phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-16 02:02:37 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge remote-tracking branch 'origin/main' into dependabot/uv/openai-2.5.0

Browse source
This commit is contained in:
Ashwin Bharambe 2025-10-22 12:17:03 -07:00
commit 13450c1a68
317 changed files with 86802 additions and 18957 deletions
Download patch file Download diff file Expand all files Collapse all files

21
docs/static/llama-stack-spec.html vendored
View file

@ -6767,7 +6767,7 @@
"enum": [
"model",
"shield",
"vector_db",
"vector_store",
"dataset",
"scoring_function",
"benchmark",
@ -6826,7 +6826,8 @@
"type": "string",
"enum": [
"llm",
"embedding"
"embedding",
"rerank"
],
"title": "ModelType",
"description": "Enumeration of supported model types in Llama Stack."
@ -7567,6 +7568,10 @@
"$ref": "#/components/schemas/OpenAIResponseUsage",
"description": "(Optional) Token usage information for the response"
},
"instructions": {
"type": "string",
"description": "(Optional) System message inserted into the model's context"
},
"input": {
"type": "array",
"items": {
@ -8115,6 +8120,10 @@
"usage": {
"$ref": "#/components/schemas/OpenAIResponseUsage",
"description": "(Optional) Token usage information for the response"
},
"instructions": {
"type": "string",
"description": "(Optional) System message inserted into the model's context"
}
},
"additionalProperties": false,
@ -10164,7 +10173,7 @@
"enum": [
"model",
"shield",
"vector_db",
"vector_store",
"dataset",
"scoring_function",
"benchmark",
@ -10646,7 +10655,7 @@
"enum": [
"model",
"shield",
"vector_db",
"vector_store",
"dataset",
"scoring_function",
"benchmark",
@ -11699,7 +11708,7 @@
"enum": [
"model",
"shield",
"vector_db",
"vector_store",
"dataset",
"scoring_function",
"benchmark",
@ -13228,7 +13237,7 @@
},
{
"name": "Inference",
"description": "Llama Stack Inference API for generating completions, chat completions, and embeddings.\n\nThis API provides the raw interface to the underlying models. Two kinds of models are supported:\n- LLM models: these models generate \"raw\" and \"chat\" (conversational) completions.\n- Embedding models: these models generate embeddings to be used for semantic search.",
"description": "Llama Stack Inference API for generating completions, chat completions, and embeddings.\n\nThis API provides the raw interface to the underlying models. Three kinds of models are supported:\n- LLM models: these models generate \"raw\" and \"chat\" (conversational) completions.\n- Embedding models: these models generate embeddings to be used for semantic search.\n- Rerank models: these models reorder the documents based on their relevance to a query.",
"x-displayName": "Inference"
},
{