phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-04 10:10:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge remote-tracking branch 'upstream/main' into elasticsearch-integration

Browse source
This commit is contained in:
Enrico Zimuel 2025-11-05 14:58:43 +01:00
commit 153e5f8971
No known key found for this signature in database
GPG key ID: 6CB203F6934A69F1
1202 changed files with 942 additions and 324667 deletions
Download patch file Download diff file Expand all files Collapse all files

2
docs/docs/distributions/k8s/ui-k8s.yaml.template
View file

@ -44,7 +44,7 @@ spec:
# Navigate to the UI directory
echo "Navigating to UI directory..."
cd /app/llama_stack/ui
cd /app/llama_stack_ui
# Check if package.json exists
if [ ! -f "package.json" ]; then

8
docs/openapi_generator/pyopenapi/operations.py
View file

@ -170,7 +170,7 @@ def _get_endpoint_functions(
for webmethod in webmethods:
print(f"Processing {colored(func_name, 'white')}...")
operation_name = func_name
if webmethod.method == "GET":
prefix = "get"
elif webmethod.method == "DELETE":
@ -196,16 +196,10 @@ def _get_endpoint_functions(
def _get_defining_class(member_fn: str, derived_cls: type) -> type:
"Find the class in which a member function is first defined in a class inheritance hierarchy."
# This import must be dynamic here
from llama_stack.apis.tools import RAGToolRuntime, ToolRuntime
# iterate in reverse member resolution order to find most specific class first
for cls in reversed(inspect.getmro(derived_cls)):
for name, _ in inspect.getmembers(cls, inspect.isfunction):
if name == member_fn:
# HACK ALERT
if cls == RAGToolRuntime:
return ToolRuntime
return cls
raise ValidationError(

2164
docs/static/experimental-llama-stack-spec.yaml vendored
View file

File diff suppressed because it is too large Load diff

13724
docs/static/llama-stack-spec.html vendored
View file

File diff suppressed because it is too large Load diff

349
docs/static/llama-stack-spec.yaml vendored
View file

@ -2052,69 +2052,6 @@ paths:
schema:
$ref: '#/components/schemas/URL'
deprecated: false
/v1/tool-runtime/rag-tool/insert:
post:
responses:
'200':
description: OK
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- ToolRuntime
summary: >-
Index documents so they can be used by the RAG system.
description: >-
Index documents so they can be used by the RAG system.
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/InsertRequest'
required: true
deprecated: false
/v1/tool-runtime/rag-tool/query:
post:
responses:
'200':
description: >-
RAGQueryResult containing the retrieved content and metadata
content:
application/json:
schema:
$ref: '#/components/schemas/RAGQueryResult'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- ToolRuntime
summary: >-
Query the RAG system for context; typically invoked by the agent.
description: >-
Query the RAG system for context; typically invoked by the agent.
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/QueryRequest'
required: true
deprecated: false
/v1/toolgroups:
get:
responses:
@ -8137,20 +8074,6 @@ components:
- error
title: ViolationLevel
description: Severity level of a safety violation.
AgentTurnInputType:
type: object
properties:
type:
type: string
const: agent_turn_input
default: agent_turn_input
description: >-
Discriminator type. Always "agent_turn_input"
additionalProperties: false
required:
- type
title: AgentTurnInputType
description: Parameter type for agent turn input.
AggregationFunctionType:
type: string
enum:
@ -8393,7 +8316,6 @@ components:
- $ref: '#/components/schemas/UnionType'
- $ref: '#/components/schemas/ChatCompletionInputType'
- $ref: '#/components/schemas/CompletionInputType'
- $ref: '#/components/schemas/AgentTurnInputType'
discriminator:
propertyName: type
mapping:
@ -8406,7 +8328,6 @@ components:
union: '#/components/schemas/UnionType'
chat_completion_input: '#/components/schemas/ChatCompletionInputType'
completion_input: '#/components/schemas/CompletionInputType'
agent_turn_input: '#/components/schemas/AgentTurnInputType'
params:
$ref: '#/components/schemas/ScoringFnParams'
additionalProperties: false
@ -8487,7 +8408,6 @@ components:
- $ref: '#/components/schemas/UnionType'
- $ref: '#/components/schemas/ChatCompletionInputType'
- $ref: '#/components/schemas/CompletionInputType'
- $ref: '#/components/schemas/AgentTurnInputType'
discriminator:
propertyName: type
mapping:
@ -8500,7 +8420,6 @@ components:
union: '#/components/schemas/UnionType'
chat_completion_input: '#/components/schemas/ChatCompletionInputType'
completion_input: '#/components/schemas/CompletionInputType'
agent_turn_input: '#/components/schemas/AgentTurnInputType'
RegisterScoringFunctionRequest:
type: object
properties:
@ -8935,274 +8854,6 @@ components:
title: ListToolDefsResponse
description: >-
Response containing a list of tool definitions.
RAGDocument:
type: object
properties:
document_id:
type: string
description: The unique identifier for the document.
content:
oneOf:
- type: string
- $ref: '#/components/schemas/InterleavedContentItem'
- type: array
items:
$ref: '#/components/schemas/InterleavedContentItem'
- $ref: '#/components/schemas/URL'
description: The content of the document.
mime_type:
type: string
description: The MIME type of the document.
metadata:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
description: Additional metadata for the document.
additionalProperties: false
required:
- document_id
- content
- metadata
title: RAGDocument
description: >-
A document to be used for document ingestion in the RAG Tool.
InsertRequest:
type: object
properties:
documents:
type: array
items:
$ref: '#/components/schemas/RAGDocument'
description: >-
List of documents to index in the RAG system
vector_store_id:
type: string
description: >-
ID of the vector database to store the document embeddings
chunk_size_in_tokens:
type: integer
description: >-
(Optional) Size in tokens for document chunking during indexing
additionalProperties: false
required:
- documents
- vector_store_id
- chunk_size_in_tokens
title: InsertRequest
DefaultRAGQueryGeneratorConfig:
type: object
properties:
type:
type: string
const: default
default: default
description: >-
Type of query generator, always 'default'
separator:
type: string
default: ' '
description: >-
String separator used to join query terms
additionalProperties: false
required:
- type
- separator
title: DefaultRAGQueryGeneratorConfig
description: >-
Configuration for the default RAG query generator.
LLMRAGQueryGeneratorConfig:
type: object
properties:
type:
type: string
const: llm
default: llm
description: Type of query generator, always 'llm'
model:
type: string
description: >-
Name of the language model to use for query generation
template:
type: string
description: >-
Template string for formatting the query generation prompt
additionalProperties: false
required:
- type
- model
- template
title: LLMRAGQueryGeneratorConfig
description: >-
Configuration for the LLM-based RAG query generator.
RAGQueryConfig:
type: object
properties:
query_generator_config:
oneOf:
- $ref: '#/components/schemas/DefaultRAGQueryGeneratorConfig'
- $ref: '#/components/schemas/LLMRAGQueryGeneratorConfig'
discriminator:
propertyName: type
mapping:
default: '#/components/schemas/DefaultRAGQueryGeneratorConfig'
llm: '#/components/schemas/LLMRAGQueryGeneratorConfig'
description: Configuration for the query generator.
max_tokens_in_context:
type: integer
default: 4096
description: Maximum number of tokens in the context.
max_chunks:
type: integer
default: 5
description: Maximum number of chunks to retrieve.
chunk_template:
type: string
default: >
Result {index}
Content: {chunk.content}
Metadata: {metadata}
description: >-
Template for formatting each retrieved chunk in the context. Available
placeholders: {index} (1-based chunk ordinal), {chunk.content} (chunk
content string), {metadata} (chunk metadata dict). Default: "Result {index}\nContent:
{chunk.content}\nMetadata: {metadata}\n"
mode:
$ref: '#/components/schemas/RAGSearchMode'
default: vector
description: >-
Search mode for retrieval—either "vector", "keyword", or "hybrid". Default
"vector".
ranker:
$ref: '#/components/schemas/Ranker'
description: >-
Configuration for the ranker to use in hybrid search. Defaults to RRF
ranker.
additionalProperties: false
required:
- query_generator_config
- max_tokens_in_context
- max_chunks
- chunk_template
title: RAGQueryConfig
description: >-
Configuration for the RAG query generation.
RAGSearchMode:
type: string
enum:
- vector
- keyword
- hybrid
title: RAGSearchMode
description: >-
Search modes for RAG query retrieval: - VECTOR: Uses vector similarity search
for semantic matching - KEYWORD: Uses keyword-based search for exact matching
- HYBRID: Combines both vector and keyword search for better results
RRFRanker:
type: object
properties:
type:
type: string
const: rrf
default: rrf
description: The type of ranker, always "rrf"
impact_factor:
type: number
default: 60.0
description: >-
The impact factor for RRF scoring. Higher values give more weight to higher-ranked
results. Must be greater than 0
additionalProperties: false
required:
- type
- impact_factor
title: RRFRanker
description: >-
Reciprocal Rank Fusion (RRF) ranker configuration.
Ranker:
oneOf:
- $ref: '#/components/schemas/RRFRanker'
- $ref: '#/components/schemas/WeightedRanker'
discriminator:
propertyName: type
mapping:
rrf: '#/components/schemas/RRFRanker'
weighted: '#/components/schemas/WeightedRanker'
WeightedRanker:
type: object
properties:
type:
type: string
const: weighted
default: weighted
description: The type of ranker, always "weighted"
alpha:
type: number
default: 0.5
description: >-
Weight factor between 0 and 1. 0 means only use keyword scores, 1 means
only use vector scores, values in between blend both scores.
additionalProperties: false
required:
- type
- alpha
title: WeightedRanker
description: >-
Weighted ranker configuration that combines vector and keyword scores.
QueryRequest:
type: object
properties:
content:
$ref: '#/components/schemas/InterleavedContent'
description: >-
The query content to search for in the indexed documents
vector_store_ids:
type: array
items:
type: string
description: >-
List of vector database IDs to search within
query_config:
$ref: '#/components/schemas/RAGQueryConfig'
description: >-
(Optional) Configuration parameters for the query operation
additionalProperties: false
required:
- content
- vector_store_ids
title: QueryRequest
RAGQueryResult:
type: object
properties:
content:
$ref: '#/components/schemas/InterleavedContent'
description: >-
(Optional) The retrieved content from the query
metadata:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
description: >-
Additional metadata about the query result
additionalProperties: false
required:
- metadata
title: RAGQueryResult
description: >-
Result of a RAG query containing retrieved content and metadata.
ToolGroup:
type: object
properties:

2221
docs/static/stainless-llama-stack-spec.yaml vendored
View file

File diff suppressed because it is too large Load diff