chore: Stack server no longer depends on llama-stack-client (#4094)

This dependency has been bothering folks for a long time (cc @leseb). We
really needed it due to "library client" which is primarily used for our
tests and is not a part of the Stack server. Anyone who needs to use the
library client can certainly install `llama-stack-client` in their
environment to make that work.

Updated the notebook references to install `llama-stack-client`
additionally when setting things up.

docs/docs/distributions/importing_as_library.mdx

@@ -11,7 +11,7 @@ If you are planning to use an external service for Inference (even Ollama or TGI
 This avoids the overhead of setting up a server.
 ```bash
 # setup
-uv pip install llama-stack
+uv pip install llama-stack llama-stack-client
 llama stack list-deps starter | xargs -L1 uv pip install
 ```
 

docs/notebooks/Llama_Stack_Agent_Workflows.ipynb

@@ -37,7 +37,7 @@
    "outputs": [],
    "source": [
     "# NBVAL_SKIP\n",
-    "!pip install -U llama-stack\n",
+    "!pip install -U llama-stack llama-stack-client\n",
     "llama stack list-deps fireworks | xargs -L1 uv pip install\n"
    ]
   },

docs/notebooks/Llama_Stack_Benchmark_Evals.ipynb

@@ -44,7 +44,7 @@
    "outputs": [],
    "source": [
     "# NBVAL_SKIP\n",
-    "!pip install -U llama-stack"
+    "!pip install -U llama-stack llama-stack-client\n"
    ]
   },
   {

docs/notebooks/nvidia/beginner_e2e/Llama_Stack_NVIDIA_E2E_Flow.ipynb

@@ -74,6 +74,7 @@
    "source": [
     "```bash\n",
     "uv sync --extra dev\n",
+    "uv pip install -U llama-stack-client\n",
     "uv pip install -e .\n",
     "source .venv/bin/activate\n",
     "```"

pyproject.toml

@@ -24,13 +24,13 @@ classifiers = [
     "Topic :: Scientific/Engineering :: Information Analysis",
 ]
 dependencies = [
+    "PyYAML>=6.0",
     "aiohttp",
     "fastapi>=0.115.0,<1.0",                          # server
     "fire",                                           # for MCP in LLS client
     "httpx",
     "jinja2>=3.1.6",
     "jsonschema",
-    "llama-stack-client>=0.3.0",
     "openai>=2.5.0",
     "prompt-toolkit",
     "python-dotenv",
@@ -51,6 +51,11 @@ dependencies = [
     "sqlalchemy[asyncio]>=2.0.41",                    # server - for conversations
 ]
 
+[project.optional-dependencies]
+client = [
+    "llama-stack-client>=0.3.0",  # Optional for library-only usage
+]
+
 [dependency-groups]
 dev = [
     "pytest>=8.4",
@@ -96,6 +101,7 @@ type_checking = [
     "lm-format-enforcer",
     "mcp",
     "ollama",
+    "llama-stack-client>=0.3.0",
 ]
 # These are the dependencies required for running unit tests.
 unit = [

src/llama_stack/__init__.py

@@ -3,8 +3,3 @@
 #
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
-
-from llama_stack.core.library_client import (  # noqa: F401
-    AsyncLlamaStackAsLibraryClient,
-    LlamaStackAsLibraryClient,
-)

src/llama_stack/core/library_client.py

@@ -18,14 +18,21 @@ from typing import Any, TypeVar, Union, get_args, get_origin
 import httpx
 import yaml
 from fastapi import Response as FastAPIResponse
-from llama_stack_client import (
-    NOT_GIVEN,
-    APIResponse,
-    AsyncAPIResponse,
-    AsyncLlamaStackClient,
-    AsyncStream,
-    LlamaStackClient,
-)
+
+try:
+    from llama_stack_client import (
+        NOT_GIVEN,
+        APIResponse,
+        AsyncAPIResponse,
+        AsyncLlamaStackClient,
+        AsyncStream,
+        LlamaStackClient,
+    )
+except ImportError as e:
+    raise ImportError(
+        "llama-stack-client is not installed. Please install it with `uv pip install llama-stack[client]`."
+    ) from e
+
 from pydantic import BaseModel, TypeAdapter
 from rich.console import Console
 from termcolor import cprint

src/llama_stack/providers/remote/datasetio/nvidia/README.md

@@ -20,6 +20,7 @@ This provider enables dataset management using NVIDIA's NeMo Customizer service.
 Build the NVIDIA environment:
 
 ```bash
+uv pip install llama-stack-client
 uv run llama stack list-deps nvidia | xargs -L1 uv pip install
 ```
 

src/llama_stack/providers/remote/inference/nvidia/NVIDIA.md

@@ -18,6 +18,7 @@ This provider enables running inference using NVIDIA NIM.
 Build the NVIDIA environment:
 
 ```bash
+uv pip install llama-stack-client
 uv run llama stack list-deps nvidia | xargs -L1 uv pip install
 ```
 
@@ -199,4 +200,4 @@ rerank_response = client.alpha.inference.rerank(
 
 for i, result in enumerate(rerank_response):
     print(f"{i+1}. [Index: {result.index}, " f"Score: {(result.relevance_score):.3f}]")
-```
+```

src/llama_stack/providers/remote/post_training/nvidia/README.md

@@ -22,6 +22,7 @@ This provider enables fine-tuning of LLMs using NVIDIA's NeMo Customizer service
 Build the NVIDIA environment:
 
 ```bash
+uv pip install llama-stack-client
 uv run llama stack list-deps nvidia | xargs -L1 uv pip install
 ```
 

src/llama_stack/providers/remote/safety/nvidia/README.md

@@ -19,6 +19,7 @@ This provider enables safety checks and guardrails for LLM interactions using NV
 Build the NVIDIA environment:
 
 ```bash
+uv pip install llama-stack-client
 uv run llama stack list-deps nvidia | xargs -L1 uv pip install
 ```
 

tests/integration/fixtures/common.py

@@ -20,8 +20,8 @@ import yaml
 from llama_stack_client import LlamaStackClient
 from openai import OpenAI
 
-from llama_stack import LlamaStackAsLibraryClient
 from llama_stack.core.datatypes import VectorStoresConfig
+from llama_stack.core.library_client import LlamaStackAsLibraryClient
 from llama_stack.core.stack import run_config_from_adhoc_config_spec
 from llama_stack.env import get_env_or_fail
 

tests/integration/inference/test_provider_data_routing.py

@@ -16,7 +16,6 @@ from unittest.mock import AsyncMock, patch
 
 import pytest
 
-from llama_stack import LlamaStackAsLibraryClient
 from llama_stack.apis.datatypes import Api
 from llama_stack.apis.inference.inference import (
     OpenAIAssistantMessageParam,
@@ -24,6 +23,7 @@ from llama_stack.apis.inference.inference import (
     OpenAIChatCompletionUsage,
     OpenAIChoice,
 )
+from llama_stack.core.library_client import LlamaStackAsLibraryClient
 from llama_stack.core.telemetry.telemetry import MetricEvent
 
 

tests/integration/inference/test_tools_with_schemas.py

@@ -13,7 +13,7 @@ import json
 
 import pytest
 
-from llama_stack import LlamaStackAsLibraryClient
+from llama_stack.core.library_client import LlamaStackAsLibraryClient
 from llama_stack.models.llama.datatypes import ToolDefinition
 from tests.common.mcp import make_mcp_server
 

tests/integration/inspect/test_inspect.py

@@ -7,7 +7,7 @@
 import pytest
 from llama_stack_client import LlamaStackClient
 
-from llama_stack import LlamaStackAsLibraryClient
+from llama_stack.core.library_client import LlamaStackAsLibraryClient
 
 
 class TestInspect:

tests/integration/providers/test_providers.py

@@ -6,7 +6,7 @@
 
 from llama_stack_client import LlamaStackClient
 
-from llama_stack import LlamaStackAsLibraryClient
+from llama_stack.core.library_client import LlamaStackAsLibraryClient
 
 
 class TestProviders:

tests/integration/responses/fixtures/fixtures.py

@@ -11,7 +11,7 @@ import pytest
 import yaml
 from openai import OpenAI
 
-from llama_stack import LlamaStackAsLibraryClient
+from llama_stack.core.library_client import LlamaStackAsLibraryClient
 
 # --- Helper Functions ---
 

tests/integration/responses/test_file_search.py

@@ -9,7 +9,7 @@ import time
 
 import pytest
 
-from llama_stack import LlamaStackAsLibraryClient
+from llama_stack.core.library_client import LlamaStackAsLibraryClient
 
 from .helpers import new_vector_store, upload_file
 

tests/integration/responses/test_tool_responses.py

@@ -12,8 +12,8 @@ import httpx
 import openai
 import pytest
 
-from llama_stack import LlamaStackAsLibraryClient
 from llama_stack.core.datatypes import AuthenticationRequiredError
+from llama_stack.core.library_client import LlamaStackAsLibraryClient
 from tests.common.mcp import dependency_tools, make_mcp_server
 
 from .fixtures.test_cases import (

tests/integration/tool_runtime/test_mcp.py

@@ -10,7 +10,7 @@ import pytest
 from llama_stack_client.lib.agents.agent import Agent
 from llama_stack_client.lib.agents.turn_events import StepCompleted, StepProgress, ToolCallIssuedDelta
 
-from llama_stack import LlamaStackAsLibraryClient
+from llama_stack.core.library_client import LlamaStackAsLibraryClient
 
 AUTH_TOKEN = "test-token"
 

tests/integration/tool_runtime/test_mcp_json_schema.py

@@ -13,7 +13,7 @@ import json
 
 import pytest
 
-from llama_stack import LlamaStackAsLibraryClient
+from llama_stack.core.library_client import LlamaStackAsLibraryClient
 from tests.common.mcp import make_mcp_server
 
 AUTH_TOKEN = "test-token"

tests/integration/tool_runtime/test_registration.py

@@ -8,8 +8,8 @@ import re
 
 import pytest
 
-from llama_stack import LlamaStackAsLibraryClient
 from llama_stack.apis.common.errors import ToolGroupNotFoundError
+from llama_stack.core.library_client import LlamaStackAsLibraryClient
 from tests.common.mcp import MCP_TOOLGROUP_ID, make_mcp_server
 
 

uv.lock

@@ -1945,7 +1945,6 @@ dependencies = [
     { name = "httpx" },
     { name = "jinja2" },
     { name = "jsonschema" },
-    { name = "llama-stack-client" },
     { name = "openai" },
     { name = "opentelemetry-exporter-otlp-proto-http" },
     { name = "opentelemetry-sdk" },
@@ -1955,6 +1954,7 @@ dependencies = [
     { name = "pyjwt", extra = ["crypto"] },
     { name = "python-dotenv" },
     { name = "python-multipart" },
+    { name = "pyyaml" },
     { name = "rich" },
     { name = "sqlalchemy", extra = ["asyncio"] },
     { name = "starlette" },
@@ -1963,6 +1963,11 @@ dependencies = [
     { name = "uvicorn" },
 ]
 
+[package.optional-dependencies]
+client = [
+    { name = "llama-stack-client" },
+]
+
 [package.dev-dependencies]
 benchmark = [
     { name = "locust" },
@@ -2035,6 +2040,7 @@ type-checking = [
     { name = "datasets" },
     { name = "fairscale" },
     { name = "faiss-cpu" },
+    { name = "llama-stack-client" },
     { name = "lm-format-enforcer" },
     { name = "mcp" },
     { name = "nest-asyncio" },
@@ -2088,7 +2094,7 @@ requires-dist = [
     { name = "httpx" },
     { name = "jinja2", specifier = ">=3.1.6" },
     { name = "jsonschema" },
-    { name = "llama-stack-client", specifier = ">=0.3.0" },
+    { name = "llama-stack-client", marker = "extra == 'client'", specifier = ">=0.3.0" },
     { name = "openai", specifier = ">=2.5.0" },
     { name = "opentelemetry-exporter-otlp-proto-http", specifier = ">=1.30.0" },
     { name = "opentelemetry-sdk", specifier = ">=1.30.0" },
@@ -2098,6 +2104,7 @@ requires-dist = [
     { name = "pyjwt", extras = ["crypto"], specifier = ">=2.10.0" },
     { name = "python-dotenv" },
     { name = "python-multipart", specifier = ">=0.0.20" },
+    { name = "pyyaml", specifier = ">=6.0" },
     { name = "rich" },
     { name = "sqlalchemy", extras = ["asyncio"], specifier = ">=2.0.41" },
     { name = "starlette" },
@@ -2105,6 +2112,7 @@ requires-dist = [
     { name = "tiktoken" },
     { name = "uvicorn", specifier = ">=0.34.0" },
 ]
+provides-extras = ["client"]
 
 [package.metadata.requires-dev]
 benchmark = [{ name = "locust", specifier = ">=2.39.1" }]
@@ -2175,6 +2183,7 @@ type-checking = [
     { name = "datasets" },
     { name = "fairscale" },
     { name = "faiss-cpu" },
+    { name = "llama-stack-client", specifier = ">=0.3.0" },
     { name = "lm-format-enforcer" },
     { name = "mcp" },
     { name = "nest-asyncio" },