phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-06 20:44:58 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: Updating files/content response to return additional fields

Browse source 
Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
This commit is contained in:
Francisco Javier Arceo 2025-08-06 16:55:14 -04:00
parent e12524af85
commit a19c16428f
143 changed files with 6907 additions and 15104 deletions
Download patch file Download diff file Expand all files Collapse all files

209
docs/_static/llama-stack-spec.html vendored
View file

@ -4734,6 +4734,49 @@
}
}
},
"/v1/openai/v1/moderations": {
"post": {
"responses": {
"200": {
"description": "A moderation object.",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/ModerationObject"
}
}
}
},
"400": {
"$ref": "#/components/responses/BadRequest400"
},
"429": {
"$ref": "#/components/responses/TooManyRequests429"
},
"500": {
"$ref": "#/components/responses/InternalServerError500"
},
"default": {
"$ref": "#/components/responses/DefaultError"
}
},
"tags": [
"Safety"
],
"description": "Classifies if text and/or image inputs are potentially harmful.",
"parameters": [],
"requestBody": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/RunModerationRequest"
}
}
},
"required": true
}
}
},
"/v1/safety/run-shield": {
"post": {
"responses": {
@ -14778,6 +14821,47 @@
"text": {
"type": "string",
"description": "The actual text content"
},
"embedding": {
"type": "array",
"items": {
"type": "number"
},
"description": "(Optional) Embedding vector for the content, if available"
},
"created_timestamp": {
"type": "integer",
"description": "(Optional) Timestamp when the content was created"
},
"metadata": {
"type": "object",
"additionalProperties": {
"oneOf": [
{
"type": "null"
},
{
"type": "boolean"
},
{
"type": "number"
},
{
"type": "string"
},
{
"type": "array"
},
{
"type": "object"
}
]
},
"description": "(Optional) Metadata associated with the content, such as source, author, etc."
},
"chunk_metadata": {
"$ref": "#/components/schemas/ChunkMetadata",
"description": "(Optional) Metadata associated with the chunk, such as document ID, source, etc."
}
},
"additionalProperties": false,
@ -16401,6 +16485,131 @@
],
"title": "RunEvalRequest"
},
"RunModerationRequest": {
"type": "object",
"properties": {
"input": {
"oneOf": [
{
"type": "string"
},
{
"type": "array",
"items": {
"type": "string"
}
}
],
"description": "Input (or inputs) to classify. Can be a single string, an array of strings, or an array of multi-modal input objects similar to other models."
},
"model": {
"type": "string",
"description": "The content moderation model you would like to use."
}
},
"additionalProperties": false,
"required": [
"input",
"model"
],
"title": "RunModerationRequest"
},
"ModerationObject": {
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "The unique identifier for the moderation request."
},
"model": {
"type": "string",
"description": "The model used to generate the moderation results."
},
"results": {
"type": "array",
"items": {
"$ref": "#/components/schemas/ModerationObjectResults"
},
"description": "A list of moderation objects"
}
},
"additionalProperties": false,
"required": [
"id",
"model",
"results"
],
"title": "ModerationObject",
"description": "A moderation object."
},
"ModerationObjectResults": {
"type": "object",
"properties": {
"flagged": {
"type": "boolean",
"description": "Whether any of the below categories are flagged."
},
"categories": {
"type": "object",
"additionalProperties": {
"type": "boolean"
},
"description": "A list of the categories, and whether they are flagged or not."
},
"category_applied_input_types": {
"type": "object",
"additionalProperties": {
"type": "array",
"items": {
"type": "string"
}
},
"description": "A list of the categories along with the input type(s) that the score applies to."
},
"category_scores": {
"type": "object",
"additionalProperties": {
"type": "number"
},
"description": "A list of the categories along with their scores as predicted by model. Required set of categories that need to be in response - violence - violence/graphic - harassment - harassment/threatening - hate - hate/threatening - illicit - illicit/violent - sexual - sexual/minors - self-harm - self-harm/intent - self-harm/instructions"
},
"user_message": {
"type": "string"
},
"metadata": {
"type": "object",
"additionalProperties": {
"oneOf": [
{
"type": "null"
},
{
"type": "boolean"
},
{
"type": "number"
},
{
"type": "string"
},
{
"type": "array"
},
{
"type": "object"
}
]
}
}
},
"additionalProperties": false,
"required": [
"flagged",
"metadata"
],
"title": "ModerationObjectResults",
"description": "A moderation object."
},
"RunShieldRequest": {
"type": "object",
"properties": {

152
docs/_static/llama-stack-spec.yaml vendored
View file

@ -3358,6 +3358,36 @@ paths:
schema:
$ref: '#/components/schemas/RunEvalRequest'
required: true
/v1/openai/v1/moderations:
post:
responses:
'200':
description: A moderation object.
content:
application/json:
schema:
$ref: '#/components/schemas/ModerationObject'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Safety
description: >-
Classifies if text and/or image inputs are potentially harmful.
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/RunModerationRequest'
required: true
/v1/safety/run-shield:
post:
responses:
@ -10966,6 +10996,34 @@ components:
text:
type: string
description: The actual text content
embedding:
type: array
items:
type: number
description: >-
(Optional) Embedding vector for the content, if available
created_timestamp:
type: integer
description: >-
(Optional) Timestamp when the content was created
metadata:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
description: >-
(Optional) Metadata associated with the content, such as source, author,
etc.
chunk_metadata:
$ref: '#/components/schemas/ChunkMetadata'
description: >-
(Optional) Metadata associated with the chunk, such as document ID, source,
etc.
additionalProperties: false
required:
- type
@ -12184,6 +12242,100 @@ components:
required:
- benchmark_config
title: RunEvalRequest
RunModerationRequest:
type: object
properties:
input:
oneOf:
- type: string
- type: array
items:
type: string
description: >-
Input (or inputs) to classify. Can be a single string, an array of strings,
or an array of multi-modal input objects similar to other models.
model:
type: string
description: >-
The content moderation model you would like to use.
additionalProperties: false
required:
- input
- model
title: RunModerationRequest
ModerationObject:
type: object
properties:
id:
type: string
description: >-
The unique identifier for the moderation request.
model:
type: string
description: >-
The model used to generate the moderation results.
results:
type: array
items:
$ref: '#/components/schemas/ModerationObjectResults'
description: A list of moderation objects
additionalProperties: false
required:
- id
- model
- results
title: ModerationObject
description: A moderation object.
ModerationObjectResults:
type: object
properties:
flagged:
type: boolean
description: >-
Whether any of the below categories are flagged.
categories:
type: object
additionalProperties:
type: boolean
description: >-
A list of the categories, and whether they are flagged or not.
category_applied_input_types:
type: object
additionalProperties:
type: array
items:
type: string
description: >-
A list of the categories along with the input type(s) that the score applies
to.
category_scores:
type: object
additionalProperties:
type: number
description: >-
A list of the categories along with their scores as predicted by model.
Required set of categories that need to be in response - violence - violence/graphic
- harassment - harassment/threatening - hate - hate/threatening - illicit
- illicit/violent - sexual - sexual/minors - self-harm - self-harm/intent
- self-harm/instructions
user_message:
type: string
metadata:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
additionalProperties: false
required:
- flagged
- metadata
title: ModerationObjectResults
description: A moderation object.
RunShieldRequest:
type: object
properties:

23
docs/source/distributions/building_distro.md
View file

@ -53,24 +53,31 @@ The main points to consider are:
```
llama stack build -h
usage: llama stack build [-h] [--config CONFIG] [--template TEMPLATE] [--list-templates] [--image-type {container,venv}] [--image-name IMAGE_NAME] [--print-deps-only] [--run]
usage: llama stack build [-h] [--config CONFIG] [--template TEMPLATE] [--distro DISTRIBUTION] [--list-distros] [--image-type {container,venv}] [--image-name IMAGE_NAME] [--print-deps-only]
[--run] [--providers PROVIDERS]
Build a Llama stack container
options:
-h, --help show this help message and exit
--config CONFIG Path to a config file to use for the build. You can find example configs in llama_stack.cores/**/build.yaml. If this argument is not provided, you will
be prompted to enter information interactively (default: None)
--template TEMPLATE Name of the example template config to use for build. You may use `llama stack build --list-templates` to check out the available templates (default: None)
--list-templates Show the available templates for building a Llama Stack distribution (default: False)
--config CONFIG Path to a config file to use for the build. You can find example configs in llama_stack.cores/**/build.yaml. If this argument is not provided, you will be prompted to
enter information interactively (default: None)
--template TEMPLATE (deprecated) Name of the example template config to use for build. You may use `llama stack build --list-distros` to check out the available distributions (default:
None)
--distro DISTRIBUTION, --distribution DISTRIBUTION
Name of the distribution to use for build. You may use `llama stack build --list-distros` to check out the available distributions (default: None)
--list-distros, --list-distributions
Show the available distributions for building a Llama Stack distribution (default: False)
--image-type {container,venv}
Image Type to use for the build. If not specified, will use the image type from the template config. (default: None)
--image-name IMAGE_NAME
[for image-type=container|venv] Name of the virtual environment to use for the build. If not specified, currently active environment will be used if
found. (default: None)
[for image-type=container|venv] Name of the virtual environment to use for the build. If not specified, currently active environment will be used if found. (default:
None)
--print-deps-only Print the dependencies for the stack only, without building the stack (default: False)
--run Run the stack after building using the same image type, name, and other applicable arguments (default: False)
--providers PROVIDERS
Build a config for a list of providers and only those providers. This list is formatted like: api1=provider1,api2=provider2. Where there can be multiple providers per
API. (default: None)
```
After this step is complete, a file named `<name>-build.yaml` and template file `<name>-run.yaml` will be generated and saved at the output file path specified at the end of the command.

8
docs/source/distributions/ondevice_distro/android_sdk.md
View file

@ -56,12 +56,12 @@ Breaking down the demo app, this section will show the core pieces that are used
### Setup Remote Inferencing
Start a Llama Stack server on localhost. Here is an example of how you can do this using the firework.ai distribution:
```
python -m venv stack-fireworks
source stack-fireworks/bin/activate # On Windows: stack-fireworks\Scripts\activate
uv venv starter --python 3.12
source starter/bin/activate # On Windows: starter\Scripts\activate
pip install --no-cache llama-stack==0.2.2
llama stack build --distro fireworks --image-type venv
llama stack build --distro starter --image-type venv
export FIREWORKS_API_KEY=<SOME_KEY>
llama stack run fireworks --port 5050
llama stack run starter --port 5050
```
Ensure the Llama Stack server version is the same as the Kotlin SDK Library for maximum compatibility.

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

@ -157,7 +157,7 @@ docker run \
If you've set up your local development environment, you can also build the image using your local virtual environment.
```bash
INFERENCE_MODEL=meta-llama/Llama-3.1-8b-Instruct
INFERENCE_MODEL=meta-llama/Llama-3.1-8B-Instruct
llama stack build --distro nvidia --image-type venv
llama stack run ./run.yaml \
--port 8321 \

11
docs/source/getting_started/demo_script.py
View file

@ -52,11 +52,16 @@ agent = Agent(
prompt = "How do you do great work?"
print("prompt>", prompt)
use_stream = True
response = agent.create_turn(
messages=[{"role": "user", "content": prompt}],
session_id=agent.create_session("rag_session"),
stream=True,
stream=use_stream,
)
for log in AgentEventLogger().log(response):
log.print()
# Only call `AgentEventLogger().log(response)` for streaming responses.
if use_stream:
for log in AgentEventLogger().log(response):
log.print()
else:
print(response)

8
docs/source/getting_started/detailed_tutorial.md
View file

@ -150,13 +150,7 @@ pip install llama-stack-client
```
:::
:::{tab-item} Install with `venv`
```bash
python -m venv stack-client
source stack-client/bin/activate # On Windows: stack-client\Scripts\activate
pip install llama-stack-client
```
:::
::::
Now let's use the `llama-stack-client` [CLI](../references/llama_stack_client_cli_reference.md) to check the

2
docs/source/providers/agents/index.md
View file

@ -1,4 +1,4 @@
# Agents
# Agents
## Overview

2
docs/source/providers/datasetio/index.md
View file

@ -1,4 +1,4 @@
# Datasetio
# Datasetio
## Overview

2
docs/source/providers/eval/index.md
View file

@ -1,4 +1,4 @@
# Eval
# Eval
## Overview

2
docs/source/providers/files/index.md
View file

@ -1,4 +1,4 @@
# Files
# Files
## Overview

2
docs/source/providers/files/inline_localfs.md
View file

@ -8,7 +8,7 @@ Local filesystem-based file storage provider for managing files and documents lo
| Field | Type | Required | Default | Description |
|-------|------|----------|---------|-------------|
| `storage_dir` | `<class 'str'>` | No | PydanticUndefined | Directory to store uploaded files |
| `storage_dir` | `<class 'str'>` | No | | Directory to store uploaded files |
| `metadata_store` | `utils.sqlstore.sqlstore.SqliteSqlStoreConfig \| utils.sqlstore.sqlstore.PostgresSqlStoreConfig` | No | sqlite | SQL store configuration for file metadata |
| `ttl_secs` | `<class 'int'>` | No | 31536000 | |

2
docs/source/providers/inference/index.md
View file

@ -1,4 +1,4 @@
# Inference
# Inference
## Overview

2
docs/source/providers/inference/remote_hf_endpoint.md
View file

@ -8,7 +8,7 @@ HuggingFace Inference Endpoints provider for dedicated model serving.
| Field | Type | Required | Default | Description |
|-------|------|----------|---------|-------------|
| `endpoint_name` | `<class 'str'>` | No | PydanticUndefined | The name of the Hugging Face Inference Endpoint in the format of '{namespace}/{endpoint_name}' (e.g. 'my-cool-org/meta-llama-3-1-8b-instruct-rce'). Namespace is optional and will default to the user account if not provided. |
| `endpoint_name` | `<class 'str'>` | No | | The name of the Hugging Face Inference Endpoint in the format of '{namespace}/{endpoint_name}' (e.g. 'my-cool-org/meta-llama-3-1-8b-instruct-rce'). Namespace is optional and will default to the user account if not provided. |
| `api_token` | `pydantic.types.SecretStr \| None` | No | | Your Hugging Face user access token (will default to locally saved token if not provided) |
## Sample Configuration

2
docs/source/providers/inference/remote_hf_serverless.md
View file

@ -8,7 +8,7 @@ HuggingFace Inference API serverless provider for on-demand model inference.
| Field | Type | Required | Default | Description |
|-------|------|----------|---------|-------------|
| `huggingface_repo` | `<class 'str'>` | No | PydanticUndefined | The model ID of the model on the Hugging Face Hub (e.g. 'meta-llama/Meta-Llama-3.1-70B-Instruct') |
| `huggingface_repo` | `<class 'str'>` | No | | The model ID of the model on the Hugging Face Hub (e.g. 'meta-llama/Meta-Llama-3.1-70B-Instruct') |
| `api_token` | `pydantic.types.SecretStr \| None` | No | | Your Hugging Face user access token (will default to locally saved token if not provided) |
## Sample Configuration

2
docs/source/providers/inference/remote_tgi.md
View file

@ -8,7 +8,7 @@ Text Generation Inference (TGI) provider for HuggingFace model serving.
| Field | Type | Required | Default | Description |
|-------|------|----------|---------|-------------|
| `url` | `<class 'str'>` | No | PydanticUndefined | The URL for the TGI serving endpoint |
| `url` | `<class 'str'>` | No | | The URL for the TGI serving endpoint |
## Sample Configuration

2
docs/source/providers/post_training/index.md
View file

@ -1,4 +1,4 @@
# Post_Training
# Post_Training
## Overview

3
docs/source/providers/post_training/inline_huggingface.md
View file

@ -27,7 +27,7 @@ HuggingFace-based post-training provider for fine-tuning models using the Huggin
| `dpo_beta` | `<class 'float'>` | No | 0.1 | |
| `use_reference_model` | `<class 'bool'>` | No | True | |
| `dpo_loss_type` | `Literal['sigmoid', 'hinge', 'ipo', 'kto_pair'` | No | sigmoid | |
| `dpo_output_dir` | `<class 'str'>` | No | ./checkpoints/dpo | |
| `dpo_output_dir` | `<class 'str'>` | No | | |
## Sample Configuration
@ -35,6 +35,7 @@ HuggingFace-based post-training provider for fine-tuning models using the Huggin
checkpoint_format: huggingface
distributed_backend: null
device: cpu
dpo_output_dir: ~/.llama/dummy/dpo_output
```

2
docs/source/providers/safety/index.md
View file

@ -1,4 +1,4 @@
# Safety
# Safety
## Overview

2
docs/source/providers/scoring/index.md
View file

@ -1,4 +1,4 @@
# Scoring
# Scoring
## Overview

2
docs/source/providers/telemetry/index.md
View file

@ -1,4 +1,4 @@
# Telemetry
# Telemetry
## Overview

2
docs/source/providers/tool_runtime/index.md
View file

@ -1,4 +1,4 @@
# Tool_Runtime
# Tool_Runtime
## Overview

2
docs/source/providers/vector_io/index.md
View file

@ -1,4 +1,4 @@
# Vector_Io
# Vector_Io
## Overview

2
docs/source/providers/vector_io/inline_chromadb.md
View file

@ -41,7 +41,7 @@ See [Chroma's documentation](https://docs.trychroma.com/docs/overview/introducti
| Field | Type | Required | Default | Description |
|-------|------|----------|---------|-------------|
| `db_path` | `<class 'str'>` | No | PydanticUndefined | |
| `db_path` | `<class 'str'>` | No | | |
| `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig` | No | sqlite | Config for KV store backend |
## Sample Configuration

2
docs/source/providers/vector_io/inline_milvus.md
View file

@ -10,7 +10,7 @@ Please refer to the remote provider documentation.
| Field | Type | Required | Default | Description |
|-------|------|----------|---------|-------------|
| `db_path` | `<class 'str'>` | No | PydanticUndefined | |
| `db_path` | `<class 'str'>` | No | | |
| `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig` | No | sqlite | Config for KV store backend (SQLite only for now) |
| `consistency_level` | `<class 'str'>` | No | Strong | The consistency level of the Milvus server |

2
docs/source/providers/vector_io/inline_qdrant.md
View file

@ -50,7 +50,7 @@ See the [Qdrant documentation](https://qdrant.tech/documentation/) for more deta
| Field | Type | Required | Default | Description |
|-------|------|----------|---------|-------------|
| `path` | `<class 'str'>` | No | PydanticUndefined | |
| `path` | `<class 'str'>` | No | | |
| `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig` | No | sqlite | |
## Sample Configuration

2
docs/source/providers/vector_io/inline_sqlite-vec.md
View file

@ -205,7 +205,7 @@ See [sqlite-vec's GitHub repo](https://github.com/asg017/sqlite-vec/tree/main) f
| Field | Type | Required | Default | Description |
|-------|------|----------|---------|-------------|
| `db_path` | `<class 'str'>` | No | PydanticUndefined | Path to the SQLite database file |
| `db_path` | `<class 'str'>` | No | | Path to the SQLite database file |
| `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig` | No | sqlite | Config for KV store backend (SQLite only for now) |
## Sample Configuration

2
docs/source/providers/vector_io/inline_sqlite_vec.md
View file

@ -10,7 +10,7 @@ Please refer to the sqlite-vec provider documentation.
| Field | Type | Required | Default | Description |
|-------|------|----------|---------|-------------|
| `db_path` | `<class 'str'>` | No | PydanticUndefined | Path to the SQLite database file |
| `db_path` | `<class 'str'>` | No | | Path to the SQLite database file |
| `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig` | No | sqlite | Config for KV store backend (SQLite only for now) |
## Sample Configuration

2
docs/source/providers/vector_io/remote_chromadb.md
View file

@ -40,7 +40,7 @@ See [Chroma's documentation](https://docs.trychroma.com/docs/overview/introducti
| Field | Type | Required | Default | Description |
|-------|------|----------|---------|-------------|
| `url` | `str \| None` | No | PydanticUndefined | |
| `url` | `str \| None` | No | | |
| `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig` | No | sqlite | Config for KV store backend |
## Sample Configuration

4
docs/source/providers/vector_io/remote_milvus.md
View file

@ -111,8 +111,8 @@ For more details on TLS configuration, refer to the [TLS setup guide](https://mi
| Field | Type | Required | Default | Description |
|-------|------|----------|---------|-------------|
| `uri` | `<class 'str'>` | No | PydanticUndefined | The URI of the Milvus server |
| `token` | `str \| None` | No | PydanticUndefined | The token of the Milvus server |
| `uri` | `<class 'str'>` | No | | The URI of the Milvus server |
| `token` | `str \| None` | No | | The token of the Milvus server |
| `consistency_level` | `<class 'str'>` | No | Strong | The consistency level of the Milvus server |
| `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig` | No | sqlite | Config for KV store backend |
| `config` | `dict` | No | {} | This configuration allows additional fields to be passed through to the underlying Milvus client. See the [Milvus](https://milvus.io/docs/install-overview.md) documentation for more details about Milvus in general. |

2
docs/source/references/llama_cli_reference/download_models.md
View file

@ -19,7 +19,7 @@ You have two ways to install Llama Stack:
cd ~/local
git clone git@github.com:meta-llama/llama-stack.git
python -m venv myenv
uv venv myenv --python 3.12
source myenv/bin/activate # On Windows: myenv\Scripts\activate
cd llama-stack

2
docs/source/references/llama_cli_reference/index.md
View file

@ -19,7 +19,7 @@ You have two ways to install Llama Stack:
cd ~/local
git clone git@github.com:meta-llama/llama-stack.git
python -m venv myenv
uv venv myenv --python 3.12
source myenv/bin/activate # On Windows: myenv\Scripts\activate
cd llama-stack