mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-07-18 10:52:28 +00:00
Merge branch 'main' into suffic
This commit is contained in:
Hardik Shah
GitHub
commit
2edb9eb7e0
37 changed files with 2105 additions and 63 deletions
446
docs/_static/llama-stack-spec.html
vendored
446
docs/_static/llama-stack-spec.html
vendored
|
|
@ -3240,6 +3240,59 @@
|
|||
}
|
||||
}
|
||||
},
|
||||
"/v1/openai/v1/vector_stores/{vector_store_id}/files": {
|
||||
"post": {
|
||||
"responses": {
|
||||
"200": {
|
||||
"description": "A VectorStoreFileObject representing the attached file.",
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/VectorStoreFileObject"
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"400": {
|
||||
"$ref": "#/components/responses/BadRequest400"
|
||||
},
|
||||
"429": {
|
||||
"$ref": "#/components/responses/TooManyRequests429"
|
||||
},
|
||||
"500": {
|
||||
"$ref": "#/components/responses/InternalServerError500"
|
||||
},
|
||||
"default": {
|
||||
"$ref": "#/components/responses/DefaultError"
|
||||
}
|
||||
},
|
||||
"tags": [
|
||||
"VectorIO"
|
||||
],
|
||||
"description": "Attach a file to a vector store.",
|
||||
"parameters": [
|
||||
{
|
||||
"name": "vector_store_id",
|
||||
"in": "path",
|
||||
"description": "The ID of the vector store to attach the file to.",
|
||||
"required": true,
|
||||
"schema": {
|
||||
"type": "string"
|
||||
}
|
||||
}
|
||||
],
|
||||
"requestBody": {
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/OpenaiAttachFileToVectorStoreRequest"
|
||||
}
|
||||
}
|
||||
},
|
||||
"required": true
|
||||
}
|
||||
}
|
||||
},
|
||||
"/v1/openai/v1/completions": {
|
||||
"post": {
|
||||
"responses": {
|
||||
|
|
@ -7047,6 +7100,9 @@
|
|||
{
|
||||
"$ref": "#/components/schemas/OpenAIResponseOutputMessageWebSearchToolCall"
|
||||
},
|
||||
{
|
||||
"$ref": "#/components/schemas/OpenAIResponseOutputMessageFileSearchToolCall"
|
||||
},
|
||||
{
|
||||
"$ref": "#/components/schemas/OpenAIResponseOutputMessageFunctionToolCall"
|
||||
},
|
||||
|
|
@ -7193,12 +7249,41 @@
|
|||
"const": "file_search",
|
||||
"default": "file_search"
|
||||
},
|
||||
"vector_store_id": {
|
||||
"vector_store_ids": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
"filters": {
|
||||
"type": "object",
|
||||
"additionalProperties": {
|
||||
"oneOf": [
|
||||
{
|
||||
"type": "null"
|
||||
},
|
||||
{
|
||||
"type": "boolean"
|
||||
},
|
||||
{
|
||||
"type": "number"
|
||||
},
|
||||
{
|
||||
"type": "string"
|
||||
},
|
||||
{
|
||||
"type": "array"
|
||||
},
|
||||
{
|
||||
"type": "object"
|
||||
}
|
||||
]
|
||||
}
|
||||
},
|
||||
"max_num_results": {
|
||||
"type": "integer",
|
||||
"default": 10
|
||||
},
|
||||
"ranking_options": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
|
|
@ -7217,7 +7302,7 @@
|
|||
"additionalProperties": false,
|
||||
"required": [
|
||||
"type",
|
||||
"vector_store_id"
|
||||
"vector_store_ids"
|
||||
],
|
||||
"title": "OpenAIResponseInputToolFileSearch"
|
||||
},
|
||||
|
|
@ -7484,6 +7569,64 @@
|
|||
],
|
||||
"title": "OpenAIResponseOutputMessageContentOutputText"
|
||||
},
|
||||
"OpenAIResponseOutputMessageFileSearchToolCall": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"id": {
|
||||
"type": "string"
|
||||
},
|
||||
"queries": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
"status": {
|
||||
"type": "string"
|
||||
},
|
||||
"type": {
|
||||
"type": "string",
|
||||
"const": "file_search_call",
|
||||
"default": "file_search_call"
|
||||
},
|
||||
"results": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "object",
|
||||
"additionalProperties": {
|
||||
"oneOf": [
|
||||
{
|
||||
"type": "null"
|
||||
},
|
||||
{
|
||||
"type": "boolean"
|
||||
},
|
||||
{
|
||||
"type": "number"
|
||||
},
|
||||
{
|
||||
"type": "string"
|
||||
},
|
||||
{
|
||||
"type": "array"
|
||||
},
|
||||
{
|
||||
"type": "object"
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"id",
|
||||
"queries",
|
||||
"status",
|
||||
"type"
|
||||
],
|
||||
"title": "OpenAIResponseOutputMessageFileSearchToolCall"
|
||||
},
|
||||
"OpenAIResponseOutputMessageFunctionToolCall": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
|
|
@ -7760,6 +7903,9 @@
|
|||
{
|
||||
"$ref": "#/components/schemas/OpenAIResponseOutputMessageWebSearchToolCall"
|
||||
},
|
||||
{
|
||||
"$ref": "#/components/schemas/OpenAIResponseOutputMessageFileSearchToolCall"
|
||||
},
|
||||
{
|
||||
"$ref": "#/components/schemas/OpenAIResponseOutputMessageFunctionToolCall"
|
||||
},
|
||||
|
|
@ -7775,6 +7921,7 @@
|
|||
"mapping": {
|
||||
"message": "#/components/schemas/OpenAIResponseMessage",
|
||||
"web_search_call": "#/components/schemas/OpenAIResponseOutputMessageWebSearchToolCall",
|
||||
"file_search_call": "#/components/schemas/OpenAIResponseOutputMessageFileSearchToolCall",
|
||||
"function_call": "#/components/schemas/OpenAIResponseOutputMessageFunctionToolCall",
|
||||
"mcp_call": "#/components/schemas/OpenAIResponseOutputMessageMCPCall",
|
||||
"mcp_list_tools": "#/components/schemas/OpenAIResponseOutputMessageMCPListTools"
|
||||
|
|
@ -11766,6 +11913,232 @@
|
|||
],
|
||||
"title": "LogEventRequest"
|
||||
},
|
||||
"VectorStoreChunkingStrategy": {
|
||||
"oneOf": [
|
||||
{
|
||||
"$ref": "#/components/schemas/VectorStoreChunkingStrategyAuto"
|
||||
},
|
||||
{
|
||||
"$ref": "#/components/schemas/VectorStoreChunkingStrategyStatic"
|
||||
}
|
||||
],
|
||||
"discriminator": {
|
||||
"propertyName": "type",
|
||||
"mapping": {
|
||||
"auto": "#/components/schemas/VectorStoreChunkingStrategyAuto",
|
||||
"static": "#/components/schemas/VectorStoreChunkingStrategyStatic"
|
||||
}
|
||||
}
|
||||
},
|
||||
"VectorStoreChunkingStrategyAuto": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"type": {
|
||||
"type": "string",
|
||||
"const": "auto",
|
||||
"default": "auto"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"type"
|
||||
],
|
||||
"title": "VectorStoreChunkingStrategyAuto"
|
||||
},
|
||||
"VectorStoreChunkingStrategyStatic": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"type": {
|
||||
"type": "string",
|
||||
"const": "static",
|
||||
"default": "static"
|
||||
},
|
||||
"static": {
|
||||
"$ref": "#/components/schemas/VectorStoreChunkingStrategyStaticConfig"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"type",
|
||||
"static"
|
||||
],
|
||||
"title": "VectorStoreChunkingStrategyStatic"
|
||||
},
|
||||
"VectorStoreChunkingStrategyStaticConfig": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"chunk_overlap_tokens": {
|
||||
"type": "integer",
|
||||
"default": 400
|
||||
},
|
||||
"max_chunk_size_tokens": {
|
||||
"type": "integer",
|
||||
"default": 800
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"chunk_overlap_tokens",
|
||||
"max_chunk_size_tokens"
|
||||
],
|
||||
"title": "VectorStoreChunkingStrategyStaticConfig"
|
||||
},
|
||||
"OpenaiAttachFileToVectorStoreRequest": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"file_id": {
|
||||
"type": "string",
|
||||
"description": "The ID of the file to attach to the vector store."
|
||||
},
|
||||
"attributes": {
|
||||
"type": "object",
|
||||
"additionalProperties": {
|
||||
"oneOf": [
|
||||
{
|
||||
"type": "null"
|
||||
},
|
||||
{
|
||||
"type": "boolean"
|
||||
},
|
||||
{
|
||||
"type": "number"
|
||||
},
|
||||
{
|
||||
"type": "string"
|
||||
},
|
||||
{
|
||||
"type": "array"
|
||||
},
|
||||
{
|
||||
"type": "object"
|
||||
}
|
||||
]
|
||||
},
|
||||
"description": "The key-value attributes stored with the file, which can be used for filtering."
|
||||
},
|
||||
"chunking_strategy": {
|
||||
"$ref": "#/components/schemas/VectorStoreChunkingStrategy",
|
||||
"description": "The chunking strategy to use for the file."
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"file_id"
|
||||
],
|
||||
"title": "OpenaiAttachFileToVectorStoreRequest"
|
||||
},
|
||||
"VectorStoreFileLastError": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"code": {
|
||||
"oneOf": [
|
||||
{
|
||||
"type": "string",
|
||||
"const": "server_error"
|
||||
},
|
||||
{
|
||||
"type": "string",
|
||||
"const": "rate_limit_exceeded"
|
||||
}
|
||||
]
|
||||
},
|
||||
"message": {
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"code",
|
||||
"message"
|
||||
],
|
||||
"title": "VectorStoreFileLastError"
|
||||
},
|
||||
"VectorStoreFileObject": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"id": {
|
||||
"type": "string"
|
||||
},
|
||||
"object": {
|
||||
"type": "string",
|
||||
"default": "vector_store.file"
|
||||
},
|
||||
"attributes": {
|
||||
"type": "object",
|
||||
"additionalProperties": {
|
||||
"oneOf": [
|
||||
{
|
||||
"type": "null"
|
||||
},
|
||||
{
|
||||
"type": "boolean"
|
||||
},
|
||||
{
|
||||
"type": "number"
|
||||
},
|
||||
{
|
||||
"type": "string"
|
||||
},
|
||||
{
|
||||
"type": "array"
|
||||
},
|
||||
{
|
||||
"type": "object"
|
||||
}
|
||||
]
|
||||
}
|
||||
},
|
||||
"chunking_strategy": {
|
||||
"$ref": "#/components/schemas/VectorStoreChunkingStrategy"
|
||||
},
|
||||
"created_at": {
|
||||
"type": "integer"
|
||||
},
|
||||
"last_error": {
|
||||
"$ref": "#/components/schemas/VectorStoreFileLastError"
|
||||
},
|
||||
"status": {
|
||||
"oneOf": [
|
||||
{
|
||||
"type": "string",
|
||||
"const": "completed"
|
||||
},
|
||||
{
|
||||
"type": "string",
|
||||
"const": "in_progress"
|
||||
},
|
||||
{
|
||||
"type": "string",
|
||||
"const": "cancelled"
|
||||
},
|
||||
{
|
||||
"type": "string",
|
||||
"const": "failed"
|
||||
}
|
||||
]
|
||||
},
|
||||
"usage_bytes": {
|
||||
"type": "integer",
|
||||
"default": 0
|
||||
},
|
||||
"vector_store_id": {
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"id",
|
||||
"object",
|
||||
"attributes",
|
||||
"chunking_strategy",
|
||||
"created_at",
|
||||
"status",
|
||||
"usage_bytes",
|
||||
"vector_store_id"
|
||||
],
|
||||
"title": "VectorStoreFileObject",
|
||||
"description": "OpenAI Vector Store File object."
|
||||
},
|
||||
"OpenAIJSONSchema": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
|
|
@ -13625,7 +13998,11 @@
|
|||
},
|
||||
"mode": {
|
||||
"type": "string",
|
||||
"description": "Search mode for retrieval—either \"vector\" or \"keyword\". Default \"vector\"."
|
||||
"description": "Search mode for retrieval—either \"vector\", \"keyword\", or \"hybrid\". Default \"vector\"."
|
||||
},
|
||||
"ranker": {
|
||||
"$ref": "#/components/schemas/Ranker",
|
||||
"description": "Configuration for the ranker to use in hybrid search. Defaults to RRF ranker."
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
|
|
@ -13655,6 +14032,69 @@
|
|||
}
|
||||
}
|
||||
},
|
||||
"RRFRanker": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"type": {
|
||||
"type": "string",
|
||||
"const": "rrf",
|
||||
"default": "rrf",
|
||||
"description": "The type of ranker, always \"rrf\""
|
||||
},
|
||||
"impact_factor": {
|
||||
"type": "number",
|
||||
"default": 60.0,
|
||||
"description": "The impact factor for RRF scoring. Higher values give more weight to higher-ranked results. Must be greater than 0. Default of 60 is from the original RRF paper (Cormack et al., 2009)."
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"type",
|
||||
"impact_factor"
|
||||
],
|
||||
"title": "RRFRanker",
|
||||
"description": "Reciprocal Rank Fusion (RRF) ranker configuration."
|
||||
},
|
||||
"Ranker": {
|
||||
"oneOf": [
|
||||
{
|
||||
"$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": {
|
||||
|
|
|
|||
294
docs/_static/llama-stack-spec.yaml
vendored
294
docs/_static/llama-stack-spec.yaml
vendored
|
|
@ -2263,6 +2263,43 @@ paths:
|
|||
schema:
|
||||
$ref: '#/components/schemas/LogEventRequest'
|
||||
required: true
|
||||
/v1/openai/v1/vector_stores/{vector_store_id}/files:
|
||||
post:
|
||||
responses:
|
||||
'200':
|
||||
description: >-
|
||||
A VectorStoreFileObject representing the attached file.
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: '#/components/schemas/VectorStoreFileObject'
|
||||
'400':
|
||||
$ref: '#/components/responses/BadRequest400'
|
||||
'429':
|
||||
$ref: >-
|
||||
#/components/responses/TooManyRequests429
|
||||
'500':
|
||||
$ref: >-
|
||||
#/components/responses/InternalServerError500
|
||||
default:
|
||||
$ref: '#/components/responses/DefaultError'
|
||||
tags:
|
||||
- VectorIO
|
||||
description: Attach a file to a vector store.
|
||||
parameters:
|
||||
- name: vector_store_id
|
||||
in: path
|
||||
description: >-
|
||||
The ID of the vector store to attach the file to.
|
||||
required: true
|
||||
schema:
|
||||
type: string
|
||||
requestBody:
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: '#/components/schemas/OpenaiAttachFileToVectorStoreRequest'
|
||||
required: true
|
||||
/v1/openai/v1/completions:
|
||||
post:
|
||||
responses:
|
||||
|
|
@ -5021,6 +5058,7 @@ components:
|
|||
OpenAIResponseInput:
|
||||
oneOf:
|
||||
- $ref: '#/components/schemas/OpenAIResponseOutputMessageWebSearchToolCall'
|
||||
- $ref: '#/components/schemas/OpenAIResponseOutputMessageFileSearchToolCall'
|
||||
- $ref: '#/components/schemas/OpenAIResponseOutputMessageFunctionToolCall'
|
||||
- $ref: '#/components/schemas/OpenAIResponseInputFunctionToolCallOutput'
|
||||
- $ref: '#/components/schemas/OpenAIResponseMessage'
|
||||
|
|
@ -5115,10 +5153,23 @@ components:
|
|||
type: string
|
||||
const: file_search
|
||||
default: file_search
|
||||
vector_store_id:
|
||||
vector_store_ids:
|
||||
type: array
|
||||
items:
|
||||
type: string
|
||||
filters:
|
||||
type: object
|
||||
additionalProperties:
|
||||
oneOf:
|
||||
- type: 'null'
|
||||
- type: boolean
|
||||
- type: number
|
||||
- type: string
|
||||
- type: array
|
||||
- type: object
|
||||
max_num_results:
|
||||
type: integer
|
||||
default: 10
|
||||
ranking_options:
|
||||
type: object
|
||||
properties:
|
||||
|
|
@ -5132,7 +5183,7 @@ components:
|
|||
additionalProperties: false
|
||||
required:
|
||||
- type
|
||||
- vector_store_id
|
||||
- vector_store_ids
|
||||
title: OpenAIResponseInputToolFileSearch
|
||||
OpenAIResponseInputToolFunction:
|
||||
type: object
|
||||
|
|
@ -5294,6 +5345,41 @@ components:
|
|||
- type
|
||||
title: >-
|
||||
OpenAIResponseOutputMessageContentOutputText
|
||||
"OpenAIResponseOutputMessageFileSearchToolCall":
|
||||
type: object
|
||||
properties:
|
||||
id:
|
||||
type: string
|
||||
queries:
|
||||
type: array
|
||||
items:
|
||||
type: string
|
||||
status:
|
||||
type: string
|
||||
type:
|
||||
type: string
|
||||
const: file_search_call
|
||||
default: file_search_call
|
||||
results:
|
||||
type: array
|
||||
items:
|
||||
type: object
|
||||
additionalProperties:
|
||||
oneOf:
|
||||
- type: 'null'
|
||||
- type: boolean
|
||||
- type: number
|
||||
- type: string
|
||||
- type: array
|
||||
- type: object
|
||||
additionalProperties: false
|
||||
required:
|
||||
- id
|
||||
- queries
|
||||
- status
|
||||
- type
|
||||
title: >-
|
||||
OpenAIResponseOutputMessageFileSearchToolCall
|
||||
"OpenAIResponseOutputMessageFunctionToolCall":
|
||||
type: object
|
||||
properties:
|
||||
|
|
@ -5491,6 +5577,7 @@ components:
|
|||
oneOf:
|
||||
- $ref: '#/components/schemas/OpenAIResponseMessage'
|
||||
- $ref: '#/components/schemas/OpenAIResponseOutputMessageWebSearchToolCall'
|
||||
- $ref: '#/components/schemas/OpenAIResponseOutputMessageFileSearchToolCall'
|
||||
- $ref: '#/components/schemas/OpenAIResponseOutputMessageFunctionToolCall'
|
||||
- $ref: '#/components/schemas/OpenAIResponseOutputMessageMCPCall'
|
||||
- $ref: '#/components/schemas/OpenAIResponseOutputMessageMCPListTools'
|
||||
|
|
@ -5499,6 +5586,7 @@ components:
|
|||
mapping:
|
||||
message: '#/components/schemas/OpenAIResponseMessage'
|
||||
web_search_call: '#/components/schemas/OpenAIResponseOutputMessageWebSearchToolCall'
|
||||
file_search_call: '#/components/schemas/OpenAIResponseOutputMessageFileSearchToolCall'
|
||||
function_call: '#/components/schemas/OpenAIResponseOutputMessageFunctionToolCall'
|
||||
mcp_call: '#/components/schemas/OpenAIResponseOutputMessageMCPCall'
|
||||
mcp_list_tools: '#/components/schemas/OpenAIResponseOutputMessageMCPListTools'
|
||||
|
|
@ -8251,6 +8339,148 @@ components:
|
|||
- event
|
||||
- ttl_seconds
|
||||
title: LogEventRequest
|
||||
VectorStoreChunkingStrategy:
|
||||
oneOf:
|
||||
- $ref: '#/components/schemas/VectorStoreChunkingStrategyAuto'
|
||||
- $ref: '#/components/schemas/VectorStoreChunkingStrategyStatic'
|
||||
discriminator:
|
||||
propertyName: type
|
||||
mapping:
|
||||
auto: '#/components/schemas/VectorStoreChunkingStrategyAuto'
|
||||
static: '#/components/schemas/VectorStoreChunkingStrategyStatic'
|
||||
VectorStoreChunkingStrategyAuto:
|
||||
type: object
|
||||
properties:
|
||||
type:
|
||||
type: string
|
||||
const: auto
|
||||
default: auto
|
||||
additionalProperties: false
|
||||
required:
|
||||
- type
|
||||
title: VectorStoreChunkingStrategyAuto
|
||||
VectorStoreChunkingStrategyStatic:
|
||||
type: object
|
||||
properties:
|
||||
type:
|
||||
type: string
|
||||
const: static
|
||||
default: static
|
||||
static:
|
||||
$ref: '#/components/schemas/VectorStoreChunkingStrategyStaticConfig'
|
||||
additionalProperties: false
|
||||
required:
|
||||
- type
|
||||
- static
|
||||
title: VectorStoreChunkingStrategyStatic
|
||||
VectorStoreChunkingStrategyStaticConfig:
|
||||
type: object
|
||||
properties:
|
||||
chunk_overlap_tokens:
|
||||
type: integer
|
||||
default: 400
|
||||
max_chunk_size_tokens:
|
||||
type: integer
|
||||
default: 800
|
||||
additionalProperties: false
|
||||
required:
|
||||
- chunk_overlap_tokens
|
||||
- max_chunk_size_tokens
|
||||
title: VectorStoreChunkingStrategyStaticConfig
|
||||
OpenaiAttachFileToVectorStoreRequest:
|
||||
type: object
|
||||
properties:
|
||||
file_id:
|
||||
type: string
|
||||
description: >-
|
||||
The ID of the file to attach to the vector store.
|
||||
attributes:
|
||||
type: object
|
||||
additionalProperties:
|
||||
oneOf:
|
||||
- type: 'null'
|
||||
- type: boolean
|
||||
- type: number
|
||||
- type: string
|
||||
- type: array
|
||||
- type: object
|
||||
description: >-
|
||||
The key-value attributes stored with the file, which can be used for filtering.
|
||||
chunking_strategy:
|
||||
$ref: '#/components/schemas/VectorStoreChunkingStrategy'
|
||||
description: >-
|
||||
The chunking strategy to use for the file.
|
||||
additionalProperties: false
|
||||
required:
|
||||
- file_id
|
||||
title: OpenaiAttachFileToVectorStoreRequest
|
||||
VectorStoreFileLastError:
|
||||
type: object
|
||||
properties:
|
||||
code:
|
||||
oneOf:
|
||||
- type: string
|
||||
const: server_error
|
||||
- type: string
|
||||
const: rate_limit_exceeded
|
||||
message:
|
||||
type: string
|
||||
additionalProperties: false
|
||||
required:
|
||||
- code
|
||||
- message
|
||||
title: VectorStoreFileLastError
|
||||
VectorStoreFileObject:
|
||||
type: object
|
||||
properties:
|
||||
id:
|
||||
type: string
|
||||
object:
|
||||
type: string
|
||||
default: vector_store.file
|
||||
attributes:
|
||||
type: object
|
||||
additionalProperties:
|
||||
oneOf:
|
||||
- type: 'null'
|
||||
- type: boolean
|
||||
- type: number
|
||||
- type: string
|
||||
- type: array
|
||||
- type: object
|
||||
chunking_strategy:
|
||||
$ref: '#/components/schemas/VectorStoreChunkingStrategy'
|
||||
created_at:
|
||||
type: integer
|
||||
last_error:
|
||||
$ref: '#/components/schemas/VectorStoreFileLastError'
|
||||
status:
|
||||
oneOf:
|
||||
- type: string
|
||||
const: completed
|
||||
- type: string
|
||||
const: in_progress
|
||||
- type: string
|
||||
const: cancelled
|
||||
- type: string
|
||||
const: failed
|
||||
usage_bytes:
|
||||
type: integer
|
||||
default: 0
|
||||
vector_store_id:
|
||||
type: string
|
||||
additionalProperties: false
|
||||
required:
|
||||
- id
|
||||
- object
|
||||
- attributes
|
||||
- chunking_strategy
|
||||
- created_at
|
||||
- status
|
||||
- usage_bytes
|
||||
- vector_store_id
|
||||
title: VectorStoreFileObject
|
||||
description: OpenAI Vector Store File object.
|
||||
OpenAIJSONSchema:
|
||||
type: object
|
||||
properties:
|
||||
|
|
@ -9530,7 +9760,13 @@ components:
|
|||
mode:
|
||||
type: string
|
||||
description: >-
|
||||
Search mode for retrieval—either "vector" or "keyword". Default "vector".
|
||||
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
|
||||
|
|
@ -9549,6 +9785,58 @@ components:
|
|||
mapping:
|
||||
default: '#/components/schemas/DefaultRAGQueryGeneratorConfig'
|
||||
llm: '#/components/schemas/LLMRAGQueryGeneratorConfig'
|
||||
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. Default of 60 is from the original RRF
|
||||
paper (Cormack et al., 2009).
|
||||
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:
|
||||
|
|
|
|||
|
|
@ -18,6 +18,7 @@ The `llamastack/distribution-ollama` distribution consists of the following prov
|
|||
| agents | `inline::meta-reference` |
|
||||
| datasetio | `remote::huggingface`, `inline::localfs` |
|
||||
| eval | `inline::meta-reference` |
|
||||
| files | `inline::localfs` |
|
||||
| inference | `remote::ollama` |
|
||||
| post_training | `inline::huggingface` |
|
||||
| safety | `inline::llama-guard` |
|
||||
|
|
|
|||
|
|
@ -66,25 +66,126 @@ To use sqlite-vec in your Llama Stack project, follow these steps:
|
|||
2. Configure your Llama Stack project to use SQLite-Vec.
|
||||
3. Start storing and querying vectors.
|
||||
|
||||
## Supported Search Modes
|
||||
The SQLite-vec provider supports three search modes:
|
||||
|
||||
The sqlite-vec provider supports both vector-based and keyword-based (full-text) search modes.
|
||||
|
||||
When using the RAGTool interface, you can specify the desired search behavior via the `mode` parameter in
|
||||
`RAGQueryConfig`. For example:
|
||||
1. **Vector Search** (`mode="vector"`): Performs pure vector similarity search using the embeddings.
|
||||
2. **Keyword Search** (`mode="keyword"`): Performs full-text search using SQLite's FTS5.
|
||||
3. **Hybrid Search** (`mode="hybrid"`): Combines both vector and keyword search for better results. First performs keyword search to get candidate matches, then applies vector similarity search on those candidates.
|
||||
|
||||
Example with hybrid search:
|
||||
```python
|
||||
from llama_stack.apis.tool_runtime.rag import RAGQueryConfig
|
||||
response = await vector_io.query_chunks(
|
||||
vector_db_id="my_db",
|
||||
query="your query here",
|
||||
params={"mode": "hybrid", "max_chunks": 3, "score_threshold": 0.7},
|
||||
)
|
||||
|
||||
query_config = RAGQueryConfig(max_chunks=6, mode="vector")
|
||||
# Using RRF ranker
|
||||
response = await vector_io.query_chunks(
|
||||
vector_db_id="my_db",
|
||||
query="your query here",
|
||||
params={
|
||||
"mode": "hybrid",
|
||||
"max_chunks": 3,
|
||||
"score_threshold": 0.7,
|
||||
"ranker": {"type": "rrf", "impact_factor": 60.0},
|
||||
},
|
||||
)
|
||||
|
||||
results = client.tool_runtime.rag_tool.query(
|
||||
vector_db_ids=[vector_db_id],
|
||||
content="what is torchtune",
|
||||
query_config=query_config,
|
||||
# Using weighted ranker
|
||||
response = await vector_io.query_chunks(
|
||||
vector_db_id="my_db",
|
||||
query="your query here",
|
||||
params={
|
||||
"mode": "hybrid",
|
||||
"max_chunks": 3,
|
||||
"score_threshold": 0.7,
|
||||
"ranker": {"type": "weighted", "alpha": 0.7}, # 70% vector, 30% keyword
|
||||
},
|
||||
)
|
||||
```
|
||||
|
||||
Example with explicit vector search:
|
||||
```python
|
||||
response = await vector_io.query_chunks(
|
||||
vector_db_id="my_db",
|
||||
query="your query here",
|
||||
params={"mode": "vector", "max_chunks": 3, "score_threshold": 0.7},
|
||||
)
|
||||
```
|
||||
|
||||
Example with keyword search:
|
||||
```python
|
||||
response = await vector_io.query_chunks(
|
||||
vector_db_id="my_db",
|
||||
query="your query here",
|
||||
params={"mode": "keyword", "max_chunks": 3, "score_threshold": 0.7},
|
||||
)
|
||||
```
|
||||
|
||||
## Supported Search Modes
|
||||
|
||||
The SQLite vector store supports three search modes:
|
||||
|
||||
1. **Vector Search** (`mode="vector"`): Uses vector similarity to find relevant chunks
|
||||
2. **Keyword Search** (`mode="keyword"`): Uses keyword matching to find relevant chunks
|
||||
3. **Hybrid Search** (`mode="hybrid"`): Combines both vector and keyword scores using a ranker
|
||||
|
||||
### Hybrid Search
|
||||
|
||||
Hybrid search combines the strengths of both vector and keyword search by:
|
||||
- Computing vector similarity scores
|
||||
- Computing keyword match scores
|
||||
- Using a ranker to combine these scores
|
||||
|
||||
Two ranker types are supported:
|
||||
|
||||
1. **RRF (Reciprocal Rank Fusion)**:
|
||||
- Combines ranks from both vector and keyword results
|
||||
- Uses an impact factor (default: 60.0) to control the weight of higher-ranked results
|
||||
- Good for balancing between vector and keyword results
|
||||
- The default impact factor of 60.0 comes from the original RRF paper by Cormack et al. (2009) [^1], which found this value to provide optimal performance across various retrieval tasks
|
||||
|
||||
2. **Weighted**:
|
||||
- Linearly combines normalized vector and keyword scores
|
||||
- Uses an alpha parameter (0-1) to control the blend:
|
||||
- alpha=0: Only use keyword scores
|
||||
- alpha=1: Only use vector scores
|
||||
- alpha=0.5: Equal weight to both (default)
|
||||
|
||||
Example using RAGQueryConfig with different search modes:
|
||||
|
||||
```python
|
||||
from llama_stack.apis.tools import RAGQueryConfig, RRFRanker, WeightedRanker
|
||||
|
||||
# Vector search
|
||||
config = RAGQueryConfig(mode="vector", max_chunks=5)
|
||||
|
||||
# Keyword search
|
||||
config = RAGQueryConfig(mode="keyword", max_chunks=5)
|
||||
|
||||
# Hybrid search with custom RRF ranker
|
||||
config = RAGQueryConfig(
|
||||
mode="hybrid",
|
||||
max_chunks=5,
|
||||
ranker=RRFRanker(impact_factor=50.0), # Custom impact factor
|
||||
)
|
||||
|
||||
# Hybrid search with weighted ranker
|
||||
config = RAGQueryConfig(
|
||||
mode="hybrid",
|
||||
max_chunks=5,
|
||||
ranker=WeightedRanker(alpha=0.7), # 70% vector, 30% keyword
|
||||
)
|
||||
|
||||
# Hybrid search with default RRF ranker
|
||||
config = RAGQueryConfig(
|
||||
mode="hybrid", max_chunks=5
|
||||
) # Will use RRF with impact_factor=60.0
|
||||
```
|
||||
|
||||
Note: The ranker configuration is only used in hybrid mode. For vector or keyword modes, the ranker parameter is ignored.
|
||||
|
||||
## Installation
|
||||
|
||||
You can install SQLite-Vec using pip:
|
||||
|
|
@ -96,3 +197,5 @@ pip install sqlite-vec
|
|||
## Documentation
|
||||
|
||||
See [sqlite-vec's GitHub repo](https://github.com/asg017/sqlite-vec/tree/main) for more details about sqlite-vec in general.
|
||||
|
||||
[^1]: Cormack, G. V., Clarke, C. L., & Buettcher, S. (2009). [Reciprocal rank fusion outperforms condorcet and individual rank learning methods](https://dl.acm.org/doi/10.1145/1571941.1572114). In Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval (pp. 758-759).
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue