phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-28 01:21:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'main' into rag-metadata-support

Browse source
This commit is contained in:
Francisco Arceo 2025-05-13 21:14:02 -06:00 • committed by GitHub
commit 227ff4c9b3
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
42 changed files with 1294 additions and 563 deletions
Download patch file Download diff file Expand all files Collapse all files

408
docs/_static/llama-stack-spec.html vendored
View file

@ -6466,54 +6466,51 @@
],
"title": "AgentTurnResponseTurnStartPayload"
},
"OpenAIResponseInputMessage": {
"OpenAIResponseInput": {
"oneOf": [
{
"$ref": "#/components/schemas/OpenAIResponseOutputMessageWebSearchToolCall"
},
{
"$ref": "#/components/schemas/OpenAIResponseOutputMessageFunctionToolCall"
},
{
"$ref": "#/components/schemas/OpenAIResponseInputFunctionToolCallOutput"
},
{
"$ref": "#/components/schemas/OpenAIResponseMessage"
}
]
},
"OpenAIResponseInputFunctionToolCallOutput": {
"type": "object",
"properties": {
"content": {
"oneOf": [
{
"type": "string"
},
{
"type": "array",
"items": {
"$ref": "#/components/schemas/OpenAIResponseInputMessageContent"
}
}
]
"call_id": {
"type": "string"
},
"role": {
"oneOf": [
{
"type": "string",
"const": "system"
},
{
"type": "string",
"const": "developer"
},
{
"type": "string",
"const": "user"
},
{
"type": "string",
"const": "assistant"
}
]
"output": {
"type": "string"
},
"type": {
"type": "string",
"const": "message",
"default": "message"
"const": "function_call_output",
"default": "function_call_output"
},
"id": {
"type": "string"
},
"status": {
"type": "string"
}
},
"additionalProperties": false,
"required": [
"content",
"role"
"call_id",
"output",
"type"
],
"title": "OpenAIResponseInputMessage"
"title": "OpenAIResponseInputFunctionToolCallOutput",
"description": "This represents the output of a function call that gets passed back to the model."
},
"OpenAIResponseInputMessageContent": {
"oneOf": [
@ -6588,6 +6585,113 @@
"title": "OpenAIResponseInputMessageContentText"
},
"OpenAIResponseInputTool": {
"oneOf": [
{
"$ref": "#/components/schemas/OpenAIResponseInputToolWebSearch"
},
{
"$ref": "#/components/schemas/OpenAIResponseInputToolFileSearch"
},
{
"$ref": "#/components/schemas/OpenAIResponseInputToolFunction"
}
],
"discriminator": {
"propertyName": "type",
"mapping": {
"web_search": "#/components/schemas/OpenAIResponseInputToolWebSearch",
"file_search": "#/components/schemas/OpenAIResponseInputToolFileSearch",
"function": "#/components/schemas/OpenAIResponseInputToolFunction"
}
}
},
"OpenAIResponseInputToolFileSearch": {
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "file_search",
"default": "file_search"
},
"vector_store_id": {
"type": "array",
"items": {
"type": "string"
}
},
"ranking_options": {
"type": "object",
"properties": {
"ranker": {
"type": "string"
},
"score_threshold": {
"type": "number",
"default": 0.0
}
},
"additionalProperties": false,
"title": "FileSearchRankingOptions"
}
},
"additionalProperties": false,
"required": [
"type",
"vector_store_id"
],
"title": "OpenAIResponseInputToolFileSearch"
},
"OpenAIResponseInputToolFunction": {
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "function",
"default": "function"
},
"name": {
"type": "string"
},
"description": {
"type": "string"
},
"parameters": {
"type": "object",
"additionalProperties": {
"oneOf": [
{
"type": "null"
},
{
"type": "boolean"
},
{
"type": "number"
},
{
"type": "string"
},
{
"type": "array"
},
{
"type": "object"
}
]
}
},
"strict": {
"type": "boolean"
}
},
"additionalProperties": false,
"required": [
"type",
"name"
],
"title": "OpenAIResponseInputToolFunction"
},
"OpenAIResponseInputToolWebSearch": {
"type": "object",
"properties": {
"type": {
@ -6614,6 +6718,146 @@
],
"title": "OpenAIResponseInputToolWebSearch"
},
"OpenAIResponseMessage": {
"type": "object",
"properties": {
"content": {
"oneOf": [
{
"type": "string"
},
{
"type": "array",
"items": {
"$ref": "#/components/schemas/OpenAIResponseInputMessageContent"
}
},
{
"type": "array",
"items": {
"$ref": "#/components/schemas/OpenAIResponseOutputMessageContent"
}
}
]
},
"role": {
"oneOf": [
{
"type": "string",
"const": "system"
},
{
"type": "string",
"const": "developer"
},
{
"type": "string",
"const": "user"
},
{
"type": "string",
"const": "assistant"
}
]
},
"type": {
"type": "string",
"const": "message",
"default": "message"
},
"id": {
"type": "string"
},
"status": {
"type": "string"
}
},
"additionalProperties": false,
"required": [
"content",
"role",
"type"
],
"title": "OpenAIResponseMessage",
"description": "Corresponds to the various Message types in the Responses API. They are all under one type because the Responses API gives them all the same \"type\" value, and there is no way to tell them apart in certain scenarios."
},
"OpenAIResponseOutputMessageContent": {
"type": "object",
"properties": {
"text": {
"type": "string"
},
"type": {
"type": "string",
"const": "output_text",
"default": "output_text"
}
},
"additionalProperties": false,
"required": [
"text",
"type"
],
"title": "OpenAIResponseOutputMessageContentOutputText"
},
"OpenAIResponseOutputMessageFunctionToolCall": {
"type": "object",
"properties": {
"arguments": {
"type": "string"
},
"call_id": {
"type": "string"
},
"name": {
"type": "string"
},
"type": {
"type": "string",
"const": "function_call",
"default": "function_call"
},
"id": {
"type": "string"
},
"status": {
"type": "string"
}
},
"additionalProperties": false,
"required": [
"arguments",
"call_id",
"name",
"type",
"id",
"status"
],
"title": "OpenAIResponseOutputMessageFunctionToolCall"
},
"OpenAIResponseOutputMessageWebSearchToolCall": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"status": {
"type": "string"
},
"type": {
"type": "string",
"const": "web_search_call",
"default": "web_search_call"
}
},
"additionalProperties": false,
"required": [
"id",
"status",
"type"
],
"title": "OpenAIResponseOutputMessageWebSearchToolCall"
},
"CreateOpenaiResponseRequest": {
"type": "object",
"properties": {
@ -6625,7 +6869,7 @@
{
"type": "array",
"items": {
"$ref": "#/components/schemas/OpenAIResponseInputMessage"
"$ref": "#/components/schemas/OpenAIResponseInput"
}
}
],
@ -6743,98 +6987,24 @@
"OpenAIResponseOutput": {
"oneOf": [
{
"$ref": "#/components/schemas/OpenAIResponseOutputMessage"
"$ref": "#/components/schemas/OpenAIResponseMessage"
},
{
"$ref": "#/components/schemas/OpenAIResponseOutputMessageWebSearchToolCall"
},
{
"$ref": "#/components/schemas/OpenAIResponseOutputMessageFunctionToolCall"
}
],
"discriminator": {
"propertyName": "type",
"mapping": {
"message": "#/components/schemas/OpenAIResponseOutputMessage",
"web_search_call": "#/components/schemas/OpenAIResponseOutputMessageWebSearchToolCall"
"message": "#/components/schemas/OpenAIResponseMessage",
"web_search_call": "#/components/schemas/OpenAIResponseOutputMessageWebSearchToolCall",
"function_call": "#/components/schemas/OpenAIResponseOutputMessageFunctionToolCall"
}
}
},
"OpenAIResponseOutputMessage": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"content": {
"type": "array",
"items": {
"$ref": "#/components/schemas/OpenAIResponseOutputMessageContent"
}
},
"role": {
"type": "string",
"const": "assistant",
"default": "assistant"
},
"status": {
"type": "string"
},
"type": {
"type": "string",
"const": "message",
"default": "message"
}
},
"additionalProperties": false,
"required": [
"id",
"content",
"role",
"status",
"type"
],
"title": "OpenAIResponseOutputMessage"
},
"OpenAIResponseOutputMessageContent": {
"type": "object",
"properties": {
"text": {
"type": "string"
},
"type": {
"type": "string",
"const": "output_text",
"default": "output_text"
}
},
"additionalProperties": false,
"required": [
"text",
"type"
],
"title": "OpenAIResponseOutputMessageContentOutputText"
},
"OpenAIResponseOutputMessageWebSearchToolCall": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"status": {
"type": "string"
},
"type": {
"type": "string",
"const": "web_search_call",
"default": "web_search_call"
}
},
"additionalProperties": false,
"required": [
"id",
"status",
"type"
],
"title": "OpenAIResponseOutputMessageWebSearchToolCall"
},
"OpenAIResponseObjectStream": {
"oneOf": [
{

280
docs/_static/llama-stack-spec.yaml vendored
View file

@ -4534,34 +4534,37 @@ components:
- event_type
- turn_id
title: AgentTurnResponseTurnStartPayload
OpenAIResponseInputMessage:
OpenAIResponseInput:
oneOf:
- $ref: '#/components/schemas/OpenAIResponseOutputMessageWebSearchToolCall'
- $ref: '#/components/schemas/OpenAIResponseOutputMessageFunctionToolCall'
- $ref: '#/components/schemas/OpenAIResponseInputFunctionToolCallOutput'
- $ref: '#/components/schemas/OpenAIResponseMessage'
"OpenAIResponseInputFunctionToolCallOutput":
type: object
properties:
content:
oneOf:
- type: string
- type: array
items:
$ref: '#/components/schemas/OpenAIResponseInputMessageContent'
role:
oneOf:
- type: string
const: system
- type: string
const: developer
- type: string
const: user
- type: string
const: assistant
call_id:
type: string
output:
type: string
type:
type: string
const: message
default: message
const: function_call_output
default: function_call_output
id:
type: string
status:
type: string
additionalProperties: false
required:
- content
- role
title: OpenAIResponseInputMessage
- call_id
- output
- type
title: >-
OpenAIResponseInputFunctionToolCallOutput
description: >-
This represents the output of a function call that gets passed back to the
model.
OpenAIResponseInputMessageContent:
oneOf:
- $ref: '#/components/schemas/OpenAIResponseInputMessageContentText'
@ -4609,6 +4612,71 @@ components:
- type
title: OpenAIResponseInputMessageContentText
OpenAIResponseInputTool:
oneOf:
- $ref: '#/components/schemas/OpenAIResponseInputToolWebSearch'
- $ref: '#/components/schemas/OpenAIResponseInputToolFileSearch'
- $ref: '#/components/schemas/OpenAIResponseInputToolFunction'
discriminator:
propertyName: type
mapping:
web_search: '#/components/schemas/OpenAIResponseInputToolWebSearch'
file_search: '#/components/schemas/OpenAIResponseInputToolFileSearch'
function: '#/components/schemas/OpenAIResponseInputToolFunction'
OpenAIResponseInputToolFileSearch:
type: object
properties:
type:
type: string
const: file_search
default: file_search
vector_store_id:
type: array
items:
type: string
ranking_options:
type: object
properties:
ranker:
type: string
score_threshold:
type: number
default: 0.0
additionalProperties: false
title: FileSearchRankingOptions
additionalProperties: false
required:
- type
- vector_store_id
title: OpenAIResponseInputToolFileSearch
OpenAIResponseInputToolFunction:
type: object
properties:
type:
type: string
const: function
default: function
name:
type: string
description:
type: string
parameters:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
strict:
type: boolean
additionalProperties: false
required:
- type
- name
title: OpenAIResponseInputToolFunction
OpenAIResponseInputToolWebSearch:
type: object
properties:
type:
@ -4625,6 +4693,106 @@ components:
required:
- type
title: OpenAIResponseInputToolWebSearch
OpenAIResponseMessage:
type: object
properties:
content:
oneOf:
- type: string
- type: array
items:
$ref: '#/components/schemas/OpenAIResponseInputMessageContent'
- type: array
items:
$ref: '#/components/schemas/OpenAIResponseOutputMessageContent'
role:
oneOf:
- type: string
const: system
- type: string
const: developer
- type: string
const: user
- type: string
const: assistant
type:
type: string
const: message
default: message
id:
type: string
status:
type: string
additionalProperties: false
required:
- content
- role
- type
title: OpenAIResponseMessage
description: >-
Corresponds to the various Message types in the Responses API. They are all
under one type because the Responses API gives them all the same "type" value,
and there is no way to tell them apart in certain scenarios.
OpenAIResponseOutputMessageContent:
type: object
properties:
text:
type: string
type:
type: string
const: output_text
default: output_text
additionalProperties: false
required:
- text
- type
title: >-
OpenAIResponseOutputMessageContentOutputText
"OpenAIResponseOutputMessageFunctionToolCall":
type: object
properties:
arguments:
type: string
call_id:
type: string
name:
type: string
type:
type: string
const: function_call
default: function_call
id:
type: string
status:
type: string
additionalProperties: false
required:
- arguments
- call_id
- name
- type
- id
- status
title: >-
OpenAIResponseOutputMessageFunctionToolCall
"OpenAIResponseOutputMessageWebSearchToolCall":
type: object
properties:
id:
type: string
status:
type: string
type:
type: string
const: web_search_call
default: web_search_call
additionalProperties: false
required:
- id
- status
- type
title: >-
OpenAIResponseOutputMessageWebSearchToolCall
CreateOpenaiResponseRequest:
type: object
properties:
@ -4633,7 +4801,7 @@ components:
- type: string
- type: array
items:
$ref: '#/components/schemas/OpenAIResponseInputMessage'
$ref: '#/components/schemas/OpenAIResponseInput'
description: Input message(s) to create the response.
model:
type: string
@ -4717,73 +4885,15 @@ components:
title: OpenAIResponseObject
OpenAIResponseOutput:
oneOf:
- $ref: '#/components/schemas/OpenAIResponseOutputMessage'
- $ref: '#/components/schemas/OpenAIResponseMessage'
- $ref: '#/components/schemas/OpenAIResponseOutputMessageWebSearchToolCall'
- $ref: '#/components/schemas/OpenAIResponseOutputMessageFunctionToolCall'
discriminator:
propertyName: type
mapping:
message: '#/components/schemas/OpenAIResponseOutputMessage'
message: '#/components/schemas/OpenAIResponseMessage'
web_search_call: '#/components/schemas/OpenAIResponseOutputMessageWebSearchToolCall'
OpenAIResponseOutputMessage:
type: object
properties:
id:
type: string
content:
type: array
items:
$ref: '#/components/schemas/OpenAIResponseOutputMessageContent'
role:
type: string
const: assistant
default: assistant
status:
type: string
type:
type: string
const: message
default: message
additionalProperties: false
required:
- id
- content
- role
- status
- type
title: OpenAIResponseOutputMessage
OpenAIResponseOutputMessageContent:
type: object
properties:
text:
type: string
type:
type: string
const: output_text
default: output_text
additionalProperties: false
required:
- text
- type
title: >-
OpenAIResponseOutputMessageContentOutputText
"OpenAIResponseOutputMessageWebSearchToolCall":
type: object
properties:
id:
type: string
status:
type: string
type:
type: string
const: web_search_call
default: web_search_call
additionalProperties: false
required:
- id
- status
- type
title: >-
OpenAIResponseOutputMessageWebSearchToolCall
function_call: '#/components/schemas/OpenAIResponseOutputMessageFunctionToolCall'
OpenAIResponseObjectStream:
oneOf:
- $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseCreated'

3
docs/getting_started.ipynb
View file

@ -1050,8 +1050,6 @@
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #800080; text-decoration-color: #800080; font-weight: bold\">ToolGroup</span><span style=\"font-weight: bold\">(</span>\n",
"<span style=\"color: #7fbf7f; text-decoration-color: #7fbf7f\">│ </span><span style=\"color: #808000; text-decoration-color: #808000\">identifier</span>=<span style=\"color: #008000; text-decoration-color: #008000\">'builtin::code_interpreter'</span>,\n",
"<span style=\"color: #7fbf7f; text-decoration-color: #7fbf7f\">│ </span><span style=\"color: #808000; text-decoration-color: #808000\">provider_id</span>=<span style=\"color: #008000; text-decoration-color: #008000\">'code-interpreter'</span>,\n",
"<span style=\"color: #7fbf7f; text-decoration-color: #7fbf7f\">│ </span><span style=\"color: #808000; text-decoration-color: #808000\">provider_resource_id</span>=<span style=\"color: #008000; text-decoration-color: #008000\">'builtin::code_interpreter'</span>,\n",
"<span style=\"color: #7fbf7f; text-decoration-color: #7fbf7f\">│ </span><span style=\"color: #808000; text-decoration-color: #808000\">type</span>=<span style=\"color: #008000; text-decoration-color: #008000\">'tool_group'</span>,\n",
"<span style=\"color: #7fbf7f; text-decoration-color: #7fbf7f\">│ </span><span style=\"color: #808000; text-decoration-color: #808000\">args</span>=<span style=\"color: #800080; text-decoration-color: #800080; font-style: italic\">None</span>,\n",
"<span style=\"color: #7fbf7f; text-decoration-color: #7fbf7f\">│ </span><span style=\"color: #808000; text-decoration-color: #808000\">mcp_endpoint</span>=<span style=\"color: #800080; text-decoration-color: #800080; font-style: italic\">None</span>\n",
@ -1061,7 +1059,6 @@
"text/plain": [
"\u001b[1;35mToolGroup\u001b[0m\u001b[1m(\u001b[0m\n",
"\u001b[2;32m│ \u001b[0m\u001b[33midentifier\u001b[0m=\u001b[32m'builtin::code_interpreter'\u001b[0m,\n",
"\u001b[2;32m│ \u001b[0m\u001b[33mprovider_id\u001b[0m=\u001b[32m'code-interpreter'\u001b[0m,\n",
"\u001b[2;32m│ \u001b[0m\u001b[33mprovider_resource_id\u001b[0m=\u001b[32m'builtin::code_interpreter'\u001b[0m,\n",
"\u001b[2;32m│ \u001b[0m\u001b[33mtype\u001b[0m=\u001b[32m'tool_group'\u001b[0m,\n",
"\u001b[2;32m│ \u001b[0m\u001b[33margs\u001b[0m=\u001b[3;35mNone\u001b[0m,\n",

14
docs/notebooks/Llama_Stack_Benchmark_Evals.ipynb
View file

@ -337,9 +337,6 @@
" provider_id: tavily-search\n",
" provider_type: remote::tavily-search\n",
" - config: <span style=\"font-weight: bold\">{}</span>\n",
" provider_id: code-interpreter\n",
" provider_type: inlin<span style=\"color: #00ff00; text-decoration-color: #00ff00; font-weight: bold\">e::c</span>ode-interpreter\n",
" - config: <span style=\"font-weight: bold\">{}</span>\n",
" provider_id: rag-runtime\n",
" provider_type: inline::rag-runtime\n",
" - config: <span style=\"font-weight: bold\">{}</span>\n",
@ -378,10 +375,6 @@
" toolgroup_id: builtin::rag\n",
"- args: null\n",
" mcp_endpoint: null\n",
" provider_id: code-interpreter\n",
" toolgroup_id: builtin::code_interpreter\n",
"- args: null\n",
" mcp_endpoint: null\n",
" provider_id: wolfram-alpha\n",
" toolgroup_id: builtin::wolfram_alpha\n",
"vector_dbs: <span style=\"font-weight: bold\">[]</span>\n",
@ -617,9 +610,6 @@
" provider_id: tavily-search\n",
" provider_type: remote::tavily-search\n",
" - config: \u001b[1m{\u001b[0m\u001b[1m}\u001b[0m\n",
" provider_id: code-interpreter\n",
" provider_type: inlin\u001b[1;92me::c\u001b[0mode-interpreter\n",
" - config: \u001b[1m{\u001b[0m\u001b[1m}\u001b[0m\n",
" provider_id: rag-runtime\n",
" provider_type: inline::rag-runtime\n",
" - config: \u001b[1m{\u001b[0m\u001b[1m}\u001b[0m\n",
@ -658,10 +648,6 @@
" toolgroup_id: builtin::rag\n",
"- args: null\n",
" mcp_endpoint: null\n",
" provider_id: code-interpreter\n",
" toolgroup_id: builtin::code_interpreter\n",
"- args: null\n",
" mcp_endpoint: null\n",
" provider_id: wolfram-alpha\n",
" toolgroup_id: builtin::wolfram_alpha\n",
"vector_dbs: \u001b[1m[\u001b[0m\u001b[1m]\u001b[0m\n",

2
docs/openapi_generator/generate.py
View file

@ -44,7 +44,7 @@ def main(output_dir: str):
if return_type_errors:
print("\nAPI Method Return Type Validation Errors:\n")
for error in return_type_errors:
print(error)
print(error, file=sys.stderr)
sys.exit(1)
now = str(datetime.now())
print(

11
docs/openapi_generator/pyopenapi/utility.py
View file

@ -174,14 +174,25 @@ def _validate_list_parameters_contain_data(method) -> str | None:
return "does not have a mandatory data attribute containing the list of objects"
def _validate_has_ellipsis(method) -> str | None:
source = inspect.getsource(method)
if "..." not in source and not "NotImplementedError" in source:
return "does not contain ellipsis (...) in its implementation"
_VALIDATORS = {
"GET": [
_validate_api_method_return_type,
_validate_list_parameters_contain_data,
_validate_api_method_doesnt_return_list,
_validate_has_ellipsis,
],
"DELETE": [
_validate_api_delete_method_returns_none,
_validate_has_ellipsis,
],
"POST": [
_validate_has_ellipsis,
],
}

28
docs/source/building_applications/tools.md
View file

@ -165,34 +165,6 @@ all_tools = client.tools.list_tools()
group_tools = client.tools.list_tools(toolgroup_id="search_tools")
```
## Simple Example: Using an Agent with the Code-Interpreter Tool
```python
from llama_stack_client import Agent
# Instantiate the AI agent with the given configuration
agent = Agent(
client,
name="code-interpreter",
description="A code interpreter agent for executing Python code snippets",
instructions="""
You are a highly reliable, concise, and precise assistant.
Always show the generated code, never generate your own code, and never anticipate results.
""",
model="meta-llama/Llama-3.2-3B-Instruct",
tools=["builtin::code_interpreter"],
max_infer_iters=5,
)
# Start a session
session_id = agent.create_session("tool_session")
# Send a query to the AI agent for code execution
response = agent.create_turn(
messages=[{"role": "user", "content": "Run this code: print(3 ** 4 - 5 * 2)"}],
session_id=session_id,
)
```
## Simple Example 2: Using an Agent with the Web Search Tool
1. Start by registering a Tavily API key at [Tavily](https://tavily.com/).
2. [Optional] Provide the API key directly to the Llama Stack server

3
docs/source/contributing/new_api_provider.md
View file

@ -6,7 +6,7 @@ This guide will walk you through the process of adding a new API provider to Lla
- Begin by reviewing the [core concepts](../concepts/index.md) of Llama Stack and choose the API your provider belongs to (Inference, Safety, VectorIO, etc.)
- Determine the provider type ({repopath}`Remote::llama_stack/providers/remote` or {repopath}`Inline::llama_stack/providers/inline`). Remote providers make requests to external services, while inline providers execute implementation locally.
- Add your provider to the appropriate {repopath}`Registry::llama_stack/providers/registry/`. Specify pip dependencies necessary.
- Update any distribution {repopath}`Templates::llama_stack/templates/` build.yaml and run.yaml files if they should include your provider by default. Run {repopath}`./scripts/distro_codegen.py` if necessary. Note that `distro_codegen.py` will fail if the new provider causes any distribution template to attempt to import provider-specific dependencies. This usually means the distribution's `get_distribution_template()` code path should only import any necessary Config or model alias definitions from each provider and not the provider's actual implementation.
- Update any distribution {repopath}`Templates::llama_stack/templates/` `build.yaml` and `run.yaml` files if they should include your provider by default. Run {repopath}`./scripts/distro_codegen.py` if necessary. Note that `distro_codegen.py` will fail if the new provider causes any distribution template to attempt to import provider-specific dependencies. This usually means the distribution's `get_distribution_template()` code path should only import any necessary Config or model alias definitions from each provider and not the provider's actual implementation.
Here are some example PRs to help you get started:
@ -33,6 +33,7 @@ Note that each provider's `sample_run_config()` method (in the configuration cla
Unit tests are located in {repopath}`tests/unit`. Provider-specific unit tests are located in {repopath}`tests/unit/providers`. These tests are all run automatically as part of the CI process.
Consult {repopath}`tests/unit/README.md` for more details on how to run the tests manually.
### 3. Additional end-to-end testing

2
docs/source/distributions/remote_hosted_distro/watsonx.md
View file

@ -18,7 +18,7 @@ The `llamastack/distribution-watsonx` distribution consists of the following pro
| agents | `inline::meta-reference` |
| datasetio | `remote::huggingface`, `inline::localfs` |
| eval | `inline::meta-reference` |
| inference | `remote::watsonx` |
| inference | `remote::watsonx`, `inline::sentence-transformers` |
| safety | `inline::llama-guard` |
| scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` |
| telemetry | `inline::meta-reference` |

2
docs/source/distributions/self_hosted_distro/dell.md
View file

@ -23,7 +23,7 @@ The `llamastack/distribution-dell` distribution consists of the following provid
| safety | `inline::llama-guard` |
| scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` |
| telemetry | `inline::meta-reference` |
| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::rag-runtime` |
| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::rag-runtime` |
| vector_io | `inline::faiss`, `remote::chromadb`, `remote::pgvector` |

2
docs/source/references/llama_stack_client_cli_reference.md
View file

@ -253,8 +253,6 @@ llama-stack-client toolgroups list
+---------------------------+------------------+------+---------------+
| identifier | provider_id | args | mcp_endpoint |
+===========================+==================+======+===============+
| builtin::code_interpreter | code-interpreter | None | None |
+---------------------------+------------------+------+---------------+
| builtin::rag | rag-runtime | None | None |
+---------------------------+------------------+------+---------------+
| builtin::websearch | tavily-search | None | None |