mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-03 18:00:36 +00:00
chore(api)!: remove tool_runtime.rag_tool from the API surface
RAG aka file search is implemented via the Responses API by specifying the file-search tool. The backend implementation remains unchanged. This PR merely removes the directly exposed API surface which allowed users to directly perform searches from the client. This facility, while useful in theory, has not really been used as far as we could tell. The API is also quite awkward.
This commit is contained in:
parent
a8a8aa56c0
commit
2a05b14845
10 changed files with 4 additions and 1117 deletions
331
docs/static/llama-stack-spec.yaml
vendored
331
docs/static/llama-stack-spec.yaml
vendored
|
|
@ -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:
|
||||
|
|
@ -8917,274 +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:
|
||||
|
|
|
|||
331
docs/static/stainless-llama-stack-spec.yaml
vendored
331
docs/static/stainless-llama-stack-spec.yaml
vendored
|
|
@ -2055,69 +2055,6 @@ 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:
|
||||
|
|
@ -9633,274 +9570,6 @@ 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:
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue