diff --git a/docs/openapi_generator/generate.py b/docs/openapi_generator/generate.py
index c41e3d003..97d265aeb 100644
--- a/docs/openapi_generator/generate.py
+++ b/docs/openapi_generator/generate.py
@@ -34,20 +34,6 @@ schema_utils.json_schema_type = json_schema_type
from llama_stack.distribution.stack import LlamaStack
-# TODO: this should be fixed in the generator itself so it reads appropriate annotations
-STREAMING_ENDPOINTS = [
- "/agents/turn/create",
- "/inference/chat_completion",
-]
-
-
-def patch_sse_stream_responses(spec: Specification):
- for path, path_item in spec.document.paths.items():
- if path in STREAMING_ENDPOINTS:
- content = path_item.post.responses["200"].content.pop("application/json")
- path_item.post.responses["200"].content["text/event-stream"] = content
-
-
def main(output_dir: str):
output_dir = Path(output_dir)
if not output_dir.exists():
@@ -74,8 +60,6 @@ def main(output_dir: str):
),
)
- patch_sse_stream_responses(spec)
-
with open(output_dir / "llama-stack-spec.yaml", "w", encoding="utf-8") as fp:
yaml.dump(spec.get_json(), fp, allow_unicode=True)
diff --git a/docs/openapi_generator/pyopenapi/generator.py b/docs/openapi_generator/pyopenapi/generator.py
index 0c8dcbdcb..12e3396e4 100644
--- a/docs/openapi_generator/pyopenapi/generator.py
+++ b/docs/openapi_generator/pyopenapi/generator.py
@@ -4,6 +4,7 @@
# This source code is licensed under the terms described in the LICENSE file in
# the root directory of this source tree.
+import collections
import hashlib
import ipaddress
import typing
@@ -176,9 +177,20 @@ class ContentBuilder:
) -> Dict[str, MediaType]:
"Creates the content subtree for a request or response."
+ def has_iterator_type(t):
+ if typing.get_origin(t) is typing.Union:
+ return any(has_iterator_type(a) for a in typing.get_args(t))
+ else:
+ # TODO: needs a proper fix where we let all types correctly flow upwards
+ # and then test against AsyncIterator
+ return "StreamChunk" in str(t)
+
if is_generic_list(payload_type):
media_type = "application/jsonl"
item_type = unwrap_generic_list(payload_type)
+ elif has_iterator_type(payload_type):
+ item_type = payload_type
+ media_type = "text/event-stream"
else:
media_type = "application/json"
item_type = payload_type
@@ -671,6 +683,8 @@ class Generator:
for extra_tag_group in extra_tag_groups.values():
tags.extend(extra_tag_group)
+ tags = sorted(tags, key=lambda t: t.name)
+
tag_groups = []
if operation_tags:
tag_groups.append(
diff --git a/docs/resources/llama-stack-spec.html b/docs/resources/llama-stack-spec.html
index 44554f2ff..a0b4bccca 100644
--- a/docs/resources/llama-stack-spec.html
+++ b/docs/resources/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 2024-11-13 21:05:58.323310"
+ "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 2024-11-14 12:51:12.176325"
},
"servers": [
{
@@ -195,7 +195,7 @@
"200": {
"description": "Completion response. **OR** streamed completion response.",
"content": {
- "application/json": {
+ "text/event-stream": {
"schema": {
"oneOf": [
{
@@ -7965,242 +7965,24 @@
],
"tags": [
{
- "name": "Agents"
- },
- {
- "name": "DatasetIO"
- },
- {
- "name": "Models"
- },
- {
- "name": "Inference"
- },
- {
- "name": "BatchInference"
- },
- {
- "name": "Memory"
- },
- {
- "name": "Safety"
- },
- {
- "name": "Inspect"
- },
- {
- "name": "EvalTasks"
- },
- {
- "name": "Scoring"
- },
- {
- "name": "Datasets"
- },
- {
- "name": "PostTraining"
- },
- {
- "name": "Eval"
- },
- {
- "name": "Shields"
- },
- {
- "name": "Telemetry"
- },
- {
- "name": "ScoringFunctions"
- },
- {
- "name": "MemoryBanks"
- },
- {
- "name": "SyntheticDataGeneration"
- },
- {
- "name": "BuiltinTool",
- "description": ""
- },
- {
- "name": "CompletionMessage",
- "description": ""
- },
- {
- "name": "ImageMedia",
- "description": ""
- },
- {
- "name": "SamplingParams",
- "description": ""
- },
- {
- "name": "SamplingStrategy",
- "description": ""
- },
- {
- "name": "StopReason",
- "description": ""
- },
- {
- "name": "SystemMessage",
- "description": ""
- },
- {
- "name": "ToolCall",
- "description": ""
- },
- {
- "name": "ToolChoice",
- "description": ""
- },
- {
- "name": "ToolDefinition",
- "description": ""
- },
- {
- "name": "ToolParamDefinition",
- "description": ""
- },
- {
- "name": "ToolPromptFormat",
- "description": "This Enum refers to the prompt format for calling custom / zero shot tools\n\n`json` --\n Refers to the json format for calling tools.\n The json format takes the form like\n {\n \"type\": \"function\",\n \"function\" : {\n \"name\": \"function_name\",\n \"description\": \"function_description\",\n \"parameters\": {...}\n }\n }\n\n`function_tag` --\n This is an example of how you could define\n your own user defined format for making tool calls.\n The function_tag format looks like this,\n (parameters)\n\nThe detailed prompts for each of these formats are added to llama cli\n\n"
- },
- {
- "name": "ToolResponseMessage",
- "description": ""
- },
- {
- "name": "URL",
- "description": ""
- },
- {
- "name": "UserMessage",
- "description": ""
- },
- {
- "name": "BatchChatCompletionRequest",
- "description": ""
- },
- {
- "name": "BatchChatCompletionResponse",
- "description": ""
- },
- {
- "name": "BatchCompletionRequest",
- "description": ""
- },
- {
- "name": "BatchCompletionResponse",
- "description": ""
- },
- {
- "name": "CancelTrainingJobRequest",
- "description": ""
- },
- {
- "name": "ChatCompletionRequest",
- "description": ""
- },
- {
- "name": "ChatCompletionResponse",
- "description": "Chat completion response.\n\n"
- },
- {
- "name": "ChatCompletionResponseEvent",
- "description": "Chat completion response event.\n\n"
- },
- {
- "name": "ChatCompletionResponseEventType",
- "description": ""
- },
- {
- "name": "ChatCompletionResponseStreamChunk",
- "description": "SSE-stream of these events.\n\n"
- },
- {
- "name": "TokenLogProbs",
- "description": ""
- },
- {
- "name": "ToolCallDelta",
- "description": ""
- },
- {
- "name": "ToolCallParseStatus",
- "description": ""
- },
- {
- "name": "CompletionRequest",
- "description": ""
- },
- {
- "name": "CompletionResponse",
- "description": "Completion response.\n\n"
- },
- {
- "name": "CompletionResponseStreamChunk",
- "description": "streamed completion response.\n\n"
+ "name": "AgentCandidate",
+ "description": ""
},
{
"name": "AgentConfig",
"description": ""
},
- {
- "name": "CodeInterpreterToolDefinition",
- "description": ""
- },
- {
- "name": "FunctionCallToolDefinition",
- "description": ""
- },
- {
- "name": "MemoryToolDefinition",
- "description": ""
- },
- {
- "name": "PhotogenToolDefinition",
- "description": ""
- },
- {
- "name": "RestAPIExecutionConfig",
- "description": ""
- },
- {
- "name": "RestAPIMethod",
- "description": ""
- },
- {
- "name": "SearchToolDefinition",
- "description": ""
- },
- {
- "name": "WolframAlphaToolDefinition",
- "description": ""
- },
- {
- "name": "CreateAgentRequest",
- "description": ""
- },
{
"name": "AgentCreateResponse",
"description": ""
},
- {
- "name": "CreateAgentSessionRequest",
- "description": ""
- },
{
"name": "AgentSessionCreateResponse",
"description": ""
},
{
- "name": "Attachment",
- "description": ""
- },
- {
- "name": "CreateAgentTurnRequest",
- "description": ""
+ "name": "AgentStepResponse",
+ "description": ""
},
{
"name": "AgentTurnResponseEvent",
@@ -8231,36 +8013,116 @@
"description": ""
},
{
- "name": "InferenceStep",
- "description": ""
+ "name": "Agents"
},
{
- "name": "MemoryRetrievalStep",
- "description": ""
+ "name": "AppEvalTaskConfig",
+ "description": ""
},
{
- "name": "SafetyViolation",
- "description": ""
+ "name": "Attachment",
+ "description": ""
},
{
- "name": "ShieldCallStep",
- "description": ""
+ "name": "BatchChatCompletionRequest",
+ "description": ""
},
{
- "name": "ToolExecutionStep",
- "description": ""
+ "name": "BatchChatCompletionResponse",
+ "description": ""
},
{
- "name": "ToolResponse",
- "description": ""
+ "name": "BatchCompletionRequest",
+ "description": ""
},
{
- "name": "Turn",
- "description": "A single turn in an interaction with an Agentic System.\n\n"
+ "name": "BatchCompletionResponse",
+ "description": ""
},
{
- "name": "ViolationLevel",
- "description": ""
+ "name": "BatchInference"
+ },
+ {
+ "name": "BenchmarkEvalTaskConfig",
+ "description": ""
+ },
+ {
+ "name": "BuiltinTool",
+ "description": ""
+ },
+ {
+ "name": "CancelTrainingJobRequest",
+ "description": ""
+ },
+ {
+ "name": "ChatCompletionRequest",
+ "description": ""
+ },
+ {
+ "name": "ChatCompletionResponse",
+ "description": "Chat completion response.\n\n"
+ },
+ {
+ "name": "ChatCompletionResponseEvent",
+ "description": "Chat completion response event.\n\n"
+ },
+ {
+ "name": "ChatCompletionResponseEventType",
+ "description": ""
+ },
+ {
+ "name": "ChatCompletionResponseStreamChunk",
+ "description": "SSE-stream of these events.\n\n"
+ },
+ {
+ "name": "Checkpoint",
+ "description": "Checkpoint created during training runs\n\n"
+ },
+ {
+ "name": "CodeInterpreterToolDefinition",
+ "description": ""
+ },
+ {
+ "name": "CompletionMessage",
+ "description": ""
+ },
+ {
+ "name": "CompletionRequest",
+ "description": ""
+ },
+ {
+ "name": "CompletionResponse",
+ "description": "Completion response.\n\n"
+ },
+ {
+ "name": "CompletionResponseStreamChunk",
+ "description": "streamed completion response.\n\n"
+ },
+ {
+ "name": "CreateAgentRequest",
+ "description": ""
+ },
+ {
+ "name": "CreateAgentSessionRequest",
+ "description": ""
+ },
+ {
+ "name": "CreateAgentTurnRequest",
+ "description": ""
+ },
+ {
+ "name": "DPOAlignmentConfig",
+ "description": ""
+ },
+ {
+ "name": "Dataset",
+ "description": ""
+ },
+ {
+ "name": "DatasetIO"
+ },
+ {
+ "name": "Datasets"
},
{
"name": "DeleteAgentsRequest",
@@ -8274,6 +8136,10 @@
"name": "DeleteModelRequest",
"description": ""
},
+ {
+ "name": "DoraFinetuningConfig",
+ "description": ""
+ },
{
"name": "EmbeddingsRequest",
"description": ""
@@ -8283,40 +8149,30 @@
"description": ""
},
{
- "name": "AgentCandidate",
- "description": ""
+ "name": "Eval"
},
{
- "name": "AppEvalTaskConfig",
- "description": ""
+ "name": "EvalTask",
+ "description": ""
},
{
- "name": "BenchmarkEvalTaskConfig",
- "description": ""
- },
- {
- "name": "LLMAsJudgeScoringFnParams",
- "description": ""
- },
- {
- "name": "ModelCandidate",
- "description": ""
- },
- {
- "name": "RegexParserScoringFnParams",
- "description": ""
- },
- {
- "name": "EvaluateRowsRequest",
- "description": ""
+ "name": "EvalTasks"
},
{
"name": "EvaluateResponse",
"description": ""
},
{
- "name": "ScoringResult",
- "description": ""
+ "name": "EvaluateRowsRequest",
+ "description": ""
+ },
+ {
+ "name": "FinetuningAlgorithm",
+ "description": ""
+ },
+ {
+ "name": "FunctionCallToolDefinition",
+ "description": ""
},
{
"name": "GetAgentsSessionRequest",
@@ -8326,57 +8182,127 @@
"name": "GraphMemoryBank",
"description": ""
},
+ {
+ "name": "GraphMemoryBankParams",
+ "description": ""
+ },
+ {
+ "name": "HealthInfo",
+ "description": ""
+ },
+ {
+ "name": "ImageMedia",
+ "description": ""
+ },
+ {
+ "name": "Inference"
+ },
+ {
+ "name": "InferenceStep",
+ "description": ""
+ },
+ {
+ "name": "InsertDocumentsRequest",
+ "description": ""
+ },
+ {
+ "name": "Inspect"
+ },
+ {
+ "name": "Job",
+ "description": ""
+ },
+ {
+ "name": "JobCancelRequest",
+ "description": ""
+ },
+ {
+ "name": "JobStatus",
+ "description": ""
+ },
{
"name": "KeyValueMemoryBank",
"description": ""
},
+ {
+ "name": "KeyValueMemoryBankParams",
+ "description": ""
+ },
{
"name": "KeywordMemoryBank",
"description": ""
},
{
- "name": "Session",
- "description": "A single session of an interaction with an Agentic System.\n\n"
+ "name": "KeywordMemoryBankParams",
+ "description": ""
},
{
- "name": "VectorMemoryBank",
- "description": ""
+ "name": "LLMAsJudgeScoringFnParams",
+ "description": ""
},
{
- "name": "AgentStepResponse",
- "description": ""
+ "name": "LogEventRequest",
+ "description": ""
},
{
- "name": "Dataset",
- "description": ""
+ "name": "LogSeverity",
+ "description": ""
},
{
- "name": "EvalTask",
- "description": ""
+ "name": "LoraFinetuningConfig",
+ "description": ""
+ },
+ {
+ "name": "Memory"
+ },
+ {
+ "name": "MemoryBankDocument",
+ "description": ""
+ },
+ {
+ "name": "MemoryBanks"
+ },
+ {
+ "name": "MemoryRetrievalStep",
+ "description": ""
+ },
+ {
+ "name": "MemoryToolDefinition",
+ "description": ""
+ },
+ {
+ "name": "MetricEvent",
+ "description": ""
},
{
"name": "Model",
"description": ""
},
+ {
+ "name": "ModelCandidate",
+ "description": ""
+ },
+ {
+ "name": "Models"
+ },
+ {
+ "name": "OptimizerConfig",
+ "description": ""
+ },
{
"name": "PaginatedRowsResult",
"description": ""
},
{
- "name": "ScoringFn",
- "description": ""
+ "name": "PhotogenToolDefinition",
+ "description": ""
},
{
- "name": "Shield",
- "description": "A safety shield resource that can be used to check content\n\n"
+ "name": "PostTraining"
},
{
- "name": "Trace",
- "description": ""
- },
- {
- "name": "Checkpoint",
- "description": "Checkpoint created during training runs\n\n"
+ "name": "PostTrainingJob",
+ "description": ""
},
{
"name": "PostTrainingJobArtifactsResponse",
@@ -8395,88 +8321,16 @@
"description": "Status of a finetuning job.\n\n"
},
{
- "name": "PostTrainingJob",
- "description": ""
- },
- {
- "name": "HealthInfo",
- "description": ""
- },
- {
- "name": "MemoryBankDocument",
- "description": ""
- },
- {
- "name": "InsertDocumentsRequest",
- "description": ""
- },
- {
- "name": "JobCancelRequest",
- "description": ""
- },
- {
- "name": "JobStatus",
- "description": ""
+ "name": "PreferenceOptimizeRequest",
+ "description": ""
},
{
"name": "ProviderInfo",
"description": ""
},
{
- "name": "RouteInfo",
- "description": ""
- },
- {
- "name": "LogSeverity",
- "description": ""
- },
- {
- "name": "MetricEvent",
- "description": ""
- },
- {
- "name": "SpanEndPayload",
- "description": ""
- },
- {
- "name": "SpanStartPayload",
- "description": ""
- },
- {
- "name": "SpanStatus",
- "description": ""
- },
- {
- "name": "StructuredLogEvent",
- "description": ""
- },
- {
- "name": "UnstructuredLogEvent",
- "description": ""
- },
- {
- "name": "LogEventRequest",
- "description": ""
- },
- {
- "name": "DPOAlignmentConfig",
- "description": ""
- },
- {
- "name": "OptimizerConfig",
- "description": ""
- },
- {
- "name": "RLHFAlgorithm",
- "description": ""
- },
- {
- "name": "TrainingConfig",
- "description": ""
- },
- {
- "name": "PreferenceOptimizeRequest",
- "description": ""
+ "name": "QLoraFinetuningConfig",
+ "description": ""
},
{
"name": "QueryDocumentsRequest",
@@ -8486,6 +8340,14 @@
"name": "QueryDocumentsResponse",
"description": ""
},
+ {
+ "name": "RLHFAlgorithm",
+ "description": ""
+ },
+ {
+ "name": "RegexParserScoringFnParams",
+ "description": ""
+ },
{
"name": "RegisterDatasetRequest",
"description": ""
@@ -8494,22 +8356,6 @@
"name": "RegisterEvalTaskRequest",
"description": ""
},
- {
- "name": "GraphMemoryBankParams",
- "description": ""
- },
- {
- "name": "KeyValueMemoryBankParams",
- "description": ""
- },
- {
- "name": "KeywordMemoryBankParams",
- "description": ""
- },
- {
- "name": "VectorMemoryBankParams",
- "description": ""
- },
{
"name": "RegisterMemoryBankRequest",
"description": ""
@@ -8527,12 +8373,20 @@
"description": ""
},
{
- "name": "RunEvalRequest",
- "description": ""
+ "name": "RestAPIExecutionConfig",
+ "description": ""
},
{
- "name": "Job",
- "description": ""
+ "name": "RestAPIMethod",
+ "description": ""
+ },
+ {
+ "name": "RouteInfo",
+ "description": ""
+ },
+ {
+ "name": "RunEvalRequest",
+ "description": ""
},
{
"name": "RunShieldRequest",
@@ -8543,12 +8397,19 @@
"description": ""
},
{
- "name": "ScoreRequest",
- "description": ""
+ "name": "Safety"
},
{
- "name": "ScoreResponse",
- "description": ""
+ "name": "SafetyViolation",
+ "description": ""
+ },
+ {
+ "name": "SamplingParams",
+ "description": ""
+ },
+ {
+ "name": "SamplingStrategy",
+ "description": ""
},
{
"name": "ScoreBatchRequest",
@@ -8559,20 +8420,65 @@
"description": ""
},
{
- "name": "DoraFinetuningConfig",
- "description": ""
+ "name": "ScoreRequest",
+ "description": ""
},
{
- "name": "FinetuningAlgorithm",
- "description": ""
+ "name": "ScoreResponse",
+ "description": ""
},
{
- "name": "LoraFinetuningConfig",
- "description": ""
+ "name": "Scoring"
},
{
- "name": "QLoraFinetuningConfig",
- "description": ""
+ "name": "ScoringFn",
+ "description": ""
+ },
+ {
+ "name": "ScoringFunctions"
+ },
+ {
+ "name": "ScoringResult",
+ "description": ""
+ },
+ {
+ "name": "SearchToolDefinition",
+ "description": ""
+ },
+ {
+ "name": "Session",
+ "description": "A single session of an interaction with an Agentic System.\n\n"
+ },
+ {
+ "name": "Shield",
+ "description": "A safety shield resource that can be used to check content\n\n"
+ },
+ {
+ "name": "ShieldCallStep",
+ "description": ""
+ },
+ {
+ "name": "Shields"
+ },
+ {
+ "name": "SpanEndPayload",
+ "description": ""
+ },
+ {
+ "name": "SpanStartPayload",
+ "description": ""
+ },
+ {
+ "name": "SpanStatus",
+ "description": ""
+ },
+ {
+ "name": "StopReason",
+ "description": ""
+ },
+ {
+ "name": "StructuredLogEvent",
+ "description": ""
},
{
"name": "SupervisedFineTuneRequest",
@@ -8582,13 +8488,107 @@
"name": "SyntheticDataGenerateRequest",
"description": ""
},
+ {
+ "name": "SyntheticDataGeneration"
+ },
{
"name": "SyntheticDataGenerationResponse",
"description": "Response from the synthetic data generation. Batch of (prompt, response, score) tuples that pass the threshold.\n\n"
},
+ {
+ "name": "SystemMessage",
+ "description": ""
+ },
+ {
+ "name": "Telemetry"
+ },
+ {
+ "name": "TokenLogProbs",
+ "description": ""
+ },
+ {
+ "name": "ToolCall",
+ "description": ""
+ },
+ {
+ "name": "ToolCallDelta",
+ "description": ""
+ },
+ {
+ "name": "ToolCallParseStatus",
+ "description": ""
+ },
+ {
+ "name": "ToolChoice",
+ "description": ""
+ },
+ {
+ "name": "ToolDefinition",
+ "description": ""
+ },
+ {
+ "name": "ToolExecutionStep",
+ "description": ""
+ },
+ {
+ "name": "ToolParamDefinition",
+ "description": ""
+ },
+ {
+ "name": "ToolPromptFormat",
+ "description": "This Enum refers to the prompt format for calling custom / zero shot tools\n\n`json` --\n Refers to the json format for calling tools.\n The json format takes the form like\n {\n \"type\": \"function\",\n \"function\" : {\n \"name\": \"function_name\",\n \"description\": \"function_description\",\n \"parameters\": {...}\n }\n }\n\n`function_tag` --\n This is an example of how you could define\n your own user defined format for making tool calls.\n The function_tag format looks like this,\n (parameters)\n\nThe detailed prompts for each of these formats are added to llama cli\n\n"
+ },
+ {
+ "name": "ToolResponse",
+ "description": ""
+ },
+ {
+ "name": "ToolResponseMessage",
+ "description": ""
+ },
+ {
+ "name": "Trace",
+ "description": ""
+ },
+ {
+ "name": "TrainingConfig",
+ "description": ""
+ },
+ {
+ "name": "Turn",
+ "description": "A single turn in an interaction with an Agentic System.\n\n"
+ },
+ {
+ "name": "URL",
+ "description": ""
+ },
+ {
+ "name": "UnstructuredLogEvent",
+ "description": ""
+ },
{
"name": "UpdateModelRequest",
"description": ""
+ },
+ {
+ "name": "UserMessage",
+ "description": ""
+ },
+ {
+ "name": "VectorMemoryBank",
+ "description": ""
+ },
+ {
+ "name": "VectorMemoryBankParams",
+ "description": ""
+ },
+ {
+ "name": "ViolationLevel",
+ "description": ""
+ },
+ {
+ "name": "WolframAlphaToolDefinition",
+ "description": ""
}
],
"x-tagGroups": [
diff --git a/docs/resources/llama-stack-spec.yaml b/docs/resources/llama-stack-spec.yaml
index fc28405d7..2ca26f759 100644
--- a/docs/resources/llama-stack-spec.yaml
+++ b/docs/resources/llama-stack-spec.yaml
@@ -3414,7 +3414,7 @@ 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 2024-11-13 21:05:58.323310"
+ \ draft and subject to change.\n Generated at 2024-11-14 12:51:12.176325"
title: '[DRAFT] Llama Stack Specification'
version: 0.0.1
jsonSchemaDialect: https://json-schema.org/draft/2020-12/schema
@@ -4065,7 +4065,7 @@ paths:
responses:
'200':
content:
- application/json:
+ text/event-stream:
schema:
oneOf:
- $ref: '#/components/schemas/CompletionResponse'
@@ -4824,168 +4824,19 @@ security:
servers:
- url: http://any-hosted-llama-stack.com
tags:
-- name: Agents
-- name: DatasetIO
-- name: Models
-- name: Inference
-- name: BatchInference
-- name: Memory
-- name: Safety
-- name: Inspect
-- name: EvalTasks
-- name: Scoring
-- name: Datasets
-- name: PostTraining
-- name: Eval
-- name: Shields
-- name: Telemetry
-- name: ScoringFunctions
-- name: MemoryBanks
-- name: SyntheticDataGeneration
-- description:
- name: BuiltinTool
-- description:
- name: CompletionMessage
-- description:
- name: ImageMedia
-- description:
- name: SamplingParams
-- description:
- name: SamplingStrategy
-- description:
- name: StopReason
-- description:
- name: SystemMessage
-- description:
- name: ToolCall
-- description:
- name: ToolChoice
-- description:
- name: ToolDefinition
-- description:
- name: ToolParamDefinition
-- description: "This Enum refers to the prompt format for calling custom / zero shot\
- \ tools\n\n`json` --\n Refers to the json format for calling tools.\n The\
- \ json format takes the form like\n {\n \"type\": \"function\",\n \
- \ \"function\" : {\n \"name\": \"function_name\",\n \
- \ \"description\": \"function_description\",\n \"parameters\": {...}\n\
- \ }\n }\n\n`function_tag` --\n This is an example of how you could\
- \ define\n your own user defined format for making tool calls.\n The function_tag\
- \ format looks like this,\n (parameters)\n\
- \nThe detailed prompts for each of these formats are added to llama cli\n\n"
- name: ToolPromptFormat
-- description:
- name: ToolResponseMessage
-- description:
- name: URL
-- description:
- name: UserMessage
-- description:
- name: BatchChatCompletionRequest
-- description:
- name: BatchChatCompletionResponse
-- description:
- name: BatchCompletionRequest
-- description:
- name: BatchCompletionResponse
-- description:
- name: CancelTrainingJobRequest
-- description:
- name: ChatCompletionRequest
-- description: 'Chat completion response.
-
-
- '
- name: ChatCompletionResponse
-- description: 'Chat completion response event.
-
-
- '
- name: ChatCompletionResponseEvent
-- description:
- name: ChatCompletionResponseEventType
-- description: 'SSE-stream of these events.
-
-
- '
- name: ChatCompletionResponseStreamChunk
-- description:
- name: TokenLogProbs
-- description:
- name: ToolCallDelta
-- description:
- name: ToolCallParseStatus
-- description:
- name: CompletionRequest
-- description: 'Completion response.
-
-
- '
- name: CompletionResponse
-- description: 'streamed completion response.
-
-
- '
- name: CompletionResponseStreamChunk
+- description:
+ name: AgentCandidate
- description:
name: AgentConfig
-- description:
- name: CodeInterpreterToolDefinition
-- description:
- name: FunctionCallToolDefinition
-- description:
- name: MemoryToolDefinition
-- description:
- name: PhotogenToolDefinition
-- description:
- name: RestAPIExecutionConfig
-- description:
- name: RestAPIMethod
-- description:
- name: SearchToolDefinition
-- description:
- name: WolframAlphaToolDefinition
-- description:
- name: CreateAgentRequest
- description:
name: AgentCreateResponse
-- description:
- name: CreateAgentSessionRequest
- description:
name: AgentSessionCreateResponse
-- description:
- name: Attachment
-- description:
- name: CreateAgentTurnRequest
+ name: AgentStepResponse
- description: 'Streamed agent execution response.
@@ -5012,28 +4863,97 @@ tags:
- description:
name: AgentTurnResponseTurnStartPayload
-- description:
- name: InferenceStep
-- description:
- name: MemoryRetrievalStep
-- description:
+ name: Attachment
+- description:
- name: SafetyViolation
-- description:
- name: ShieldCallStep
-- description:
- name: ToolExecutionStep
-- description:
- name: ToolResponse
-- description: 'A single turn in an interaction with an Agentic System.
+ name: BatchChatCompletionResponse
+- description:
+ name: BatchCompletionRequest
+- description:
+ name: BatchCompletionResponse
+- name: BatchInference
+- description:
+ name: BenchmarkEvalTaskConfig
+- description:
+ name: BuiltinTool
+- description:
+ name: CancelTrainingJobRequest
+- description:
+ name: ChatCompletionRequest
+- description: 'Chat completion response.
- '
- name: Turn
-- description:
- name: ViolationLevel
+ '
+ name: ChatCompletionResponse
+- description: 'Chat completion response event.
+
+
+ '
+ name: ChatCompletionResponseEvent
+- description:
+ name: ChatCompletionResponseEventType
+- description: 'SSE-stream of these events.
+
+
+ '
+ name: ChatCompletionResponseStreamChunk
+- description: 'Checkpoint created during training runs
+
+
+ '
+ name: Checkpoint
+- description:
+ name: CodeInterpreterToolDefinition
+- description:
+ name: CompletionMessage
+- description:
+ name: CompletionRequest
+- description: 'Completion response.
+
+
+ '
+ name: CompletionResponse
+- description: 'streamed completion response.
+
+
+ '
+ name: CompletionResponseStreamChunk
+- description:
+ name: CreateAgentRequest
+- description:
+ name: CreateAgentSessionRequest
+- description:
+ name: CreateAgentTurnRequest
+- description:
+ name: DPOAlignmentConfig
+- description:
+ name: Dataset
+- name: DatasetIO
+- name: Datasets
- description:
name: DeleteAgentsRequest
@@ -5043,82 +4963,112 @@ tags:
- description:
name: DeleteModelRequest
+- description:
+ name: DoraFinetuningConfig
- description:
name: EmbeddingsRequest
- description:
name: EmbeddingsResponse
-- description:
- name: AgentCandidate
-- description:
- name: AppEvalTaskConfig
-- description:
- name: BenchmarkEvalTaskConfig
-- description:
- name: LLMAsJudgeScoringFnParams
-- description:
- name: ModelCandidate
-- description:
- name: RegexParserScoringFnParams
-- description:
- name: EvaluateRowsRequest
+- name: Eval
+- description:
+ name: EvalTask
+- name: EvalTasks
- description:
name: EvaluateResponse
-- description:
- name: ScoringResult
+- description:
+ name: EvaluateRowsRequest
+- description:
+ name: FinetuningAlgorithm
+- description:
+ name: FunctionCallToolDefinition
- description:
name: GetAgentsSessionRequest
- description:
name: GraphMemoryBank
+- description:
+ name: GraphMemoryBankParams
+- description:
+ name: HealthInfo
+- description:
+ name: ImageMedia
+- name: Inference
+- description:
+ name: InferenceStep
+- description:
+ name: InsertDocumentsRequest
+- name: Inspect
+- description:
+ name: Job
+- description:
+ name: JobCancelRequest
+- description:
+ name: JobStatus
- description:
name: KeyValueMemoryBank
+- description:
+ name: KeyValueMemoryBankParams
- description:
name: KeywordMemoryBank
-- description: 'A single session of an interaction with an Agentic System.
-
-
- '
- name: Session
-- description:
- name: VectorMemoryBank
-- description:
- name: AgentStepResponse
-- description:
- name: Dataset
-- description:
- name: EvalTask
+ name: LLMAsJudgeScoringFnParams
+- description:
+ name: LogEventRequest
+- description:
+ name: LogSeverity
+- description:
+ name: LoraFinetuningConfig
+- name: Memory
+- description:
+ name: MemoryBankDocument
+- name: MemoryBanks
+- description:
+ name: MemoryRetrievalStep
+- description:
+ name: MemoryToolDefinition
+- description:
+ name: MetricEvent
- description:
name: Model
+- description:
+ name: ModelCandidate
+- name: Models
+- description:
+ name: OptimizerConfig
- description:
name: PaginatedRowsResult
-- description:
- name: ScoringFn
-- description: 'A safety shield resource that can be used to check content
-
-
- '
- name: Shield
-- description:
- name: Trace
-- description: 'Checkpoint created during training runs
-
-
- '
- name: Checkpoint
+- description:
+ name: PhotogenToolDefinition
+- name: PostTraining
+- description:
+ name: PostTrainingJob
- description: 'Artifacts of a finetuning job.
@@ -5139,83 +5089,31 @@ tags:
'
name: PostTrainingJobStatusResponse
-- description:
- name: PostTrainingJob
-- description:
- name: HealthInfo
-- description:
- name: MemoryBankDocument
-- description:
- name: InsertDocumentsRequest
-- description:
- name: JobCancelRequest
-- description:
- name: JobStatus
-- description:
- name: ProviderInfo
-- description:
- name: RouteInfo
-- description:
- name: LogSeverity
-- description:
- name: MetricEvent
-- description:
- name: SpanEndPayload
-- description:
- name: SpanStartPayload
-- description:
- name: SpanStatus
-- description:
- name: StructuredLogEvent
-- description:
- name: UnstructuredLogEvent
-- description:
- name: LogEventRequest
-- description:
- name: DPOAlignmentConfig
-- description:
- name: OptimizerConfig
-- description:
- name: RLHFAlgorithm
-- description:
- name: TrainingConfig
- description:
name: PreferenceOptimizeRequest
+- description:
+ name: ProviderInfo
+- description:
+ name: QLoraFinetuningConfig
- description:
name: QueryDocumentsRequest
- description:
name: QueryDocumentsResponse
+- description:
+ name: RLHFAlgorithm
+- description:
+ name: RegexParserScoringFnParams
- description:
name: RegisterDatasetRequest
- description:
name: RegisterEvalTaskRequest
-- description:
- name: GraphMemoryBankParams
-- description:
- name: KeyValueMemoryBankParams
-- description:
- name: KeywordMemoryBankParams
-- description:
- name: VectorMemoryBankParams
- description:
name: RegisterMemoryBankRequest
@@ -5228,44 +5126,81 @@ tags:
- description:
name: RegisterShieldRequest
+- description:
+ name: RestAPIExecutionConfig
+- description:
+ name: RestAPIMethod
+- description:
+ name: RouteInfo
- description:
name: RunEvalRequest
-- description:
- name: Job
- description:
name: RunShieldRequest
- description:
name: RunShieldResponse
-- description:
- name: ScoreRequest
-- description:
- name: ScoreResponse
+- name: Safety
+- description:
+ name: SafetyViolation
+- description:
+ name: SamplingParams
+- description:
+ name: SamplingStrategy
- description:
name: ScoreBatchRequest
- description:
name: ScoreBatchResponse
-- description:
+ name: ScoreRequest
+- description:
+ name: ScoreResponse
+- name: Scoring
+- description:
+ name: ScoringFn
+- name: ScoringFunctions
+- description:
+ name: ScoringResult
+- description:
- name: DoraFinetuningConfig
-- description: '
+ name: Session
+- description: 'A safety shield resource that can be used to check content
+
+
+ '
+ name: Shield
+- description:
+ name: ShieldCallStep
+- name: Shields
+- description:
+ name: SpanEndPayload
+- description:
- name: FinetuningAlgorithm
-- description:
+ name: SpanStatus
+- description:
+ name: StopReason
+- description:
- name: LoraFinetuningConfig
-- description:
- name: QLoraFinetuningConfig
+ name: StructuredLogEvent
- description:
name: SupervisedFineTuneRequest
- description:
name: SyntheticDataGenerateRequest
+- name: SyntheticDataGeneration
- description: 'Response from the synthetic data generation. Batch of (prompt, response,
score) tuples that pass the threshold.
@@ -5273,9 +5208,74 @@ tags:
'
name: SyntheticDataGenerationResponse
+- description:
+ name: SystemMessage
+- name: Telemetry
+- description:
+ name: TokenLogProbs
+- description:
+ name: ToolCall
+- description:
+ name: ToolCallDelta
+- description:
+ name: ToolCallParseStatus
+- description:
+ name: ToolChoice
+- description:
+ name: ToolDefinition
+- description:
+ name: ToolExecutionStep
+- description:
+ name: ToolParamDefinition
+- description: "This Enum refers to the prompt format for calling custom / zero shot\
+ \ tools\n\n`json` --\n Refers to the json format for calling tools.\n The\
+ \ json format takes the form like\n {\n \"type\": \"function\",\n \
+ \ \"function\" : {\n \"name\": \"function_name\",\n \
+ \ \"description\": \"function_description\",\n \"parameters\": {...}\n\
+ \ }\n }\n\n`function_tag` --\n This is an example of how you could\
+ \ define\n your own user defined format for making tool calls.\n The function_tag\
+ \ format looks like this,\n (parameters)\n\
+ \nThe detailed prompts for each of these formats are added to llama cli\n\n"
+ name: ToolPromptFormat
+- description:
+ name: ToolResponse
+- description:
+ name: ToolResponseMessage
+- description:
+ name: Trace
+- description:
+ name: TrainingConfig
+- description: 'A single turn in an interaction with an Agentic System.
+
+
+ '
+ name: Turn
+- description:
+ name: URL
+- description:
+ name: UnstructuredLogEvent
- description:
name: UpdateModelRequest
+- description:
+ name: UserMessage
+- description:
+ name: VectorMemoryBank
+- description:
+ name: VectorMemoryBankParams
+- description:
+ name: ViolationLevel
+- description:
+ name: WolframAlphaToolDefinition
x-tagGroups:
- name: Operations
tags: