phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-01 16:24:44 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

updating doc strings

Browse source 
Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
This commit is contained in:
Francisco Javier Arceo 2025-05-14 14:10:45 -04:00
parent 1e59ef1f76
commit 76679e2f0b
3 changed files with 26 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

15
docs/_static/llama-stack-spec.html vendored
View file

@ -11294,19 +11294,23 @@
"type": "object",
"properties": {
"query_generator_config": {
"$ref": "#/components/schemas/RAGQueryGeneratorConfig"
"$ref": "#/components/schemas/RAGQueryGeneratorConfig",
"description": "Configuration for the query generator."
},
"max_tokens_in_context": {
"type": "integer",
"default": 4096
"default": 4096,
"description": "Maximum number of tokens in the context."
},
"max_chunks": {
"type": "integer",
"default": 5
"default": 5,
"description": "Maximum number of chunks to retrieve."
},
"chunk_template": {
"type": "string",
"default": "Result {index}\nContent: {chunk.content}\nMetadata: {metadata}\n"
"default": "Result {index}\nContent: {chunk.content}\nMetadata: {metadata}\n",
"description": "Template for formatting each retrieved chunk in the context."
}
},
"additionalProperties": false,
@ -11316,7 +11320,8 @@
"max_chunks",
"chunk_template"
],
"title": "RAGQueryConfig"
"title": "RAGQueryConfig",
"description": "Configuration for the RAG query generation."
},
"RAGQueryGeneratorConfig": {
"oneOf": [

7
docs/_static/llama-stack-spec.yaml vendored
View file

@ -7794,12 +7794,15 @@ components:
properties:
query_generator_config:
$ref: '#/components/schemas/RAGQueryGeneratorConfig'
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: >
@ -7808,6 +7811,8 @@ components:
Content: {chunk.content}
Metadata: {metadata}
description: >-
Template for formatting each retrieved chunk in the context.
additionalProperties: false
required:
- query_generator_config
@ -7815,6 +7820,8 @@ components:
- max_chunks
- chunk_template
title: RAGQueryConfig
description: >-
Configuration for the RAG query generation.
RAGQueryGeneratorConfig:
oneOf:
- $ref: '#/components/schemas/DefaultRAGQueryGeneratorConfig'

9
llama_stack/apis/tools/rag_tool.py
View file

@ -67,6 +67,15 @@ register_schema(RAGQueryGeneratorConfig, name="RAGQueryGeneratorConfig")
@json_schema_type
class RAGQueryConfig(BaseModel):
"""
Configuration for the RAG query generation.
:param query_generator_config: Configuration for the query generator.
:param max_tokens_in_context: Maximum number of tokens in the context.
:param max_chunks: Maximum number of chunks to retrieve.
:param chunk_template: Template for formatting each retrieved chunk in the context.
"""
# This config defines how a query is generated using the messages
# for memory bank retrieval.
query_generator_config: RAGQueryGeneratorConfig = Field(default=DefaultRAGQueryGeneratorConfig())