mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-27 11:12:01 +00:00
feat: implement provider updating
add `v1/providers/` which uses PUT to allow users to change their provider configuration this is a follow up to #1429 and related to #1359 a user can call something like: `llama_stack_client.providers.update(api="inference", provider_id="ollama", provider_type="remote::ollama", config={'url': 'http:/localhost:12345'})` or `llama-stack-client providers update inference ollama remote::ollama "{'url': 'http://localhost:12345'}"` this API works by adding a `RequestMiddleware` to the server which checks requests, and if the user is using PUT /v1/providers, the routes are re-registered with the re-initialized provider configurations/methods for the client, `self.impls` is updated to hold the proper methods+configurations this depends on a client PR, the CI will fail until then but succeeded locally Signed-off-by: Charlie Doern <cdoern@redhat.com>
This commit is contained in:
parent
d165000bbc
commit
436f8ade9e
8 changed files with 449 additions and 56 deletions
103
docs/_static/llama-stack-spec.html
vendored
103
docs/_static/llama-stack-spec.html
vendored
|
|
@ -4946,6 +4946,74 @@
|
|||
}
|
||||
}
|
||||
},
|
||||
"/v1/providers/{api}/{provider_id}/{provider_type}": {
|
||||
"post": {
|
||||
"responses": {
|
||||
"200": {
|
||||
"description": "OK",
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/ProviderInfo"
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"400": {
|
||||
"$ref": "#/components/responses/BadRequest400"
|
||||
},
|
||||
"429": {
|
||||
"$ref": "#/components/responses/TooManyRequests429"
|
||||
},
|
||||
"500": {
|
||||
"$ref": "#/components/responses/InternalServerError500"
|
||||
},
|
||||
"default": {
|
||||
"$ref": "#/components/responses/DefaultError"
|
||||
}
|
||||
},
|
||||
"tags": [
|
||||
"Providers"
|
||||
],
|
||||
"description": "",
|
||||
"parameters": [
|
||||
{
|
||||
"name": "api",
|
||||
"in": "path",
|
||||
"required": true,
|
||||
"schema": {
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "provider_id",
|
||||
"in": "path",
|
||||
"required": true,
|
||||
"schema": {
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "provider_type",
|
||||
"in": "path",
|
||||
"required": true,
|
||||
"schema": {
|
||||
"type": "string"
|
||||
}
|
||||
}
|
||||
],
|
||||
"requestBody": {
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/UpdateProviderRequest"
|
||||
}
|
||||
}
|
||||
},
|
||||
"required": true
|
||||
}
|
||||
}
|
||||
},
|
||||
"/v1/version": {
|
||||
"get": {
|
||||
"responses": {
|
||||
|
|
@ -16101,6 +16169,41 @@
|
|||
"title": "SyntheticDataGenerationResponse",
|
||||
"description": "Response from the synthetic data generation. Batch of (prompt, response, score) tuples that pass the threshold."
|
||||
},
|
||||
"UpdateProviderRequest": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"config": {
|
||||
"type": "object",
|
||||
"additionalProperties": {
|
||||
"oneOf": [
|
||||
{
|
||||
"type": "null"
|
||||
},
|
||||
{
|
||||
"type": "boolean"
|
||||
},
|
||||
{
|
||||
"type": "number"
|
||||
},
|
||||
{
|
||||
"type": "string"
|
||||
},
|
||||
{
|
||||
"type": "array"
|
||||
},
|
||||
{
|
||||
"type": "object"
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"config"
|
||||
],
|
||||
"title": "UpdateProviderRequest"
|
||||
},
|
||||
"VersionInfo": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue