forked from phoenix-oss/llama-stack-mirror
Enable sane naming of registered objects with defaults (#429)
# What does this PR do? This is a follow-up to #425. That PR allows for specifying models in the registry, but each entry needs to look like: ```yaml - identifier: ... provider_id: ... provider_resource_identifier: ... ``` This is headache-inducing. The current PR makes this situation better by adopting the shape of our APIs. Namely, we need the user to only specify `model-id`. The rest should be optional and figured out by the Stack. You can always override it. Here's what example `ollama` "full stack" registry looks like (we still need to kill or simplify shield_type crap): ```yaml models: - model_id: Llama3.2-3B-Instruct - model_id: Llama-Guard-3-1B shields: - shield_id: llama_guard shield_type: llama_guard ``` ## Test Plan See test plan for #425. Re-ran it.
This commit is contained in:
Ashwin Bharambe
GitHub
parent
d9d271a684
commit
09269e2a44
17 changed files with 295 additions and 207 deletions
|
|
@ -21,7 +21,7 @@
|
|||
"info": {
|
||||
"title": "[DRAFT] Llama Stack Specification",
|
||||
"version": "0.0.1",
|
||||
"description": "This is the specification of the llama stack that provides\n a set of endpoints and their corresponding interfaces that are tailored to\n best leverage Llama Models. The specification is still in draft and subject to change.\n Generated at 2024-11-11 18:44:30.967321"
|
||||
"description": "This is the specification of the llama stack that provides\n a set of endpoints and their corresponding interfaces that are tailored to\n best leverage Llama Models. The specification is still in draft and subject to change.\n Generated at 2024-11-12 11:16:58.657871"
|
||||
},
|
||||
"servers": [
|
||||
{
|
||||
|
|
@ -5778,8 +5778,7 @@
|
|||
"provider_resource_id",
|
||||
"provider_id",
|
||||
"type",
|
||||
"shield_type",
|
||||
"params"
|
||||
"shield_type"
|
||||
],
|
||||
"title": "A safety shield resource that can be used to check content"
|
||||
},
|
||||
|
|
@ -7027,7 +7026,7 @@
|
|||
"provider_id": {
|
||||
"type": "string"
|
||||
},
|
||||
"provider_memorybank_id": {
|
||||
"provider_memory_bank_id": {
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
|
|
@ -7854,59 +7853,59 @@
|
|||
}
|
||||
],
|
||||
"tags": [
|
||||
{
|
||||
"name": "Datasets"
|
||||
},
|
||||
{
|
||||
"name": "Telemetry"
|
||||
},
|
||||
{
|
||||
"name": "PostTraining"
|
||||
},
|
||||
{
|
||||
"name": "MemoryBanks"
|
||||
},
|
||||
{
|
||||
"name": "Eval"
|
||||
},
|
||||
{
|
||||
"name": "Memory"
|
||||
},
|
||||
{
|
||||
"name": "EvalTasks"
|
||||
},
|
||||
{
|
||||
"name": "Models"
|
||||
},
|
||||
{
|
||||
"name": "Scoring"
|
||||
},
|
||||
{
|
||||
"name": "Inference"
|
||||
},
|
||||
{
|
||||
"name": "Shields"
|
||||
},
|
||||
{
|
||||
"name": "DatasetIO"
|
||||
},
|
||||
{
|
||||
"name": "Safety"
|
||||
},
|
||||
{
|
||||
"name": "Agents"
|
||||
},
|
||||
{
|
||||
"name": "SyntheticDataGeneration"
|
||||
"name": "Telemetry"
|
||||
},
|
||||
{
|
||||
"name": "Eval"
|
||||
},
|
||||
{
|
||||
"name": "Models"
|
||||
},
|
||||
{
|
||||
"name": "Inspect"
|
||||
},
|
||||
{
|
||||
"name": "EvalTasks"
|
||||
},
|
||||
{
|
||||
"name": "ScoringFunctions"
|
||||
},
|
||||
{
|
||||
"name": "BatchInference"
|
||||
"name": "Memory"
|
||||
},
|
||||
{
|
||||
"name": "Inspect"
|
||||
"name": "Safety"
|
||||
},
|
||||
{
|
||||
"name": "DatasetIO"
|
||||
},
|
||||
{
|
||||
"name": "MemoryBanks"
|
||||
},
|
||||
{
|
||||
"name": "Shields"
|
||||
},
|
||||
{
|
||||
"name": "PostTraining"
|
||||
},
|
||||
{
|
||||
"name": "Datasets"
|
||||
},
|
||||
{
|
||||
"name": "Scoring"
|
||||
},
|
||||
{
|
||||
"name": "SyntheticDataGeneration"
|
||||
},
|
||||
{
|
||||
"name": "BatchInference"
|
||||
},
|
||||
{
|
||||
"name": "BuiltinTool",
|
||||
|
|
|
|||
|
|
@ -2068,7 +2068,7 @@ components:
|
|||
- $ref: '#/components/schemas/GraphMemoryBankParams'
|
||||
provider_id:
|
||||
type: string
|
||||
provider_memorybank_id:
|
||||
provider_memory_bank_id:
|
||||
type: string
|
||||
required:
|
||||
- memory_bank_id
|
||||
|
|
@ -2710,7 +2710,6 @@ components:
|
|||
- provider_id
|
||||
- type
|
||||
- shield_type
|
||||
- params
|
||||
title: A safety shield resource that can be used to check content
|
||||
type: object
|
||||
ShieldCallStep:
|
||||
|
|
@ -3398,7 +3397,7 @@ info:
|
|||
description: "This is the specification of the llama stack that provides\n \
|
||||
\ a set of endpoints and their corresponding interfaces that are tailored\
|
||||
\ to\n best leverage Llama Models. The specification is still in\
|
||||
\ draft and subject to change.\n Generated at 2024-11-11 18:44:30.967321"
|
||||
\ draft and subject to change.\n Generated at 2024-11-12 11:16:58.657871"
|
||||
title: '[DRAFT] Llama Stack Specification'
|
||||
version: 0.0.1
|
||||
jsonSchemaDialect: https://json-schema.org/draft/2020-12/schema
|
||||
|
|
@ -4762,24 +4761,24 @@ security:
|
|||
servers:
|
||||
- url: http://any-hosted-llama-stack.com
|
||||
tags:
|
||||
- name: Datasets
|
||||
- name: Telemetry
|
||||
- name: PostTraining
|
||||
- name: MemoryBanks
|
||||
- name: Eval
|
||||
- name: Memory
|
||||
- name: EvalTasks
|
||||
- name: Models
|
||||
- name: Scoring
|
||||
- name: Inference
|
||||
- name: Shields
|
||||
- name: DatasetIO
|
||||
- name: Safety
|
||||
- name: Agents
|
||||
- name: SyntheticDataGeneration
|
||||
- name: ScoringFunctions
|
||||
- name: BatchInference
|
||||
- name: Telemetry
|
||||
- name: Eval
|
||||
- name: Models
|
||||
- name: Inspect
|
||||
- name: EvalTasks
|
||||
- name: ScoringFunctions
|
||||
- name: Memory
|
||||
- name: Safety
|
||||
- name: DatasetIO
|
||||
- name: MemoryBanks
|
||||
- name: Shields
|
||||
- name: PostTraining
|
||||
- name: Datasets
|
||||
- name: Scoring
|
||||
- name: SyntheticDataGeneration
|
||||
- name: BatchInference
|
||||
- description: <SchemaDefinition schemaRef="#/components/schemas/BuiltinTool" />
|
||||
name: BuiltinTool
|
||||
- description: <SchemaDefinition schemaRef="#/components/schemas/CompletionMessage"
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue