mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-07-23 04:53:14 +00:00
Support model resource updates and deletes (#452)
# What does this PR do?
* Changes the registry to store only one RoutableObject per identifier.
Before it was a list, which is not really required.
* Adds impl for updates and deletes
* Updates routing table to handle updates correctly
## Test Plan
```
❯ llama-stack-client models list
+------------------------+---------------+------------------------------------+------------+
| identifier | provider_id | provider_resource_id | metadata |
+========================+===============+====================================+============+
| Llama3.1-405B-Instruct | fireworks-0 | fireworks/llama-v3p1-405b-instruct | {} |
+------------------------+---------------+------------------------------------+------------+
| Llama3.1-8B-Instruct | fireworks-0 | fireworks/llama-v3p1-8b-instruct | {} |
+------------------------+---------------+------------------------------------+------------+
| Llama3.2-3B-Instruct | fireworks-0 | fireworks/llama-v3p2-1b-instruct | {} |
+------------------------+---------------+------------------------------------+------------+
❯ llama-stack-client models register dineshyv-model --provider-model-id=fireworks/llama-v3p1-70b-instruct
Successfully registered model dineshyv-model
❯ llama-stack-client models list
+------------------------+---------------+------------------------------------+------------+
| identifier | provider_id | provider_resource_id | metadata |
+========================+===============+====================================+============+
| Llama3.1-405B-Instruct | fireworks-0 | fireworks/llama-v3p1-405b-instruct | {} |
+------------------------+---------------+------------------------------------+------------+
| Llama3.1-8B-Instruct | fireworks-0 | fireworks/llama-v3p1-8b-instruct | {} |
+------------------------+---------------+------------------------------------+------------+
| Llama3.2-3B-Instruct | fireworks-0 | fireworks/llama-v3p2-1b-instruct | {} |
+------------------------+---------------+------------------------------------+------------+
| dineshyv-model | fireworks-0 | fireworks/llama-v3p1-70b-instruct | {} |
+------------------------+---------------+------------------------------------+------------+
❯ llama-stack-client models update dineshyv-model --provider-model-id=fireworks/llama-v3p1-405b-instruct
Successfully updated model dineshyv-model
❯ llama-stack-client models list
+------------------------+---------------+------------------------------------+------------+
| identifier | provider_id | provider_resource_id | metadata |
+========================+===============+====================================+============+
| Llama3.1-405B-Instruct | fireworks-0 | fireworks/llama-v3p1-405b-instruct | {} |
+------------------------+---------------+------------------------------------+------------+
| Llama3.1-8B-Instruct | fireworks-0 | fireworks/llama-v3p1-8b-instruct | {} |
+------------------------+---------------+------------------------------------+------------+
| Llama3.2-3B-Instruct | fireworks-0 | fireworks/llama-v3p2-1b-instruct | {} |
+------------------------+---------------+------------------------------------+------------+
| dineshyv-model | fireworks-0 | fireworks/llama-v3p1-405b-instruct | {} |
+------------------------+---------------+------------------------------------+------------+
llama-stack-client models delete dineshyv-model
❯ llama-stack-client models list
+------------------------+---------------+------------------------------------+------------+
| identifier | provider_id | provider_resource_id | metadata |
+========================+===============+====================================+============+
| Llama3.1-405B-Instruct | fireworks-0 | fireworks/llama-v3p1-405b-instruct | {} |
+------------------------+---------------+------------------------------------+------------+
| Llama3.1-8B-Instruct | fireworks-0 | fireworks/llama-v3p1-8b-instruct | {} |
+------------------------+---------------+------------------------------------+------------+
| Llama3.2-3B-Instruct | fireworks-0 | fireworks/llama-v3p2-1b-instruct | {} |
+------------------------+---------------+------------------------------------+------------+
```
---------
Co-authored-by: Dinesh Yeduguru <dineshyv@fb.com>
This commit is contained in:
Dinesh Yeduguru
GitHub
parent
4253cfcd7f
commit
efe791bab7
7 changed files with 447 additions and 129 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 2024-11-13 11:02:50.081698"
|
||||
"description": "This is the specification of the llama stack that provides\n a set of endpoints and their corresponding interfaces that are tailored to\n best leverage Llama Models. The specification is still in draft and subject to change.\n Generated at 2024-11-13 21:05:58.323310"
|
||||
},
|
||||
"servers": [
|
||||
{
|
||||
|
|
@ -429,6 +429,39 @@
|
|||
}
|
||||
}
|
||||
},
|
||||
"/models/delete": {
|
||||
"post": {
|
||||
"responses": {
|
||||
"200": {
|
||||
"description": "OK"
|
||||
}
|
||||
},
|
||||
"tags": [
|
||||
"Models"
|
||||
],
|
||||
"parameters": [
|
||||
{
|
||||
"name": "X-LlamaStack-ProviderData",
|
||||
"in": "header",
|
||||
"description": "JSON-encoded provider data which will be made available to the adapter servicing the API",
|
||||
"required": false,
|
||||
"schema": {
|
||||
"type": "string"
|
||||
}
|
||||
}
|
||||
],
|
||||
"requestBody": {
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/DeleteModelRequest"
|
||||
}
|
||||
}
|
||||
},
|
||||
"required": true
|
||||
}
|
||||
}
|
||||
},
|
||||
"/inference/embeddings": {
|
||||
"post": {
|
||||
"responses": {
|
||||
|
|
@ -2225,6 +2258,46 @@
|
|||
"required": true
|
||||
}
|
||||
}
|
||||
},
|
||||
"/models/update": {
|
||||
"post": {
|
||||
"responses": {
|
||||
"200": {
|
||||
"description": "OK",
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/Model"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"tags": [
|
||||
"Models"
|
||||
],
|
||||
"parameters": [
|
||||
{
|
||||
"name": "X-LlamaStack-ProviderData",
|
||||
"in": "header",
|
||||
"description": "JSON-encoded provider data which will be made available to the adapter servicing the API",
|
||||
"required": false,
|
||||
"schema": {
|
||||
"type": "string"
|
||||
}
|
||||
}
|
||||
],
|
||||
"requestBody": {
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/UpdateModelRequest"
|
||||
}
|
||||
}
|
||||
},
|
||||
"required": true
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"jsonSchemaDialect": "https://json-schema.org/draft/2020-12/schema",
|
||||
|
|
@ -4549,6 +4622,18 @@
|
|||
"session_id"
|
||||
]
|
||||
},
|
||||
"DeleteModelRequest": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"model_id": {
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"model_id"
|
||||
]
|
||||
},
|
||||
"EmbeddingsRequest": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
|
|
@ -7826,6 +7911,49 @@
|
|||
"synthetic_data"
|
||||
],
|
||||
"title": "Response from the synthetic data generation. Batch of (prompt, response, score) tuples that pass the threshold."
|
||||
},
|
||||
"UpdateModelRequest": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"model_id": {
|
||||
"type": "string"
|
||||
},
|
||||
"provider_model_id": {
|
||||
"type": "string"
|
||||
},
|
||||
"provider_id": {
|
||||
"type": "string"
|
||||
},
|
||||
"metadata": {
|
||||
"type": "object",
|
||||
"additionalProperties": {
|
||||
"oneOf": [
|
||||
{
|
||||
"type": "null"
|
||||
},
|
||||
{
|
||||
"type": "boolean"
|
||||
},
|
||||
{
|
||||
"type": "number"
|
||||
},
|
||||
{
|
||||
"type": "string"
|
||||
},
|
||||
{
|
||||
"type": "array"
|
||||
},
|
||||
{
|
||||
"type": "object"
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"model_id"
|
||||
]
|
||||
}
|
||||
},
|
||||
"responses": {}
|
||||
|
|
@ -7837,23 +7965,20 @@
|
|||
],
|
||||
"tags": [
|
||||
{
|
||||
"name": "Inspect"
|
||||
"name": "Agents"
|
||||
},
|
||||
{
|
||||
"name": "DatasetIO"
|
||||
},
|
||||
{
|
||||
"name": "Models"
|
||||
},
|
||||
{
|
||||
"name": "Eval"
|
||||
},
|
||||
{
|
||||
"name": "EvalTasks"
|
||||
},
|
||||
{
|
||||
"name": "Scoring"
|
||||
},
|
||||
{
|
||||
"name": "Inference"
|
||||
},
|
||||
{
|
||||
"name": "BatchInference"
|
||||
},
|
||||
{
|
||||
"name": "Memory"
|
||||
},
|
||||
|
|
@ -7861,35 +7986,38 @@
|
|||
"name": "Safety"
|
||||
},
|
||||
{
|
||||
"name": "PostTraining"
|
||||
"name": "Inspect"
|
||||
},
|
||||
{
|
||||
"name": "ScoringFunctions"
|
||||
"name": "EvalTasks"
|
||||
},
|
||||
{
|
||||
"name": "Telemetry"
|
||||
},
|
||||
{
|
||||
"name": "Shields"
|
||||
},
|
||||
{
|
||||
"name": "BatchInference"
|
||||
},
|
||||
{
|
||||
"name": "MemoryBanks"
|
||||
"name": "Scoring"
|
||||
},
|
||||
{
|
||||
"name": "Datasets"
|
||||
},
|
||||
{
|
||||
"name": "PostTraining"
|
||||
},
|
||||
{
|
||||
"name": "Eval"
|
||||
},
|
||||
{
|
||||
"name": "Shields"
|
||||
},
|
||||
{
|
||||
"name": "Telemetry"
|
||||
},
|
||||
{
|
||||
"name": "ScoringFunctions"
|
||||
},
|
||||
{
|
||||
"name": "MemoryBanks"
|
||||
},
|
||||
{
|
||||
"name": "SyntheticDataGeneration"
|
||||
},
|
||||
{
|
||||
"name": "DatasetIO"
|
||||
},
|
||||
{
|
||||
"name": "Agents"
|
||||
},
|
||||
{
|
||||
"name": "BuiltinTool",
|
||||
"description": "<SchemaDefinition schemaRef=\"#/components/schemas/BuiltinTool\" />"
|
||||
|
|
@ -8142,6 +8270,10 @@
|
|||
"name": "DeleteAgentsSessionRequest",
|
||||
"description": "<SchemaDefinition schemaRef=\"#/components/schemas/DeleteAgentsSessionRequest\" />"
|
||||
},
|
||||
{
|
||||
"name": "DeleteModelRequest",
|
||||
"description": "<SchemaDefinition schemaRef=\"#/components/schemas/DeleteModelRequest\" />"
|
||||
},
|
||||
{
|
||||
"name": "EmbeddingsRequest",
|
||||
"description": "<SchemaDefinition schemaRef=\"#/components/schemas/EmbeddingsRequest\" />"
|
||||
|
|
@ -8453,6 +8585,10 @@
|
|||
{
|
||||
"name": "SyntheticDataGenerationResponse",
|
||||
"description": "Response from the synthetic data generation. Batch of (prompt, response, score) tuples that pass the threshold.\n\n<SchemaDefinition schemaRef=\"#/components/schemas/SyntheticDataGenerationResponse\" />"
|
||||
},
|
||||
{
|
||||
"name": "UpdateModelRequest",
|
||||
"description": "<SchemaDefinition schemaRef=\"#/components/schemas/UpdateModelRequest\" />"
|
||||
}
|
||||
],
|
||||
"x-tagGroups": [
|
||||
|
|
@ -8521,6 +8657,7 @@
|
|||
"Dataset",
|
||||
"DeleteAgentsRequest",
|
||||
"DeleteAgentsSessionRequest",
|
||||
"DeleteModelRequest",
|
||||
"DoraFinetuningConfig",
|
||||
"EmbeddingsRequest",
|
||||
"EmbeddingsResponse",
|
||||
|
|
@ -8618,6 +8755,7 @@
|
|||
"Turn",
|
||||
"URL",
|
||||
"UnstructuredLogEvent",
|
||||
"UpdateModelRequest",
|
||||
"UserMessage",
|
||||
"VectorMemoryBank",
|
||||
"VectorMemoryBankParams",
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue