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.

Author: ashwinb

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 @@
 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
 ```