phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-29 15:23:51 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

added more docs

Browse source
This commit is contained in:
Raghotham Murthy 2024-07-11 01:38:04 -07:00
parent 6778359493
commit b88f8ad616
3 changed files with 102 additions and 100 deletions
Download patch file Download diff file Expand all files Collapse all files

6
source/api_definitions.py
View file

@ -143,22 +143,26 @@ class BatchChatCompletionRequest:
class Inference(Protocol):
"""Set of methods that can be called on the inference service."""
@webmethod(route="/inference/completion")
def post_completion(
self,
request: CompletionRequest,
) -> Union[CompletionResponse, CompletionResponseStreamChunk]: ...
@webmethod(route="/inference/chat_completion")
def post_chat_completion(
self,
request: ChatCompletionRequest,
) -> Union[ChatCompletionResponse, ChatCompletionResponseStreamChunk]: ...
@webmethod(route="/inference/batch_completion")
def post_batch_completion(
self,
request: BatchCompletionRequest,
) -> List[CompletionResponse]: ...
@webmethod(route="/inference/batch_chat_completion")
def post_batch_chat_completion(
self,
request: BatchChatCompletionRequest,

29
source/openapi.html
View file

@ -386,7 +386,7 @@
]
}
},
"/batch_chat_completion": {
"/inference/batch_chat_completion": {
"post": {
"responses": {
"200": {
@ -416,7 +416,7 @@
}
}
},
"/batch_completion": {
"/inference/batch_completion": {
"post": {
"responses": {
"200": {
@ -446,7 +446,7 @@
}
}
},
"/chat_completion": {
"/inference/chat_completion": {
"post": {
"responses": {
"200": {
@ -483,7 +483,7 @@
}
}
},
"/completion": {
"/inference/completion": {
"post": {
"responses": {
"200": {
@ -3317,27 +3317,26 @@
}
],
"tags": [
{
"name": "RewardScoring"
},
{
"name": "PostTraining"
},
{
"name": "Inference",
"x-displayName": "Set of methods that can be called on the inference service."
},
{
"name": "MemoryBanks"
},
{
"name": "Datasets"
},
{
"name": "AgenticSystem"
},
{
"name": "Datasets"
},
{
"name": "SyntheticDataGeneration"
},
{
"name": "RewardScoring"
"name": "Inference"
},
{
"name": "MemoryBanks"
},
{
"name": "ShieldConfig",

167
source/openapi.yaml
View file

@ -1563,83 +1563,6 @@ paths:
agent execution response.
tags:
- AgenticSystem
/batch_chat_completion:
post:
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/BatchChatCompletionRequest'
required: true
responses:
'200':
content:
application/jsonl:
schema:
$ref: '#/components/schemas/ChatCompletionResponse'
description: OK
tags:
- Inference
/batch_completion:
post:
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/BatchCompletionRequest'
required: true
responses:
'200':
content:
application/jsonl:
schema:
$ref: '#/components/schemas/CompletionResponse'
description: OK
tags:
- Inference
/chat_completion:
post:
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/ChatCompletionRequest'
required: true
responses:
'200':
content:
application/json:
schema:
oneOf:
- $ref: '#/components/schemas/ChatCompletionResponse'
- $ref: '#/components/schemas/ChatCompletionResponseStreamChunk'
description: Normal chat completion response. **OR** Streamed chat completion
response. The actual response is a series of such objects.
tags:
- Inference
/completion:
post:
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/CompletionRequest'
required: true
responses:
'200':
content:
application/json:
schema:
oneOf:
- $ref: '#/components/schemas/CompletionResponse'
- $ref: '#/components/schemas/CompletionResponseStreamChunk'
description: Normal completion response. **OR** streamed completion response.
tags:
- Inference
/datasets/create:
post:
parameters: []
@ -1684,6 +1607,83 @@ paths:
description: OK
tags:
- Datasets
/inference/batch_chat_completion:
post:
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/BatchChatCompletionRequest'
required: true
responses:
'200':
content:
application/jsonl:
schema:
$ref: '#/components/schemas/ChatCompletionResponse'
description: OK
tags:
- Inference
/inference/batch_completion:
post:
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/BatchCompletionRequest'
required: true
responses:
'200':
content:
application/jsonl:
schema:
$ref: '#/components/schemas/CompletionResponse'
description: OK
tags:
- Inference
/inference/chat_completion:
post:
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/ChatCompletionRequest'
required: true
responses:
'200':
content:
application/json:
schema:
oneOf:
- $ref: '#/components/schemas/ChatCompletionResponse'
- $ref: '#/components/schemas/ChatCompletionResponseStreamChunk'
description: Normal chat completion response. **OR** Streamed chat completion
response. The actual response is a series of such objects.
tags:
- Inference
/inference/completion:
post:
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/CompletionRequest'
required: true
responses:
'200':
content:
application/json:
schema:
oneOf:
- $ref: '#/components/schemas/CompletionResponse'
- $ref: '#/components/schemas/CompletionResponseStreamChunk'
description: Normal completion response. **OR** streamed completion response.
tags:
- Inference
/memory_bank/delete:
post:
parameters:
@ -2015,14 +2015,13 @@ security:
servers:
- url: http://any-hosted-llama-stack.com
tags:
- name: PostTraining
- name: Inference
x-displayName: Set of methods that can be called on the inference service.
- name: MemoryBanks
- name: Datasets
- name: AgenticSystem
- name: SyntheticDataGeneration
- name: RewardScoring
- name: PostTraining
- name: AgenticSystem
- name: Datasets
- name: SyntheticDataGeneration
- name: Inference
- name: MemoryBanks
- description: <SchemaDefinition schemaRef="#/components/schemas/ShieldConfig" />
name: ShieldConfig
- description: <SchemaDefinition schemaRef="#/components/schemas/AgenticSystemCreateRequest"