phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-31 18:10:00 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'refs/heads/main' into preprocessors

Browse source
This commit is contained in:
ilya-kolchinsky 2025-03-11 20:05:52 +01:00
commit d38aea33c1
37 changed files with 493 additions and 255 deletions
Download patch file Download diff file Expand all files Collapse all files

169
docs/_static/llama-stack-spec.html vendored
View file

@ -363,6 +363,37 @@
}
},
"/v1/agents": {
"get": {
"responses": {
"200": {
"description": "A ListAgentsResponse.",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/ListAgentsResponse"
}
}
}
},
"400": {
"$ref": "#/components/responses/BadRequest400"
},
"429": {
"$ref": "#/components/responses/TooManyRequests429"
},
"500": {
"$ref": "#/components/responses/InternalServerError500"
},
"default": {
"$ref": "#/components/responses/DefaultError"
}
},
"tags": [
"Agents"
],
"description": "List all agents.",
"parameters": []
},
"post": {
"responses": {
"200": {
@ -609,6 +640,47 @@
}
},
"/v1/agents/{agent_id}": {
"get": {
"responses": {
"200": {
"description": "An Agent of the agent.",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/Agent"
}
}
}
},
"400": {
"$ref": "#/components/responses/BadRequest400"
},
"429": {
"$ref": "#/components/responses/TooManyRequests429"
},
"500": {
"$ref": "#/components/responses/InternalServerError500"
},
"default": {
"$ref": "#/components/responses/DefaultError"
}
},
"tags": [
"Agents"
],
"description": "Describe an agent by its ID.",
"parameters": [
{
"name": "agent_id",
"in": "path",
"description": "ID of the agent.",
"required": true,
"schema": {
"type": "string"
}
}
]
},
"delete": {
"responses": {
"200": {
@ -2358,6 +2430,49 @@
]
}
},
"/v1/agents/{agent_id}/sessions": {
"get": {
"responses": {
"200": {
"description": "A ListAgentSessionsResponse.",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/ListAgentSessionsResponse"
}
}
}
},
"400": {
"$ref": "#/components/responses/BadRequest400"
},
"429": {
"$ref": "#/components/responses/TooManyRequests429"
},
"500": {
"$ref": "#/components/responses/InternalServerError500"
},
"default": {
"$ref": "#/components/responses/DefaultError"
}
},
"tags": [
"Agents"
],
"description": "List all session(s) of a given agent.",
"parameters": [
{
"name": "agent_id",
"in": "path",
"description": "The ID of the agent to list sessions for.",
"required": true,
"schema": {
"type": "string"
}
}
]
}
},
"/v1/eval/benchmarks": {
"get": {
"responses": {
@ -6776,6 +6891,28 @@
"title": "ScoringResult",
"description": "A scoring result for a single row."
},
"Agent": {
"type": "object",
"properties": {
"agent_id": {
"type": "string"
},
"agent_config": {
"$ref": "#/components/schemas/AgentConfig"
},
"created_at": {
"type": "string",
"format": "date-time"
}
},
"additionalProperties": false,
"required": [
"agent_id",
"agent_config",
"created_at"
],
"title": "Agent"
},
"Session": {
"type": "object",
"properties": {
@ -8214,6 +8351,38 @@
],
"title": "ToolInvocationResult"
},
"ListAgentSessionsResponse": {
"type": "object",
"properties": {
"data": {
"type": "array",
"items": {
"$ref": "#/components/schemas/Session"
}
}
},
"additionalProperties": false,
"required": [
"data"
],
"title": "ListAgentSessionsResponse"
},
"ListAgentsResponse": {
"type": "object",
"properties": {
"data": {
"type": "array",
"items": {
"$ref": "#/components/schemas/Agent"
}
}
},
"additionalProperties": false,
"required": [
"data"
],
"title": "ListAgentsResponse"
},
"BucketResponse": {
"type": "object",
"properties": {

118
docs/_static/llama-stack-spec.yaml vendored
View file

@ -238,6 +238,28 @@ paths:
$ref: '#/components/schemas/CompletionRequest'
required: true
/v1/agents:
get:
responses:
'200':
description: A ListAgentsResponse.
content:
application/json:
schema:
$ref: '#/components/schemas/ListAgentsResponse'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Agents
description: List all agents.
parameters: []
post:
responses:
'200':
@ -410,6 +432,34 @@ paths:
$ref: '#/components/schemas/CreateUploadSessionRequest'
required: true
/v1/agents/{agent_id}:
get:
responses:
'200':
description: An Agent of the agent.
content:
application/json:
schema:
$ref: '#/components/schemas/Agent'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Agents
description: Describe an agent by its ID.
parameters:
- name: agent_id
in: path
description: ID of the agent.
required: true
schema:
type: string
delete:
responses:
'200':
@ -1581,6 +1631,36 @@ paths:
required: true
schema:
type: string
/v1/agents/{agent_id}/sessions:
get:
responses:
'200':
description: A ListAgentSessionsResponse.
content:
application/json:
schema:
$ref: '#/components/schemas/ListAgentSessionsResponse'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Agents
description: List all session(s) of a given agent.
parameters:
- name: agent_id
in: path
description: >-
The ID of the agent to list sessions for.
required: true
schema:
type: string
/v1/eval/benchmarks:
get:
responses:
@ -4690,6 +4770,22 @@ components:
- aggregated_results
title: ScoringResult
description: A scoring result for a single row.
Agent:
type: object
properties:
agent_id:
type: string
agent_config:
$ref: '#/components/schemas/AgentConfig'
created_at:
type: string
format: date-time
additionalProperties: false
required:
- agent_id
- agent_config
- created_at
title: Agent
Session:
type: object
properties:
@ -5579,6 +5675,28 @@ components:
required:
- content
title: ToolInvocationResult
ListAgentSessionsResponse:
type: object
properties:
data:
type: array
items:
$ref: '#/components/schemas/Session'
additionalProperties: false
required:
- data
title: ListAgentSessionsResponse
ListAgentsResponse:
type: object
properties:
data:
type: array
items:
$ref: '#/components/schemas/Agent'
additionalProperties: false
required:
- data
title: ListAgentsResponse
BucketResponse:
type: object
properties:

8
docs/openapi_generator/README.md
View file

@ -1,9 +1 @@
The RFC Specification (OpenAPI format) is generated from the set of API endpoints located in `llama_stack/distribution/server/endpoints.py` using the `generate.py` utility.
Please install the following packages before running the script:
```
pip install fire PyYAML
```
Then simply run `sh run_openapi_generator.sh`

2
docs/source/distributions/building_distro.md
View file

@ -33,6 +33,8 @@ Can be set to any of the following log levels:
The default global log level is `info`. `all` sets the log level for all components.
A user can also set `LLAMA_STACK_LOG_FILE` which will pipe the logs to the specified path as well as to the terminal. An example would be: `export LLAMA_STACK_LOG_FILE=server.log`
### Llama Stack Build
In order to build your own distribution, we recommend you clone the `llama-stack` repository.

1
docs/source/distributions/self_hosted_distro/fireworks.md
View file

@ -41,7 +41,6 @@ The following models are available by default:
- `accounts/fireworks/models/llama-v3p1-8b-instruct (aliases: meta-llama/Llama-3.1-8B-Instruct)`
- `accounts/fireworks/models/llama-v3p1-70b-instruct (aliases: meta-llama/Llama-3.1-70B-Instruct)`
- `accounts/fireworks/models/llama-v3p1-405b-instruct (aliases: meta-llama/Llama-3.1-405B-Instruct-FP8)`
- `accounts/fireworks/models/llama-v3p2-1b-instruct (aliases: meta-llama/Llama-3.2-1B-Instruct)`
- `accounts/fireworks/models/llama-v3p2-3b-instruct (aliases: meta-llama/Llama-3.2-3B-Instruct)`
- `accounts/fireworks/models/llama-v3p2-11b-vision-instruct (aliases: meta-llama/Llama-3.2-11B-Vision-Instruct)`
- `accounts/fireworks/models/llama-v3p2-90b-vision-instruct (aliases: meta-llama/Llama-3.2-90B-Vision-Instruct)`

15
docs/source/references/llama_cli_reference/index.md
View file

@ -1,6 +1,6 @@
# llama (server-side) CLI Reference
The `llama` CLI tool helps you setup and use the Llama Stack. It should be available on your path after installing the `llama-stack` package.
The `llama` CLI tool helps you set up and use the Llama Stack. The CLI is available on your path after installing the `llama-stack` package.
## Installation
@ -27,9 +27,9 @@ You have two ways to install Llama Stack:
## `llama` subcommands
1. `download`: `llama` cli tools supports downloading the model from Meta or Hugging Face.
2. `model`: Lists available models and their properties.
3. `stack`: Allows you to build and run a Llama Stack server. You can read more about this [here](../../distributions/building_distro).
1. `download`: Supports downloading models from Meta or Hugging Face. [Downloading models](#downloading-models)
2. `model`: Lists available models and their properties. [Understanding models](#understand-the-models)
3. `stack`: Allows you to build a stack using the `llama stack` distribution and run a Llama Stack server. You can read more about how to build a Llama Stack distribution in the [Build your own Distribution](../../distributions/building_distro) documentation.
### Sample Usage
@ -117,7 +117,7 @@ You should see a table like this:
+----------------------------------+------------------------------------------+----------------+
```
To download models, you can use the llama download command.
To download models, you can use the `llama download` command.
### Downloading from [Meta](https://llama.meta.com/llama-downloads/)
@ -191,7 +191,7 @@ You should see a table like this:
The `llama model` command helps you explore the model’s interface.
1. `download`: Download the model from different sources. (meta, huggingface)
2. `list`: Lists all the models available for download with hardware requirements to deploy the models.
2. `list`: Lists all the models available for download with hardware requirements for deploying the models.
3. `prompt-format`: Show llama model message formats.
4. `describe`: Describes all the properties of the model.
@ -262,13 +262,12 @@ llama model prompt-format -m Llama3.2-3B-Instruct
![alt text](../../../resources/prompt-format.png)
You will be shown a Markdown formatted description of the model interface and how prompts / messages are formatted for various scenarios.
**NOTE**: Outputs in terminal are color printed to show special tokens.
### Remove model
You can run `llama model remove` to remove unecessary model:
You can run `llama model remove` to remove an unnecessary model:
```
llama model remove -m Llama-Guard-3-8B-int8