phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 04:04:14 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge remote-tracking branch 'origin/main' into openai_v1

Browse source
This commit is contained in:
Ashwin Bharambe 2025-09-29 13:41:11 -07:00
commit 35546386a2
52 changed files with 580 additions and 802 deletions
Download patch file Download diff file Expand all files Collapse all files

120
docs/static/llama-stack-spec.html vendored
View file

@ -1239,50 +1239,6 @@
]
}
},
"/v1/inference/embeddings": {
"post": {
"responses": {
"200": {
"description": "An array of embeddings, one for each content. Each embedding is a list of floats. The dimensionality of the embedding is model-specific; you can check model metadata using /models/{model_id}.",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/EmbeddingsResponse"
}
}
}
},
"400": {
"$ref": "#/components/responses/BadRequest400"
},
"429": {
"$ref": "#/components/responses/TooManyRequests429"
},
"500": {
"$ref": "#/components/responses/InternalServerError500"
},
"default": {
"$ref": "#/components/responses/DefaultError"
}
},
"tags": [
"Inference"
],
"summary": "Generate embeddings for content pieces using the specified model.",
"description": "Generate embeddings for content pieces using the specified model.",
"parameters": [],
"requestBody": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/EmbeddingsRequest"
}
}
},
"required": true
}
}
},
"/v1alpha/eval/benchmarks/{benchmark_id}/evaluations": {
"post": {
"responses": {
@ -6965,7 +6921,7 @@
}
}
},
"/v1/inference/rerank": {
"/v1alpha/inference/rerank": {
"post": {
"responses": {
"200": {
@ -12081,80 +12037,6 @@
"title": "OpenAIDeleteResponseObject",
"description": "Response object confirming deletion of an OpenAI response."
},
"EmbeddingsRequest": {
"type": "object",
"properties": {
"model_id": {
"type": "string",
"description": "The identifier of the model to use. The model must be an embedding model registered with Llama Stack and available via the /models endpoint."
},
"contents": {
"oneOf": [
{
"type": "array",
"items": {
"type": "string"
}
},
{
"type": "array",
"items": {
"$ref": "#/components/schemas/InterleavedContentItem"
}
}
],
"description": "List of contents to generate embeddings for. Each content can be a string or an InterleavedContentItem (and hence can be multimodal). The behavior depends on the model and provider. Some models may only support text."
},
"text_truncation": {
"type": "string",
"enum": [
"none",
"start",
"end"
],
"description": "(Optional) Config for how to truncate text for embedding when text is longer than the model's max sequence length."
},
"output_dimension": {
"type": "integer",
"description": "(Optional) Output dimensionality for the embeddings. Only supported by Matryoshka models."
},
"task_type": {
"type": "string",
"enum": [
"query",
"document"
],
"description": "(Optional) How is the embedding being used? This is only supported by asymmetric embedding models."
}
},
"additionalProperties": false,
"required": [
"model_id",
"contents"
],
"title": "EmbeddingsRequest"
},
"EmbeddingsResponse": {
"type": "object",
"properties": {
"embeddings": {
"type": "array",
"items": {
"type": "array",
"items": {
"type": "number"
}
},
"description": "List of embedding vectors, one per input content. Each embedding is a list of floats. The dimensionality of the embedding is model-specific; you can check model metadata using /models/{model_id}"
}
},
"additionalProperties": false,
"required": [
"embeddings"
],
"title": "EmbeddingsResponse",
"description": "Response containing generated embeddings."
},
"AgentCandidate": {
"type": "object",
"properties": {