mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-03 18:00:36 +00:00
Merge branch 'main' into add-mcp-authentication-param
This commit is contained in:
Omar Abdelwahab
GitHub
commit
8632c705aa
1250 changed files with 2278 additions and 343484 deletions
796
docs/static/llama-stack-spec.yaml
vendored
796
docs/static/llama-stack-spec.yaml
vendored
|
|
@ -974,11 +974,11 @@ paths:
|
|||
get:
|
||||
responses:
|
||||
'200':
|
||||
description: A ListModelsResponse.
|
||||
description: A OpenAIListModelsResponse.
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: '#/components/schemas/ListModelsResponse'
|
||||
$ref: '#/components/schemas/OpenAIListModelsResponse'
|
||||
'400':
|
||||
$ref: '#/components/responses/BadRequest400'
|
||||
'429':
|
||||
|
|
@ -991,8 +991,8 @@ paths:
|
|||
$ref: '#/components/responses/DefaultError'
|
||||
tags:
|
||||
- Models
|
||||
summary: List all models.
|
||||
description: List all models.
|
||||
summary: List models using the OpenAI API.
|
||||
description: List models using the OpenAI API.
|
||||
parameters: []
|
||||
deprecated: false
|
||||
post:
|
||||
|
|
@ -1982,40 +1982,6 @@ paths:
|
|||
schema:
|
||||
type: string
|
||||
deprecated: false
|
||||
/v1/synthetic-data-generation/generate:
|
||||
post:
|
||||
responses:
|
||||
'200':
|
||||
description: >-
|
||||
Response containing filtered synthetic data samples and optional statistics
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: '#/components/schemas/SyntheticDataGenerationResponse'
|
||||
'400':
|
||||
$ref: '#/components/responses/BadRequest400'
|
||||
'429':
|
||||
$ref: >-
|
||||
#/components/responses/TooManyRequests429
|
||||
'500':
|
||||
$ref: >-
|
||||
#/components/responses/InternalServerError500
|
||||
default:
|
||||
$ref: '#/components/responses/DefaultError'
|
||||
tags:
|
||||
- SyntheticDataGeneration (Coming Soon)
|
||||
summary: >-
|
||||
Generate synthetic data based on input dialogs and apply filtering.
|
||||
description: >-
|
||||
Generate synthetic data based on input dialogs and apply filtering.
|
||||
parameters: []
|
||||
requestBody:
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: '#/components/schemas/SyntheticDataGenerateRequest'
|
||||
required: true
|
||||
deprecated: false
|
||||
/v1/tool-runtime/invoke:
|
||||
post:
|
||||
responses:
|
||||
|
|
@ -2086,69 +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:
|
||||
|
|
@ -5619,6 +5522,88 @@ components:
|
|||
title: ListRoutesResponse
|
||||
description: >-
|
||||
Response containing a list of all available API routes.
|
||||
OpenAIModel:
|
||||
type: object
|
||||
properties:
|
||||
id:
|
||||
type: string
|
||||
object:
|
||||
type: string
|
||||
const: model
|
||||
default: model
|
||||
created:
|
||||
type: integer
|
||||
owned_by:
|
||||
type: string
|
||||
custom_metadata:
|
||||
type: object
|
||||
additionalProperties:
|
||||
oneOf:
|
||||
- type: 'null'
|
||||
- type: boolean
|
||||
- type: number
|
||||
- type: string
|
||||
- type: array
|
||||
- type: object
|
||||
additionalProperties: false
|
||||
required:
|
||||
- id
|
||||
- object
|
||||
- created
|
||||
- owned_by
|
||||
title: OpenAIModel
|
||||
description: A model from OpenAI.
|
||||
OpenAIListModelsResponse:
|
||||
type: object
|
||||
properties:
|
||||
data:
|
||||
type: array
|
||||
items:
|
||||
$ref: '#/components/schemas/OpenAIModel'
|
||||
additionalProperties: false
|
||||
required:
|
||||
- data
|
||||
title: OpenAIListModelsResponse
|
||||
ModelType:
|
||||
type: string
|
||||
enum:
|
||||
- llm
|
||||
- embedding
|
||||
- rerank
|
||||
title: ModelType
|
||||
description: >-
|
||||
Enumeration of supported model types in Llama Stack.
|
||||
RegisterModelRequest:
|
||||
type: object
|
||||
properties:
|
||||
model_id:
|
||||
type: string
|
||||
description: The identifier of the model to register.
|
||||
provider_model_id:
|
||||
type: string
|
||||
description: >-
|
||||
The identifier of the model in the provider.
|
||||
provider_id:
|
||||
type: string
|
||||
description: The identifier of the provider.
|
||||
metadata:
|
||||
type: object
|
||||
additionalProperties:
|
||||
oneOf:
|
||||
- type: 'null'
|
||||
- type: boolean
|
||||
- type: number
|
||||
- type: string
|
||||
- type: array
|
||||
- type: object
|
||||
description: Any additional metadata for this model.
|
||||
model_type:
|
||||
$ref: '#/components/schemas/ModelType'
|
||||
description: The type of model to register.
|
||||
additionalProperties: false
|
||||
required:
|
||||
- model_id
|
||||
title: RegisterModelRequest
|
||||
Model:
|
||||
type: object
|
||||
properties:
|
||||
|
|
@ -5676,57 +5661,6 @@ components:
|
|||
title: Model
|
||||
description: >-
|
||||
A model resource representing an AI model registered in Llama Stack.
|
||||
ModelType:
|
||||
type: string
|
||||
enum:
|
||||
- llm
|
||||
- embedding
|
||||
- rerank
|
||||
title: ModelType
|
||||
description: >-
|
||||
Enumeration of supported model types in Llama Stack.
|
||||
ListModelsResponse:
|
||||
type: object
|
||||
properties:
|
||||
data:
|
||||
type: array
|
||||
items:
|
||||
$ref: '#/components/schemas/Model'
|
||||
additionalProperties: false
|
||||
required:
|
||||
- data
|
||||
title: ListModelsResponse
|
||||
RegisterModelRequest:
|
||||
type: object
|
||||
properties:
|
||||
model_id:
|
||||
type: string
|
||||
description: The identifier of the model to register.
|
||||
provider_model_id:
|
||||
type: string
|
||||
description: >-
|
||||
The identifier of the model in the provider.
|
||||
provider_id:
|
||||
type: string
|
||||
description: The identifier of the provider.
|
||||
metadata:
|
||||
type: object
|
||||
additionalProperties:
|
||||
oneOf:
|
||||
- type: 'null'
|
||||
- type: boolean
|
||||
- type: number
|
||||
- type: string
|
||||
- type: array
|
||||
- type: object
|
||||
description: Any additional metadata for this model.
|
||||
model_type:
|
||||
$ref: '#/components/schemas/ModelType'
|
||||
description: The type of model to register.
|
||||
additionalProperties: false
|
||||
required:
|
||||
- model_id
|
||||
title: RegisterModelRequest
|
||||
RunModerationRequest:
|
||||
type: object
|
||||
properties:
|
||||
|
|
@ -8144,20 +8078,6 @@ components:
|
|||
- error
|
||||
title: ViolationLevel
|
||||
description: Severity level of a safety violation.
|
||||
AgentTurnInputType:
|
||||
type: object
|
||||
properties:
|
||||
type:
|
||||
type: string
|
||||
const: agent_turn_input
|
||||
default: agent_turn_input
|
||||
description: >-
|
||||
Discriminator type. Always "agent_turn_input"
|
||||
additionalProperties: false
|
||||
required:
|
||||
- type
|
||||
title: AgentTurnInputType
|
||||
description: Parameter type for agent turn input.
|
||||
AggregationFunctionType:
|
||||
type: string
|
||||
enum:
|
||||
|
|
@ -8400,7 +8320,6 @@ components:
|
|||
- $ref: '#/components/schemas/UnionType'
|
||||
- $ref: '#/components/schemas/ChatCompletionInputType'
|
||||
- $ref: '#/components/schemas/CompletionInputType'
|
||||
- $ref: '#/components/schemas/AgentTurnInputType'
|
||||
discriminator:
|
||||
propertyName: type
|
||||
mapping:
|
||||
|
|
@ -8413,7 +8332,6 @@ components:
|
|||
union: '#/components/schemas/UnionType'
|
||||
chat_completion_input: '#/components/schemas/ChatCompletionInputType'
|
||||
completion_input: '#/components/schemas/CompletionInputType'
|
||||
agent_turn_input: '#/components/schemas/AgentTurnInputType'
|
||||
params:
|
||||
$ref: '#/components/schemas/ScoringFnParams'
|
||||
additionalProperties: false
|
||||
|
|
@ -8494,7 +8412,6 @@ components:
|
|||
- $ref: '#/components/schemas/UnionType'
|
||||
- $ref: '#/components/schemas/ChatCompletionInputType'
|
||||
- $ref: '#/components/schemas/CompletionInputType'
|
||||
- $ref: '#/components/schemas/AgentTurnInputType'
|
||||
discriminator:
|
||||
propertyName: type
|
||||
mapping:
|
||||
|
|
@ -8507,7 +8424,6 @@ components:
|
|||
union: '#/components/schemas/UnionType'
|
||||
chat_completion_input: '#/components/schemas/ChatCompletionInputType'
|
||||
completion_input: '#/components/schemas/CompletionInputType'
|
||||
agent_turn_input: '#/components/schemas/AgentTurnInputType'
|
||||
RegisterScoringFunctionRequest:
|
||||
type: object
|
||||
properties:
|
||||
|
|
@ -8744,45 +8660,29 @@ components:
|
|||
required:
|
||||
- shield_id
|
||||
title: RegisterShieldRequest
|
||||
CompletionMessage:
|
||||
InvokeToolRequest:
|
||||
type: object
|
||||
properties:
|
||||
role:
|
||||
tool_name:
|
||||
type: string
|
||||
const: assistant
|
||||
default: assistant
|
||||
description: The name of the tool to invoke.
|
||||
kwargs:
|
||||
type: object
|
||||
additionalProperties:
|
||||
oneOf:
|
||||
- type: 'null'
|
||||
- type: boolean
|
||||
- type: number
|
||||
- type: string
|
||||
- type: array
|
||||
- type: object
|
||||
description: >-
|
||||
Must be "assistant" to identify this as the model's response
|
||||
content:
|
||||
$ref: '#/components/schemas/InterleavedContent'
|
||||
description: The content of the model's response
|
||||
stop_reason:
|
||||
type: string
|
||||
enum:
|
||||
- end_of_turn
|
||||
- end_of_message
|
||||
- out_of_tokens
|
||||
description: >-
|
||||
Reason why the model stopped generating. Options are: - `StopReason.end_of_turn`:
|
||||
The model finished generating the entire response. - `StopReason.end_of_message`:
|
||||
The model finished generating but generated a partial response -- usually,
|
||||
a tool call. The user may call the tool and continue the conversation
|
||||
with the tool's response. - `StopReason.out_of_tokens`: The model ran
|
||||
out of token budget.
|
||||
tool_calls:
|
||||
type: array
|
||||
items:
|
||||
$ref: '#/components/schemas/ToolCall'
|
||||
description: >-
|
||||
List of tool calls. Each tool call is a ToolCall object.
|
||||
A dictionary of arguments to pass to the tool.
|
||||
additionalProperties: false
|
||||
required:
|
||||
- role
|
||||
- content
|
||||
- stop_reason
|
||||
title: CompletionMessage
|
||||
description: >-
|
||||
A message containing the model's (assistant) response in a chat conversation.
|
||||
- tool_name
|
||||
- kwargs
|
||||
title: InvokeToolRequest
|
||||
ImageContentItem:
|
||||
type: object
|
||||
properties:
|
||||
|
|
@ -8829,41 +8729,6 @@ components:
|
|||
mapping:
|
||||
image: '#/components/schemas/ImageContentItem'
|
||||
text: '#/components/schemas/TextContentItem'
|
||||
Message:
|
||||
oneOf:
|
||||
- $ref: '#/components/schemas/UserMessage'
|
||||
- $ref: '#/components/schemas/SystemMessage'
|
||||
- $ref: '#/components/schemas/ToolResponseMessage'
|
||||
- $ref: '#/components/schemas/CompletionMessage'
|
||||
discriminator:
|
||||
propertyName: role
|
||||
mapping:
|
||||
user: '#/components/schemas/UserMessage'
|
||||
system: '#/components/schemas/SystemMessage'
|
||||
tool: '#/components/schemas/ToolResponseMessage'
|
||||
assistant: '#/components/schemas/CompletionMessage'
|
||||
SystemMessage:
|
||||
type: object
|
||||
properties:
|
||||
role:
|
||||
type: string
|
||||
const: system
|
||||
default: system
|
||||
description: >-
|
||||
Must be "system" to identify this as a system message
|
||||
content:
|
||||
$ref: '#/components/schemas/InterleavedContent'
|
||||
description: >-
|
||||
The content of the "system prompt". If multiple system messages are provided,
|
||||
they are concatenated. The underlying Llama Stack code may also add other
|
||||
system messages (for example, for formatting tool definitions).
|
||||
additionalProperties: false
|
||||
required:
|
||||
- role
|
||||
- content
|
||||
title: SystemMessage
|
||||
description: >-
|
||||
A system message providing instructions or context to the model.
|
||||
TextContentItem:
|
||||
type: object
|
||||
properties:
|
||||
|
|
@ -8882,179 +8747,6 @@ components:
|
|||
- text
|
||||
title: TextContentItem
|
||||
description: A text content item
|
||||
ToolCall:
|
||||
type: object
|
||||
properties:
|
||||
call_id:
|
||||
type: string
|
||||
tool_name:
|
||||
oneOf:
|
||||
- type: string
|
||||
enum:
|
||||
- brave_search
|
||||
- wolfram_alpha
|
||||
- photogen
|
||||
- code_interpreter
|
||||
title: BuiltinTool
|
||||
- type: string
|
||||
arguments:
|
||||
type: string
|
||||
additionalProperties: false
|
||||
required:
|
||||
- call_id
|
||||
- tool_name
|
||||
- arguments
|
||||
title: ToolCall
|
||||
ToolResponseMessage:
|
||||
type: object
|
||||
properties:
|
||||
role:
|
||||
type: string
|
||||
const: tool
|
||||
default: tool
|
||||
description: >-
|
||||
Must be "tool" to identify this as a tool response
|
||||
call_id:
|
||||
type: string
|
||||
description: >-
|
||||
Unique identifier for the tool call this response is for
|
||||
content:
|
||||
$ref: '#/components/schemas/InterleavedContent'
|
||||
description: The response content from the tool
|
||||
additionalProperties: false
|
||||
required:
|
||||
- role
|
||||
- call_id
|
||||
- content
|
||||
title: ToolResponseMessage
|
||||
description: >-
|
||||
A message representing the result of a tool invocation.
|
||||
URL:
|
||||
type: object
|
||||
properties:
|
||||
uri:
|
||||
type: string
|
||||
description: The URL string pointing to the resource
|
||||
additionalProperties: false
|
||||
required:
|
||||
- uri
|
||||
title: URL
|
||||
description: A URL reference to external content.
|
||||
UserMessage:
|
||||
type: object
|
||||
properties:
|
||||
role:
|
||||
type: string
|
||||
const: user
|
||||
default: user
|
||||
description: >-
|
||||
Must be "user" to identify this as a user message
|
||||
content:
|
||||
$ref: '#/components/schemas/InterleavedContent'
|
||||
description: >-
|
||||
The content of the message, which can include text and other media
|
||||
context:
|
||||
$ref: '#/components/schemas/InterleavedContent'
|
||||
description: >-
|
||||
(Optional) This field is used internally by Llama Stack to pass RAG context.
|
||||
This field may be removed in the API in the future.
|
||||
additionalProperties: false
|
||||
required:
|
||||
- role
|
||||
- content
|
||||
title: UserMessage
|
||||
description: >-
|
||||
A message from the user in a chat conversation.
|
||||
SyntheticDataGenerateRequest:
|
||||
type: object
|
||||
properties:
|
||||
dialogs:
|
||||
type: array
|
||||
items:
|
||||
$ref: '#/components/schemas/Message'
|
||||
description: >-
|
||||
List of conversation messages to use as input for synthetic data generation
|
||||
filtering_function:
|
||||
type: string
|
||||
enum:
|
||||
- none
|
||||
- random
|
||||
- top_k
|
||||
- top_p
|
||||
- top_k_top_p
|
||||
- sigmoid
|
||||
description: >-
|
||||
Type of filtering to apply to generated synthetic data samples
|
||||
model:
|
||||
type: string
|
||||
description: >-
|
||||
(Optional) The identifier of the model to use. The model must be registered
|
||||
with Llama Stack and available via the /models endpoint
|
||||
additionalProperties: false
|
||||
required:
|
||||
- dialogs
|
||||
- filtering_function
|
||||
title: SyntheticDataGenerateRequest
|
||||
SyntheticDataGenerationResponse:
|
||||
type: object
|
||||
properties:
|
||||
synthetic_data:
|
||||
type: array
|
||||
items:
|
||||
type: object
|
||||
additionalProperties:
|
||||
oneOf:
|
||||
- type: 'null'
|
||||
- type: boolean
|
||||
- type: number
|
||||
- type: string
|
||||
- type: array
|
||||
- type: object
|
||||
description: >-
|
||||
List of generated synthetic data samples that passed the filtering criteria
|
||||
statistics:
|
||||
type: object
|
||||
additionalProperties:
|
||||
oneOf:
|
||||
- type: 'null'
|
||||
- type: boolean
|
||||
- type: number
|
||||
- type: string
|
||||
- type: array
|
||||
- type: object
|
||||
description: >-
|
||||
(Optional) Statistical information about the generation process and filtering
|
||||
results
|
||||
additionalProperties: false
|
||||
required:
|
||||
- synthetic_data
|
||||
title: SyntheticDataGenerationResponse
|
||||
description: >-
|
||||
Response from the synthetic data generation. Batch of (prompt, response, score)
|
||||
tuples that pass the threshold.
|
||||
InvokeToolRequest:
|
||||
type: object
|
||||
properties:
|
||||
tool_name:
|
||||
type: string
|
||||
description: The name of the tool to invoke.
|
||||
kwargs:
|
||||
type: object
|
||||
additionalProperties:
|
||||
oneOf:
|
||||
- type: 'null'
|
||||
- type: boolean
|
||||
- type: number
|
||||
- type: string
|
||||
- type: array
|
||||
- type: object
|
||||
description: >-
|
||||
A dictionary of arguments to pass to the tool.
|
||||
additionalProperties: false
|
||||
required:
|
||||
- tool_name
|
||||
- kwargs
|
||||
title: InvokeToolRequest
|
||||
ToolInvocationResult:
|
||||
type: object
|
||||
properties:
|
||||
|
|
@ -9085,6 +8777,17 @@ components:
|
|||
additionalProperties: false
|
||||
title: ToolInvocationResult
|
||||
description: Result of a tool invocation.
|
||||
URL:
|
||||
type: object
|
||||
properties:
|
||||
uri:
|
||||
type: string
|
||||
description: The URL string pointing to the resource
|
||||
additionalProperties: false
|
||||
required:
|
||||
- uri
|
||||
title: URL
|
||||
description: A URL reference to external content.
|
||||
ToolDef:
|
||||
type: object
|
||||
properties:
|
||||
|
|
@ -9155,274 +8858,6 @@ 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:
|
||||
|
|
@ -10686,8 +10121,6 @@ tags:
|
|||
description: ''
|
||||
- name: Shields
|
||||
description: ''
|
||||
- name: SyntheticDataGeneration (Coming Soon)
|
||||
description: ''
|
||||
- name: ToolGroups
|
||||
description: ''
|
||||
- name: ToolRuntime
|
||||
|
|
@ -10710,7 +10143,6 @@ x-tagGroups:
|
|||
- Scoring
|
||||
- ScoringFunctions
|
||||
- Shields
|
||||
- SyntheticDataGeneration (Coming Soon)
|
||||
- ToolGroups
|
||||
- ToolRuntime
|
||||
- VectorIO
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue