mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-27 18:50:41 +00:00
feat: add input validation for search mode of rag query
This commit is contained in:
parent
dbdc811d16
commit
7f43bc6d76
3 changed files with 40 additions and 3 deletions
13
docs/_static/llama-stack-spec.html
vendored
13
docs/_static/llama-stack-spec.html
vendored
|
@ -14676,7 +14676,8 @@
|
|||
"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": {
|
||||
"type": "string",
|
||||
"$ref": "#/components/schemas/RAGSearchMode",
|
||||
"default": "vector",
|
||||
"description": "Search mode for retrieval—either \"vector\", \"keyword\", or \"hybrid\". Default \"vector\"."
|
||||
},
|
||||
"ranker": {
|
||||
|
@ -14711,6 +14712,16 @@
|
|||
}
|
||||
}
|
||||
},
|
||||
"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": {
|
||||
|
|
14
docs/_static/llama-stack-spec.yaml
vendored
14
docs/_static/llama-stack-spec.yaml
vendored
|
@ -10260,7 +10260,8 @@ components:
|
|||
content string), {metadata} (chunk metadata dict). Default: "Result {index}\nContent:
|
||||
{chunk.content}\nMetadata: {metadata}\n"
|
||||
mode:
|
||||
type: string
|
||||
$ref: '#/components/schemas/RAGSearchMode'
|
||||
default: vector
|
||||
description: >-
|
||||
Search mode for retrieval—either "vector", "keyword", or "hybrid". Default
|
||||
"vector".
|
||||
|
@ -10287,6 +10288,17 @@ components:
|
|||
mapping:
|
||||
default: '#/components/schemas/DefaultRAGQueryGeneratorConfig'
|
||||
llm: '#/components/schemas/LLMRAGQueryGeneratorConfig'
|
||||
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:
|
||||
|
|
|
@ -87,6 +87,20 @@ class RAGQueryGenerator(Enum):
|
|||
custom = "custom"
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class RAGSearchMode(Enum):
|
||||
"""
|
||||
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
|
||||
"""
|
||||
|
||||
VECTOR = "vector"
|
||||
KEYWORD = "keyword"
|
||||
HYBRID = "hybrid"
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class DefaultRAGQueryGeneratorConfig(BaseModel):
|
||||
type: Literal["default"] = "default"
|
||||
|
@ -128,7 +142,7 @@ class RAGQueryConfig(BaseModel):
|
|||
max_tokens_in_context: int = 4096
|
||||
max_chunks: int = 5
|
||||
chunk_template: str = "Result {index}\nContent: {chunk.content}\nMetadata: {metadata}\n"
|
||||
mode: str | None = None
|
||||
mode: RAGSearchMode | None = RAGSearchMode.VECTOR
|
||||
ranker: Ranker | None = Field(default=None) # Only used for hybrid mode
|
||||
|
||||
@field_validator("chunk_template")
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue