Skip to content

feat(swagger): update swagger #11585

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
mudler merged 1 commit into from
Aug 19, 2026
+108 −5
Merged

feat(swagger): update swagger #11585

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
36 changes: 35 additions & 1 deletion swagger/docs.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2110,7 +2110,7 @@ const docTemplate = `{
},
"/audio/transformations/stream": {
"get": {
"description": "Streams binary PCM frames in (interleaved stereo: ch0=audio, ch1=reference) and out (mono). The first message must be a JSON ` + "`" + `session.update` + "`" + ` envelope describing model + sample format + frame size + backend params. Server emits binary PCM on the same cadence.",
"description": "Streams binary PCM frames in (interleaved stereo: ch0=audio, ch1=reference) and out (mono). The model must support the audio_transform use case. Any-to-any models such as liquid-audio use the OpenAI Realtime API instead. The first message must be a JSON ` + "`" + `session.update` + "`" + ` envelope describing model + sample format + frame size + backend params. Server emits binary PCM on the same cadence.",
"tags": [
"audio"
],
Expand Down Expand Up @@ -5080,6 +5080,29 @@ const docTemplate = `{
}
}
},
"schema.CompressionMetadata": {
"type": "object",
"properties": {
"compressed_tokens": {
"type": "integer"
},
"compressor": {
"type": "string"
},
"dropped_turns": {
"type": "integer"
},
"original_tokens": {
"type": "integer"
},
"overflow_recoveries": {
"type": "integer"
},
"summary_tokens": {
"type": "integer"
}
}
},
"schema.DepthRequest": {
"type": "object",
"properties": {
Expand Down Expand Up @@ -6992,6 +7015,14 @@ const docTemplate = `{
"negative_prompt_scale": {
"type": "number"
},
"pooling": {
"description": "Pooling is a LocalAI extension for /v1/embeddings: how the backend's\nper-token vectors are reduced to a single embedding. \"\" or \"backend\"\nleaves pooling to the inference backend (the pre-existing behavior);\n\"mean\", \"last\" and \"decayed_mean\" pool Go-side from raw per-token\nvectors (the backend must run with the \"pooling:none\" option, which\nmodel configs get automatically when this is set).",
"type": "string"
},
"pooling_half_life_tokens": {
"description": "PoolingHalfLifeTokens is a LocalAI extension for /v1/embeddings: the\nhalf-life (in tokens) of the \"decayed_mean\" pooling scheme — a token's\nweight halves every this-many positions counting back from the end of\nthe conversation. Defaults to 256 when unset.",
"type": "integer"
},
"presence_penalty": {
"type": "number"
},
Expand Down Expand Up @@ -7129,6 +7160,9 @@ const docTemplate = `{
"completion_tokens": {
"type": "integer"
},
"compression_meta": {
"$ref": "#/definitions/schema.CompressionMetadata"
},
"input_tokens": {
"description": "Fields for image generation API compatibility",
"type": "integer"
Expand Down
36 changes: 35 additions & 1 deletion swagger/swagger.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2107,7 +2107,7 @@
},
"/audio/transformations/stream": {
"get": {
"description": "Streams binary PCM frames in (interleaved stereo: ch0=audio, ch1=reference) and out (mono). The first message must be a JSON `session.update` envelope describing model + sample format + frame size + backend params. Server emits binary PCM on the same cadence.",
"description": "Streams binary PCM frames in (interleaved stereo: ch0=audio, ch1=reference) and out (mono). The model must support the audio_transform use case. Any-to-any models such as liquid-audio use the OpenAI Realtime API instead. The first message must be a JSON `session.update` envelope describing model + sample format + frame size + backend params. Server emits binary PCM on the same cadence.",
"tags": [
"audio"
],
Expand Down Expand Up @@ -5077,6 +5077,29 @@
}
}
},
"schema.CompressionMetadata": {
"type": "object",
"properties": {
"compressed_tokens": {
"type": "integer"
},
"compressor": {
"type": "string"
},
"dropped_turns": {
"type": "integer"
},
"original_tokens": {
"type": "integer"
},
"overflow_recoveries": {
"type": "integer"
},
"summary_tokens": {
"type": "integer"
}
}
},
"schema.DepthRequest": {
"type": "object",
"properties": {
Expand Down Expand Up @@ -6989,6 +7012,14 @@
"negative_prompt_scale": {
"type": "number"
},
"pooling": {
"description": "Pooling is a LocalAI extension for /v1/embeddings: how the backend's\nper-token vectors are reduced to a single embedding. \"\" or \"backend\"\nleaves pooling to the inference backend (the pre-existing behavior);\n\"mean\", \"last\" and \"decayed_mean\" pool Go-side from raw per-token\nvectors (the backend must run with the \"pooling:none\" option, which\nmodel configs get automatically when this is set).",
"type": "string"
},
"pooling_half_life_tokens": {
"description": "PoolingHalfLifeTokens is a LocalAI extension for /v1/embeddings: the\nhalf-life (in tokens) of the \"decayed_mean\" pooling scheme — a token's\nweight halves every this-many positions counting back from the end of\nthe conversation. Defaults to 256 when unset.",
"type": "integer"
},
"presence_penalty": {
"type": "number"
},
Expand Down Expand Up @@ -7126,6 +7157,9 @@
"completion_tokens": {
"type": "integer"
},
"compression_meta": {
"$ref": "#/definitions/schema.CompressionMetadata"
},
"input_tokens": {
"description": "Fields for image generation API compatibility",
"type": "integer"
Expand Down
41 changes: 38 additions & 3 deletions swagger/swagger.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -750,6 +750,21 @@ definitions:
text:
type: string
type: object
schema.CompressionMetadata:
properties:
compressed_tokens:
type: integer
compressor:
type: string
dropped_turns:
type: integer
original_tokens:
type: integer
overflow_recoveries:
type: integer
summary_tokens:
type: integer
type: object
schema.DepthRequest:
properties:
dst:
Expand Down Expand Up @@ -2072,6 +2087,22 @@ definitions:
type: string
negative_prompt_scale:
type: number
pooling:
description: |-
Pooling is a LocalAI extension for /v1/embeddings: how the backend's
per-token vectors are reduced to a single embedding. "" or "backend"
leaves pooling to the inference backend (the pre-existing behavior);
"mean", "last" and "decayed_mean" pool Go-side from raw per-token
vectors (the backend must run with the "pooling:none" option, which
model configs get automatically when this is set).
type: string
pooling_half_life_tokens:
description: |-
PoolingHalfLifeTokens is a LocalAI extension for /v1/embeddings: the
half-life (in tokens) of the "decayed_mean" pooling scheme — a token's
weight halves every this-many positions counting back from the end of
the conversation. Defaults to 256 when unset.
type: integer
presence_penalty:
type: number
prompt:
Expand Down Expand Up @@ -2172,6 +2203,8 @@ definitions:
properties:
completion_tokens:
type: integer
compression_meta:
$ref: '#/definitions/schema.CompressionMetadata'
input_tokens:
description: Fields for image generation API compatibility
type: integer
Expand Down Expand Up @@ -4407,9 +4440,11 @@ paths:
/audio/transformations/stream:
get:
description: 'Streams binary PCM frames in (interleaved stereo: ch0=audio, ch1=reference)
and out (mono). The first message must be a JSON `session.update` envelope
describing model + sample format + frame size + backend params. Server emits
binary PCM on the same cadence.'
and out (mono). The model must support the audio_transform use case. Any-to-any
models such as liquid-audio use the OpenAI Realtime API instead. The first
message must be a JSON `session.update` envelope describing model + sample
format + frame size + backend params. Server emits binary PCM on the same
cadence.'
responses: {}
summary: Bidirectional realtime audio transform over WebSocket.
tags:
Expand Down
Loading