phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-20 19:56:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'main' into nvidia-e2e-notebook

Browse source
This commit is contained in:
Jash Gulabrai 2025-05-19 09:23:07 -04:00
commit 51b68b4be6
234 changed files with 21943 additions and 7540 deletions
Download patch file Download diff file Expand all files Collapse all files

3956
docs/_static/llama-stack-spec.html vendored
View file

File diff suppressed because it is too large Load diff

2930
docs/_static/llama-stack-spec.yaml vendored
View file

File diff suppressed because it is too large Load diff

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/notebooks/Llama_Stack_RAG_Lifecycle.ipynb
View file

@ -840,7 +840,6 @@
" \"memory_optimizations.rst\",\n",
" \"chat.rst\",\n",
" \"llama3.rst\",\n",
" \"datasets.rst\",\n",
" \"qat_finetune.rst\",\n",
" \"lora_finetune.rst\",\n",
"]\n",
@ -1586,7 +1585,6 @@
" \"memory_optimizations.rst\",\n",
" \"chat.rst\",\n",
" \"llama3.rst\",\n",
" \"datasets.rst\",\n",
" \"qat_finetune.rst\",\n",
" \"lora_finetune.rst\",\n",
"]\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(

4
docs/openapi_generator/pyopenapi/generator.py
View file

@ -759,7 +759,7 @@ class Generator:
)
return Operation(
tags=[op.defining_class.__name__],
tags=[getattr(op.defining_class, "API_NAMESPACE", op.defining_class.__name__)],
summary=None,
# summary=doc_string.short_description,
description=description,
@ -805,6 +805,8 @@ class Generator:
operation_tags: List[Tag] = []
for cls in endpoint_classes:
doc_string = parse_type(cls)
if hasattr(cls, "API_NAMESPACE") and cls.API_NAMESPACE != cls.__name__:
continue
operation_tags.append(
Tag(
name=cls.__name__,

50
docs/openapi_generator/pyopenapi/utility.py
View file

@ -174,14 +174,64 @@ 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"
def _validate_has_return_in_docstring(method) -> str | None:
source = inspect.getsource(method)
return_type = method.__annotations__.get('return')
if return_type is not None and return_type != type(None) and ":returns:" not in source:
return "does not have a ':returns:' in its docstring"
def _validate_has_params_in_docstring(method) -> str | None:
source = inspect.getsource(method)
sig = inspect.signature(method)
# Only check if the method has more than one parameter
if len(sig.parameters) > 1 and ":param" not in source:
return "does not have a ':param' in its docstring"
def _validate_has_no_return_none_in_docstring(method) -> str | None:
source = inspect.getsource(method)
return_type = method.__annotations__.get('return')
if return_type is None and ":returns: None" in source:
return "has a ':returns: None' in its docstring which is redundant for None-returning functions"
def _validate_docstring_lines_end_with_dot(method) -> str | None:
docstring = inspect.getdoc(method)
if docstring is None:
return None
lines = docstring.split('\n')
for line in lines:
line = line.strip()
if line and not any(line.endswith(char) for char in '.:{}[]()",'):
return f"docstring line '{line}' does not end with a valid character: . : {{ }} [ ] ( ) , \""
_VALIDATORS = {
"GET": [
_validate_api_method_return_type,
_validate_list_parameters_contain_data,
_validate_api_method_doesnt_return_list,
_validate_has_ellipsis,
_validate_has_return_in_docstring,
_validate_has_params_in_docstring,
_validate_docstring_lines_end_with_dot,
],
"DELETE": [
_validate_api_delete_method_returns_none,
_validate_has_ellipsis,
_validate_has_return_in_docstring,
_validate_has_params_in_docstring,
_validate_has_no_return_none_in_docstring
],
"POST": [
_validate_has_ellipsis,
_validate_has_return_in_docstring,
_validate_has_params_in_docstring,
_validate_has_no_return_none_in_docstring,
_validate_docstring_lines_end_with_dot,
],
}

18
docs/source/building_applications/rag.md
View file

@ -51,6 +51,7 @@ chunks = [
"mime_type": "text/plain",
"metadata": {
"document_id": "doc1",
"author": "Jane Doe",
},
},
]
@ -98,6 +99,17 @@ results = client.tool_runtime.rag_tool.query(
)
```
You can configure how the RAG tool adds metadata to the context if you find it useful for your application. Simply add:
```python
# Query documents
results = client.tool_runtime.rag_tool.query(
vector_db_ids=[vector_db_id],
content="What do you know about...",
query_config={
"chunk_template": "Result {index}\nContent: {chunk.content}\nMetadata: {metadata}\n",
},
)
```
### Building RAG-Enhanced Agents
One of the most powerful patterns is combining agents with RAG capabilities. Here's a complete example:
@ -115,6 +127,12 @@ agent = Agent(
"name": "builtin::rag/knowledge_search",
"args": {
"vector_db_ids": [vector_db_id],
# Defaults
"query_config": {
"chunk_size_in_tokens": 512,
"chunk_overlap_in_tokens": 0,
"chunk_template": "Result {index}\nContent: {chunk.content}\nMetadata: {metadata}\n",
},
},
}
],

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

2
docs/source/conf.py
View file

@ -110,6 +110,8 @@ html_theme_options = {
"canonical_url": "https://github.com/meta-llama/llama-stack",
"collapse_navigation": False,
# "style_nav_header_background": "#c3c9d4",
'display_version': True,
'version_selector': True,
}
default_dark_mode = False

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

7
docs/source/distributions/building_distro.md
View file

@ -178,7 +178,7 @@ image_name: ollama
image_type: conda
# If some providers are external, you can specify the path to the implementation
external_providers_dir: /etc/llama-stack/providers.d
external_providers_dir: ~/.llama/providers.d
```
```
@ -206,7 +206,7 @@ distribution_spec:
image_type: container
image_name: ci-test
# Path to external provider implementations
external_providers_dir: /etc/llama-stack/providers.d
external_providers_dir: ~/.llama/providers.d
```
Here's an example for a custom Ollama provider:
@ -271,7 +271,7 @@ Now, let's start the Llama Stack Distribution Server. You will need the YAML con
```
llama stack run -h
usage: llama stack run [-h] [--port PORT] [--image-name IMAGE_NAME] [--disable-ipv6] [--env KEY=VALUE] [--tls-keyfile TLS_KEYFILE] [--tls-certfile TLS_CERTFILE]
usage: llama stack run [-h] [--port PORT] [--image-name IMAGE_NAME] [--env KEY=VALUE] [--tls-keyfile TLS_KEYFILE] [--tls-certfile TLS_CERTFILE]
[--image-type {conda,container,venv}]
config
@ -285,7 +285,6 @@ options:
--port PORT Port to run the server on. It can also be passed via the env var LLAMA_STACK_PORT. (default: 8321)
--image-name IMAGE_NAME
Name of the image to run. Defaults to the current environment (default: None)
--disable-ipv6 Disable IPv6 support (default: False)
--env KEY=VALUE Environment variables to pass to the server in KEY=VALUE format. Can be specified multiple times. (default: [])
--tls-keyfile TLS_KEYFILE
Path to TLS key file for HTTPS (default: None)

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

@ -172,7 +172,7 @@ spec:
- name: llama-stack
image: localhost/llama-stack-run-k8s:latest
imagePullPolicy: IfNotPresent
command: ["python", "-m", "llama_stack.distribution.server.server", "--yaml-config", "/app/config.yaml"]
command: ["python", "-m", "llama_stack.distribution.server.server", "--config", "/app/config.yaml"]
ports:
- containerPort: 5000
volumeMounts:

4
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` |
@ -70,7 +70,7 @@ docker run \
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
-v ./run.yaml:/root/my-run.yaml \
llamastack/distribution-watsonx \
--yaml-config /root/my-run.yaml \
--config /root/my-run.yaml \
--port $LLAMA_STACK_PORT \
--env WATSONX_API_KEY=$WATSONX_API_KEY \
--env WATSONX_PROJECT_ID=$WATSONX_PROJECT_ID \

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

@ -52,7 +52,7 @@ docker run \
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
-v ./run.yaml:/root/my-run.yaml \
llamastack/distribution-cerebras \
--yaml-config /root/my-run.yaml \
--config /root/my-run.yaml \
--port $LLAMA_STACK_PORT \
--env CEREBRAS_API_KEY=$CEREBRAS_API_KEY
```

4
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` |
@ -155,7 +155,7 @@ docker run \
-v $HOME/.llama:/root/.llama \
-v ./llama_stack/templates/tgi/run-with-safety.yaml:/root/my-run.yaml \
llamastack/distribution-dell \
--yaml-config /root/my-run.yaml \
--config /root/my-run.yaml \
--port $LLAMA_STACK_PORT \
--env INFERENCE_MODEL=$INFERENCE_MODEL \
--env DEH_URL=$DEH_URL \

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

@ -144,7 +144,7 @@ docker run \
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
-v ./run.yaml:/root/my-run.yaml \
llamastack/distribution-nvidia \
--yaml-config /root/my-run.yaml \
--config /root/my-run.yaml \
--port $LLAMA_STACK_PORT \
--env NVIDIA_API_KEY=$NVIDIA_API_KEY
```

3
docs/source/distributions/self_hosted_distro/ollama.md
View file

@ -19,6 +19,7 @@ The `llamastack/distribution-ollama` distribution consists of the following prov
| datasetio | `remote::huggingface`, `inline::localfs` |
| eval | `inline::meta-reference` |
| inference | `remote::ollama` |
| post_training | `inline::huggingface` |
| safety | `inline::llama-guard` |
| scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` |
| telemetry | `inline::meta-reference` |
@ -97,7 +98,7 @@ docker run \
-v ~/.llama:/root/.llama \
-v ./llama_stack/templates/ollama/run-with-safety.yaml:/root/my-run.yaml \
llamastack/distribution-ollama \
--yaml-config /root/my-run.yaml \
--config /root/my-run.yaml \
--port $LLAMA_STACK_PORT \
--env INFERENCE_MODEL=$INFERENCE_MODEL \
--env SAFETY_MODEL=$SAFETY_MODEL \

4
docs/source/distributions/self_hosted_distro/remote-vllm.md
View file

@ -233,7 +233,7 @@ docker run \
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
-v ./llama_stack/templates/remote-vllm/run.yaml:/root/my-run.yaml \
llamastack/distribution-remote-vllm \
--yaml-config /root/my-run.yaml \
--config /root/my-run.yaml \
--port $LLAMA_STACK_PORT \
--env INFERENCE_MODEL=$INFERENCE_MODEL \
--env VLLM_URL=http://host.docker.internal:$INFERENCE_PORT/v1
@ -255,7 +255,7 @@ docker run \
-v ~/.llama:/root/.llama \
-v ./llama_stack/templates/remote-vllm/run-with-safety.yaml:/root/my-run.yaml \
llamastack/distribution-remote-vllm \
--yaml-config /root/my-run.yaml \
--config /root/my-run.yaml \
--port $LLAMA_STACK_PORT \
--env INFERENCE_MODEL=$INFERENCE_MODEL \
--env VLLM_URL=http://host.docker.internal:$INFERENCE_PORT/v1 \

26
docs/source/distributions/self_hosted_distro/sambanova.md
View file

@ -16,10 +16,10 @@ The `llamastack/distribution-sambanova` distribution consists of the following p
| API | Provider(s) |
|-----|-------------|
| agents | `inline::meta-reference` |
| inference | `remote::sambanova` |
| inference | `remote::sambanova`, `inline::sentence-transformers` |
| safety | `inline::llama-guard` |
| telemetry | `inline::meta-reference` |
| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::rag-runtime` |
| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::rag-runtime`, `remote::model-context-protocol`, `remote::wolfram-alpha` |
| vector_io | `inline::faiss`, `remote::chromadb`, `remote::pgvector` |
@ -28,22 +28,22 @@ The `llamastack/distribution-sambanova` distribution consists of the following p
The following environment variables can be configured:
- `LLAMASTACK_PORT`: Port for the Llama Stack distribution server (default: `8321`)
- `SAMBANOVA_API_KEY`: SambaNova.AI API Key (default: ``)
- `SAMBANOVA_API_KEY`: SambaNova API Key (default: ``)
### Models
The following models are available by default:
- `Meta-Llama-3.1-8B-Instruct (aliases: meta-llama/Llama-3.1-8B-Instruct)`
- `Meta-Llama-3.1-70B-Instruct (aliases: meta-llama/Llama-3.1-70B-Instruct)`
- `Meta-Llama-3.1-405B-Instruct (aliases: meta-llama/Llama-3.1-405B-Instruct-FP8)`
- `Meta-Llama-3.2-1B-Instruct (aliases: meta-llama/Llama-3.2-1B-Instruct)`
- `Meta-Llama-3.2-3B-Instruct (aliases: meta-llama/Llama-3.2-3B-Instruct)`
- `Meta-Llama-3.3-70B-Instruct (aliases: meta-llama/Llama-3.3-70B-Instruct)`
- `Llama-3.2-11B-Vision-Instruct (aliases: meta-llama/Llama-3.2-11B-Vision-Instruct)`
- `Llama-3.2-90B-Vision-Instruct (aliases: meta-llama/Llama-3.2-90B-Vision-Instruct)`
- `Meta-Llama-Guard-3-8B (aliases: meta-llama/Llama-Guard-3-8B)`
- `Llama-4-Scout-17B-16E-Instruct (aliases: meta-llama/Llama-4-Scout-17B-16E-Instruct)`
- `sambanova/Meta-Llama-3.1-8B-Instruct (aliases: meta-llama/Llama-3.1-8B-Instruct)`
- `sambanova/Meta-Llama-3.1-405B-Instruct (aliases: meta-llama/Llama-3.1-405B-Instruct-FP8)`
- `sambanova/Meta-Llama-3.2-1B-Instruct (aliases: meta-llama/Llama-3.2-1B-Instruct)`
- `sambanova/Meta-Llama-3.2-3B-Instruct (aliases: meta-llama/Llama-3.2-3B-Instruct)`
- `sambanova/Meta-Llama-3.3-70B-Instruct (aliases: meta-llama/Llama-3.3-70B-Instruct)`
- `sambanova/Llama-3.2-11B-Vision-Instruct (aliases: meta-llama/Llama-3.2-11B-Vision-Instruct)`
- `sambanova/Llama-3.2-90B-Vision-Instruct (aliases: meta-llama/Llama-3.2-90B-Vision-Instruct)`
- `sambanova/Llama-4-Scout-17B-16E-Instruct (aliases: meta-llama/Llama-4-Scout-17B-16E-Instruct)`
- `sambanova/Llama-4-Maverick-17B-128E-Instruct (aliases: meta-llama/Llama-4-Maverick-17B-128E-Instruct)`
- `sambanova/Meta-Llama-Guard-3-8B (aliases: meta-llama/Llama-Guard-3-8B)`
### Prerequisite: API Keys

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

@ -117,7 +117,7 @@ docker run \
-v ~/.llama:/root/.llama \
-v ./llama_stack/templates/tgi/run-with-safety.yaml:/root/my-run.yaml \
llamastack/distribution-tgi \
--yaml-config /root/my-run.yaml \
--config /root/my-run.yaml \
--port $LLAMA_STACK_PORT \
--env INFERENCE_MODEL=$INFERENCE_MODEL \
--env TGI_URL=http://host.docker.internal:$INFERENCE_PORT \

4
docs/source/getting_started/detailed_tutorial.md
View file

@ -42,7 +42,7 @@ powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | ie
Setup your virtual environment.
```bash
uv venv --python 3.10
uv sync --python 3.10
source .venv/bin/activate
```
## Step 2: Run Llama Stack
@ -445,7 +445,6 @@ from llama_stack_client import LlamaStackClient
from llama_stack_client import Agent, AgentEventLogger
from llama_stack_client.types import Document
import uuid
from termcolor import cprint
client = LlamaStackClient(base_url="http://localhost:8321")
@ -463,7 +462,6 @@ urls = [
"memory_optimizations.rst",
"chat.rst",
"llama3.rst",
"datasets.rst",
"qat_finetune.rst",
"lora_finetune.rst",
]

8
docs/source/providers/external.md
View file

@ -10,7 +10,7 @@ Llama Stack supports external providers that live outside of the main codebase.
To enable external providers, you need to configure the `external_providers_dir` in your Llama Stack configuration. This directory should contain your external provider specifications:
```yaml
external_providers_dir: /etc/llama-stack/providers.d/
external_providers_dir: ~/.llama/providers.d/
```
## Directory Structure
@ -53,7 +53,7 @@ Here's a list of known external providers that you can use with Llama Stack:
| Name | Description | API | Type | Repository |
|------|-------------|-----|------|------------|
| KubeFlow Training | Train models with KubeFlow | Post Training | Remote | [llama-stack-provider-kft](https://github.com/opendatahub-io/llama-stack-provider-kft) |
| KubeFlow Pipelines | Train models with KubeFlow Pipelines | Post Training | Remote | [llama-stack-provider-kfp-trainer](https://github.com/opendatahub-io/llama-stack-provider-kfp-trainer) |
| KubeFlow Pipelines | Train models with KubeFlow Pipelines | Post Training | Inline **and** Remote | [llama-stack-provider-kfp-trainer](https://github.com/opendatahub-io/llama-stack-provider-kfp-trainer) |
| RamaLama | Inference models with RamaLama | Inference | Remote | [ramalama-stack](https://github.com/containers/ramalama-stack) |
| TrustyAI LM-Eval | Evaluate models with TrustyAI LM-Eval | Eval | Remote | [llama-stack-provider-lmeval](https://github.com/trustyai-explainability/llama-stack-provider-lmeval) |
@ -182,7 +182,7 @@ dependencies = ["llama-stack", "pydantic", "ollama", "aiohttp"]
3. Create the provider specification:
```yaml
# /etc/llama-stack/providers.d/remote/inference/custom_ollama.yaml
# ~/.llama/providers.d/remote/inference/custom_ollama.yaml
adapter:
adapter_type: custom_ollama
pip_packages: ["ollama", "aiohttp"]
@ -201,7 +201,7 @@ uv pip install -e .
5. Configure Llama Stack to use external providers:
```yaml
external_providers_dir: /etc/llama-stack/providers.d/
external_providers_dir: ~/.llama/providers.d/
```
The provider will now be available in Llama Stack with the type `remote::custom_ollama`.

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 |