phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-11 19:56:03 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

removing APIs

Browse source 
Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
This commit is contained in:
Francisco Javier Arceo 2025-10-27 23:03:07 -04:00
parent e97a48d1d0
commit 2dd0557048
6 changed files with 1 additions and 1843 deletions
Download patch file Download diff file Expand all files Collapse all files

331
client-sdks/stainless/openapi.yml
View file

@ -1869,69 +1869,6 @@ paths:
$ref: '#/components/schemas/SyntheticDataGenerateRequest'
required: true
deprecated: false
/v1/tool-runtime/file_search-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/file_search-tool/query:
post:
responses:
'200':
description: >-
FileSearchResult containing the retrieved content and metadata
content:
application/json:
schema:
$ref: '#/components/schemas/FileSearchResult'
'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/tool-runtime/invoke:
post:
responses:
@ -9698,274 +9635,6 @@ components:
description: >-
Response from the synthetic data generation. Batch of (prompt, response, score)
tuples that pass the threshold.
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_db_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_db_id
- chunk_size_in_tokens
title: InsertRequest
DefaultFileSearchGeneratorConfig:
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: DefaultFileSearchGeneratorConfig
description: >-
Configuration for the default RAG query generator.
FileSearchConfig:
type: object
properties:
query_generator_config:
oneOf:
- $ref: '#/components/schemas/DefaultFileSearchGeneratorConfig'
- $ref: '#/components/schemas/LLMFileSearchGeneratorConfig'
discriminator:
propertyName: type
mapping:
default: '#/components/schemas/DefaultFileSearchGeneratorConfig'
llm: '#/components/schemas/LLMFileSearchGeneratorConfig'
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/FileSearchMode'
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: FileSearchConfig
description: >-
Configuration for the RAG query generation.
FileSearchMode:
type: string
enum:
- vector
- keyword
- hybrid
title: FileSearchMode
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
LLMFileSearchGeneratorConfig:
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: LLMFileSearchGeneratorConfig
description: >-
Configuration for the LLM-based File Search generator.
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_db_ids:
type: array
items:
type: string
description: >-
List of vector database IDs to search within
query_config:
$ref: '#/components/schemas/FileSearchConfig'
description: >-
(Optional) Configuration parameters for the query operation
additionalProperties: false
required:
- content
- vector_db_ids
title: QueryRequest
FileSearchResult:
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: FileSearchResult
description: >-
Result of a RAG query containing retrieved content and metadata.
InvokeToolRequest:
type: object
properties:

423
docs/static/llama-stack-spec.html vendored
View file

@ -2492,89 +2492,6 @@
"deprecated": false
}
},
"/v1/tool-runtime/file_search-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": {
"$ref": "#/components/schemas/InsertRequest"
}
}
},
"required": true
},
"deprecated": false
}
},
"/v1/tool-runtime/file_search-tool/query": {
"post": {
"responses": {
"200": {
"description": "FileSearchResult containing the retrieved content and metadata",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/FileSearchResult"
}
}
}
},
"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": {
"$ref": "#/components/schemas/QueryRequest"
}
}
},
"required": true
},
"deprecated": false
}
},
"/v1/tool-runtime/invoke": {
"post": {
"responses": {
@ -11144,346 +11061,6 @@
"title": "SyntheticDataGenerationResponse",
"description": "Response from the synthetic data generation. Batch of (prompt, response, score) tuples that pass the threshold."
},
"RAGDocument": {
"type": "object",
"properties": {
"document_id": {
"type": "string",
"description": "The unique identifier for the document."
},
"content": {
"oneOf": [
{
"type": "string"
},
{
"$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": {
"$ref": "#/components/schemas/RAGDocument"
},
"description": "List of documents to index in the RAG system"
},
"vector_db_id": {
"type": "string",
"description": "ID of the vector database to store the document embeddings"
},
"chunk_size_in_tokens": {
"type": "integer",
"description": "(Optional) Size in tokens for document chunking during indexing"
}
},
"additionalProperties": false,
"required": [
"documents",
"vector_db_id",
"chunk_size_in_tokens"
],
"title": "InsertRequest"
},
"DefaultFileSearchGeneratorConfig": {
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "default",
"default": "default",
"description": "Type of query generator, always 'default'"
},
"separator": {
"type": "string",
"default": " ",
"description": "String separator used to join query terms"
}
},
"additionalProperties": false,
"required": [
"type",
"separator"
],
"title": "DefaultFileSearchGeneratorConfig",
"description": "Configuration for the default RAG query generator."
},
"FileSearchConfig": {
"type": "object",
"properties": {
"query_generator_config": {
"oneOf": [
{
"$ref": "#/components/schemas/DefaultFileSearchGeneratorConfig"
},
{
"$ref": "#/components/schemas/LLMFileSearchGeneratorConfig"
}
],
"discriminator": {
"propertyName": "type",
"mapping": {
"default": "#/components/schemas/DefaultFileSearchGeneratorConfig",
"llm": "#/components/schemas/LLMFileSearchGeneratorConfig"
}
},
"description": "Configuration for the query generator."
},
"max_tokens_in_context": {
"type": "integer",
"default": 4096,
"description": "Maximum number of tokens in the context."
},
"max_chunks": {
"type": "integer",
"default": 5,
"description": "Maximum number of chunks to retrieve."
},
"chunk_template": {
"type": "string",
"default": "Result {index}\nContent: {chunk.content}\nMetadata: {metadata}\n",
"description": "Template for formatting each retrieved chunk in the context. Available placeholders: {index} (1-based chunk ordinal), {chunk.content} (chunk content string), {metadata} (chunk metadata dict). Default: \"Result {index}\\nContent: {chunk.content}\\nMetadata: {metadata}\\n\""
},
"mode": {
"$ref": "#/components/schemas/FileSearchMode",
"default": "vector",
"description": "Search mode for retrieval—either \"vector\", \"keyword\", or \"hybrid\". Default \"vector\"."
},
"ranker": {
"$ref": "#/components/schemas/Ranker",
"description": "Configuration for the ranker to use in hybrid search. Defaults to RRF ranker."
}
},
"additionalProperties": false,
"required": [
"query_generator_config",
"max_tokens_in_context",
"max_chunks",
"chunk_template"
],
"title": "FileSearchConfig",
"description": "Configuration for the RAG query generation."
},
"FileSearchMode": {
"type": "string",
"enum": [
"vector",
"keyword",
"hybrid"
],
"title": "FileSearchMode",
"description": "Search modes for RAG query retrieval: - VECTOR: Uses vector similarity search for semantic matching - KEYWORD: Uses keyword-based search for exact matching - HYBRID: Combines both vector and keyword search for better results"
},
"LLMFileSearchGeneratorConfig": {
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "llm",
"default": "llm",
"description": "Type of query generator, always 'llm'"
},
"model": {
"type": "string",
"description": "Name of the language model to use for query generation"
},
"template": {
"type": "string",
"description": "Template string for formatting the query generation prompt"
}
},
"additionalProperties": false,
"required": [
"type",
"model",
"template"
],
"title": "LLMFileSearchGeneratorConfig",
"description": "Configuration for the LLM-based File Search generator."
},
"RRFRanker": {
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "rrf",
"default": "rrf",
"description": "The type of ranker, always \"rrf\""
},
"impact_factor": {
"type": "number",
"default": 60.0,
"description": "The impact factor for RRF scoring. Higher values give more weight to higher-ranked results. Must be greater than 0"
}
},
"additionalProperties": false,
"required": [
"type",
"impact_factor"
],
"title": "RRFRanker",
"description": "Reciprocal Rank Fusion (RRF) ranker configuration."
},
"Ranker": {
"oneOf": [
{
"$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_db_ids": {
"type": "array",
"items": {
"type": "string"
},
"description": "List of vector database IDs to search within"
},
"query_config": {
"$ref": "#/components/schemas/FileSearchConfig",
"description": "(Optional) Configuration parameters for the query operation"
}
},
"additionalProperties": false,
"required": [
"content",
"vector_db_ids"
],
"title": "QueryRequest"
},
"FileSearchResult": {
"type": "object",
"properties": {
"content": {
"$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": "FileSearchResult",
"description": "Result of a RAG query containing retrieved content and metadata."
},
"InvokeToolRequest": {
"type": "object",
"properties": {

331
docs/static/llama-stack-spec.yaml vendored
View file

@ -1866,69 +1866,6 @@ paths:
$ref: '#/components/schemas/SyntheticDataGenerateRequest'
required: true
deprecated: false
/v1/tool-runtime/file_search-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/file_search-tool/query:
post:
responses:
'200':
description: >-
FileSearchResult containing the retrieved content and metadata
content:
application/json:
schema:
$ref: '#/components/schemas/FileSearchResult'
'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/tool-runtime/invoke:
post:
responses:
@ -8485,274 +8422,6 @@ components:
description: >-
Response from the synthetic data generation. Batch of (prompt, response, score)
tuples that pass the threshold.
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_db_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_db_id
- chunk_size_in_tokens
title: InsertRequest
DefaultFileSearchGeneratorConfig:
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: DefaultFileSearchGeneratorConfig
description: >-
Configuration for the default RAG query generator.
FileSearchConfig:
type: object
properties:
query_generator_config:
oneOf:
- $ref: '#/components/schemas/DefaultFileSearchGeneratorConfig'
- $ref: '#/components/schemas/LLMFileSearchGeneratorConfig'
discriminator:
propertyName: type
mapping:
default: '#/components/schemas/DefaultFileSearchGeneratorConfig'
llm: '#/components/schemas/LLMFileSearchGeneratorConfig'
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/FileSearchMode'
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: FileSearchConfig
description: >-
Configuration for the RAG query generation.
FileSearchMode:
type: string
enum:
- vector
- keyword
- hybrid
title: FileSearchMode
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
LLMFileSearchGeneratorConfig:
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: LLMFileSearchGeneratorConfig
description: >-
Configuration for the LLM-based File Search generator.
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_db_ids:
type: array
items:
type: string
description: >-
List of vector database IDs to search within
query_config:
$ref: '#/components/schemas/FileSearchConfig'
description: >-
(Optional) Configuration parameters for the query operation
additionalProperties: false
required:
- content
- vector_db_ids
title: QueryRequest
FileSearchResult:
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: FileSearchResult
description: >-
Result of a RAG query containing retrieved content and metadata.
InvokeToolRequest:
type: object
properties:

423
docs/static/stainless-llama-stack-spec.html vendored
View file

@ -2492,89 +2492,6 @@
"deprecated": false
}
},
"/v1/tool-runtime/file_search-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": {
"$ref": "#/components/schemas/InsertRequest"
}
}
},
"required": true
},
"deprecated": false
}
},
"/v1/tool-runtime/file_search-tool/query": {
"post": {
"responses": {
"200": {
"description": "FileSearchResult containing the retrieved content and metadata",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/FileSearchResult"
}
}
}
},
"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": {
"$ref": "#/components/schemas/QueryRequest"
}
}
},
"required": true
},
"deprecated": false
}
},
"/v1/tool-runtime/invoke": {
"post": {
"responses": {
@ -12816,346 +12733,6 @@
"title": "SyntheticDataGenerationResponse",
"description": "Response from the synthetic data generation. Batch of (prompt, response, score) tuples that pass the threshold."
},
"RAGDocument": {
"type": "object",
"properties": {
"document_id": {
"type": "string",
"description": "The unique identifier for the document."
},
"content": {
"oneOf": [
{
"type": "string"
},
{
"$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": {
"$ref": "#/components/schemas/RAGDocument"
},
"description": "List of documents to index in the RAG system"
},
"vector_db_id": {
"type": "string",
"description": "ID of the vector database to store the document embeddings"
},
"chunk_size_in_tokens": {
"type": "integer",
"description": "(Optional) Size in tokens for document chunking during indexing"
}
},
"additionalProperties": false,
"required": [
"documents",
"vector_db_id",
"chunk_size_in_tokens"
],
"title": "InsertRequest"
},
"DefaultFileSearchGeneratorConfig": {
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "default",
"default": "default",
"description": "Type of query generator, always 'default'"
},
"separator": {
"type": "string",
"default": " ",
"description": "String separator used to join query terms"
}
},
"additionalProperties": false,
"required": [
"type",
"separator"
],
"title": "DefaultFileSearchGeneratorConfig",
"description": "Configuration for the default RAG query generator."
},
"FileSearchConfig": {
"type": "object",
"properties": {
"query_generator_config": {
"oneOf": [
{
"$ref": "#/components/schemas/DefaultFileSearchGeneratorConfig"
},
{
"$ref": "#/components/schemas/LLMFileSearchGeneratorConfig"
}
],
"discriminator": {
"propertyName": "type",
"mapping": {
"default": "#/components/schemas/DefaultFileSearchGeneratorConfig",
"llm": "#/components/schemas/LLMFileSearchGeneratorConfig"
}
},
"description": "Configuration for the query generator."
},
"max_tokens_in_context": {
"type": "integer",
"default": 4096,
"description": "Maximum number of tokens in the context."
},
"max_chunks": {
"type": "integer",
"default": 5,
"description": "Maximum number of chunks to retrieve."
},
"chunk_template": {
"type": "string",
"default": "Result {index}\nContent: {chunk.content}\nMetadata: {metadata}\n",
"description": "Template for formatting each retrieved chunk in the context. Available placeholders: {index} (1-based chunk ordinal), {chunk.content} (chunk content string), {metadata} (chunk metadata dict). Default: \"Result {index}\\nContent: {chunk.content}\\nMetadata: {metadata}\\n\""
},
"mode": {
"$ref": "#/components/schemas/FileSearchMode",
"default": "vector",
"description": "Search mode for retrieval—either \"vector\", \"keyword\", or \"hybrid\". Default \"vector\"."
},
"ranker": {
"$ref": "#/components/schemas/Ranker",
"description": "Configuration for the ranker to use in hybrid search. Defaults to RRF ranker."
}
},
"additionalProperties": false,
"required": [
"query_generator_config",
"max_tokens_in_context",
"max_chunks",
"chunk_template"
],
"title": "FileSearchConfig",
"description": "Configuration for the RAG query generation."
},
"FileSearchMode": {
"type": "string",
"enum": [
"vector",
"keyword",
"hybrid"
],
"title": "FileSearchMode",
"description": "Search modes for RAG query retrieval: - VECTOR: Uses vector similarity search for semantic matching - KEYWORD: Uses keyword-based search for exact matching - HYBRID: Combines both vector and keyword search for better results"
},
"LLMFileSearchGeneratorConfig": {
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "llm",
"default": "llm",
"description": "Type of query generator, always 'llm'"
},
"model": {
"type": "string",
"description": "Name of the language model to use for query generation"
},
"template": {
"type": "string",
"description": "Template string for formatting the query generation prompt"
}
},
"additionalProperties": false,
"required": [
"type",
"model",
"template"
],
"title": "LLMFileSearchGeneratorConfig",
"description": "Configuration for the LLM-based File Search generator."
},
"RRFRanker": {
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "rrf",
"default": "rrf",
"description": "The type of ranker, always \"rrf\""
},
"impact_factor": {
"type": "number",
"default": 60.0,
"description": "The impact factor for RRF scoring. Higher values give more weight to higher-ranked results. Must be greater than 0"
}
},
"additionalProperties": false,
"required": [
"type",
"impact_factor"
],
"title": "RRFRanker",
"description": "Reciprocal Rank Fusion (RRF) ranker configuration."
},
"Ranker": {
"oneOf": [
{
"$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_db_ids": {
"type": "array",
"items": {
"type": "string"
},
"description": "List of vector database IDs to search within"
},
"query_config": {
"$ref": "#/components/schemas/FileSearchConfig",
"description": "(Optional) Configuration parameters for the query operation"
}
},
"additionalProperties": false,
"required": [
"content",
"vector_db_ids"
],
"title": "QueryRequest"
},
"FileSearchResult": {
"type": "object",
"properties": {
"content": {
"$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": "FileSearchResult",
"description": "Result of a RAG query containing retrieved content and metadata."
},
"InvokeToolRequest": {
"type": "object",
"properties": {

331
docs/static/stainless-llama-stack-spec.yaml vendored
View file

@ -1869,69 +1869,6 @@ paths:
$ref: '#/components/schemas/SyntheticDataGenerateRequest'
required: true
deprecated: false
/v1/tool-runtime/file_search-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/file_search-tool/query:
post:
responses:
'200':
description: >-
FileSearchResult containing the retrieved content and metadata
content:
application/json:
schema:
$ref: '#/components/schemas/FileSearchResult'
'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/tool-runtime/invoke:
post:
responses:
@ -9698,274 +9635,6 @@ components:
description: >-
Response from the synthetic data generation. Batch of (prompt, response, score)
tuples that pass the threshold.
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_db_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_db_id
- chunk_size_in_tokens
title: InsertRequest
DefaultFileSearchGeneratorConfig:
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: DefaultFileSearchGeneratorConfig
description: >-
Configuration for the default RAG query generator.
FileSearchConfig:
type: object
properties:
query_generator_config:
oneOf:
- $ref: '#/components/schemas/DefaultFileSearchGeneratorConfig'
- $ref: '#/components/schemas/LLMFileSearchGeneratorConfig'
discriminator:
propertyName: type
mapping:
default: '#/components/schemas/DefaultFileSearchGeneratorConfig'
llm: '#/components/schemas/LLMFileSearchGeneratorConfig'
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/FileSearchMode'
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: FileSearchConfig
description: >-
Configuration for the RAG query generation.
FileSearchMode:
type: string
enum:
- vector
- keyword
- hybrid
title: FileSearchMode
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
LLMFileSearchGeneratorConfig:
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: LLMFileSearchGeneratorConfig
description: >-
Configuration for the LLM-based File Search generator.
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_db_ids:
type: array
items:
type: string
description: >-
List of vector database IDs to search within
query_config:
$ref: '#/components/schemas/FileSearchConfig'
description: >-
(Optional) Configuration parameters for the query operation
additionalProperties: false
required:
- content
- vector_db_ids
title: QueryRequest
FileSearchResult:
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: FileSearchResult
description: >-
Result of a RAG query containing retrieved content and metadata.
InvokeToolRequest:
type: object
properties:

5
llama_stack/apis/tools/file_search_tool.py
View file

@ -11,9 +11,8 @@ from pydantic import BaseModel, Field, field_validator
from typing_extensions import runtime_checkable
from llama_stack.apis.common.content_types import URL, InterleavedContent
from llama_stack.apis.version import LLAMA_STACK_API_V1
from llama_stack.core.telemetry.trace_protocol import trace_protocol
from llama_stack.schema_utils import json_schema_type, register_schema, webmethod
from llama_stack.schema_utils import json_schema_type, register_schema
@json_schema_type
@ -186,7 +185,6 @@ class FileSearchConfig(BaseModel):
@runtime_checkable
@trace_protocol
class FileSearchToolRuntime(Protocol):
@webmethod(route="/tool-runtime/file_search-tool/insert", method="POST", level=LLAMA_STACK_API_V1)
async def insert(
self,
documents: list[RAGDocument],
@ -201,7 +199,6 @@ class FileSearchToolRuntime(Protocol):
"""
...
@webmethod(route="/tool-runtime/file_search-tool/query", method="POST", level=LLAMA_STACK_API_V1)
async def query(
self,
content: InterleavedContent,