phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 12:07:34 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat(tools): use { input_schema, output_schema } for ToolDefinition

Browse source
This commit is contained in:
Ashwin Bharambe 2025-09-30 19:13:15 -07:00
parent 42414a1a1b
commit 139320e19f
20 changed files with 1989 additions and 386 deletions
Download patch file Download diff file Expand all files Collapse all files

24
docs/docs/providers/agents/index.mdx
View file

@ -1,12 +1,12 @@
---
description: "Agents API for creating and interacting with agentic systems.
Main functionalities provided by this API:
- Create agents with specific instructions and ability to use tools.
- Interactions with agents are grouped into sessions (\"threads\"), and each interaction is called a \"turn\".
- Agents can be provided with various tools (see the ToolGroups and ToolRuntime APIs for more details).
- Agents can be provided with various shields (see the Safety API for more details).
- Agents can also use Memory to retrieve information from knowledge bases. See the RAG Tool and Vector IO APIs for more details."
Main functionalities provided by this API:
- Create agents with specific instructions and ability to use tools.
- Interactions with agents are grouped into sessions (\"threads\"), and each interaction is called a \"turn\".
- Agents can be provided with various tools (see the ToolGroups and ToolRuntime APIs for more details).
- Agents can be provided with various shields (see the Safety API for more details).
- Agents can also use Memory to retrieve information from knowledge bases. See the RAG Tool and Vector IO APIs for more details."
sidebar_label: Agents
title: Agents
---
@ -17,11 +17,11 @@ title: Agents
Agents API for creating and interacting with agentic systems.
Main functionalities provided by this API:
- Create agents with specific instructions and ability to use tools.
- Interactions with agents are grouped into sessions ("threads"), and each interaction is called a "turn".
- Agents can be provided with various tools (see the ToolGroups and ToolRuntime APIs for more details).
- Agents can be provided with various shields (see the Safety API for more details).
- Agents can also use Memory to retrieve information from knowledge bases. See the RAG Tool and Vector IO APIs for more details.
Main functionalities provided by this API:
- Create agents with specific instructions and ability to use tools.
- Interactions with agents are grouped into sessions ("threads"), and each interaction is called a "turn".
- Agents can be provided with various tools (see the ToolGroups and ToolRuntime APIs for more details).
- Agents can be provided with various shields (see the Safety API for more details).
- Agents can also use Memory to retrieve information from knowledge bases. See the RAG Tool and Vector IO APIs for more details.
This section contains documentation for all available providers for the **agents** API.

24
docs/docs/providers/batches/index.mdx
View file

@ -1,14 +1,14 @@
---
description: "The Batches API enables efficient processing of multiple requests in a single operation,
particularly useful for processing large datasets, batch evaluation workflows, and
cost-effective inference at scale.
particularly useful for processing large datasets, batch evaluation workflows, and
cost-effective inference at scale.
The API is designed to allow use of openai client libraries for seamless integration.
The API is designed to allow use of openai client libraries for seamless integration.
This API provides the following extensions:
- idempotent batch creation
This API provides the following extensions:
- idempotent batch creation
Note: This API is currently under active development and may undergo changes."
Note: This API is currently under active development and may undergo changes."
sidebar_label: Batches
title: Batches
---
@ -18,14 +18,14 @@ title: Batches
## Overview
The Batches API enables efficient processing of multiple requests in a single operation,
particularly useful for processing large datasets, batch evaluation workflows, and
cost-effective inference at scale.
particularly useful for processing large datasets, batch evaluation workflows, and
cost-effective inference at scale.
The API is designed to allow use of openai client libraries for seamless integration.
The API is designed to allow use of openai client libraries for seamless integration.
This API provides the following extensions:
- idempotent batch creation
This API provides the following extensions:
- idempotent batch creation
Note: This API is currently under active development and may undergo changes.
Note: This API is currently under active development and may undergo changes.
This section contains documentation for all available providers for the **batches** API.

12
docs/docs/providers/inference/index.mdx
View file

@ -1,9 +1,9 @@
---
description: "Llama Stack Inference API for generating completions, chat completions, and embeddings.
This API provides the raw interface to the underlying models. Two kinds of models are supported:
- LLM models: these models generate \"raw\" and \"chat\" (conversational) completions.
- Embedding models: these models generate embeddings to be used for semantic search."
This API provides the raw interface to the underlying models. Two kinds of models are supported:
- LLM models: these models generate \"raw\" and \"chat\" (conversational) completions.
- Embedding models: these models generate embeddings to be used for semantic search."
sidebar_label: Inference
title: Inference
---
@ -14,8 +14,8 @@ title: Inference
Llama Stack Inference API for generating completions, chat completions, and embeddings.
This API provides the raw interface to the underlying models. Two kinds of models are supported:
- LLM models: these models generate "raw" and "chat" (conversational) completions.
- Embedding models: these models generate embeddings to be used for semantic search.
This API provides the raw interface to the underlying models. Two kinds of models are supported:
- LLM models: these models generate "raw" and "chat" (conversational) completions.
- Embedding models: these models generate embeddings to be used for semantic search.
This section contains documentation for all available providers for the **inference** API.

179
docs/static/llama-stack-spec.html vendored
View file

@ -7383,12 +7383,57 @@
"type": "string",
"description": "(Optional) Human-readable description of what the tool does"
},
"parameters": {
"type": "array",
"items": {
"$ref": "#/components/schemas/ToolParameter"
"input_schema": {
"type": "object",
"additionalProperties": {
"oneOf": [
{
"type": "null"
},
{
"type": "boolean"
},
{
"type": "number"
},
{
"type": "string"
},
{
"type": "array"
},
{
"type": "object"
}
]
},
"description": "(Optional) List of parameters this tool accepts"
"description": "(Optional) JSON Schema for tool inputs (MCP inputSchema)"
},
"output_schema": {
"type": "object",
"additionalProperties": {
"oneOf": [
{
"type": "null"
},
{
"type": "boolean"
},
{
"type": "number"
},
{
"type": "string"
},
{
"type": "array"
},
{
"type": "object"
}
]
},
"description": "(Optional) JSON Schema for tool outputs (MCP outputSchema)"
},
"metadata": {
"type": "object",
@ -7424,68 +7469,6 @@
"title": "ToolDef",
"description": "Tool definition used in runtime contexts."
},
"ToolParameter": {
"type": "object",
"properties": {
"name": {
"type": "string",
"description": "Name of the parameter"
},
"parameter_type": {
"type": "string",
"description": "Type of the parameter (e.g., string, integer)"
},
"description": {
"type": "string",
"description": "Human-readable description of what the parameter does"
},
"required": {
"type": "boolean",
"default": true,
"description": "Whether this parameter is required for tool invocation"
},
"items": {
"type": "object",
"description": "Type of the elements when parameter_type is array"
},
"title": {
"type": "string",
"description": "(Optional) Title of the parameter"
},
"default": {
"oneOf": [
{
"type": "null"
},
{
"type": "boolean"
},
{
"type": "number"
},
{
"type": "string"
},
{
"type": "array"
},
{
"type": "object"
}
],
"description": "(Optional) Default value for the parameter if not provided"
}
},
"additionalProperties": false,
"required": [
"name",
"parameter_type",
"description",
"required"
],
"title": "ToolParameter",
"description": "Parameter definition for a tool."
},
"TopKSamplingStrategy": {
"type": "object",
"properties": {
@ -13132,6 +13115,68 @@
"title": "Tool",
"description": "A tool that can be invoked by agents."
},
"ToolParameter": {
"type": "object",
"properties": {
"name": {
"type": "string",
"description": "Name of the parameter"
},
"parameter_type": {
"type": "string",
"description": "Type of the parameter (e.g., string, integer)"
},
"description": {
"type": "string",
"description": "Human-readable description of what the parameter does"
},
"required": {
"type": "boolean",
"default": true,
"description": "Whether this parameter is required for tool invocation"
},
"items": {
"type": "object",
"description": "Type of the elements when parameter_type is array"
},
"title": {
"type": "string",
"description": "(Optional) Title of the parameter"
},
"default": {
"oneOf": [
{
"type": "null"
},
{
"type": "boolean"
},
{
"type": "number"
},
{
"type": "string"
},
{
"type": "array"
},
{
"type": "object"
}
],
"description": "(Optional) Default value for the parameter if not provided"
}
},
"additionalProperties": false,
"required": [
"name",
"parameter_type",
"description",
"required"
],
"title": "ToolParameter",
"description": "Parameter definition for a tool."
},
"ToolGroup": {
"type": "object",
"properties": {

116
docs/static/llama-stack-spec.yaml vendored
View file

@ -5322,12 +5322,30 @@ components:
type: string
description: >-
(Optional) Human-readable description of what the tool does
parameters:
type: array
items:
$ref: '#/components/schemas/ToolParameter'
input_schema:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
description: >-
(Optional) List of parameters this tool accepts
(Optional) JSON Schema for tool inputs (MCP inputSchema)
output_schema:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
description: >-
(Optional) JSON Schema for tool outputs (MCP outputSchema)
metadata:
type: object
additionalProperties:
@ -5346,50 +5364,6 @@ components:
title: ToolDef
description: >-
Tool definition used in runtime contexts.
ToolParameter:
type: object
properties:
name:
type: string
description: Name of the parameter
parameter_type:
type: string
description: >-
Type of the parameter (e.g., string, integer)
description:
type: string
description: >-
Human-readable description of what the parameter does
required:
type: boolean
default: true
description: >-
Whether this parameter is required for tool invocation
items:
type: object
description: >-
Type of the elements when parameter_type is array
title:
type: string
description: (Optional) Title of the parameter
default:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
description: >-
(Optional) Default value for the parameter if not provided
additionalProperties: false
required:
- name
- parameter_type
- description
- required
title: ToolParameter
description: Parameter definition for a tool.
TopKSamplingStrategy:
type: object
properties:
@ -9667,6 +9641,50 @@ components:
- parameters
title: Tool
description: A tool that can be invoked by agents.
ToolParameter:
type: object
properties:
name:
type: string
description: Name of the parameter
parameter_type:
type: string
description: >-
Type of the parameter (e.g., string, integer)
description:
type: string
description: >-
Human-readable description of what the parameter does
required:
type: boolean
default: true
description: >-
Whether this parameter is required for tool invocation
items:
type: object
description: >-
Type of the elements when parameter_type is array
title:
type: string
description: (Optional) Title of the parameter
default:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
description: >-
(Optional) Default value for the parameter if not provided
additionalProperties: false
required:
- name
- parameter_type
- description
- required
title: ToolParameter
description: Parameter definition for a tool.
ToolGroup:
type: object
properties: