phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

Merge branch 'main' into eval_api_final

Browse source
This commit is contained in:
Xi Yan 2025-03-18 14:49:57 -07:00
commit 46f2ba5910
46 changed files with 1030 additions and 423 deletions
Download patch file Download diff file Expand all files Collapse all files

64
docs/_static/llama-stack-spec.html vendored
View file

@ -1126,6 +1126,7 @@
"application/json": {
"schema": {
"$ref": "#/components/schemas/Benchmark"
"$ref": "#/components/schemas/Benchmark"
}
}
}
@ -1168,14 +1169,7 @@
"content": {
"application/json": {
"schema": {
"oneOf": [
{
"$ref": "#/components/schemas/Dataset"
},
{
"type": "null"
}
]
"$ref": "#/components/schemas/Dataset"
}
}
}
@ -1250,14 +1244,7 @@
"content": {
"application/json": {
"schema": {
"oneOf": [
{
"$ref": "#/components/schemas/Model"
},
{
"type": "null"
}
]
"$ref": "#/components/schemas/Model"
}
}
}
@ -1332,14 +1319,7 @@
"content": {
"application/json": {
"schema": {
"oneOf": [
{
"$ref": "#/components/schemas/Shield"
},
{
"type": "null"
}
]
"$ref": "#/components/schemas/Shield"
}
}
}
@ -1642,14 +1622,7 @@
"content": {
"application/json": {
"schema": {
"oneOf": [
{
"$ref": "#/components/schemas/PostTrainingJobArtifactsResponse"
},
{
"type": "null"
}
]
"$ref": "#/components/schemas/PostTrainingJobArtifactsResponse"
}
}
}
@ -1691,14 +1664,7 @@
"content": {
"application/json": {
"schema": {
"oneOf": [
{
"$ref": "#/components/schemas/PostTrainingJobStatusResponse"
},
{
"type": "null"
}
]
"$ref": "#/components/schemas/PostTrainingJobStatusResponse"
}
}
}
@ -1773,14 +1739,7 @@
"content": {
"application/json": {
"schema": {
"oneOf": [
{
"$ref": "#/components/schemas/FileUploadResponse"
},
{
"type": "null"
}
]
"$ref": "#/components/schemas/FileUploadResponse"
}
}
}
@ -1882,14 +1841,7 @@
"content": {
"application/json": {
"schema": {
"oneOf": [
{
"$ref": "#/components/schemas/VectorDB"
},
{
"type": "null"
}
]
"$ref": "#/components/schemas/VectorDB"
}
}
}

29
docs/_static/llama-stack-spec.yaml vendored
View file

@ -774,6 +774,7 @@ paths:
application/json:
schema:
$ref: '#/components/schemas/Benchmark'
$ref: '#/components/schemas/Benchmark'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
@ -802,9 +803,7 @@ paths:
content:
application/json:
schema:
oneOf:
- $ref: '#/components/schemas/Dataset'
- type: 'null'
$ref: '#/components/schemas/Dataset'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
@ -855,9 +854,7 @@ paths:
content:
application/json:
schema:
oneOf:
- $ref: '#/components/schemas/Model'
- type: 'null'
$ref: '#/components/schemas/Model'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
@ -908,9 +905,7 @@ paths:
content:
application/json:
schema:
oneOf:
- $ref: '#/components/schemas/Shield'
- type: 'null'
$ref: '#/components/schemas/Shield'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
@ -1112,9 +1107,7 @@ paths:
content:
application/json:
schema:
oneOf:
- $ref: '#/components/schemas/PostTrainingJobArtifactsResponse'
- type: 'null'
$ref: '#/components/schemas/PostTrainingJobArtifactsResponse'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
@ -1142,9 +1135,7 @@ paths:
content:
application/json:
schema:
oneOf:
- $ref: '#/components/schemas/PostTrainingJobStatusResponse'
- type: 'null'
$ref: '#/components/schemas/PostTrainingJobStatusResponse'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
@ -1195,9 +1186,7 @@ paths:
content:
application/json:
schema:
oneOf:
- $ref: '#/components/schemas/FileUploadResponse'
- type: 'null'
$ref: '#/components/schemas/FileUploadResponse'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
@ -1266,9 +1255,7 @@ paths:
content:
application/json:
schema:
oneOf:
- $ref: '#/components/schemas/VectorDB'
- type: 'null'
$ref: '#/components/schemas/VectorDB'
'400':
$ref: '#/components/responses/BadRequest400'
'429':

12
docs/openapi_generator/generate.py
View file

@ -12,7 +12,7 @@
from datetime import datetime
from pathlib import Path
import sys
import fire
import ruamel.yaml as yaml
@ -21,7 +21,7 @@ from llama_stack.distribution.stack import LlamaStack # noqa: E402
from .pyopenapi.options import Options # noqa: E402
from .pyopenapi.specification import Info, Server # noqa: E402
from .pyopenapi.utility import Specification # noqa: E402
from .pyopenapi.utility import Specification, validate_api_method_return_types # noqa: E402
def str_presenter(dumper, data):
@ -39,6 +39,14 @@ def main(output_dir: str):
if not output_dir.exists():
raise ValueError(f"Directory {output_dir} does not exist")
# Validate API protocols before generating spec
print("Validating API method return types...")
return_type_errors = validate_api_method_return_types()
if return_type_errors:
print("\nAPI Method Return Type Validation Errors:\n")
for error in return_type_errors:
print(error)
sys.exit(1)
now = str(datetime.now())
print(
"Converting the spec to YAML (openapi.yaml) and HTML (openapi.html) at " + now

39
docs/openapi_generator/pyopenapi/utility.py
View file

@ -6,16 +6,19 @@
import json
import typing
import inspect
import os
from pathlib import Path
from typing import TextIO
from typing import Any, Dict, List, Optional, Protocol, Type, Union, get_type_hints, get_origin, get_args
from llama_stack.strong_typing.schema import object_to_json, StrictJsonType
from llama_stack.distribution.resolver import api_protocol_map
from .generator import Generator
from .options import Options
from .specification import Document
THIS_DIR = Path(__file__).parent
@ -114,3 +117,37 @@ class Specification:
)
f.write(html)
def is_optional_type(type_: Any) -> bool:
"""Check if a type is Optional."""
origin = get_origin(type_)
args = get_args(type_)
return origin is Optional or (origin is Union and type(None) in args)
def validate_api_method_return_types() -> List[str]:
"""Validate that all API methods have proper return types."""
errors = []
protocols = api_protocol_map()
for protocol_name, protocol in protocols.items():
methods = inspect.getmembers(protocol, predicate=inspect.isfunction)
for method_name, method in methods:
if not hasattr(method, '__webmethod__'):
continue
# Only check GET methods
if method.__webmethod__.method != "GET":
continue
hints = get_type_hints(method)
if 'return' not in hints:
errors.append(f"Method {protocol_name}.{method_name} has no return type annotation")
else:
return_type = hints['return']
if is_optional_type(return_type):
errors.append(f"Method {protocol_name}.{method_name} returns Optional type")
return errors

8
docs/source/distributions/building_distro.md
View file

@ -185,8 +185,12 @@ llama stack build --config llama_stack/templates/ollama/build.yaml
:::
:::{tab-item} Building Container
> [!TIP]
> Podman is supported as an alternative to Docker. Set `CONTAINER_BINARY` to `podman` in your environment to use Podman.
```{admonition} Podman Alternative
:class: tip
Podman is supported as an alternative to Docker. Set `CONTAINER_BINARY` to `podman` in your environment to use Podman.
```
To build a container image, you may start off from a template and use the `--image-type container` flag to specify `container` as the build image type.

27
docs/source/playground/index.md
View file

@ -92,6 +92,8 @@ Interactive pages for users to play with and explore Llama Stack API capabilitie
## Starting the Llama Stack Playground
### Llama CLI
To start the Llama Stack Playground, run the following commands:
1. Start up the Llama Stack API server
@ -107,3 +109,28 @@ cd llama_stack/distribution/ui
pip install -r requirements.txt
streamlit run app.py
```
### Docker
Playground can also be started in a docker image:
```sh
export LLAMA_STACK_URL=http://localhost:11434
docker run \
-p 8501:8501 \
-e LLAMA_STACK_ENDPOINT=$LLAMA_STACK_URL \
quay.io/jland/llama-stack-playground
```
## Configurable Environment Variables
## Environment Variables
| Environment Variable | Description | Default Value |
|----------------------------|------------------------------------|---------------------------|
| LLAMA_STACK_ENDPOINT | The endpoint for the Llama Stack | http://localhost:8321 |
| FIREWORKS_API_KEY | API key for Fireworks provider | (empty string) |
| TOGETHER_API_KEY | API key for Together provider | (empty string) |
| SAMBANOVA_API_KEY | API key for SambaNova provider | (empty string) |
| OPENAI_API_KEY | API key for OpenAI provider | (empty string) |

21
docs/source/providers/vector_io/qdrant.md
View file

@ -3,21 +3,36 @@ orphan: true
---
# Qdrant
[Qdrant](https://qdrant.tech/documentation/) is a remote vector database provider for Llama Stack. It
[Qdrant](https://qdrant.tech/documentation/) is an inline and remote vector database provider for Llama Stack. It
allows you to store and query vectors directly in memory.
That means you'll get fast and efficient vector retrieval.
> By default, Qdrant stores vectors in RAM, delivering incredibly fast access for datasets that fit comfortably in
> memory. But when your dataset exceeds RAM capacity, Qdrant offers Memmap as an alternative.
>
> \[[An Introduction to Vector Databases](https://qdrant.tech/articles/what-is-a-vector-database/)\]
## Features
- Easy to use
- Lightweight and easy to use
- Fully integrated with Llama Stack
- Apache 2.0 license terms
- Store embeddings and their metadata
- Supports search by
[Keyword](https://qdrant.tech/articles/qdrant-introduces-full-text-filters-and-indexes/)
and [Hybrid](https://qdrant.tech/articles/hybrid-search/#building-a-hybrid-search-system-in-qdrant) search
- [Multilingual and Multimodal retrieval](https://qdrant.tech/documentation/multimodal-search/)
- [Medatata filtering](https://qdrant.tech/articles/vector-search-filtering/)
- [GPU support](https://qdrant.tech/documentation/guides/running-with-gpu/)
## Usage
To use Qdrant in your Llama Stack project, follow these steps:
1. Install the necessary dependencies.
2. Configure your Llama Stack project to use Faiss.
2. Configure your Llama Stack project to use Qdrant.
3. Start storing and querying vectors.
## Installation