Add pyopenapi fork to the repository, update RFC assets

This commit is contained in:
Ashwin Bharambe 2024-09-03 21:22:30 -07:00
parent 0d619b9f8e
commit b60c125c55
12 changed files with 2240 additions and 452 deletions

View file

@ -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 2024-08-23 06:36:10.417114"
"description": "This is the specification of the llama stack that provides\n a set of endpoints and their corresponding interfaces that are tailored to\n best leverage Llama Models. The specification is still in draft and subject to change.\n Generated at 2024-09-03 21:36:00.770405"
},
"servers": [
{
@ -29,7 +29,7 @@
}
],
"paths": {
"/inference/batch_chat_completion": {
"/batch_inference/chat_completion": {
"post": {
"responses": {
"200": {
@ -44,7 +44,7 @@
}
},
"tags": [
"Inference"
"BatchInference"
],
"parameters": [],
"requestBody": {
@ -59,7 +59,7 @@
}
}
},
"/inference/batch_completion": {
"/batch_inference/completion": {
"post": {
"responses": {
"200": {
@ -74,7 +74,7 @@
}
},
"tags": [
"Inference"
"BatchInference"
],
"parameters": [],
"requestBody": {
@ -550,6 +550,58 @@
]
}
},
"/inference/embeddings": {
"post": {
"responses": {
"200": {
"description": "OK",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/EmbeddingsResponse"
}
}
}
}
},
"tags": [
"Inference"
],
"parameters": [
{
"name": "model",
"in": "query",
"required": true,
"schema": {
"type": "string"
}
}
],
"requestBody": {
"content": {
"application/json": {
"schema": {
"type": "array",
"items": {
"oneOf": [
{
"type": "string"
},
{
"type": "array",
"items": {
"type": "string"
}
}
]
}
}
}
},
"required": true
}
}
},
"/evaluate/question_answering/": {
"post": {
"responses": {
@ -1053,7 +1105,14 @@
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/MemoryBank"
"oneOf": [
{
"$ref": "#/components/schemas/MemoryBank"
},
{
"type": "null"
}
]
}
}
}
@ -1228,6 +1287,14 @@
"schema": {
"type": "string"
}
},
{
"name": "ttl_seconds",
"in": "query",
"required": false,
"schema": {
"type": "integer"
}
}
],
"requestBody": {
@ -1973,8 +2040,8 @@
"json",
"function_tag"
],
"title": "This Enum refers to the prompt format for calling zero shot tools",
"description": "`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 <function=function_name>(parameters)</function>\n\nThe detailed prompts for each of these formats are defined in `system_prompt.py`"
"title": "This Enum refers to the prompt format for calling custom / zero shot tools",
"description": "`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 <function=function_name>(parameters)</function>\n\nThe detailed prompts for each of these formats are added to llama cli"
},
"ToolResponseMessage": {
"type": "object",
@ -2037,6 +2104,19 @@
}
}
]
},
"context": {
"oneOf": [
{
"type": "string"
},
{
"type": "array",
"items": {
"type": "string"
}
}
]
}
},
"additionalProperties": false,
@ -2393,95 +2473,6 @@
},
"instructions": {
"type": "string"
},
"memory_bank_configs": {
"type": "array",
"items": {
"oneOf": [
{
"type": "object",
"properties": {
"bank_id": {
"type": "string"
},
"type": {
"type": "string",
"const": "vector"
}
},
"additionalProperties": false,
"required": [
"bank_id",
"type"
]
},
{
"type": "object",
"properties": {
"bank_id": {
"type": "string"
},
"type": {
"type": "string",
"const": "keyvalue"
},
"keys": {
"type": "array",
"items": {
"type": "string"
}
}
},
"additionalProperties": false,
"required": [
"bank_id",
"type",
"keys"
]
},
{
"type": "object",
"properties": {
"bank_id": {
"type": "string"
},
"type": {
"type": "string",
"const": "keyword"
}
},
"additionalProperties": false,
"required": [
"bank_id",
"type"
]
},
{
"type": "object",
"properties": {
"bank_id": {
"type": "string"
},
"type": {
"type": "string",
"const": "graph"
},
"entities": {
"type": "array",
"items": {
"type": "string"
}
}
},
"additionalProperties": false,
"required": [
"bank_id",
"type",
"entities"
]
}
]
}
}
},
"additionalProperties": false,
@ -2579,6 +2570,9 @@
"type": "string",
"const": "function_call"
},
"function_name": {
"type": "string"
},
"description": {
"type": "string"
},
@ -2595,90 +2589,11 @@
"additionalProperties": false,
"required": [
"type",
"function_name",
"description",
"parameters"
]
},
"MemoryBank": {
"type": "object",
"properties": {
"bank_id": {
"type": "string"
},
"name": {
"type": "string"
},
"config": {
"oneOf": [
{
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "vector"
},
"embedding_model": {
"type": "string"
}
},
"additionalProperties": false,
"required": [
"type",
"embedding_model"
]
},
{
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "keyvalue"
}
},
"additionalProperties": false,
"required": [
"type"
]
},
{
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "keyword"
}
},
"additionalProperties": false,
"required": [
"type"
]
},
{
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "graph"
}
},
"additionalProperties": false,
"required": [
"type"
]
}
]
},
"url": {
"$ref": "#/components/schemas/URL"
}
},
"additionalProperties": false,
"required": [
"bank_id",
"name",
"config"
]
},
"MemoryToolDefinition": {
"type": "object",
"properties": {
@ -2698,17 +2613,108 @@
"type": "string",
"const": "memory"
},
"memory_banks": {
"memory_bank_configs": {
"type": "array",
"items": {
"$ref": "#/components/schemas/MemoryBank"
"oneOf": [
{
"type": "object",
"properties": {
"bank_id": {
"type": "string"
},
"type": {
"type": "string",
"const": "vector"
}
},
"additionalProperties": false,
"required": [
"bank_id",
"type"
]
},
{
"type": "object",
"properties": {
"bank_id": {
"type": "string"
},
"type": {
"type": "string",
"const": "keyvalue"
},
"keys": {
"type": "array",
"items": {
"type": "string"
}
}
},
"additionalProperties": false,
"required": [
"bank_id",
"type",
"keys"
]
},
{
"type": "object",
"properties": {
"bank_id": {
"type": "string"
},
"type": {
"type": "string",
"const": "keyword"
}
},
"additionalProperties": false,
"required": [
"bank_id",
"type"
]
},
{
"type": "object",
"properties": {
"bank_id": {
"type": "string"
},
"type": {
"type": "string",
"const": "graph"
},
"entities": {
"type": "array",
"items": {
"type": "string"
}
}
},
"additionalProperties": false,
"required": [
"bank_id",
"type",
"entities"
]
}
]
}
},
"max_tokens_in_context": {
"type": "integer"
},
"max_chunks": {
"type": "integer"
}
},
"additionalProperties": false,
"required": [
"type",
"memory_banks"
"memory_bank_configs",
"max_tokens_in_context",
"max_chunks"
]
},
"OnViolationAction": {
@ -2973,8 +2979,21 @@
"Attachment": {
"type": "object",
"properties": {
"url": {
"$ref": "#/components/schemas/URL"
"content": {
"oneOf": [
{
"type": "string"
},
{
"type": "array",
"items": {
"type": "string"
}
},
{
"$ref": "#/components/schemas/URL"
}
]
},
"mime_type": {
"type": "string"
@ -2982,7 +3001,7 @@
},
"additionalProperties": false,
"required": [
"url",
"content",
"mime_type"
]
},
@ -3177,12 +3196,19 @@
},
"embedding_model": {
"type": "string"
},
"chunk_size_in_tokens": {
"type": "integer"
},
"overlap_size_in_tokens": {
"type": "integer"
}
},
"additionalProperties": false,
"required": [
"type",
"embedding_model"
"embedding_model",
"chunk_size_in_tokens"
]
},
{
@ -3235,6 +3261,93 @@
"config"
]
},
"MemoryBank": {
"type": "object",
"properties": {
"bank_id": {
"type": "string"
},
"name": {
"type": "string"
},
"config": {
"oneOf": [
{
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "vector"
},
"embedding_model": {
"type": "string"
},
"chunk_size_in_tokens": {
"type": "integer"
},
"overlap_size_in_tokens": {
"type": "integer"
}
},
"additionalProperties": false,
"required": [
"type",
"embedding_model",
"chunk_size_in_tokens"
]
},
{
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "keyvalue"
}
},
"additionalProperties": false,
"required": [
"type"
]
},
{
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "keyword"
}
},
"additionalProperties": false,
"required": [
"type"
]
},
{
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "graph"
}
},
"additionalProperties": false,
"required": [
"type"
]
}
]
},
"url": {
"$ref": "#/components/schemas/URL"
}
},
"additionalProperties": false,
"required": [
"bank_id",
"name",
"config"
]
},
"CreateRunRequest": {
"type": "object",
"properties": {
@ -3327,6 +3440,24 @@
"metadata"
]
},
"EmbeddingsResponse": {
"type": "object",
"properties": {
"embeddings": {
"type": "array",
"items": {
"type": "array",
"items": {
"type": "number"
}
}
}
},
"additionalProperties": false,
"required": [
"embeddings"
]
},
"Checkpoint": {
"description": "Checkpoint created during training runs"
},
@ -3484,65 +3615,6 @@
"model_response"
]
},
"MemoryBankDocument": {
"type": "object",
"properties": {
"document_id": {
"type": "string"
},
"content": {
"oneOf": [
{
"type": "string"
},
{
"type": "array",
"items": {
"type": "string"
}
},
{
"$ref": "#/components/schemas/URL"
}
]
},
"mime_type": {
"type": "string"
},
"metadata": {
"type": "object",
"additionalProperties": {
"oneOf": [
{
"type": "null"
},
{
"type": "boolean"
},
{
"type": "number"
},
{
"type": "string"
},
{
"type": "array"
},
{
"type": "object"
}
]
}
}
},
"additionalProperties": false,
"required": [
"document_id",
"content",
"mime_type",
"metadata"
]
},
"MemoryRetrievalStep": {
"type": "object",
"properties": {
@ -3570,17 +3642,18 @@
"type": "string"
}
},
"documents": {
"type": "array",
"items": {
"$ref": "#/components/schemas/MemoryBankDocument"
}
},
"scores": {
"type": "array",
"items": {
"type": "number"
}
"inserted_context": {
"oneOf": [
{
"type": "string"
},
{
"type": "array",
"items": {
"type": "string"
}
}
]
}
},
"additionalProperties": false,
@ -3589,8 +3662,7 @@
"step_id",
"step_type",
"memory_bank_ids",
"documents",
"scores"
"inserted_context"
]
},
"Session": {
@ -3611,6 +3683,9 @@
"started_at": {
"type": "string",
"format": "date-time"
},
"memory_bank": {
"$ref": "#/components/schemas/MemoryBank"
}
},
"additionalProperties": false,
@ -3928,6 +4003,65 @@
"other"
]
},
"MemoryBankDocument": {
"type": "object",
"properties": {
"document_id": {
"type": "string"
},
"content": {
"oneOf": [
{
"type": "string"
},
{
"type": "array",
"items": {
"type": "string"
}
},
{
"$ref": "#/components/schemas/URL"
}
]
},
"mime_type": {
"type": "string"
},
"metadata": {
"type": "object",
"additionalProperties": {
"oneOf": [
{
"type": "null"
},
{
"type": "boolean"
},
{
"type": "number"
},
{
"type": "string"
},
{
"type": "array"
},
{
"type": "object"
}
]
}
}
},
"additionalProperties": false,
"required": [
"document_id",
"content",
"mime_type",
"metadata"
]
},
"EvaluationJobArtifactsResponse": {
"type": "object",
"properties": {
@ -4504,12 +4638,16 @@
},
"token_count": {
"type": "integer"
},
"document_id": {
"type": "string"
}
},
"additionalProperties": false,
"required": [
"content",
"token_count"
"token_count",
"document_id"
]
}
},
@ -5109,7 +5247,7 @@
],
"tags": [
{
"name": "Observability"
"name": "BatchInference"
},
{
"name": "AgenticSystem"
@ -5121,19 +5259,22 @@
"name": "Memory"
},
{
"name": "Evaluations"
"name": "Observability"
},
{
"name": "Datasets"
"name": "SyntheticDataGeneration"
},
{
"name": "Evaluations"
},
{
"name": "RewardScoring"
},
{
"name": "Inference"
"name": "Datasets"
},
{
"name": "SyntheticDataGeneration"
"name": "Inference"
},
{
"name": "BatchChatCompletionRequest",
@ -5181,7 +5322,7 @@
},
{
"name": "ToolPromptFormat",
"description": "This Enum refers to the prompt format for calling 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 <function=function_name>(parameters)</function>\n\nThe detailed prompts for each of these formats are defined in `system_prompt.py`\n\n<SchemaDefinition schemaRef=\"#/components/schemas/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 <function=function_name>(parameters)</function>\n\nThe detailed prompts for each of these formats are added to llama cli\n\n<SchemaDefinition schemaRef=\"#/components/schemas/ToolPromptFormat\" />"
},
{
"name": "ToolResponseMessage",
@ -5259,10 +5400,6 @@
"name": "FunctionCallToolDefinition",
"description": "<SchemaDefinition schemaRef=\"#/components/schemas/FunctionCallToolDefinition\" />"
},
{
"name": "MemoryBank",
"description": "<SchemaDefinition schemaRef=\"#/components/schemas/MemoryBank\" />"
},
{
"name": "MemoryToolDefinition",
"description": "<SchemaDefinition schemaRef=\"#/components/schemas/MemoryToolDefinition\" />"
@ -5343,6 +5480,10 @@
"name": "CreateMemoryBankRequest",
"description": "<SchemaDefinition schemaRef=\"#/components/schemas/CreateMemoryBankRequest\" />"
},
{
"name": "MemoryBank",
"description": "<SchemaDefinition schemaRef=\"#/components/schemas/MemoryBank\" />"
},
{
"name": "CreateRunRequest",
"description": "<SchemaDefinition schemaRef=\"#/components/schemas/CreateRunRequest\" />"
@ -5351,6 +5492,10 @@
"name": "Run",
"description": "<SchemaDefinition schemaRef=\"#/components/schemas/Run\" />"
},
{
"name": "EmbeddingsResponse",
"description": "<SchemaDefinition schemaRef=\"#/components/schemas/EmbeddingsResponse\" />"
},
{
"name": "Checkpoint",
"description": "Checkpoint created during training runs\n\n<SchemaDefinition schemaRef=\"#/components/schemas/Checkpoint\" />"
@ -5375,10 +5520,6 @@
"name": "InferenceStep",
"description": "<SchemaDefinition schemaRef=\"#/components/schemas/InferenceStep\" />"
},
{
"name": "MemoryBankDocument",
"description": "<SchemaDefinition schemaRef=\"#/components/schemas/MemoryBankDocument\" />"
},
{
"name": "MemoryRetrievalStep",
"description": "<SchemaDefinition schemaRef=\"#/components/schemas/MemoryRetrievalStep\" />"
@ -5419,6 +5560,10 @@
"name": "ArtifactType",
"description": "<SchemaDefinition schemaRef=\"#/components/schemas/ArtifactType\" />"
},
{
"name": "MemoryBankDocument",
"description": "<SchemaDefinition schemaRef=\"#/components/schemas/MemoryBankDocument\" />"
},
{
"name": "EvaluationJobArtifactsResponse",
"description": "Artifacts of a evaluation job.\n\n<SchemaDefinition schemaRef=\"#/components/schemas/EvaluationJobArtifactsResponse\" />"
@ -5565,6 +5710,7 @@
"name": "Operations",
"tags": [
"AgenticSystem",
"BatchInference",
"Datasets",
"Evaluations",
"Inference",
@ -5610,6 +5756,7 @@
"DPOAlignmentConfig",
"DialogGenerations",
"DoraFinetuningConfig",
"EmbeddingsResponse",
"EvaluateQuestionAnsweringRequest",
"EvaluateSummarizationRequest",
"EvaluateTextGenerationRequest",

View file

@ -10,64 +10,6 @@ components:
type: array
instructions:
type: string
memory_bank_configs:
items:
oneOf:
- additionalProperties: false
properties:
bank_id:
type: string
type:
const: vector
type: string
required:
- bank_id
- type
type: object
- additionalProperties: false
properties:
bank_id:
type: string
keys:
items:
type: string
type: array
type:
const: keyvalue
type: string
required:
- bank_id
- type
- keys
type: object
- additionalProperties: false
properties:
bank_id:
type: string
type:
const: keyword
type: string
required:
- bank_id
- type
type: object
- additionalProperties: false
properties:
bank_id:
type: string
entities:
items:
type: string
type: array
type:
const: graph
type: string
required:
- bank_id
- type
- entities
type: object
type: array
model:
type: string
output_shields:
@ -220,12 +162,17 @@ components:
Attachment:
additionalProperties: false
properties:
content:
oneOf:
- type: string
- items:
type: string
type: array
- $ref: '#/components/schemas/URL'
mime_type:
type: string
url:
$ref: '#/components/schemas/URL'
required:
- url
- content
- mime_type
type: object
BatchChatCompletionRequest:
@ -537,14 +484,19 @@ components:
oneOf:
- additionalProperties: false
properties:
chunk_size_in_tokens:
type: integer
embedding_model:
type: string
overlap_size_in_tokens:
type: integer
type:
const: vector
type: string
required:
- type
- embedding_model
- chunk_size_in_tokens
type: object
- additionalProperties: false
properties:
@ -655,6 +607,18 @@ components:
- rank
- alpha
type: object
EmbeddingsResponse:
additionalProperties: false
properties:
embeddings:
items:
items:
type: number
type: array
type: array
required:
- embeddings
type: object
EvaluateQuestionAnsweringRequest:
additionalProperties: false
properties:
@ -819,6 +783,8 @@ components:
properties:
description:
type: string
function_name:
type: string
input_shields:
items:
$ref: '#/components/schemas/ShieldDefinition'
@ -838,6 +804,7 @@ components:
type: string
required:
- type
- function_name
- description
- parameters
type: object
@ -965,14 +932,19 @@ components:
oneOf:
- additionalProperties: false
properties:
chunk_size_in_tokens:
type: integer
embedding_model:
type: string
overlap_size_in_tokens:
type: integer
type:
const: vector
type: string
required:
- type
- embedding_model
- chunk_size_in_tokens
type: object
- additionalProperties: false
properties:
@ -1043,18 +1015,16 @@ components:
completed_at:
format: date-time
type: string
documents:
items:
$ref: '#/components/schemas/MemoryBankDocument'
type: array
inserted_context:
oneOf:
- type: string
- items:
type: string
type: array
memory_bank_ids:
items:
type: string
type: array
scores:
items:
type: number
type: array
started_at:
format: date-time
type: string
@ -1070,8 +1040,7 @@ components:
- step_id
- step_type
- memory_bank_ids
- documents
- scores
- inserted_context
type: object
MemoryToolDefinition:
additionalProperties: false
@ -1080,9 +1049,67 @@ components:
items:
$ref: '#/components/schemas/ShieldDefinition'
type: array
memory_banks:
max_chunks:
type: integer
max_tokens_in_context:
type: integer
memory_bank_configs:
items:
$ref: '#/components/schemas/MemoryBank'
oneOf:
- additionalProperties: false
properties:
bank_id:
type: string
type:
const: vector
type: string
required:
- bank_id
- type
type: object
- additionalProperties: false
properties:
bank_id:
type: string
keys:
items:
type: string
type: array
type:
const: keyvalue
type: string
required:
- bank_id
- type
- keys
type: object
- additionalProperties: false
properties:
bank_id:
type: string
type:
const: keyword
type: string
required:
- bank_id
- type
type: object
- additionalProperties: false
properties:
bank_id:
type: string
entities:
items:
type: string
type: array
type:
const: graph
type: string
required:
- bank_id
- type
- entities
type: object
type: array
output_shields:
items:
@ -1093,7 +1120,9 @@ components:
type: string
required:
- type
- memory_banks
- memory_bank_configs
- max_tokens_in_context
- max_chunks
type: object
Metric:
additionalProperties: false
@ -1406,11 +1435,14 @@ components:
- items:
type: string
type: array
document_id:
type: string
token_count:
type: integer
required:
- content
- token_count
- document_id
type: object
type: array
scores:
@ -1575,6 +1607,8 @@ components:
Session:
additionalProperties: false
properties:
memory_bank:
$ref: '#/components/schemas/MemoryBank'
session_id:
type: string
session_name:
@ -1869,11 +1903,12 @@ components:
: {...}\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 <function=function_name>(parameters)</function>\n\
\nThe detailed prompts for each of these formats are defined in `system_prompt.py`"
\nThe detailed prompts for each of these formats are added to llama cli"
enum:
- json
- function_tag
title: This Enum refers to the prompt format for calling zero shot tools
title: This Enum refers to the prompt format for calling custom / zero shot
tools
type: string
ToolResponse:
additionalProperties: false
@ -2104,6 +2139,12 @@ components:
- items:
type: string
type: array
context:
oneOf:
- type: string
- items:
type: string
type: array
role:
const: user
type: string
@ -2134,7 +2175,7 @@ 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 2024-08-23 06:36:10.417114"
\ draft and subject to change.\n Generated at 2024-09-03 21:36:00.770405"
title: '[DRAFT] Llama Stack Specification'
version: 0.0.1
jsonSchemaDialect: https://json-schema.org/draft/2020-12/schema
@ -2327,6 +2368,42 @@ paths:
description: OK
tags:
- Observability
/batch_inference/chat_completion:
post:
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/BatchChatCompletionRequest'
required: true
responses:
'200':
content:
application/json:
schema:
$ref: '#/components/schemas/BatchChatCompletionResponse'
description: OK
tags:
- BatchInference
/batch_inference/completion:
post:
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/BatchCompletionRequest'
required: true
responses:
'200':
content:
application/json:
schema:
$ref: '#/components/schemas/BatchCompletionResponse'
description: OK
tags:
- BatchInference
/datasets/create:
post:
parameters: []
@ -2619,42 +2696,6 @@ paths:
description: OK
tags:
- Observability
/inference/batch_chat_completion:
post:
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/BatchChatCompletionRequest'
required: true
responses:
'200':
content:
application/json:
schema:
$ref: '#/components/schemas/BatchChatCompletionResponse'
description: OK
tags:
- Inference
/inference/batch_completion:
post:
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/BatchCompletionRequest'
required: true
responses:
'200':
content:
application/json:
schema:
$ref: '#/components/schemas/BatchCompletionResponse'
description: OK
tags:
- Inference
/inference/chat_completion:
post:
parameters: []
@ -2691,6 +2732,35 @@ paths:
description: streamed completion response.
tags:
- Inference
/inference/embeddings:
post:
parameters:
- in: query
name: model
required: true
schema:
type: string
requestBody:
content:
application/json:
schema:
items:
oneOf:
- type: string
- items:
type: string
type: array
type: array
required: true
responses:
'200':
content:
application/json:
schema:
$ref: '#/components/schemas/EmbeddingsResponse'
description: OK
tags:
- Inference
/logging/get_logs:
post:
parameters: []
@ -2777,6 +2847,11 @@ paths:
required: true
schema:
type: string
- in: query
name: ttl_seconds
required: false
schema:
type: integer
requestBody:
content:
application/json:
@ -2887,7 +2962,9 @@ paths:
content:
application/json:
schema:
$ref: '#/components/schemas/MemoryBank'
oneOf:
- $ref: '#/components/schemas/MemoryBank'
- type: 'null'
description: OK
tags:
- Memory
@ -3105,15 +3182,16 @@ security:
servers:
- url: http://any-hosted-llama-stack.com
tags:
- name: Observability
- name: BatchInference
- name: AgenticSystem
- name: PostTraining
- name: Memory
- name: Evaluations
- name: Datasets
- name: RewardScoring
- name: Inference
- name: Observability
- name: SyntheticDataGeneration
- name: Evaluations
- name: RewardScoring
- name: Datasets
- name: Inference
- description: <SchemaDefinition schemaRef="#/components/schemas/BatchChatCompletionRequest"
/>
name: BatchChatCompletionRequest
@ -3140,16 +3218,16 @@ tags:
- description: <SchemaDefinition schemaRef="#/components/schemas/ToolParamDefinition"
/>
name: ToolParamDefinition
- description: "This Enum refers to the prompt format for calling 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 <function=function_name>(parameters)</function>\n\nThe\
\ detailed prompts for each of these formats are defined in `system_prompt.py`\n\
\n<SchemaDefinition schemaRef=\"#/components/schemas/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 <function=function_name>(parameters)</function>\n\
\nThe detailed prompts for each of these formats are added to llama cli\n\n<SchemaDefinition\
\ schemaRef=\"#/components/schemas/ToolPromptFormat\" />"
name: ToolPromptFormat
- description: <SchemaDefinition schemaRef="#/components/schemas/ToolResponseMessage"
/>
@ -3212,8 +3290,6 @@ tags:
- description: <SchemaDefinition schemaRef="#/components/schemas/FunctionCallToolDefinition"
/>
name: FunctionCallToolDefinition
- description: <SchemaDefinition schemaRef="#/components/schemas/MemoryBank" />
name: MemoryBank
- description: <SchemaDefinition schemaRef="#/components/schemas/MemoryToolDefinition"
/>
name: MemoryToolDefinition
@ -3277,11 +3353,16 @@ tags:
- description: <SchemaDefinition schemaRef="#/components/schemas/CreateMemoryBankRequest"
/>
name: CreateMemoryBankRequest
- description: <SchemaDefinition schemaRef="#/components/schemas/MemoryBank" />
name: MemoryBank
- description: <SchemaDefinition schemaRef="#/components/schemas/CreateRunRequest"
/>
name: CreateRunRequest
- description: <SchemaDefinition schemaRef="#/components/schemas/Run" />
name: Run
- description: <SchemaDefinition schemaRef="#/components/schemas/EmbeddingsResponse"
/>
name: EmbeddingsResponse
- description: 'Checkpoint created during training runs
@ -3309,9 +3390,6 @@ tags:
name: EvaluateTextGenerationRequest
- description: <SchemaDefinition schemaRef="#/components/schemas/InferenceStep" />
name: InferenceStep
- description: <SchemaDefinition schemaRef="#/components/schemas/MemoryBankDocument"
/>
name: MemoryBankDocument
- description: <SchemaDefinition schemaRef="#/components/schemas/MemoryRetrievalStep"
/>
name: MemoryRetrievalStep
@ -3341,6 +3419,9 @@ tags:
name: Artifact
- description: <SchemaDefinition schemaRef="#/components/schemas/ArtifactType" />
name: ArtifactType
- description: <SchemaDefinition schemaRef="#/components/schemas/MemoryBankDocument"
/>
name: MemoryBankDocument
- description: 'Artifacts of a evaluation job.
@ -3474,6 +3555,7 @@ x-tagGroups:
- name: Operations
tags:
- AgenticSystem
- BatchInference
- Datasets
- Evaluations
- Inference
@ -3516,6 +3598,7 @@ x-tagGroups:
- DPOAlignmentConfig
- DialogGenerations
- DoraFinetuningConfig
- EmbeddingsResponse
- EvaluateQuestionAnsweringRequest
- EvaluateSummarizationRequest
- EvaluateTextGenerationRequest