phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-06-28 02:53:30 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

llama-stack version alpha -> v1

Browse source
This commit is contained in:
Ashwin Bharambe 2025-01-15 05:58:09 -08:00
parent a51c8b4efc
commit b78e6675ea
8 changed files with 390 additions and 407 deletions
Download patch file Download diff file Expand all files Collapse all files

2
docs/openapi_generator/pyopenapi/generator.py
View file

@ -537,7 +537,6 @@ class Generator:
success_type_descriptions = { success_type_descriptions = {
item: doc_string.short_description item: doc_string.short_description
for item, doc_string in success_type_docstring.items() for item, doc_string in success_type_docstring.items()
if doc_string.short_description
} }
else: else:
# use return type as a single response type # use return type as a single response type
@ -596,6 +595,7 @@ class Generator:
) )
responses.update(response_builder.build_response(response_options)) responses.update(response_builder.build_response(response_options))
assert len(responses.keys()) > 0, f"No responses found for {op.name}"
if op.event_type is not None: if op.event_type is not None:
builder = ContentBuilder(self.schema_builder) builder = ContentBuilder(self.schema_builder)
callbacks = { callbacks = {

1
docs/openapi_generator/strong_typing/inspection.py
View file

@ -342,7 +342,6 @@ def is_type_union(typ: object) -> bool:
"True if the type annotation corresponds to a union type (e.g. `Union[T1,T2,T3]`)." "True if the type annotation corresponds to a union type (e.g. `Union[T1,T2,T3]`)."
typ = unwrap_annotated_type(typ) typ = unwrap_annotated_type(typ)
if _is_union_like(typ): if _is_union_like(typ):
args = typing.get_args(typ) args = typing.get_args(typ)
return len(args) > 2 or type(None) not in args return len(args) > 2 or type(None) not in args

406
docs/resources/llama-stack-spec.html
View file

@ -20,7 +20,7 @@
"openapi": "3.1.0", "openapi": "3.1.0",
"info": { "info": {
"title": "Llama Stack Specification", "title": "Llama Stack Specification",
"version": "alpha", "version": "v1",
"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." "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."
}, },
"servers": [ "servers": [
@ -29,7 +29,7 @@
} }
], ],
"paths": { "paths": {
"/alpha/datasetio/append-rows": { "/v1/datasetio/append-rows": {
"post": { "post": {
"responses": { "responses": {
"200": { "200": {
@ -71,7 +71,7 @@
} }
} }
}, },
"/alpha/batch-inference/chat-completion": { "/v1/batch-inference/chat-completion": {
"post": { "post": {
"responses": { "responses": {
"200": { "200": {
@ -120,7 +120,7 @@
} }
} }
}, },
"/alpha/batch-inference/completion": { "/v1/batch-inference/completion": {
"post": { "post": {
"responses": { "responses": {
"200": { "200": {
@ -169,7 +169,7 @@
} }
} }
}, },
"/alpha/post-training/job/cancel": { "/v1/post-training/job/cancel": {
"post": { "post": {
"responses": { "responses": {
"200": { "200": {
@ -211,7 +211,7 @@
} }
} }
}, },
"/alpha/inference/chat-completion": { "/v1/inference/chat-completion": {
"post": { "post": {
"responses": { "responses": {
"200": { "200": {
@ -267,7 +267,7 @@
} }
} }
}, },
"/alpha/inference/completion": { "/v1/inference/completion": {
"post": { "post": {
"responses": { "responses": {
"200": { "200": {
@ -323,7 +323,7 @@
} }
} }
}, },
"/alpha/agents/create": { "/v1/agents/create": {
"post": { "post": {
"responses": { "responses": {
"200": { "200": {
@ -372,7 +372,7 @@
} }
} }
}, },
"/alpha/agents/session/create": { "/v1/agents/session/create": {
"post": { "post": {
"responses": { "responses": {
"200": { "200": {
@ -421,7 +421,7 @@
} }
} }
}, },
"/alpha/agents/turn/create": { "/v1/agents/turn/create": {
"post": { "post": {
"responses": { "responses": {
"200": { "200": {
@ -477,7 +477,7 @@
} }
} }
}, },
"/alpha/agents/delete": { "/v1/agents/delete": {
"post": { "post": {
"responses": { "responses": {
"200": { "200": {
@ -519,7 +519,7 @@
} }
} }
}, },
"/alpha/agents/session/delete": { "/v1/agents/session/delete": {
"post": { "post": {
"responses": { "responses": {
"200": { "200": {
@ -561,7 +561,7 @@
} }
} }
}, },
"/alpha/inference/embeddings": { "/v1/inference/embeddings": {
"post": { "post": {
"responses": { "responses": {
"200": { "200": {
@ -610,7 +610,7 @@
} }
} }
}, },
"/alpha/eval/evaluate-rows": { "/v1/eval/evaluate-rows": {
"post": { "post": {
"responses": { "responses": {
"200": { "200": {
@ -659,7 +659,7 @@
} }
} }
}, },
"/alpha/agents/session/get": { "/v1/agents/session/get": {
"post": { "post": {
"responses": { "responses": {
"200": { "200": {
@ -724,7 +724,7 @@
} }
} }
}, },
"/alpha/agents/step/get": { "/v1/agents/step/get": {
"get": { "get": {
"responses": { "responses": {
"200": { "200": {
@ -795,7 +795,7 @@
] ]
} }
}, },
"/alpha/agents/turn/get": { "/v1/agents/turn/get": {
"get": { "get": {
"responses": { "responses": {
"200": { "200": {
@ -858,7 +858,7 @@
] ]
} }
}, },
"/alpha/datasets/get": { "/v1/datasets/get": {
"get": { "get": {
"responses": { "responses": {
"200": { "200": {
@ -912,7 +912,7 @@
] ]
} }
}, },
"/alpha/eval-tasks/get": { "/v1/eval-tasks/get": {
"get": { "get": {
"responses": { "responses": {
"200": { "200": {
@ -966,7 +966,7 @@
] ]
} }
}, },
"/alpha/memory-banks/get": { "/v1/memory-banks/get": {
"get": { "get": {
"responses": { "responses": {
"200": { "200": {
@ -976,20 +976,7 @@
"schema": { "schema": {
"oneOf": [ "oneOf": [
{ {
"oneOf": [ "$ref": "#/components/schemas/MemoryBank"
{
"$ref": "#/components/schemas/VectorMemoryBank"
},
{
"$ref": "#/components/schemas/KeyValueMemoryBank"
},
{
"$ref": "#/components/schemas/KeywordMemoryBank"
},
{
"$ref": "#/components/schemas/GraphMemoryBank"
}
]
}, },
{ {
"type": "null" "type": "null"
@ -1033,7 +1020,7 @@
] ]
} }
}, },
"/alpha/models/get": { "/v1/models/get": {
"get": { "get": {
"responses": { "responses": {
"200": { "200": {
@ -1087,7 +1074,7 @@
] ]
} }
}, },
"/alpha/datasetio/get-rows-paginated": { "/v1/datasetio/get-rows-paginated": {
"get": { "get": {
"responses": { "responses": {
"200": { "200": {
@ -1158,7 +1145,7 @@
] ]
} }
}, },
"/alpha/scoring-functions/get": { "/v1/scoring-functions/get": {
"get": { "get": {
"responses": { "responses": {
"200": { "200": {
@ -1212,7 +1199,7 @@
] ]
} }
}, },
"/alpha/shields/get": { "/v1/shields/get": {
"get": { "get": {
"responses": { "responses": {
"200": { "200": {
@ -1266,7 +1253,7 @@
] ]
} }
}, },
"/alpha/telemetry/get-span-tree": { "/v1/telemetry/get-span-tree": {
"post": { "post": {
"responses": { "responses": {
"200": { "200": {
@ -1334,7 +1321,7 @@
} }
} }
}, },
"/alpha/tools/get": { "/v1/tools/get": {
"get": { "get": {
"responses": { "responses": {
"200": { "200": {
@ -1381,7 +1368,7 @@
] ]
} }
}, },
"/alpha/toolgroups/get": { "/v1/toolgroups/get": {
"get": { "get": {
"responses": { "responses": {
"200": { "200": {
@ -1428,7 +1415,7 @@
] ]
} }
}, },
"/alpha/post-training/job/artifacts": { "/v1/post-training/job/artifacts": {
"get": { "get": {
"responses": { "responses": {
"200": { "200": {
@ -1482,7 +1469,7 @@
] ]
} }
}, },
"/alpha/post-training/job/status": { "/v1/post-training/job/status": {
"get": { "get": {
"responses": { "responses": {
"200": { "200": {
@ -1536,7 +1523,7 @@
] ]
} }
}, },
"/alpha/post-training/jobs": { "/v1/post-training/jobs": {
"get": { "get": {
"responses": { "responses": {
"200": { "200": {
@ -1575,7 +1562,7 @@
] ]
} }
}, },
"/alpha/health": { "/v1/health": {
"get": { "get": {
"responses": { "responses": {
"200": { "200": {
@ -1614,7 +1601,7 @@
] ]
} }
}, },
"/alpha/memory/insert": { "/v1/memory/insert": {
"post": { "post": {
"responses": { "responses": {
"200": { "200": {
@ -1656,7 +1643,7 @@
} }
} }
}, },
"/alpha/tool-runtime/invoke": { "/v1/tool-runtime/invoke": {
"post": { "post": {
"responses": { "responses": {
"200": { "200": {
@ -1706,7 +1693,7 @@
} }
} }
}, },
"/alpha/eval/job/cancel": { "/v1/eval/job/cancel": {
"post": { "post": {
"responses": { "responses": {
"200": { "200": {
@ -1748,7 +1735,7 @@
} }
} }
}, },
"/alpha/eval/job/result": { "/v1/eval/job/result": {
"get": { "get": {
"responses": { "responses": {
"200": { "200": {
@ -1803,7 +1790,7 @@
] ]
} }
}, },
"/alpha/eval/job/status": { "/v1/eval/job/status": {
"get": { "get": {
"responses": { "responses": {
"200": { "200": {
@ -1865,7 +1852,7 @@
] ]
} }
}, },
"/alpha/datasets/list": { "/v1/datasets/list": {
"get": { "get": {
"responses": { "responses": {
"200": { "200": {
@ -1904,7 +1891,7 @@
] ]
} }
}, },
"/alpha/eval-tasks/list": { "/v1/eval-tasks/list": {
"get": { "get": {
"responses": { "responses": {
"200": { "200": {
@ -1943,7 +1930,7 @@
] ]
} }
}, },
"/alpha/memory-banks/list": { "/v1/memory-banks/list": {
"get": { "get": {
"responses": { "responses": {
"200": { "200": {
@ -1951,20 +1938,7 @@
"content": { "content": {
"application/jsonl": { "application/jsonl": {
"schema": { "schema": {
"oneOf": [ "$ref": "#/components/schemas/MemoryBank"
{
"$ref": "#/components/schemas/VectorMemoryBank"
},
{
"$ref": "#/components/schemas/KeyValueMemoryBank"
},
{
"$ref": "#/components/schemas/KeywordMemoryBank"
},
{
"$ref": "#/components/schemas/GraphMemoryBank"
}
]
} }
} }
} }
@ -1995,7 +1969,7 @@
] ]
} }
}, },
"/alpha/models/list": { "/v1/models/list": {
"get": { "get": {
"responses": { "responses": {
"200": { "200": {
@ -2034,7 +2008,7 @@
] ]
} }
}, },
"/alpha/providers/list": { "/v1/providers/list": {
"get": { "get": {
"responses": { "responses": {
"200": { "200": {
@ -2076,7 +2050,7 @@
] ]
} }
}, },
"/alpha/routes/list": { "/v1/routes/list": {
"get": { "get": {
"responses": { "responses": {
"200": { "200": {
@ -2121,7 +2095,7 @@
] ]
} }
}, },
"/alpha/tool-runtime/list-tools": { "/v1/tool-runtime/list-tools": {
"post": { "post": {
"responses": { "responses": {
"200": { "200": {
@ -2178,7 +2152,7 @@
} }
} }
}, },
"/alpha/scoring-functions/list": { "/v1/scoring-functions/list": {
"get": { "get": {
"responses": { "responses": {
"200": { "200": {
@ -2217,7 +2191,7 @@
] ]
} }
}, },
"/alpha/shields/list": { "/v1/shields/list": {
"get": { "get": {
"responses": { "responses": {
"200": { "200": {
@ -2256,7 +2230,7 @@
] ]
} }
}, },
"/alpha/toolgroups/list": { "/v1/toolgroups/list": {
"get": { "get": {
"responses": { "responses": {
"200": { "200": {
@ -2296,7 +2270,7 @@
] ]
} }
}, },
"/alpha/tools/list": { "/v1/tools/list": {
"get": { "get": {
"responses": { "responses": {
"200": { "200": {
@ -2344,7 +2318,7 @@
] ]
} }
}, },
"/alpha/telemetry/log-event": { "/v1/telemetry/log-event": {
"post": { "post": {
"responses": { "responses": {
"200": { "200": {
@ -2386,7 +2360,7 @@
} }
} }
}, },
"/alpha/post-training/preference-optimize": { "/v1/post-training/preference-optimize": {
"post": { "post": {
"responses": { "responses": {
"200": { "200": {
@ -2435,7 +2409,7 @@
} }
} }
}, },
"/alpha/memory/query": { "/v1/memory/query": {
"post": { "post": {
"responses": { "responses": {
"200": { "200": {
@ -2484,7 +2458,7 @@
} }
} }
}, },
"/alpha/telemetry/query-spans": { "/v1/telemetry/query-spans": {
"post": { "post": {
"responses": { "responses": {
"200": { "200": {
@ -2533,7 +2507,7 @@
} }
} }
}, },
"/alpha/telemetry/query-traces": { "/v1/telemetry/query-traces": {
"post": { "post": {
"responses": { "responses": {
"200": { "200": {
@ -2582,7 +2556,7 @@
} }
} }
}, },
"/alpha/datasets/register": { "/v1/datasets/register": {
"post": { "post": {
"responses": { "responses": {
"200": { "200": {
@ -2624,7 +2598,7 @@
} }
} }
}, },
"/alpha/eval-tasks/register": { "/v1/eval-tasks/register": {
"post": { "post": {
"responses": { "responses": {
"200": { "200": {
@ -2666,9 +2640,33 @@
} }
} }
}, },
"/alpha/memory-banks/register": { "/v1/memory-banks/register": {
"post": { "post": {
"responses": {}, "responses": {
"200": {
"description": "",
"content": {
"application/json": {
"schema": {
"oneOf": [
{
"$ref": "#/components/schemas/VectorMemoryBank"
},
{
"$ref": "#/components/schemas/KeyValueMemoryBank"
},
{
"$ref": "#/components/schemas/KeywordMemoryBank"
},
{
"$ref": "#/components/schemas/GraphMemoryBank"
}
]
}
}
}
}
},
"tags": [ "tags": [
"MemoryBanks" "MemoryBanks"
], ],
@ -2704,7 +2702,7 @@
} }
} }
}, },
"/alpha/models/register": { "/v1/models/register": {
"post": { "post": {
"responses": { "responses": {
"200": { "200": {
@ -2753,7 +2751,7 @@
} }
} }
}, },
"/alpha/scoring-functions/register": { "/v1/scoring-functions/register": {
"post": { "post": {
"responses": { "responses": {
"200": { "200": {
@ -2795,7 +2793,7 @@
} }
} }
}, },
"/alpha/shields/register": { "/v1/shields/register": {
"post": { "post": {
"responses": { "responses": {
"200": { "200": {
@ -2844,7 +2842,7 @@
} }
} }
}, },
"/alpha/toolgroups/register": { "/v1/toolgroups/register": {
"post": { "post": {
"responses": { "responses": {
"200": { "200": {
@ -2887,7 +2885,7 @@
} }
} }
}, },
"/alpha/eval/run-eval": { "/v1/eval/run-eval": {
"post": { "post": {
"responses": { "responses": {
"200": { "200": {
@ -2936,7 +2934,7 @@
} }
} }
}, },
"/alpha/safety/run-shield": { "/v1/safety/run-shield": {
"post": { "post": {
"responses": { "responses": {
"200": { "200": {
@ -2985,7 +2983,7 @@
} }
} }
}, },
"/alpha/telemetry/save-spans-to-dataset": { "/v1/telemetry/save-spans-to-dataset": {
"post": { "post": {
"responses": { "responses": {
"200": { "200": {
@ -3027,7 +3025,7 @@
} }
} }
}, },
"/alpha/scoring/score": { "/v1/scoring/score": {
"post": { "post": {
"responses": { "responses": {
"200": { "200": {
@ -3076,7 +3074,7 @@
} }
} }
}, },
"/alpha/scoring/score-batch": { "/v1/scoring/score-batch": {
"post": { "post": {
"responses": { "responses": {
"200": { "200": {
@ -3125,7 +3123,7 @@
} }
} }
}, },
"/alpha/post-training/supervised-fine-tune": { "/v1/post-training/supervised-fine-tune": {
"post": { "post": {
"responses": { "responses": {
"200": { "200": {
@ -3174,7 +3172,7 @@
} }
} }
}, },
"/alpha/synthetic-data-generation/generate": { "/v1/synthetic-data-generation/generate": {
"post": { "post": {
"responses": { "responses": {
"200": { "200": {
@ -3223,7 +3221,7 @@
} }
} }
}, },
"/alpha/datasets/unregister": { "/v1/datasets/unregister": {
"post": { "post": {
"responses": { "responses": {
"200": { "200": {
@ -3265,7 +3263,7 @@
} }
} }
}, },
"/alpha/memory-banks/unregister": { "/v1/memory-banks/unregister": {
"post": { "post": {
"responses": { "responses": {
"200": { "200": {
@ -3307,7 +3305,7 @@
} }
} }
}, },
"/alpha/models/unregister": { "/v1/models/unregister": {
"post": { "post": {
"responses": { "responses": {
"200": { "200": {
@ -3349,7 +3347,7 @@
} }
} }
}, },
"/alpha/toolgroups/unregister": { "/v1/toolgroups/unregister": {
"post": { "post": {
"responses": { "responses": {
"200": { "200": {
@ -3392,7 +3390,7 @@
} }
} }
}, },
"/alpha/version": { "/v1/version": {
"get": { "get": {
"responses": { "responses": {
"200": { "200": {
@ -3514,20 +3512,6 @@
"tool_calls" "tool_calls"
] ]
}, },
"GreedySamplingStrategy": {
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "greedy",
"default": "greedy"
}
},
"additionalProperties": false,
"required": [
"type"
]
},
"ImageContentItem": { "ImageContentItem": {
"type": "object", "type": "object",
"properties": { "properties": {
@ -3595,17 +3579,20 @@
"type": "object", "type": "object",
"properties": { "properties": {
"strategy": { "strategy": {
"oneOf": [ "$ref": "#/components/schemas/SamplingStrategy",
{ "default": "greedy"
"$ref": "#/components/schemas/GreedySamplingStrategy"
}, },
{ "temperature": {
"$ref": "#/components/schemas/TopPSamplingStrategy" "type": "number",
"default": 0.0
}, },
{ "top_p": {
"$ref": "#/components/schemas/TopKSamplingStrategy" "type": "number",
} "default": 0.95
] },
"top_k": {
"type": "integer",
"default": 0
}, },
"max_tokens": { "max_tokens": {
"type": "integer", "type": "integer",
@ -3621,6 +3608,14 @@
"strategy" "strategy"
] ]
}, },
"SamplingStrategy": {
"type": "string",
"enum": [
"greedy",
"top_p",
"top_k"
]
},
"StopReason": { "StopReason": {
"type": "string", "type": "string",
"enum": [ "enum": [
@ -3874,45 +3869,6 @@
"content" "content"
] ]
}, },
"TopKSamplingStrategy": {
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "top_k",
"default": "top_k"
},
"top_k": {
"type": "integer"
}
},
"additionalProperties": false,
"required": [
"type",
"top_k"
]
},
"TopPSamplingStrategy": {
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "top_p",
"default": "top_p"
},
"temperature": {
"type": "number"
},
"top_p": {
"type": "number",
"default": 0.95
}
},
"additionalProperties": false,
"required": [
"type"
]
},
"URL": { "URL": {
"type": "object", "type": "object",
"properties": { "properties": {
@ -4270,24 +4226,17 @@
"ContentDelta": { "ContentDelta": {
"oneOf": [ "oneOf": [
{ {
"type": "object", "$ref": "#/components/schemas/TextDelta"
"properties": {
"type": {
"type": "string",
"const": "text",
"default": "text"
},
"text": {
"type": "string"
}
},
"additionalProperties": false,
"required": [
"type",
"text"
]
}, },
{ {
"$ref": "#/components/schemas/ImageDelta"
},
{
"$ref": "#/components/schemas/ToolCallDelta"
}
]
},
"ImageDelta": {
"type": "object", "type": "object",
"properties": { "properties": {
"type": { "type": {
@ -4306,9 +4255,22 @@
"data" "data"
] ]
}, },
{ "TextDelta": {
"$ref": "#/components/schemas/ToolCallDelta" "type": "object",
"properties": {
"type": {
"type": "string",
"const": "text",
"default": "text"
},
"text": {
"type": "string"
} }
},
"additionalProperties": false,
"required": [
"type",
"text"
] ]
}, },
"TokenLogProbs": { "TokenLogProbs": {
@ -5847,6 +5809,22 @@
"memory_bank_type" "memory_bank_type"
] ]
}, },
"MemoryBank": {
"oneOf": [
{
"$ref": "#/components/schemas/VectorMemoryBank"
},
{
"$ref": "#/components/schemas/KeyValueMemoryBank"
},
{
"$ref": "#/components/schemas/KeywordMemoryBank"
},
{
"$ref": "#/components/schemas/GraphMemoryBank"
}
]
},
"Session": { "Session": {
"type": "object", "type": "object",
"properties": { "properties": {
@ -5867,20 +5845,7 @@
"format": "date-time" "format": "date-time"
}, },
"memory_bank": { "memory_bank": {
"oneOf": [ "$ref": "#/components/schemas/MemoryBank"
{
"$ref": "#/components/schemas/VectorMemoryBank"
},
{
"$ref": "#/components/schemas/KeyValueMemoryBank"
},
{
"$ref": "#/components/schemas/KeywordMemoryBank"
},
{
"$ref": "#/components/schemas/GraphMemoryBank"
}
]
} }
}, },
"additionalProperties": false, "additionalProperties": false,
@ -7303,6 +7268,9 @@
"shuffle": { "shuffle": {
"type": "boolean" "type": "boolean"
}, },
"data_format": {
"$ref": "#/components/schemas/DatasetFormat"
},
"validation_dataset_id": { "validation_dataset_id": {
"type": "string" "type": "string"
}, },
@ -7319,7 +7287,15 @@
"required": [ "required": [
"dataset_id", "dataset_id",
"batch_size", "batch_size",
"shuffle" "shuffle",
"data_format"
]
},
"DatasetFormat": {
"type": "string",
"enum": [
"instruct",
"dialog"
] ]
}, },
"EfficiencyConfig": { "EfficiencyConfig": {
@ -8869,6 +8845,10 @@
"name": "Dataset", "name": "Dataset",
"description": "<SchemaDefinition schemaRef=\"#/components/schemas/Dataset\" />" "description": "<SchemaDefinition schemaRef=\"#/components/schemas/Dataset\" />"
}, },
{
"name": "DatasetFormat",
"description": "<SchemaDefinition schemaRef=\"#/components/schemas/DatasetFormat\" />"
},
{ {
"name": "DatasetIO" "name": "DatasetIO"
}, },
@ -8929,10 +8909,6 @@
"name": "GraphMemoryBankParams", "name": "GraphMemoryBankParams",
"description": "<SchemaDefinition schemaRef=\"#/components/schemas/GraphMemoryBankParams\" />" "description": "<SchemaDefinition schemaRef=\"#/components/schemas/GraphMemoryBankParams\" />"
}, },
{
"name": "GreedySamplingStrategy",
"description": "<SchemaDefinition schemaRef=\"#/components/schemas/GreedySamplingStrategy\" />"
},
{ {
"name": "HealthInfo", "name": "HealthInfo",
"description": "<SchemaDefinition schemaRef=\"#/components/schemas/HealthInfo\" />" "description": "<SchemaDefinition schemaRef=\"#/components/schemas/HealthInfo\" />"
@ -8941,6 +8917,10 @@
"name": "ImageContentItem", "name": "ImageContentItem",
"description": "<SchemaDefinition schemaRef=\"#/components/schemas/ImageContentItem\" />" "description": "<SchemaDefinition schemaRef=\"#/components/schemas/ImageContentItem\" />"
}, },
{
"name": "ImageDelta",
"description": "<SchemaDefinition schemaRef=\"#/components/schemas/ImageDelta\" />"
},
{ {
"name": "Inference" "name": "Inference"
}, },
@ -9018,6 +8998,10 @@
{ {
"name": "Memory" "name": "Memory"
}, },
{
"name": "MemoryBank",
"description": "<SchemaDefinition schemaRef=\"#/components/schemas/MemoryBank\" />"
},
{ {
"name": "MemoryBankDocument", "name": "MemoryBankDocument",
"description": "<SchemaDefinition schemaRef=\"#/components/schemas/MemoryBankDocument\" />" "description": "<SchemaDefinition schemaRef=\"#/components/schemas/MemoryBankDocument\" />"
@ -9182,6 +9166,10 @@
"name": "SamplingParams", "name": "SamplingParams",
"description": "<SchemaDefinition schemaRef=\"#/components/schemas/SamplingParams\" />" "description": "<SchemaDefinition schemaRef=\"#/components/schemas/SamplingParams\" />"
}, },
{
"name": "SamplingStrategy",
"description": "<SchemaDefinition schemaRef=\"#/components/schemas/SamplingStrategy\" />"
},
{ {
"name": "SaveSpansToDatasetRequest", "name": "SaveSpansToDatasetRequest",
"description": "<SchemaDefinition schemaRef=\"#/components/schemas/SaveSpansToDatasetRequest\" />" "description": "<SchemaDefinition schemaRef=\"#/components/schemas/SaveSpansToDatasetRequest\" />"
@ -9285,6 +9273,10 @@
"name": "TextContentItem", "name": "TextContentItem",
"description": "<SchemaDefinition schemaRef=\"#/components/schemas/TextContentItem\" />" "description": "<SchemaDefinition schemaRef=\"#/components/schemas/TextContentItem\" />"
}, },
{
"name": "TextDelta",
"description": "<SchemaDefinition schemaRef=\"#/components/schemas/TextDelta\" />"
},
{ {
"name": "TokenLogProbs", "name": "TokenLogProbs",
"description": "<SchemaDefinition schemaRef=\"#/components/schemas/TokenLogProbs\" />" "description": "<SchemaDefinition schemaRef=\"#/components/schemas/TokenLogProbs\" />"
@ -9359,14 +9351,6 @@
{ {
"name": "ToolRuntime" "name": "ToolRuntime"
}, },
{
"name": "TopKSamplingStrategy",
"description": "<SchemaDefinition schemaRef=\"#/components/schemas/TopKSamplingStrategy\" />"
},
{
"name": "TopPSamplingStrategy",
"description": "<SchemaDefinition schemaRef=\"#/components/schemas/TopPSamplingStrategy\" />"
},
{ {
"name": "Trace", "name": "Trace",
"description": "<SchemaDefinition schemaRef=\"#/components/schemas/Trace\" />" "description": "<SchemaDefinition schemaRef=\"#/components/schemas/Trace\" />"
@ -9494,6 +9478,7 @@
"DPOAlignmentConfig", "DPOAlignmentConfig",
"DataConfig", "DataConfig",
"Dataset", "Dataset",
"DatasetFormat",
"DeleteAgentsRequest", "DeleteAgentsRequest",
"DeleteAgentsSessionRequest", "DeleteAgentsSessionRequest",
"EfficiencyConfig", "EfficiencyConfig",
@ -9506,9 +9491,9 @@
"GetSpanTreeRequest", "GetSpanTreeRequest",
"GraphMemoryBank", "GraphMemoryBank",
"GraphMemoryBankParams", "GraphMemoryBankParams",
"GreedySamplingStrategy",
"HealthInfo", "HealthInfo",
"ImageContentItem", "ImageContentItem",
"ImageDelta",
"InferenceStep", "InferenceStep",
"InsertDocumentsRequest", "InsertDocumentsRequest",
"InterleavedContent", "InterleavedContent",
@ -9526,6 +9511,7 @@
"LogEventRequest", "LogEventRequest",
"LogSeverity", "LogSeverity",
"LoraFinetuningConfig", "LoraFinetuningConfig",
"MemoryBank",
"MemoryBankDocument", "MemoryBankDocument",
"MemoryRetrievalStep", "MemoryRetrievalStep",
"Message", "Message",
@ -9564,6 +9550,7 @@
"RunShieldResponse", "RunShieldResponse",
"SafetyViolation", "SafetyViolation",
"SamplingParams", "SamplingParams",
"SamplingStrategy",
"SaveSpansToDatasetRequest", "SaveSpansToDatasetRequest",
"ScoreBatchRequest", "ScoreBatchRequest",
"ScoreBatchResponse", "ScoreBatchResponse",
@ -9586,6 +9573,7 @@
"SyntheticDataGenerationResponse", "SyntheticDataGenerationResponse",
"SystemMessage", "SystemMessage",
"TextContentItem", "TextContentItem",
"TextDelta",
"TokenLogProbs", "TokenLogProbs",
"Tool", "Tool",
"ToolCall", "ToolCall",
@ -9603,8 +9591,6 @@
"ToolPromptFormat", "ToolPromptFormat",
"ToolResponse", "ToolResponse",
"ToolResponseMessage", "ToolResponseMessage",
"TopKSamplingStrategy",
"TopPSamplingStrategy",
"Trace", "Trace",
"TrainingConfig", "TrainingConfig",
"Turn", "Turn",

327
docs/resources/llama-stack-spec.yaml
View file

@ -570,31 +570,8 @@ components:
type: object type: object
ContentDelta: ContentDelta:
oneOf: oneOf:
- additionalProperties: false - $ref: '#/components/schemas/TextDelta'
properties: - $ref: '#/components/schemas/ImageDelta'
text:
type: string
type:
const: text
default: text
type: string
required:
- type
- text
type: object
- additionalProperties: false
properties:
data:
contentEncoding: base64
type: string
type:
const: image
default: image
type: string
required:
- type
- data
type: object
- $ref: '#/components/schemas/ToolCallDelta' - $ref: '#/components/schemas/ToolCallDelta'
CreateAgentRequest: CreateAgentRequest:
additionalProperties: false additionalProperties: false
@ -680,6 +657,8 @@ components:
properties: properties:
batch_size: batch_size:
type: integer type: integer
data_format:
$ref: '#/components/schemas/DatasetFormat'
dataset_id: dataset_id:
type: string type: string
packed: packed:
@ -696,6 +675,7 @@ components:
- dataset_id - dataset_id
- batch_size - batch_size
- shuffle - shuffle
- data_format
type: object type: object
Dataset: Dataset:
additionalProperties: false additionalProperties: false
@ -735,6 +715,11 @@ components:
- url - url
- metadata - metadata
type: object type: object
DatasetFormat:
enum:
- instruct
- dialog
type: string
DeleteAgentsRequest: DeleteAgentsRequest:
additionalProperties: false additionalProperties: false
properties: properties:
@ -937,16 +922,6 @@ components:
required: required:
- memory_bank_type - memory_bank_type
type: object type: object
GreedySamplingStrategy:
additionalProperties: false
properties:
type:
const: greedy
default: greedy
type: string
required:
- type
type: object
HealthInfo: HealthInfo:
additionalProperties: false additionalProperties: false
properties: properties:
@ -970,6 +945,20 @@ components:
required: required:
- type - type
type: object type: object
ImageDelta:
additionalProperties: false
properties:
data:
contentEncoding: base64
type: string
type:
const: image
default: image
type: string
required:
- type
- data
type: object
InferenceStep: InferenceStep:
additionalProperties: false additionalProperties: false
properties: properties:
@ -1219,6 +1208,12 @@ components:
- rank - rank
- alpha - alpha
type: object type: object
MemoryBank:
oneOf:
- $ref: '#/components/schemas/VectorMemoryBank'
- $ref: '#/components/schemas/KeyValueMemoryBank'
- $ref: '#/components/schemas/KeywordMemoryBank'
- $ref: '#/components/schemas/GraphMemoryBank'
MemoryBankDocument: MemoryBankDocument:
additionalProperties: false additionalProperties: false
properties: properties:
@ -2074,13 +2069,26 @@ components:
default: 1.0 default: 1.0
type: number type: number
strategy: strategy:
oneOf: $ref: '#/components/schemas/SamplingStrategy'
- $ref: '#/components/schemas/GreedySamplingStrategy' default: greedy
- $ref: '#/components/schemas/TopPSamplingStrategy' temperature:
- $ref: '#/components/schemas/TopKSamplingStrategy' default: 0.0
type: number
top_k:
default: 0
type: integer
top_p:
default: 0.95
type: number
required: required:
- strategy - strategy
type: object type: object
SamplingStrategy:
enum:
- greedy
- top_p
- top_k
type: string
SaveSpansToDatasetRequest: SaveSpansToDatasetRequest:
additionalProperties: false additionalProperties: false
properties: properties:
@ -2245,11 +2253,7 @@ components:
additionalProperties: false additionalProperties: false
properties: properties:
memory_bank: memory_bank:
oneOf: $ref: '#/components/schemas/MemoryBank'
- $ref: '#/components/schemas/VectorMemoryBank'
- $ref: '#/components/schemas/KeyValueMemoryBank'
- $ref: '#/components/schemas/KeywordMemoryBank'
- $ref: '#/components/schemas/GraphMemoryBank'
session_id: session_id:
type: string type: string
session_name: session_name:
@ -2585,6 +2589,19 @@ components:
- type - type
- text - text
type: object type: object
TextDelta:
additionalProperties: false
properties:
text:
type: string
type:
const: text
default: text
type: string
required:
- type
- text
type: object
TokenLogProbs: TokenLogProbs:
additionalProperties: false additionalProperties: false
properties: properties:
@ -2928,34 +2945,6 @@ components:
- tool_name - tool_name
- content - content
type: object type: object
TopKSamplingStrategy:
additionalProperties: false
properties:
top_k:
type: integer
type:
const: top_k
default: top_k
type: string
required:
- type
- top_k
type: object
TopPSamplingStrategy:
additionalProperties: false
properties:
temperature:
type: number
top_p:
default: 0.95
type: number
type:
const: top_p
default: top_p
type: string
required:
- type
type: object
Trace: Trace:
additionalProperties: false additionalProperties: false
properties: properties:
@ -3223,11 +3212,11 @@ info:
\ a set of endpoints and their corresponding interfaces that are tailored\ \ a set of endpoints and their corresponding interfaces that are tailored\
\ to\n best leverage Llama Models." \ to\n best leverage Llama Models."
title: Llama Stack Specification title: Llama Stack Specification
version: alpha version: v1
jsonSchemaDialect: https://json-schema.org/draft/2020-12/schema jsonSchemaDialect: https://json-schema.org/draft/2020-12/schema
openapi: 3.1.0 openapi: 3.1.0
paths: paths:
/alpha/agents/create: /v1/agents/create:
post: post:
parameters: parameters:
- description: JSON-encoded provider data which will be made available to the - description: JSON-encoded provider data which will be made available to the
@ -3259,7 +3248,7 @@ paths:
description: OK description: OK
tags: tags:
- Agents - Agents
/alpha/agents/delete: /v1/agents/delete:
post: post:
parameters: parameters:
- description: JSON-encoded provider data which will be made available to the - description: JSON-encoded provider data which will be made available to the
@ -3287,7 +3276,7 @@ paths:
description: OK description: OK
tags: tags:
- Agents - Agents
/alpha/agents/session/create: /v1/agents/session/create:
post: post:
parameters: parameters:
- description: JSON-encoded provider data which will be made available to the - description: JSON-encoded provider data which will be made available to the
@ -3319,7 +3308,7 @@ paths:
description: OK description: OK
tags: tags:
- Agents - Agents
/alpha/agents/session/delete: /v1/agents/session/delete:
post: post:
parameters: parameters:
- description: JSON-encoded provider data which will be made available to the - description: JSON-encoded provider data which will be made available to the
@ -3347,7 +3336,7 @@ paths:
description: OK description: OK
tags: tags:
- Agents - Agents
/alpha/agents/session/get: /v1/agents/session/get:
post: post:
parameters: parameters:
- in: query - in: query
@ -3389,7 +3378,7 @@ paths:
description: OK description: OK
tags: tags:
- Agents - Agents
/alpha/agents/step/get: /v1/agents/step/get:
get: get:
parameters: parameters:
- in: query - in: query
@ -3435,7 +3424,7 @@ paths:
description: OK description: OK
tags: tags:
- Agents - Agents
/alpha/agents/turn/create: /v1/agents/turn/create:
post: post:
parameters: parameters:
- description: JSON-encoded provider data which will be made available to the - description: JSON-encoded provider data which will be made available to the
@ -3470,7 +3459,7 @@ paths:
streamed agent turn completion response. streamed agent turn completion response.
tags: tags:
- Agents - Agents
/alpha/agents/turn/get: /v1/agents/turn/get:
get: get:
parameters: parameters:
- in: query - in: query
@ -3511,7 +3500,7 @@ paths:
description: OK description: OK
tags: tags:
- Agents - Agents
/alpha/batch-inference/chat-completion: /v1/batch-inference/chat-completion:
post: post:
parameters: parameters:
- description: JSON-encoded provider data which will be made available to the - description: JSON-encoded provider data which will be made available to the
@ -3543,7 +3532,7 @@ paths:
description: OK description: OK
tags: tags:
- BatchInference (Coming Soon) - BatchInference (Coming Soon)
/alpha/batch-inference/completion: /v1/batch-inference/completion:
post: post:
parameters: parameters:
- description: JSON-encoded provider data which will be made available to the - description: JSON-encoded provider data which will be made available to the
@ -3575,7 +3564,7 @@ paths:
description: OK description: OK
tags: tags:
- BatchInference (Coming Soon) - BatchInference (Coming Soon)
/alpha/datasetio/append-rows: /v1/datasetio/append-rows:
post: post:
parameters: parameters:
- description: JSON-encoded provider data which will be made available to the - description: JSON-encoded provider data which will be made available to the
@ -3603,7 +3592,7 @@ paths:
description: OK description: OK
tags: tags:
- DatasetIO - DatasetIO
/alpha/datasetio/get-rows-paginated: /v1/datasetio/get-rows-paginated:
get: get:
parameters: parameters:
- in: query - in: query
@ -3649,7 +3638,7 @@ paths:
description: OK description: OK
tags: tags:
- DatasetIO - DatasetIO
/alpha/datasets/get: /v1/datasets/get:
get: get:
parameters: parameters:
- in: query - in: query
@ -3682,7 +3671,7 @@ paths:
description: OK description: OK
tags: tags:
- Datasets - Datasets
/alpha/datasets/list: /v1/datasets/list:
get: get:
parameters: parameters:
- description: JSON-encoded provider data which will be made available to the - description: JSON-encoded provider data which will be made available to the
@ -3708,7 +3697,7 @@ paths:
description: OK description: OK
tags: tags:
- Datasets - Datasets
/alpha/datasets/register: /v1/datasets/register:
post: post:
parameters: parameters:
- description: JSON-encoded provider data which will be made available to the - description: JSON-encoded provider data which will be made available to the
@ -3736,7 +3725,7 @@ paths:
description: OK description: OK
tags: tags:
- Datasets - Datasets
/alpha/datasets/unregister: /v1/datasets/unregister:
post: post:
parameters: parameters:
- description: JSON-encoded provider data which will be made available to the - description: JSON-encoded provider data which will be made available to the
@ -3764,7 +3753,7 @@ paths:
description: OK description: OK
tags: tags:
- Datasets - Datasets
/alpha/eval-tasks/get: /v1/eval-tasks/get:
get: get:
parameters: parameters:
- in: query - in: query
@ -3797,7 +3786,7 @@ paths:
description: OK description: OK
tags: tags:
- EvalTasks - EvalTasks
/alpha/eval-tasks/list: /v1/eval-tasks/list:
get: get:
parameters: parameters:
- description: JSON-encoded provider data which will be made available to the - description: JSON-encoded provider data which will be made available to the
@ -3823,7 +3812,7 @@ paths:
description: OK description: OK
tags: tags:
- EvalTasks - EvalTasks
/alpha/eval-tasks/register: /v1/eval-tasks/register:
post: post:
parameters: parameters:
- description: JSON-encoded provider data which will be made available to the - description: JSON-encoded provider data which will be made available to the
@ -3851,7 +3840,7 @@ paths:
description: OK description: OK
tags: tags:
- EvalTasks - EvalTasks
/alpha/eval/evaluate-rows: /v1/eval/evaluate-rows:
post: post:
parameters: parameters:
- description: JSON-encoded provider data which will be made available to the - description: JSON-encoded provider data which will be made available to the
@ -3883,7 +3872,7 @@ paths:
description: OK description: OK
tags: tags:
- Eval - Eval
/alpha/eval/job/cancel: /v1/eval/job/cancel:
post: post:
parameters: parameters:
- description: JSON-encoded provider data which will be made available to the - description: JSON-encoded provider data which will be made available to the
@ -3911,7 +3900,7 @@ paths:
description: OK description: OK
tags: tags:
- Eval - Eval
/alpha/eval/job/result: /v1/eval/job/result:
get: get:
parameters: parameters:
- in: query - in: query
@ -3947,7 +3936,7 @@ paths:
description: OK description: OK
tags: tags:
- Eval - Eval
/alpha/eval/job/status: /v1/eval/job/status:
get: get:
parameters: parameters:
- in: query - in: query
@ -3985,7 +3974,7 @@ paths:
description: OK description: OK
tags: tags:
- Eval - Eval
/alpha/eval/run-eval: /v1/eval/run-eval:
post: post:
parameters: parameters:
- description: JSON-encoded provider data which will be made available to the - description: JSON-encoded provider data which will be made available to the
@ -4017,7 +4006,7 @@ paths:
description: OK description: OK
tags: tags:
- Eval - Eval
/alpha/health: /v1/health:
get: get:
parameters: parameters:
- description: JSON-encoded provider data which will be made available to the - description: JSON-encoded provider data which will be made available to the
@ -4043,7 +4032,7 @@ paths:
description: OK description: OK
tags: tags:
- Inspect - Inspect
/alpha/inference/chat-completion: /v1/inference/chat-completion:
post: post:
parameters: parameters:
- description: JSON-encoded provider data which will be made available to the - description: JSON-encoded provider data which will be made available to the
@ -4077,7 +4066,7 @@ paths:
description: Chat completion response. **OR** SSE-stream of these events. description: Chat completion response. **OR** SSE-stream of these events.
tags: tags:
- Inference - Inference
/alpha/inference/completion: /v1/inference/completion:
post: post:
parameters: parameters:
- description: JSON-encoded provider data which will be made available to the - description: JSON-encoded provider data which will be made available to the
@ -4111,7 +4100,7 @@ paths:
description: Completion response. **OR** streamed completion response. description: Completion response. **OR** streamed completion response.
tags: tags:
- Inference - Inference
/alpha/inference/embeddings: /v1/inference/embeddings:
post: post:
parameters: parameters:
- description: JSON-encoded provider data which will be made available to the - description: JSON-encoded provider data which will be made available to the
@ -4143,7 +4132,7 @@ paths:
description: OK description: OK
tags: tags:
- Inference - Inference
/alpha/memory-banks/get: /v1/memory-banks/get:
get: get:
parameters: parameters:
- in: query - in: query
@ -4171,16 +4160,12 @@ paths:
application/json: application/json:
schema: schema:
oneOf: oneOf:
- oneOf: - $ref: '#/components/schemas/MemoryBank'
- $ref: '#/components/schemas/VectorMemoryBank'
- $ref: '#/components/schemas/KeyValueMemoryBank'
- $ref: '#/components/schemas/KeywordMemoryBank'
- $ref: '#/components/schemas/GraphMemoryBank'
- type: 'null' - type: 'null'
description: OK description: OK
tags: tags:
- MemoryBanks - MemoryBanks
/alpha/memory-banks/list: /v1/memory-banks/list:
get: get:
parameters: parameters:
- description: JSON-encoded provider data which will be made available to the - description: JSON-encoded provider data which will be made available to the
@ -4202,15 +4187,11 @@ paths:
content: content:
application/jsonl: application/jsonl:
schema: schema:
oneOf: $ref: '#/components/schemas/MemoryBank'
- $ref: '#/components/schemas/VectorMemoryBank'
- $ref: '#/components/schemas/KeyValueMemoryBank'
- $ref: '#/components/schemas/KeywordMemoryBank'
- $ref: '#/components/schemas/GraphMemoryBank'
description: OK description: OK
tags: tags:
- MemoryBanks - MemoryBanks
/alpha/memory-banks/register: /v1/memory-banks/register:
post: post:
parameters: parameters:
- description: JSON-encoded provider data which will be made available to the - description: JSON-encoded provider data which will be made available to the
@ -4233,10 +4214,20 @@ paths:
schema: schema:
$ref: '#/components/schemas/RegisterMemoryBankRequest' $ref: '#/components/schemas/RegisterMemoryBankRequest'
required: true required: true
responses: {} responses:
'200':
content:
application/json:
schema:
oneOf:
- $ref: '#/components/schemas/VectorMemoryBank'
- $ref: '#/components/schemas/KeyValueMemoryBank'
- $ref: '#/components/schemas/KeywordMemoryBank'
- $ref: '#/components/schemas/GraphMemoryBank'
description: ''
tags: tags:
- MemoryBanks - MemoryBanks
/alpha/memory-banks/unregister: /v1/memory-banks/unregister:
post: post:
parameters: parameters:
- description: JSON-encoded provider data which will be made available to the - description: JSON-encoded provider data which will be made available to the
@ -4264,7 +4255,7 @@ paths:
description: OK description: OK
tags: tags:
- MemoryBanks - MemoryBanks
/alpha/memory/insert: /v1/memory/insert:
post: post:
parameters: parameters:
- description: JSON-encoded provider data which will be made available to the - description: JSON-encoded provider data which will be made available to the
@ -4292,7 +4283,7 @@ paths:
description: OK description: OK
tags: tags:
- Memory - Memory
/alpha/memory/query: /v1/memory/query:
post: post:
parameters: parameters:
- description: JSON-encoded provider data which will be made available to the - description: JSON-encoded provider data which will be made available to the
@ -4324,7 +4315,7 @@ paths:
description: OK description: OK
tags: tags:
- Memory - Memory
/alpha/models/get: /v1/models/get:
get: get:
parameters: parameters:
- in: query - in: query
@ -4357,7 +4348,7 @@ paths:
description: OK description: OK
tags: tags:
- Models - Models
/alpha/models/list: /v1/models/list:
get: get:
parameters: parameters:
- description: JSON-encoded provider data which will be made available to the - description: JSON-encoded provider data which will be made available to the
@ -4383,7 +4374,7 @@ paths:
description: OK description: OK
tags: tags:
- Models - Models
/alpha/models/register: /v1/models/register:
post: post:
parameters: parameters:
- description: JSON-encoded provider data which will be made available to the - description: JSON-encoded provider data which will be made available to the
@ -4415,7 +4406,7 @@ paths:
description: OK description: OK
tags: tags:
- Models - Models
/alpha/models/unregister: /v1/models/unregister:
post: post:
parameters: parameters:
- description: JSON-encoded provider data which will be made available to the - description: JSON-encoded provider data which will be made available to the
@ -4443,7 +4434,7 @@ paths:
description: OK description: OK
tags: tags:
- Models - Models
/alpha/post-training/job/artifacts: /v1/post-training/job/artifacts:
get: get:
parameters: parameters:
- in: query - in: query
@ -4476,7 +4467,7 @@ paths:
description: OK description: OK
tags: tags:
- PostTraining (Coming Soon) - PostTraining (Coming Soon)
/alpha/post-training/job/cancel: /v1/post-training/job/cancel:
post: post:
parameters: parameters:
- description: JSON-encoded provider data which will be made available to the - description: JSON-encoded provider data which will be made available to the
@ -4504,7 +4495,7 @@ paths:
description: OK description: OK
tags: tags:
- PostTraining (Coming Soon) - PostTraining (Coming Soon)
/alpha/post-training/job/status: /v1/post-training/job/status:
get: get:
parameters: parameters:
- in: query - in: query
@ -4537,7 +4528,7 @@ paths:
description: OK description: OK
tags: tags:
- PostTraining (Coming Soon) - PostTraining (Coming Soon)
/alpha/post-training/jobs: /v1/post-training/jobs:
get: get:
parameters: parameters:
- description: JSON-encoded provider data which will be made available to the - description: JSON-encoded provider data which will be made available to the
@ -4563,7 +4554,7 @@ paths:
description: OK description: OK
tags: tags:
- PostTraining (Coming Soon) - PostTraining (Coming Soon)
/alpha/post-training/preference-optimize: /v1/post-training/preference-optimize:
post: post:
parameters: parameters:
- description: JSON-encoded provider data which will be made available to the - description: JSON-encoded provider data which will be made available to the
@ -4595,7 +4586,7 @@ paths:
description: OK description: OK
tags: tags:
- PostTraining (Coming Soon) - PostTraining (Coming Soon)
/alpha/post-training/supervised-fine-tune: /v1/post-training/supervised-fine-tune:
post: post:
parameters: parameters:
- description: JSON-encoded provider data which will be made available to the - description: JSON-encoded provider data which will be made available to the
@ -4627,7 +4618,7 @@ paths:
description: OK description: OK
tags: tags:
- PostTraining (Coming Soon) - PostTraining (Coming Soon)
/alpha/providers/list: /v1/providers/list:
get: get:
parameters: parameters:
- description: JSON-encoded provider data which will be made available to the - description: JSON-encoded provider data which will be made available to the
@ -4655,7 +4646,7 @@ paths:
description: OK description: OK
tags: tags:
- Inspect - Inspect
/alpha/routes/list: /v1/routes/list:
get: get:
parameters: parameters:
- description: JSON-encoded provider data which will be made available to the - description: JSON-encoded provider data which will be made available to the
@ -4685,7 +4676,7 @@ paths:
description: OK description: OK
tags: tags:
- Inspect - Inspect
/alpha/safety/run-shield: /v1/safety/run-shield:
post: post:
parameters: parameters:
- description: JSON-encoded provider data which will be made available to the - description: JSON-encoded provider data which will be made available to the
@ -4717,7 +4708,7 @@ paths:
description: OK description: OK
tags: tags:
- Safety - Safety
/alpha/scoring-functions/get: /v1/scoring-functions/get:
get: get:
parameters: parameters:
- in: query - in: query
@ -4750,7 +4741,7 @@ paths:
description: OK description: OK
tags: tags:
- ScoringFunctions - ScoringFunctions
/alpha/scoring-functions/list: /v1/scoring-functions/list:
get: get:
parameters: parameters:
- description: JSON-encoded provider data which will be made available to the - description: JSON-encoded provider data which will be made available to the
@ -4776,7 +4767,7 @@ paths:
description: OK description: OK
tags: tags:
- ScoringFunctions - ScoringFunctions
/alpha/scoring-functions/register: /v1/scoring-functions/register:
post: post:
parameters: parameters:
- description: JSON-encoded provider data which will be made available to the - description: JSON-encoded provider data which will be made available to the
@ -4804,7 +4795,7 @@ paths:
description: OK description: OK
tags: tags:
- ScoringFunctions - ScoringFunctions
/alpha/scoring/score: /v1/scoring/score:
post: post:
parameters: parameters:
- description: JSON-encoded provider data which will be made available to the - description: JSON-encoded provider data which will be made available to the
@ -4836,7 +4827,7 @@ paths:
description: OK description: OK
tags: tags:
- Scoring - Scoring
/alpha/scoring/score-batch: /v1/scoring/score-batch:
post: post:
parameters: parameters:
- description: JSON-encoded provider data which will be made available to the - description: JSON-encoded provider data which will be made available to the
@ -4868,7 +4859,7 @@ paths:
description: OK description: OK
tags: tags:
- Scoring - Scoring
/alpha/shields/get: /v1/shields/get:
get: get:
parameters: parameters:
- in: query - in: query
@ -4901,7 +4892,7 @@ paths:
description: OK description: OK
tags: tags:
- Shields - Shields
/alpha/shields/list: /v1/shields/list:
get: get:
parameters: parameters:
- description: JSON-encoded provider data which will be made available to the - description: JSON-encoded provider data which will be made available to the
@ -4927,7 +4918,7 @@ paths:
description: OK description: OK
tags: tags:
- Shields - Shields
/alpha/shields/register: /v1/shields/register:
post: post:
parameters: parameters:
- description: JSON-encoded provider data which will be made available to the - description: JSON-encoded provider data which will be made available to the
@ -4959,7 +4950,7 @@ paths:
description: OK description: OK
tags: tags:
- Shields - Shields
/alpha/synthetic-data-generation/generate: /v1/synthetic-data-generation/generate:
post: post:
parameters: parameters:
- description: JSON-encoded provider data which will be made available to the - description: JSON-encoded provider data which will be made available to the
@ -4991,7 +4982,7 @@ paths:
description: OK description: OK
tags: tags:
- SyntheticDataGeneration (Coming Soon) - SyntheticDataGeneration (Coming Soon)
/alpha/telemetry/get-span-tree: /v1/telemetry/get-span-tree:
post: post:
parameters: parameters:
- in: query - in: query
@ -5035,7 +5026,7 @@ paths:
description: OK description: OK
tags: tags:
- Telemetry - Telemetry
/alpha/telemetry/log-event: /v1/telemetry/log-event:
post: post:
parameters: parameters:
- description: JSON-encoded provider data which will be made available to the - description: JSON-encoded provider data which will be made available to the
@ -5063,7 +5054,7 @@ paths:
description: OK description: OK
tags: tags:
- Telemetry - Telemetry
/alpha/telemetry/query-spans: /v1/telemetry/query-spans:
post: post:
parameters: parameters:
- description: JSON-encoded provider data which will be made available to the - description: JSON-encoded provider data which will be made available to the
@ -5095,7 +5086,7 @@ paths:
description: OK description: OK
tags: tags:
- Telemetry - Telemetry
/alpha/telemetry/query-traces: /v1/telemetry/query-traces:
post: post:
parameters: parameters:
- description: JSON-encoded provider data which will be made available to the - description: JSON-encoded provider data which will be made available to the
@ -5127,7 +5118,7 @@ paths:
description: OK description: OK
tags: tags:
- Telemetry - Telemetry
/alpha/telemetry/save-spans-to-dataset: /v1/telemetry/save-spans-to-dataset:
post: post:
parameters: parameters:
- description: JSON-encoded provider data which will be made available to the - description: JSON-encoded provider data which will be made available to the
@ -5155,7 +5146,7 @@ paths:
description: OK description: OK
tags: tags:
- Telemetry - Telemetry
/alpha/tool-runtime/invoke: /v1/tool-runtime/invoke:
post: post:
parameters: parameters:
- description: JSON-encoded provider data which will be made available to the - description: JSON-encoded provider data which will be made available to the
@ -5188,7 +5179,7 @@ paths:
summary: Run a tool with the given arguments summary: Run a tool with the given arguments
tags: tags:
- ToolRuntime - ToolRuntime
/alpha/tool-runtime/list-tools: /v1/tool-runtime/list-tools:
post: post:
parameters: parameters:
- in: query - in: query
@ -5225,7 +5216,7 @@ paths:
description: OK description: OK
tags: tags:
- ToolRuntime - ToolRuntime
/alpha/toolgroups/get: /v1/toolgroups/get:
get: get:
parameters: parameters:
- in: query - in: query
@ -5256,7 +5247,7 @@ paths:
description: OK description: OK
tags: tags:
- ToolGroups - ToolGroups
/alpha/toolgroups/list: /v1/toolgroups/list:
get: get:
parameters: parameters:
- description: JSON-encoded provider data which will be made available to the - description: JSON-encoded provider data which will be made available to the
@ -5283,7 +5274,7 @@ paths:
summary: List tool groups with optional provider summary: List tool groups with optional provider
tags: tags:
- ToolGroups - ToolGroups
/alpha/toolgroups/register: /v1/toolgroups/register:
post: post:
parameters: parameters:
- description: JSON-encoded provider data which will be made available to the - description: JSON-encoded provider data which will be made available to the
@ -5312,7 +5303,7 @@ paths:
summary: Register a tool group summary: Register a tool group
tags: tags:
- ToolGroups - ToolGroups
/alpha/toolgroups/unregister: /v1/toolgroups/unregister:
post: post:
parameters: parameters:
- description: JSON-encoded provider data which will be made available to the - description: JSON-encoded provider data which will be made available to the
@ -5341,7 +5332,7 @@ paths:
summary: Unregister a tool group summary: Unregister a tool group
tags: tags:
- ToolGroups - ToolGroups
/alpha/tools/get: /v1/tools/get:
get: get:
parameters: parameters:
- in: query - in: query
@ -5372,7 +5363,7 @@ paths:
description: OK description: OK
tags: tags:
- ToolGroups - ToolGroups
/alpha/tools/list: /v1/tools/list:
get: get:
parameters: parameters:
- in: query - in: query
@ -5404,7 +5395,7 @@ paths:
summary: List tools with optional tool group summary: List tools with optional tool group
tags: tags:
- ToolGroups - ToolGroups
/alpha/version: /v1/version:
get: get:
parameters: parameters:
- description: JSON-encoded provider data which will be made available to the - description: JSON-encoded provider data which will be made available to the
@ -5573,6 +5564,8 @@ tags:
name: DataConfig name: DataConfig
- description: <SchemaDefinition schemaRef="#/components/schemas/Dataset" /> - description: <SchemaDefinition schemaRef="#/components/schemas/Dataset" />
name: Dataset name: Dataset
- description: <SchemaDefinition schemaRef="#/components/schemas/DatasetFormat" />
name: DatasetFormat
- name: DatasetIO - name: DatasetIO
- name: Datasets - name: Datasets
- description: <SchemaDefinition schemaRef="#/components/schemas/DeleteAgentsRequest" - description: <SchemaDefinition schemaRef="#/components/schemas/DeleteAgentsRequest"
@ -5612,14 +5605,13 @@ tags:
- description: <SchemaDefinition schemaRef="#/components/schemas/GraphMemoryBankParams" - description: <SchemaDefinition schemaRef="#/components/schemas/GraphMemoryBankParams"
/> />
name: GraphMemoryBankParams name: GraphMemoryBankParams
- description: <SchemaDefinition schemaRef="#/components/schemas/GreedySamplingStrategy"
/>
name: GreedySamplingStrategy
- description: <SchemaDefinition schemaRef="#/components/schemas/HealthInfo" /> - description: <SchemaDefinition schemaRef="#/components/schemas/HealthInfo" />
name: HealthInfo name: HealthInfo
- description: <SchemaDefinition schemaRef="#/components/schemas/ImageContentItem" - description: <SchemaDefinition schemaRef="#/components/schemas/ImageContentItem"
/> />
name: ImageContentItem name: ImageContentItem
- description: <SchemaDefinition schemaRef="#/components/schemas/ImageDelta" />
name: ImageDelta
- name: Inference - name: Inference
- description: <SchemaDefinition schemaRef="#/components/schemas/InferenceStep" /> - description: <SchemaDefinition schemaRef="#/components/schemas/InferenceStep" />
name: InferenceStep name: InferenceStep
@ -5670,6 +5662,8 @@ tags:
/> />
name: LoraFinetuningConfig name: LoraFinetuningConfig
- name: Memory - name: Memory
- description: <SchemaDefinition schemaRef="#/components/schemas/MemoryBank" />
name: MemoryBank
- description: <SchemaDefinition schemaRef="#/components/schemas/MemoryBankDocument" - description: <SchemaDefinition schemaRef="#/components/schemas/MemoryBankDocument"
/> />
name: MemoryBankDocument name: MemoryBankDocument
@ -5781,6 +5775,9 @@ tags:
name: SafetyViolation name: SafetyViolation
- description: <SchemaDefinition schemaRef="#/components/schemas/SamplingParams" /> - description: <SchemaDefinition schemaRef="#/components/schemas/SamplingParams" />
name: SamplingParams name: SamplingParams
- description: <SchemaDefinition schemaRef="#/components/schemas/SamplingStrategy"
/>
name: SamplingStrategy
- description: <SchemaDefinition schemaRef="#/components/schemas/SaveSpansToDatasetRequest" - description: <SchemaDefinition schemaRef="#/components/schemas/SaveSpansToDatasetRequest"
/> />
name: SaveSpansToDatasetRequest name: SaveSpansToDatasetRequest
@ -5849,6 +5846,8 @@ tags:
- description: <SchemaDefinition schemaRef="#/components/schemas/TextContentItem" - description: <SchemaDefinition schemaRef="#/components/schemas/TextContentItem"
/> />
name: TextContentItem name: TextContentItem
- description: <SchemaDefinition schemaRef="#/components/schemas/TextDelta" />
name: TextDelta
- description: <SchemaDefinition schemaRef="#/components/schemas/TokenLogProbs" /> - description: <SchemaDefinition schemaRef="#/components/schemas/TokenLogProbs" />
name: TokenLogProbs name: TokenLogProbs
- description: <SchemaDefinition schemaRef="#/components/schemas/Tool" /> - description: <SchemaDefinition schemaRef="#/components/schemas/Tool" />
@ -5899,12 +5898,6 @@ tags:
/> />
name: ToolResponseMessage name: ToolResponseMessage
- name: ToolRuntime - name: ToolRuntime
- description: <SchemaDefinition schemaRef="#/components/schemas/TopKSamplingStrategy"
/>
name: TopKSamplingStrategy
- description: <SchemaDefinition schemaRef="#/components/schemas/TopPSamplingStrategy"
/>
name: TopPSamplingStrategy
- description: <SchemaDefinition schemaRef="#/components/schemas/Trace" /> - description: <SchemaDefinition schemaRef="#/components/schemas/Trace" />
name: Trace name: Trace
- description: <SchemaDefinition schemaRef="#/components/schemas/TrainingConfig" /> - description: <SchemaDefinition schemaRef="#/components/schemas/TrainingConfig" />
@ -6009,6 +6002,7 @@ x-tagGroups:
- DPOAlignmentConfig - DPOAlignmentConfig
- DataConfig - DataConfig
- Dataset - Dataset
- DatasetFormat
- DeleteAgentsRequest - DeleteAgentsRequest
- DeleteAgentsSessionRequest - DeleteAgentsSessionRequest
- EfficiencyConfig - EfficiencyConfig
@ -6021,9 +6015,9 @@ x-tagGroups:
- GetSpanTreeRequest - GetSpanTreeRequest
- GraphMemoryBank - GraphMemoryBank
- GraphMemoryBankParams - GraphMemoryBankParams
- GreedySamplingStrategy
- HealthInfo - HealthInfo
- ImageContentItem - ImageContentItem
- ImageDelta
- InferenceStep - InferenceStep
- InsertDocumentsRequest - InsertDocumentsRequest
- InterleavedContent - InterleavedContent
@ -6041,6 +6035,7 @@ x-tagGroups:
- LogEventRequest - LogEventRequest
- LogSeverity - LogSeverity
- LoraFinetuningConfig - LoraFinetuningConfig
- MemoryBank
- MemoryBankDocument - MemoryBankDocument
- MemoryRetrievalStep - MemoryRetrievalStep
- Message - Message
@ -6079,6 +6074,7 @@ x-tagGroups:
- RunShieldResponse - RunShieldResponse
- SafetyViolation - SafetyViolation
- SamplingParams - SamplingParams
- SamplingStrategy
- SaveSpansToDatasetRequest - SaveSpansToDatasetRequest
- ScoreBatchRequest - ScoreBatchRequest
- ScoreBatchResponse - ScoreBatchResponse
@ -6101,6 +6097,7 @@ x-tagGroups:
- SyntheticDataGenerationResponse - SyntheticDataGenerationResponse
- SystemMessage - SystemMessage
- TextContentItem - TextContentItem
- TextDelta
- TokenLogProbs - TokenLogProbs
- Tool - Tool
- ToolCall - ToolCall
@ -6118,8 +6115,6 @@ x-tagGroups:
- ToolPromptFormat - ToolPromptFormat
- ToolResponse - ToolResponse
- ToolResponseMessage - ToolResponseMessage
- TopKSamplingStrategy
- TopPSamplingStrategy
- Trace - Trace
- TrainingConfig - TrainingConfig
- Turn - Turn

2
llama_stack/apis/common/content_types.py
View file

@ -64,11 +64,13 @@ InterleavedContent = register_schema(
) )
@json_schema_type
class TextDelta(BaseModel): class TextDelta(BaseModel):
type: Literal["text"] = "text" type: Literal["text"] = "text"
text: str text: str
@json_schema_type
class ImageDelta(BaseModel): class ImageDelta(BaseModel):
type: Literal["image"] = "image" type: Literal["image"] = "image"
data: bytes data: bytes

9
llama_stack/apis/memory_banks/memory_banks.py
View file

@ -15,7 +15,7 @@ from typing import (
Union, Union,
) )
from llama_models.schema_utils import json_schema_type, webmethod from llama_models.schema_utils import json_schema_type, register_schema, webmethod
from pydantic import BaseModel, Field from pydantic import BaseModel, Field
@ -113,7 +113,8 @@ class GraphMemoryBank(MemoryBankResourceMixin):
memory_bank_type: Literal[MemoryBankType.graph.value] = MemoryBankType.graph.value memory_bank_type: Literal[MemoryBankType.graph.value] = MemoryBankType.graph.value
MemoryBank = Annotated[ MemoryBank = register_schema(
Annotated[
Union[ Union[
VectorMemoryBank, VectorMemoryBank,
KeyValueMemoryBank, KeyValueMemoryBank,
@ -121,7 +122,9 @@ MemoryBank = Annotated[
GraphMemoryBank, GraphMemoryBank,
], ],
Field(discriminator="memory_bank_type"), Field(discriminator="memory_bank_type"),
] ],
name="MemoryBank",
)
class MemoryBankInput(BaseModel): class MemoryBankInput(BaseModel):

2
llama_stack/apis/version.py
View file

@ -4,4 +4,4 @@
# This source code is licensed under the terms described in the LICENSE file in # This source code is licensed under the terms described in the LICENSE file in
# the root directory of this source tree. # the root directory of this source tree.
LLAMA_STACK_API_VERSION = "alpha" LLAMA_STACK_API_VERSION = "v1"

2
llama_stack/distribution/stack.py
View file

@ -40,8 +40,6 @@ from llama_stack.providers.datatypes import Api
log = logging.getLogger(__name__) log = logging.getLogger(__name__)
LLAMA_STACK_API_VERSION = "alpha"
class LlamaStack( class LlamaStack(
MemoryBanks, MemoryBanks,