - session_id
+ - messages
+ type: object
CreateDatasetRequest:
additionalProperties: false
properties:
@@ -869,41 +670,6 @@ components:
required:
- uuid
- dataset
- title: Request to create a dataset.
- type: object
- CreateDatasetRequestWrapper:
- additionalProperties: false
- properties:
- request:
- $ref: '#/components/schemas/CreateDatasetRequest'
- required:
- - request
- type: object
- CreateExperimentRequest:
- additionalProperties: false
- properties:
- metadata:
- additionalProperties:
- oneOf:
- - type: 'null'
- - type: boolean
- - type: number
- - type: string
- - type: array
- - type: object
- type: object
- name:
- type: string
- required:
- - name
- type: object
- CreateExperimentRequestWrapper:
- additionalProperties: false
- properties:
- request:
- $ref: '#/components/schemas/CreateExperimentRequest'
- required:
- - request
type: object
CreateMemoryBankRequest:
additionalProperties: false
@@ -958,32 +724,6 @@ components:
- name
- config
type: object
- CreateRunRequest:
- additionalProperties: false
- properties:
- experiment_id:
- type: string
- metadata:
- additionalProperties:
- oneOf:
- - type: 'null'
- - type: boolean
- - type: number
- - type: string
- - type: array
- - type: object
- type: object
- required:
- - experiment_id
- type: object
- CreateRunRequestWrapper:
- additionalProperties: false
- properties:
- request:
- $ref: '#/components/schemas/CreateRunRequest'
- required:
- - request
- type: object
DPOAlignmentConfig:
additionalProperties: false
properties:
@@ -1126,12 +866,6 @@ components:
EvaluateQuestionAnsweringRequest:
additionalProperties: false
properties:
- checkpoint:
- $ref: '#/components/schemas/Checkpoint'
- dataset:
- $ref: '#/components/schemas/TrainEvalDataset'
- job_uuid:
- type: string
metrics:
items:
enum:
@@ -1139,33 +873,12 @@ components:
- f1
type: string
type: array
- sampling_params:
- $ref: '#/components/schemas/SamplingParams'
required:
- - job_uuid
- - dataset
- - checkpoint
- - sampling_params
- metrics
- title: Request to evaluate question answering.
- type: object
- EvaluateQuestionAnsweringRequestWrapper:
- additionalProperties: false
- properties:
- request:
- $ref: '#/components/schemas/EvaluateQuestionAnsweringRequest'
- required:
- - request
type: object
EvaluateSummarizationRequest:
additionalProperties: false
properties:
- checkpoint:
- $ref: '#/components/schemas/Checkpoint'
- dataset:
- $ref: '#/components/schemas/TrainEvalDataset'
- job_uuid:
- type: string
metrics:
items:
enum:
@@ -1173,33 +886,12 @@ components:
- bleu
type: string
type: array
- sampling_params:
- $ref: '#/components/schemas/SamplingParams'
required:
- - job_uuid
- - dataset
- - checkpoint
- - sampling_params
- metrics
- title: Request to evaluate summarization.
- type: object
- EvaluateSummarizationRequestWrapper:
- additionalProperties: false
- properties:
- request:
- $ref: '#/components/schemas/EvaluateSummarizationRequest'
- required:
- - request
type: object
EvaluateTextGenerationRequest:
additionalProperties: false
properties:
- checkpoint:
- $ref: '#/components/schemas/Checkpoint'
- dataset:
- $ref: '#/components/schemas/TrainEvalDataset'
- job_uuid:
- type: string
metrics:
items:
enum:
@@ -1208,23 +900,8 @@ components:
- bleu
type: string
type: array
- sampling_params:
- $ref: '#/components/schemas/SamplingParams'
required:
- - job_uuid
- - dataset
- - checkpoint
- - sampling_params
- metrics
- title: Request to evaluate text generation.
- type: object
- EvaluateTextGenerationRequestWrapper:
- additionalProperties: false
- properties:
- request:
- $ref: '#/components/schemas/EvaluateTextGenerationRequest'
- required:
- - request
type: object
EvaluationJob:
additionalProperties: false
@@ -1259,46 +936,6 @@ components:
required:
- job_uuid
type: object
- Experiment:
- additionalProperties: false
- properties:
- created_at:
- format: date-time
- type: string
- id:
- type: string
- metadata:
- additionalProperties:
- oneOf:
- - type: 'null'
- - type: boolean
- - type: number
- - type: string
- - type: array
- - type: object
- type: object
- name:
- type: string
- status:
- $ref: '#/components/schemas/ExperimentStatus'
- updated_at:
- format: date-time
- type: string
- required:
- - id
- - name
- - status
- - created_at
- - updated_at
- - metadata
- type: object
- ExperimentStatus:
- enum:
- - not_started
- - running
- - completed
- - failed
- type: string
FinetuningAlgorithm:
enum:
- full
@@ -1393,107 +1030,26 @@ components:
- bank_id
- documents
type: object
- ListArtifactsRequest:
+ LogEventRequest:
additionalProperties: false
properties:
- experiment_id:
- type: string
+ event:
+ oneOf:
+ - $ref: '#/components/schemas/UnstructuredLogEvent'
+ - $ref: '#/components/schemas/MetricEvent'
+ - $ref: '#/components/schemas/StructuredLogEvent'
required:
- - experiment_id
- type: object
- Log:
- additionalProperties: false
- properties:
- additional_info:
- additionalProperties:
- oneOf:
- - type: 'null'
- - type: boolean
- - type: number
- - type: string
- - type: array
- - type: object
- type: object
- level:
- type: string
- message:
- type: string
- timestamp:
- format: date-time
- type: string
- required:
- - message
- - level
- - timestamp
- - additional_info
- type: object
- LogMessagesRequest:
- additionalProperties: false
- properties:
- logs:
- items:
- $ref: '#/components/schemas/Log'
- type: array
- run_id:
- type: string
- required:
- - logs
- type: object
- LogMessagesRequestWrapper:
- additionalProperties: false
- properties:
- request:
- $ref: '#/components/schemas/LogMessagesRequest'
- required:
- - request
- type: object
- LogMetricsRequest:
- additionalProperties: false
- properties:
- metrics:
- items:
- $ref: '#/components/schemas/Metric'
- type: array
- run_id:
- type: string
- required:
- - run_id
- - metrics
- type: object
- LogMetricsRequestWrapper:
- additionalProperties: false
- properties:
- request:
- $ref: '#/components/schemas/LogMetricsRequest'
- required:
- - request
- type: object
- LogSearchRequest:
- additionalProperties: false
- properties:
- filters:
- additionalProperties:
- oneOf:
- - type: 'null'
- - type: boolean
- - type: number
- - type: string
- - type: array
- - type: object
- type: object
- query:
- type: string
- required:
- - query
- type: object
- LogSearchRequestWrapper:
- additionalProperties: false
- properties:
- request:
- $ref: '#/components/schemas/LogSearchRequest'
- required:
- - request
+ - event
type: object
+ LogSeverity:
+ enum:
+ - verbose
+ - debug
+ - info
+ - warn
+ - error
+ - critical
+ type: string
LoraFinetuningConfig:
additionalProperties: false
properties:
@@ -1635,27 +1191,45 @@ components:
- memory_bank_ids
- inserted_context
type: object
- Metric:
+ MetricEvent:
additionalProperties: false
properties:
- name:
+ attributes:
+ additionalProperties:
+ oneOf:
+ - type: 'null'
+ - type: boolean
+ - type: number
+ - type: string
+ - type: array
+ - type: object
+ type: object
+ metric:
type: string
- run_id:
+ span_id:
type: string
timestamp:
format: date-time
type: string
+ trace_id:
+ type: string
+ type:
+ const: metric
+ type: string
+ unit:
+ type: string
value:
oneOf:
- - type: number
- type: integer
- - type: string
- - type: boolean
+ - type: number
required:
- - name
- - value
+ - trace_id
+ - span_id
- timestamp
- - run_id
+ - type
+ - metric
+ - value
+ - unit
type: object
OnViolationAction:
enum:
@@ -1782,7 +1356,7 @@ components:
- checkpoints
title: Status of a finetuning job.
type: object
- PostTrainingRLHFRequest:
+ PreferenceOptimizeRequest:
additionalProperties: false
properties:
algorithm:
@@ -1832,78 +1406,6 @@ components:
- training_config
- hyperparam_search_config
- logger_config
- title: Request to finetune a model.
- type: object
- PostTrainingRLHFRequestWrapper:
- additionalProperties: false
- properties:
- request:
- $ref: '#/components/schemas/PostTrainingRLHFRequest'
- required:
- - request
- type: object
- PostTrainingSFTRequest:
- additionalProperties: false
- properties:
- algorithm:
- $ref: '#/components/schemas/FinetuningAlgorithm'
- algorithm_config:
- oneOf:
- - $ref: '#/components/schemas/LoraFinetuningConfig'
- - $ref: '#/components/schemas/QLoraFinetuningConfig'
- - $ref: '#/components/schemas/DoraFinetuningConfig'
- dataset:
- $ref: '#/components/schemas/TrainEvalDataset'
- hyperparam_search_config:
- additionalProperties:
- oneOf:
- - type: 'null'
- - type: boolean
- - type: number
- - type: string
- - type: array
- - type: object
- type: object
- job_uuid:
- type: string
- logger_config:
- additionalProperties:
- oneOf:
- - type: 'null'
- - type: boolean
- - type: number
- - type: string
- - type: array
- - type: object
- type: object
- model:
- type: string
- optimizer_config:
- $ref: '#/components/schemas/OptimizerConfig'
- training_config:
- $ref: '#/components/schemas/TrainingConfig'
- validation_dataset:
- $ref: '#/components/schemas/TrainEvalDataset'
- required:
- - job_uuid
- - model
- - dataset
- - validation_dataset
- - algorithm
- - algorithm_config
- - optimizer_config
- - training_config
- - hyperparam_search_config
- - logger_config
- title: Request to finetune a model.
- type: object
- PostTrainingSFTRequestWrapper:
- additionalProperties: false
- properties:
- request:
- $ref: '#/components/schemas/PostTrainingSFTRequest'
- required:
- - request
type: object
QLoraFinetuningConfig:
additionalProperties: false
@@ -2035,7 +1537,7 @@ components:
- PUT
- DELETE
type: string
- RewardScoringRequest:
+ RewardScoreRequest:
additionalProperties: false
properties:
dialog_generations:
@@ -2047,16 +1549,6 @@ components:
required:
- dialog_generations
- model
- title: Request to score a reward function. A list of prompts and a list of responses
- per prompt.
- type: object
- RewardScoringRequestWrapper:
- additionalProperties: false
- properties:
- request:
- $ref: '#/components/schemas/RewardScoringRequest'
- required:
- - request
type: object
RewardScoringResponse:
additionalProperties: false
@@ -2070,39 +1562,17 @@ components:
title: Response from the reward scoring. Batch of (prompt, response, score)
tuples that pass the threshold.
type: object
- Run:
+ RunShieldResponse:
additionalProperties: false
properties:
- ended_at:
- format: date-time
- type: string
- experiment_id:
- type: string
- id:
- type: string
- metadata:
- additionalProperties:
- oneOf:
- - type: 'null'
- - type: boolean
- - type: number
- - type: string
- - type: array
- - type: object
- type: object
- started_at:
- format: date-time
- type: string
- status:
- type: string
+ responses:
+ items:
+ $ref: '#/components/schemas/ShieldResponse'
+ type: array
required:
- - id
- - experiment_id
- - status
- - started_at
- - metadata
+ - responses
type: object
- RunShieldRequest:
+ RunShieldsRequest:
additionalProperties: false
properties:
messages:
@@ -2121,24 +1591,6 @@ components:
- messages
- shields
type: object
- RunShieldRequestWrapper:
- additionalProperties: false
- properties:
- request:
- $ref: '#/components/schemas/RunShieldRequest'
- required:
- - request
- type: object
- RunShieldResponse:
- additionalProperties: false
- properties:
- responses:
- items:
- $ref: '#/components/schemas/ShieldResponse'
- type: array
- required:
- - responses
- type: object
SamplingParams:
additionalProperties: false
properties:
@@ -2307,13 +1759,132 @@ components:
- shield_type
- is_violation
type: object
+ SpanEndPayload:
+ additionalProperties: false
+ properties:
+ status:
+ $ref: '#/components/schemas/SpanStatus'
+ type:
+ const: span_end
+ type: string
+ required:
+ - type
+ - status
+ type: object
+ SpanStartPayload:
+ additionalProperties: false
+ properties:
+ name:
+ type: string
+ parent_span_id:
+ type: string
+ type:
+ const: span_start
+ type: string
+ required:
+ - type
+ - name
+ type: object
+ SpanStatus:
+ enum:
+ - ok
+ - error
+ type: string
StopReason:
enum:
- end_of_turn
- end_of_message
- out_of_tokens
type: string
- SyntheticDataGenerationRequest:
+ StructuredLogEvent:
+ additionalProperties: false
+ properties:
+ attributes:
+ additionalProperties:
+ oneOf:
+ - type: 'null'
+ - type: boolean
+ - type: number
+ - type: string
+ - type: array
+ - type: object
+ type: object
+ payload:
+ oneOf:
+ - $ref: '#/components/schemas/SpanStartPayload'
+ - $ref: '#/components/schemas/SpanEndPayload'
+ span_id:
+ type: string
+ timestamp:
+ format: date-time
+ type: string
+ trace_id:
+ type: string
+ type:
+ const: structured_log
+ type: string
+ required:
+ - trace_id
+ - span_id
+ - timestamp
+ - type
+ - payload
+ type: object
+ SupervisedFineTuneRequest:
+ additionalProperties: false
+ properties:
+ algorithm:
+ $ref: '#/components/schemas/FinetuningAlgorithm'
+ algorithm_config:
+ oneOf:
+ - $ref: '#/components/schemas/LoraFinetuningConfig'
+ - $ref: '#/components/schemas/QLoraFinetuningConfig'
+ - $ref: '#/components/schemas/DoraFinetuningConfig'
+ dataset:
+ $ref: '#/components/schemas/TrainEvalDataset'
+ hyperparam_search_config:
+ additionalProperties:
+ oneOf:
+ - type: 'null'
+ - type: boolean
+ - type: number
+ - type: string
+ - type: array
+ - type: object
+ type: object
+ job_uuid:
+ type: string
+ logger_config:
+ additionalProperties:
+ oneOf:
+ - type: 'null'
+ - type: boolean
+ - type: number
+ - type: string
+ - type: array
+ - type: object
+ type: object
+ model:
+ type: string
+ optimizer_config:
+ $ref: '#/components/schemas/OptimizerConfig'
+ training_config:
+ $ref: '#/components/schemas/TrainingConfig'
+ validation_dataset:
+ $ref: '#/components/schemas/TrainEvalDataset'
+ required:
+ - job_uuid
+ - model
+ - dataset
+ - validation_dataset
+ - algorithm
+ - algorithm_config
+ - optimizer_config
+ - training_config
+ - hyperparam_search_config
+ - logger_config
+ type: object
+ SyntheticDataGenerateRequest:
additionalProperties: false
properties:
dialogs:
@@ -2339,16 +1910,6 @@ components:
required:
- dialogs
- filtering_function
- title: Request to generate synthetic data. A small batch of prompts and a filtering
- function
- type: object
- SyntheticDataGenerationRequestWrapper:
- additionalProperties: false
- properties:
- request:
- $ref: '#/components/schemas/SyntheticDataGenerationRequest'
- required:
- - request
type: object
SyntheticDataGenerationResponse:
additionalProperties: false
@@ -2580,6 +2141,24 @@ components:
- tool_name
- content
type: object
+ Trace:
+ additionalProperties: false
+ properties:
+ end_time:
+ format: date-time
+ type: string
+ root_span_id:
+ type: string
+ start_time:
+ format: date-time
+ type: string
+ trace_id:
+ type: string
+ required:
+ - trace_id
+ - root_span_id
+ - start_time
+ type: object
TrainEvalDataset:
additionalProperties: false
properties:
@@ -2685,6 +2264,41 @@ components:
format: uri
pattern: ^(https?://|file://|data:)
type: string
+ UnstructuredLogEvent:
+ additionalProperties: false
+ properties:
+ attributes:
+ additionalProperties:
+ oneOf:
+ - type: 'null'
+ - type: boolean
+ - type: number
+ - type: string
+ - type: array
+ - type: object
+ type: object
+ message:
+ type: string
+ severity:
+ $ref: '#/components/schemas/LogSeverity'
+ span_id:
+ type: string
+ timestamp:
+ format: date-time
+ type: string
+ trace_id:
+ type: string
+ type:
+ const: unstructured_log
+ type: string
+ required:
+ - trace_id
+ - span_id
+ - timestamp
+ - type
+ - message
+ - severity
+ type: object
UpdateDocumentsRequest:
additionalProperties: false
properties:
@@ -2698,101 +2312,6 @@ components:
- bank_id
- documents
type: object
- UpdateExperimentRequest:
- additionalProperties: false
- properties:
- experiment_id:
- type: string
- metadata:
- additionalProperties:
- oneOf:
- - type: 'null'
- - type: boolean
- - type: number
- - type: string
- - type: array
- - type: object
- type: object
- status:
- $ref: '#/components/schemas/ExperimentStatus'
- required:
- - experiment_id
- type: object
- UpdateExperimentRequestWrapper:
- additionalProperties: false
- properties:
- request:
- $ref: '#/components/schemas/UpdateExperimentRequest'
- required:
- - request
- type: object
- UpdateRunRequest:
- additionalProperties: false
- properties:
- ended_at:
- format: date-time
- type: string
- metadata:
- additionalProperties:
- oneOf:
- - type: 'null'
- - type: boolean
- - type: number
- - type: string
- - type: array
- - type: object
- type: object
- run_id:
- type: string
- status:
- type: string
- required:
- - run_id
- type: object
- UpdateRunRequestWrapper:
- additionalProperties: false
- properties:
- request:
- $ref: '#/components/schemas/UpdateRunRequest'
- required:
- - request
- type: object
- UploadArtifactRequest:
- additionalProperties: false
- properties:
- artifact_type:
- type: string
- content:
- contentEncoding: base64
- type: string
- experiment_id:
- type: string
- metadata:
- additionalProperties:
- oneOf:
- - type: 'null'
- - type: boolean
- - type: number
- - type: string
- - type: array
- - type: object
- type: object
- name:
- type: string
- required:
- - experiment_id
- - name
- - artifact_type
- - content
- type: object
- UploadArtifactRequestWrapper:
- additionalProperties: false
- properties:
- request:
- $ref: '#/components/schemas/UploadArtifactRequest'
- required:
- - request
- type: object
UserMessage:
additionalProperties: false
properties:
@@ -2838,7 +2357,7 @@ info:
description: "This is the specification of the llama stack that provides\n \
\ a set of endpoints and their corresponding interfaces that are tailored\
\ to\n best leverage Llama Models. The specification is still in\
- \ draft and subject to change.\n Generated at 2024-09-10 16:42:15.870336"
+ \ draft and subject to change.\n Generated at 2024-09-11 16:05:23.016090"
title: '[DRAFT] Llama Stack Specification'
version: 0.0.1
jsonSchemaDialect: https://json-schema.org/draft/2020-12/schema
@@ -2970,7 +2489,7 @@ paths:
content:
application/json:
schema:
- $ref: '#/components/schemas/AgenticSystemTurnCreateRequestWrapper'
+ $ref: '#/components/schemas/CreateAgenticSystemTurnRequest'
required: true
responses:
'200':
@@ -3003,23 +2522,6 @@ paths:
description: OK
tags:
- AgenticSystem
- /artifacts/get:
- get:
- parameters:
- - in: query
- name: artifact_id
- required: true
- schema:
- type: string
- responses:
- '200':
- content:
- application/json:
- schema:
- $ref: '#/components/schemas/Artifact'
- description: OK
- tags:
- - Telemetry
/batch_inference/chat_completion:
post:
parameters: []
@@ -3027,7 +2529,7 @@ paths:
content:
application/json:
schema:
- $ref: '#/components/schemas/BatchChatCompletionRequestWrapper'
+ $ref: '#/components/schemas/BatchChatCompletionRequest'
required: true
responses:
'200':
@@ -3045,7 +2547,7 @@ paths:
content:
application/json:
schema:
- $ref: '#/components/schemas/BatchCompletionRequestWrapper'
+ $ref: '#/components/schemas/BatchCompletionRequest'
required: true
responses:
'200':
@@ -3063,7 +2565,7 @@ paths:
content:
application/json:
schema:
- $ref: '#/components/schemas/CreateDatasetRequestWrapper'
+ $ref: '#/components/schemas/CreateDatasetRequest'
required: true
responses:
'200':
@@ -3185,7 +2687,7 @@ paths:
content:
application/json:
schema:
- $ref: '#/components/schemas/EvaluateQuestionAnsweringRequestWrapper'
+ $ref: '#/components/schemas/EvaluateQuestionAnsweringRequest'
required: true
responses:
'200':
@@ -3203,7 +2705,7 @@ paths:
content:
application/json:
schema:
- $ref: '#/components/schemas/EvaluateSummarizationRequestWrapper'
+ $ref: '#/components/schemas/EvaluateSummarizationRequest'
required: true
responses:
'200':
@@ -3221,7 +2723,7 @@ paths:
content:
application/json:
schema:
- $ref: '#/components/schemas/EvaluateTextGenerationRequestWrapper'
+ $ref: '#/components/schemas/EvaluateTextGenerationRequest'
required: true
responses:
'200':
@@ -3232,125 +2734,6 @@ paths:
description: OK
tags:
- Evaluations
- /experiments/artifacts/get:
- post:
- parameters: []
- requestBody:
- content:
- application/json:
- schema:
- $ref: '#/components/schemas/ListArtifactsRequest'
- required: true
- responses:
- '200':
- content:
- application/jsonl:
- schema:
- $ref: '#/components/schemas/Artifact'
- description: OK
- tags:
- - Telemetry
- /experiments/artifacts/upload:
- post:
- parameters: []
- requestBody:
- content:
- application/json:
- schema:
- $ref: '#/components/schemas/UploadArtifactRequestWrapper'
- required: true
- responses:
- '200':
- content:
- application/json:
- schema:
- $ref: '#/components/schemas/Artifact'
- description: OK
- tags:
- - Telemetry
- /experiments/create:
- post:
- parameters: []
- requestBody:
- content:
- application/json:
- schema:
- $ref: '#/components/schemas/CreateExperimentRequestWrapper'
- required: true
- responses:
- '200':
- content:
- application/json:
- schema:
- $ref: '#/components/schemas/Experiment'
- description: OK
- tags:
- - Telemetry
- /experiments/create_run:
- post:
- parameters: []
- requestBody:
- content:
- application/json:
- schema:
- $ref: '#/components/schemas/CreateRunRequestWrapper'
- required: true
- responses:
- '200':
- content:
- application/json:
- schema:
- $ref: '#/components/schemas/Run'
- description: OK
- tags:
- - Telemetry
- /experiments/get:
- get:
- parameters:
- - in: query
- name: experiment_id
- required: true
- schema:
- type: string
- responses:
- '200':
- content:
- application/json:
- schema:
- $ref: '#/components/schemas/Experiment'
- description: OK
- tags:
- - Telemetry
- /experiments/list:
- get:
- parameters: []
- responses:
- '200':
- content:
- application/jsonl:
- schema:
- $ref: '#/components/schemas/Experiment'
- description: OK
- tags:
- - Telemetry
- /experiments/update:
- post:
- parameters: []
- requestBody:
- content:
- application/json:
- schema:
- $ref: '#/components/schemas/UpdateExperimentRequestWrapper'
- required: true
- responses:
- '200':
- content:
- application/json:
- schema:
- $ref: '#/components/schemas/Experiment'
- description: OK
- tags:
- - Telemetry
/inference/chat_completion:
post:
parameters: []
@@ -3358,15 +2741,17 @@ paths:
content:
application/json:
schema:
- $ref: '#/components/schemas/ChatCompletionRequestWrapper'
+ $ref: '#/components/schemas/ChatCompletionRequest'
required: true
responses:
'200':
content:
text/event-stream:
schema:
- $ref: '#/components/schemas/ChatCompletionResponseStreamChunk'
- description: SSE-stream of these events.
+ oneOf:
+ - $ref: '#/components/schemas/ChatCompletionResponse'
+ - $ref: '#/components/schemas/ChatCompletionResponseStreamChunk'
+ description: Chat completion response. **OR** SSE-stream of these events.
tags:
- Inference
/inference/completion:
@@ -3376,15 +2761,17 @@ paths:
content:
application/json:
schema:
- $ref: '#/components/schemas/CompletionRequestWrapper'
+ $ref: '#/components/schemas/CompletionRequest'
required: true
responses:
'200':
content:
application/json:
schema:
- $ref: '#/components/schemas/CompletionResponseStreamChunk'
- description: streamed completion response.
+ oneOf:
+ - $ref: '#/components/schemas/CompletionResponse'
+ - $ref: '#/components/schemas/CompletionResponseStreamChunk'
+ description: Completion response. **OR** streamed completion response.
tags:
- Inference
/inference/embeddings:
@@ -3405,38 +2792,6 @@ paths:
description: OK
tags:
- Inference
- /logging/get_logs:
- post:
- parameters: []
- requestBody:
- content:
- application/json:
- schema:
- $ref: '#/components/schemas/LogSearchRequestWrapper'
- required: true
- responses:
- '200':
- content:
- application/jsonl:
- schema:
- $ref: '#/components/schemas/Log'
- description: OK
- tags:
- - Telemetry
- /logging/log_messages:
- post:
- parameters: []
- requestBody:
- content:
- application/json:
- schema:
- $ref: '#/components/schemas/LogMessagesRequestWrapper'
- required: true
- responses:
- '200':
- description: OK
- tags:
- - Telemetry
/memory_bank/documents/delete:
post:
parameters: []
@@ -3671,7 +3026,7 @@ paths:
content:
application/json:
schema:
- $ref: '#/components/schemas/PostTrainingRLHFRequestWrapper'
+ $ref: '#/components/schemas/PreferenceOptimizeRequest'
required: true
responses:
'200':
@@ -3689,7 +3044,7 @@ paths:
content:
application/json:
schema:
- $ref: '#/components/schemas/PostTrainingSFTRequestWrapper'
+ $ref: '#/components/schemas/SupervisedFineTuneRequest'
required: true
responses:
'200':
@@ -3707,7 +3062,7 @@ paths:
content:
application/json:
schema:
- $ref: '#/components/schemas/RewardScoringRequestWrapper'
+ $ref: '#/components/schemas/RewardScoreRequest'
required: true
responses:
'200':
@@ -3718,55 +3073,6 @@ paths:
description: OK
tags:
- RewardScoring
- /runs/log_metrics:
- post:
- parameters: []
- requestBody:
- content:
- application/json:
- schema:
- $ref: '#/components/schemas/LogMetricsRequestWrapper'
- required: true
- responses:
- '200':
- description: OK
- tags:
- - Telemetry
- /runs/metrics:
- get:
- parameters:
- - in: query
- name: run_id
- required: true
- schema:
- type: string
- responses:
- '200':
- content:
- application/jsonl:
- schema:
- $ref: '#/components/schemas/Metric'
- description: OK
- tags:
- - Telemetry
- /runs/update:
- post:
- parameters: []
- requestBody:
- content:
- application/json:
- schema:
- $ref: '#/components/schemas/UpdateRunRequestWrapper'
- required: true
- responses:
- '200':
- content:
- application/json:
- schema:
- $ref: '#/components/schemas/Run'
- description: OK
- tags:
- - Telemetry
/safety/run_shields:
post:
parameters: []
@@ -3774,7 +3080,7 @@ paths:
content:
application/json:
schema:
- $ref: '#/components/schemas/RunShieldRequestWrapper'
+ $ref: '#/components/schemas/RunShieldsRequest'
required: true
responses:
'200':
@@ -3792,7 +3098,7 @@ paths:
content:
application/json:
schema:
- $ref: '#/components/schemas/SyntheticDataGenerationRequestWrapper'
+ $ref: '#/components/schemas/SyntheticDataGenerateRequest'
required: true
responses:
'200':
@@ -3803,25 +3109,53 @@ paths:
description: OK
tags:
- SyntheticDataGeneration
+ /telemetry/get_trace:
+ get:
+ parameters:
+ - in: query
+ name: trace_id
+ required: true
+ schema:
+ type: string
+ responses:
+ '200':
+ content:
+ application/json:
+ schema:
+ $ref: '#/components/schemas/Trace'
+ description: OK
+ tags:
+ - Telemetry
+ /telemetry/log_event:
+ post:
+ parameters: []
+ requestBody:
+ content:
+ application/json:
+ schema:
+ $ref: '#/components/schemas/LogEventRequest'
+ required: true
+ responses:
+ '200':
+ description: OK
+ tags:
+ - Telemetry
security:
- Default: []
servers:
- url: http://any-hosted-llama-stack.com
tags:
-- name: BatchInference
-- name: Safety
-- name: Telemetry
-- name: RewardScoring
-- name: Memory
- name: SyntheticDataGeneration
-- name: Inference
-- name: Evaluations
-- name: PostTraining
- name: Datasets
+- name: Evaluations
+- name: Safety
+- name: Inference
+- name: Telemetry
+- name: PostTraining
+- name: Memory
+- name: RewardScoring
+- name: BatchInference
- name: AgenticSystem
-- description:
- name: BatchChatCompletionRequest
- description:
name: BuiltinTool
- description:
name: UserMessage
-- description:
- name: BatchChatCompletionRequestWrapper
+ name: BatchChatCompletionRequest
- description:
name: BatchChatCompletionResponse
- description:
name: BatchCompletionRequest
-- description:
- name: BatchCompletionRequestWrapper
- description:
name: BatchCompletionResponse
@@ -3885,9 +3216,11 @@ tags:
- description:
name: ChatCompletionRequest
-- description:
- name: ChatCompletionRequestWrapper
+- description: 'Chat completion response.
+
+
+ '
+ name: ChatCompletionResponse
- description: 'Chat completion response event.
@@ -3913,9 +3246,11 @@ tags:
- description:
name: CompletionRequest
-- description:
- name: CompletionRequestWrapper
+- description: 'Completion response.
+
+
+ '
+ name: CompletionResponse
- description: 'streamed completion response.
@@ -3966,14 +3301,11 @@ tags:
- description:
name: AgenticSystemSessionCreateResponse
-- description:
- name: AgenticSystemTurnCreateRequest
- description:
name: Attachment
-- description:
- name: AgenticSystemTurnCreateRequestWrapper
+ name: CreateAgenticSystemTurnRequest
- description: 'Streamed agent execution response.
@@ -4017,11 +3349,6 @@ tags:
'
name: Turn
-- description: 'Request to create a dataset.
-
-
- '
- name: CreateDatasetRequest
- description: 'Dataset to be used for training or evaluating language models.
@@ -4030,33 +3357,14 @@ tags:
- description:
name: TrainEvalDatasetColumnType
-- description:
- name: CreateDatasetRequestWrapper
-- description:
- name: CreateExperimentRequest
-- description:
- name: CreateExperimentRequestWrapper
-- description:
- name: Experiment
-- description:
- name: ExperimentStatus
+ name: CreateDatasetRequest
- description:
name: CreateMemoryBankRequest
- description:
name: MemoryBank
-- description:
- name: CreateRunRequest
-- description:
- name: CreateRunRequestWrapper
-- description:
- name: Run
- description:
name: DeleteAgenticSystemRequest
@@ -4078,40 +3386,17 @@ tags:
- description:
name: EmbeddingsResponse
-- description: 'Checkpoint created during training runs
-
-
- '
- name: Checkpoint
-- description: 'Request to evaluate question answering.
-
-
- '
- name: EvaluateQuestionAnsweringRequest
-- description:
- name: EvaluateQuestionAnsweringRequestWrapper
+ name: EvaluateQuestionAnsweringRequest
- description:
name: EvaluationJob
-- description: 'Request to evaluate summarization.
-
-
- '
+- description:
name: EvaluateSummarizationRequest
-- description:
- name: EvaluateSummarizationRequestWrapper
-- description: 'Request to evaluate text generation.
-
-
- '
name: EvaluateTextGenerationRequest
-- description:
- name: EvaluateTextGenerationRequestWrapper
- description:
name: GetAgenticSystemSessionRequest
@@ -4123,10 +3408,6 @@ tags:
- description:
name: AgenticSystemStepResponse
-- description:
- name: Artifact
-- description:
- name: ArtifactType
- description:
name: GetDocumentsRequest
@@ -4145,16 +3426,13 @@ tags:
- description:
name: EvaluationJobStatusResponse
-- description:
- name: LogSearchRequest
-- description:
- name: LogSearchRequestWrapper
-- description:
- name: Log
-- description:
- name: Metric
+- description:
+ name: Trace
+- description: 'Checkpoint created during training runs
+
+
+ '
+ name: Checkpoint
- description: 'Artifacts of a finetuning job.
@@ -4181,39 +3459,39 @@ tags:
- description:
name: InsertDocumentsRequest
-- description:
+ name: LogSeverity
+- description:
+ name: MetricEvent
+- description:
+ name: SpanEndPayload
+- description:
- name: ListArtifactsRequest
-- description:
+ name: SpanStatus
+- description:
- name: LogMessagesRequest
-- description:
- name: LogMessagesRequestWrapper
-- description:
- name: LogMetricsRequest
-- description:
- name: LogMetricsRequestWrapper
+ name: LogEventRequest
- description:
name: DPOAlignmentConfig
- description:
name: OptimizerConfig
-- description: 'Request to finetune a model.
-
-
- '
- name: PostTrainingRLHFRequest
- description:
name: RLHFAlgorithm
- description:
name: TrainingConfig
-- description:
- name: PostTrainingRLHFRequestWrapper
+ name: PreferenceOptimizeRequest
- description:
name: QueryDocumentsRequest
@@ -4223,15 +3501,9 @@ tags:
- description:
name: DialogGenerations
-- description: 'Request to score a reward function. A list of prompts and a list of
- responses per prompt.
-
-
- '
- name: RewardScoringRequest
-- description:
- name: RewardScoringRequestWrapper
+ name: RewardScoreRequest
- description: 'Response from the reward scoring. Batch of (prompt, response, score)
tuples that pass the threshold.
@@ -4243,12 +3515,9 @@ tags:
name: ScoredDialogGenerations
- description:
name: ScoredMessage
-- description:
- name: RunShieldRequest
-- description:
- name: RunShieldRequestWrapper
+ name: RunShieldsRequest
- description:
name: RunShieldResponse
@@ -4261,27 +3530,15 @@ tags:
- description:
name: LoraFinetuningConfig
-- description: 'Request to finetune a model.
-
-
- '
- name: PostTrainingSFTRequest
- description:
name: QLoraFinetuningConfig
-- description:
- name: PostTrainingSFTRequestWrapper
-- description: 'Request to generate synthetic data. A small batch of prompts and a
- filtering function
-
-
- '
- name: SyntheticDataGenerationRequest
-- description:
- name: SyntheticDataGenerationRequestWrapper
+ name: SyntheticDataGenerateRequest
- description: 'Response from the synthetic data generation. Batch of (prompt, response,
score) tuples that pass the threshold.
@@ -4292,24 +3549,6 @@ tags:
- description:
name: UpdateDocumentsRequest
-- description:
- name: UpdateExperimentRequest
-- description:
- name: UpdateExperimentRequestWrapper
-- description:
- name: UpdateRunRequest
-- description:
- name: UpdateRunRequestWrapper
-- description:
- name: UploadArtifactRequest
-- description:
- name: UploadArtifactRequestWrapper
x-tagGroups:
- name: Operations
tags:
@@ -4330,8 +3569,6 @@ x-tagGroups:
- AgenticSystemCreateResponse
- AgenticSystemSessionCreateResponse
- AgenticSystemStepResponse
- - AgenticSystemTurnCreateRequest
- - AgenticSystemTurnCreateRequestWrapper
- AgenticSystemTurnResponseEvent
- AgenticSystemTurnResponseStepCompletePayload
- AgenticSystemTurnResponseStepProgressPayload
@@ -4339,21 +3576,17 @@ x-tagGroups:
- AgenticSystemTurnResponseStreamChunk
- AgenticSystemTurnResponseTurnCompletePayload
- AgenticSystemTurnResponseTurnStartPayload
- - Artifact
- - ArtifactType
- Attachment
- BatchChatCompletionRequest
- - BatchChatCompletionRequestWrapper
- BatchChatCompletionResponse
- BatchCompletionRequest
- - BatchCompletionRequestWrapper
- BatchCompletionResponse
- BuiltinShield
- BuiltinTool
- CancelEvaluationJobRequest
- CancelTrainingJobRequest
- ChatCompletionRequest
- - ChatCompletionRequestWrapper
+ - ChatCompletionResponse
- ChatCompletionResponseEvent
- ChatCompletionResponseEventType
- ChatCompletionResponseStreamChunk
@@ -4361,17 +3594,13 @@ x-tagGroups:
- CodeInterpreterToolDefinition
- CompletionMessage
- CompletionRequest
- - CompletionRequestWrapper
+ - CompletionResponse
- CompletionResponseStreamChunk
- CreateAgenticSystemRequest
- CreateAgenticSystemSessionRequest
+ - CreateAgenticSystemTurnRequest
- CreateDatasetRequest
- - CreateDatasetRequestWrapper
- - CreateExperimentRequest
- - CreateExperimentRequestWrapper
- CreateMemoryBankRequest
- - CreateRunRequest
- - CreateRunRequestWrapper
- DPOAlignmentConfig
- DeleteAgenticSystemRequest
- DeleteAgenticSystemSessionRequest
@@ -4383,36 +3612,25 @@ x-tagGroups:
- EmbeddingsRequest
- EmbeddingsResponse
- EvaluateQuestionAnsweringRequest
- - EvaluateQuestionAnsweringRequestWrapper
- EvaluateSummarizationRequest
- - EvaluateSummarizationRequestWrapper
- EvaluateTextGenerationRequest
- - EvaluateTextGenerationRequestWrapper
- EvaluationJob
- EvaluationJobArtifactsResponse
- EvaluationJobLogStream
- EvaluationJobStatusResponse
- - Experiment
- - ExperimentStatus
- FinetuningAlgorithm
- FunctionCallToolDefinition
- GetAgenticSystemSessionRequest
- GetDocumentsRequest
- InferenceStep
- InsertDocumentsRequest
- - ListArtifactsRequest
- - Log
- - LogMessagesRequest
- - LogMessagesRequestWrapper
- - LogMetricsRequest
- - LogMetricsRequestWrapper
- - LogSearchRequest
- - LogSearchRequestWrapper
+ - LogEventRequest
+ - LogSeverity
- LoraFinetuningConfig
- MemoryBank
- MemoryBankDocument
- MemoryRetrievalStep
- - Metric
+ - MetricEvent
- OnViolationAction
- OptimizerConfig
- PhotogenToolDefinition
@@ -4421,23 +3639,17 @@ x-tagGroups:
- PostTrainingJobLogStream
- PostTrainingJobStatus
- PostTrainingJobStatusResponse
- - PostTrainingRLHFRequest
- - PostTrainingRLHFRequestWrapper
- - PostTrainingSFTRequest
- - PostTrainingSFTRequestWrapper
+ - PreferenceOptimizeRequest
- QLoraFinetuningConfig
- QueryDocumentsRequest
- QueryDocumentsResponse
- RLHFAlgorithm
- RestAPIExecutionConfig
- RestAPIMethod
- - RewardScoringRequest
- - RewardScoringRequestWrapper
+ - RewardScoreRequest
- RewardScoringResponse
- - Run
- - RunShieldRequest
- - RunShieldRequestWrapper
- RunShieldResponse
+ - RunShieldsRequest
- SamplingParams
- SamplingStrategy
- ScoredDialogGenerations
@@ -4447,9 +3659,13 @@ x-tagGroups:
- ShieldCallStep
- ShieldDefinition
- ShieldResponse
+ - SpanEndPayload
+ - SpanStartPayload
+ - SpanStatus
- StopReason
- - SyntheticDataGenerationRequest
- - SyntheticDataGenerationRequestWrapper
+ - StructuredLogEvent
+ - SupervisedFineTuneRequest
+ - SyntheticDataGenerateRequest
- SyntheticDataGenerationResponse
- SystemMessage
- TokenLogProbs
@@ -4463,17 +3679,13 @@ x-tagGroups:
- ToolPromptFormat
- ToolResponse
- ToolResponseMessage
+ - Trace
- TrainEvalDataset
- TrainEvalDatasetColumnType
- TrainingConfig
- Turn
- URL
+ - UnstructuredLogEvent
- UpdateDocumentsRequest
- - UpdateExperimentRequest
- - UpdateExperimentRequestWrapper
- - UpdateRunRequest
- - UpdateRunRequestWrapper
- - UploadArtifactRequest
- - UploadArtifactRequestWrapper
- UserMessage
- WolframAlphaToolDefinition
diff --git a/rfcs/openapi_generator/pyopenapi/generator.py b/rfcs/openapi_generator/pyopenapi/generator.py
index a711d9f68..f6be71854 100644
--- a/rfcs/openapi_generator/pyopenapi/generator.py
+++ b/rfcs/openapi_generator/pyopenapi/generator.py
@@ -471,14 +471,9 @@ class Generator:
from dataclasses import make_dataclass
- if len(op.request_params) == 1 and "Request" in first[1].__name__:
- # TODO(ashwin): Undo the "Request" hack and this entire block eventually
- request_name = first[1].__name__ + "Wrapper"
- request_type = make_dataclass(request_name, op.request_params)
- else:
- op_name = "".join(word.capitalize() for word in op.name.split("_"))
- request_name = f"{op_name}Request"
- request_type = make_dataclass(request_name, op.request_params)
+ op_name = "".join(word.capitalize() for word in op.name.split("_"))
+ request_name = f"{op_name}Request"
+ request_type = make_dataclass(request_name, op.request_params)
requestBody = RequestBody(
content={
diff --git a/tests/test_inference.py b/tests/test_inference.py
index 277cf7e8a..800046355 100644
--- a/tests/test_inference.py
+++ b/tests/test_inference.py
@@ -249,7 +249,12 @@ class InferenceTests(unittest.IsolatedAsyncioTestCase):
stream=True,
tools=[ToolDefinition(tool_name=BuiltinTool.brave_search)],
)
- iterator = self.api.chat_completion(request)
+ iterator = self.api.chat_completion(
+ request.model,
+ request.messages,
+ stream=request.stream,
+ tools=request.tools,
+ )
events = []
async for chunk in iterator:
diff --git a/tests/test_ollama_inference.py b/tests/test_ollama_inference.py
index f5b172e69..c3cef3a10 100644
--- a/tests/test_ollama_inference.py
+++ b/tests/test_ollama_inference.py
@@ -61,7 +61,9 @@ class OllamaInferenceTests(unittest.IsolatedAsyncioTestCase):
],
stream=False,
)
- iterator = self.api.chat_completion(request)
+ iterator = self.api.chat_completion(
+ request.model, request.messages, stream=request.stream
+ )
async for r in iterator:
response = r
print(response.completion_message.content)