Merge branch 'main' into qdrant-keyword-search

llama_stack/cli/stack/_build.py

@@ -45,6 +45,7 @@ from llama_stack.core.utils.dynamic import instantiate_class_type
 from llama_stack.core.utils.exec import formulate_run_args, run_command
 from llama_stack.core.utils.image_types import LlamaStackImageType
 from llama_stack.providers.datatypes import Api
+from llama_stack.providers.utils.sqlstore.sqlstore import SqliteSqlStoreConfig
 
 DISTRIBS_PATH = Path(__file__).parent.parent.parent / "distributions"
 
@@ -294,6 +295,12 @@ def _generate_run_config(
         if build_config.external_providers_dir
         else EXTERNAL_PROVIDERS_DIR,
     )
+    if not run_config.inference_store:
+        run_config.inference_store = SqliteSqlStoreConfig(
+            **SqliteSqlStoreConfig.sample_run_config(
+                __distro_dir__=(DISTRIBS_BASE_DIR / image_name).as_posix(), db_name="inference_store.db"
+            )
+        )
     # build providers dict
     provider_registry = get_provider_registry(build_config)
     for api in apis:

llama_stack/core/library_client.py

@@ -10,7 +10,6 @@ import json
 import logging  # allow-direct-logging
 import os
 import sys
-from concurrent.futures import ThreadPoolExecutor
 from enum import Enum
 from io import BytesIO
 from pathlib import Path
@@ -148,7 +147,6 @@ class LlamaStackAsLibraryClient(LlamaStackClient):
         self.async_client = AsyncLlamaStackAsLibraryClient(
             config_path_or_distro_name, custom_provider_registry, provider_data, skip_logger_removal
         )
-        self.pool_executor = ThreadPoolExecutor(max_workers=4)
         self.provider_data = provider_data
 
         self.loop = asyncio.new_event_loop()

llama_stack/providers/registry/datasetio.py

@@ -30,7 +30,7 @@ def available_providers() -> list[ProviderSpec]:
             adapter=AdapterSpec(
                 adapter_type="huggingface",
                 pip_packages=[
-                    "datasets",
+                    "datasets>=4.0.0",
                 ],
                 module="llama_stack.providers.remote.datasetio.huggingface",
                 config_class="llama_stack.providers.remote.datasetio.huggingface.HuggingfaceDatasetIOConfig",
@@ -42,7 +42,7 @@ def available_providers() -> list[ProviderSpec]:
             adapter=AdapterSpec(
                 adapter_type="nvidia",
                 pip_packages=[
-                    "datasets",
+                    "datasets>=4.0.0",
                 ],
                 module="llama_stack.providers.remote.datasetio.nvidia",
                 config_class="llama_stack.providers.remote.datasetio.nvidia.NvidiaDatasetIOConfig",

llama_stack/providers/registry/post_training.py

@@ -48,7 +48,7 @@ def available_providers() -> list[ProviderSpec]:
         InlineProviderSpec(
             api=Api.post_training,
             provider_type="inline::huggingface-gpu",
-            pip_packages=["trl", "transformers", "peft", "datasets", "torch"],
+            pip_packages=["trl", "transformers", "peft", "datasets>=4.0.0", "torch"],
             module="llama_stack.providers.inline.post_training.huggingface",
             config_class="llama_stack.providers.inline.post_training.huggingface.HuggingFacePostTrainingConfig",
             api_dependencies=[

llama_stack/ui/package-lock.json

@@ -18,7 +18,7 @@
         "class-variance-authority": "^0.7.1",
         "clsx": "^2.1.1",
         "framer-motion": "^12.23.12",
-        "llama-stack-client": "^0.2.20",
+        "llama-stack-client": "^0.2.21",
         "lucide-react": "^0.542.0",
         "next": "15.3.3",
         "next-auth": "^4.24.11",
@@ -10278,9 +10278,9 @@
       "license": "MIT"
     },
     "node_modules/llama-stack-client": {
-      "version": "0.2.20",
-      "resolved": "https://registry.npmjs.org/llama-stack-client/-/llama-stack-client-0.2.20.tgz",
-      "integrity": "sha512-1vD5nizTX5JEW8TADxKgy/P1W8YZoPSpdnmfxbdYbWgpQ3BWtbvLS6jmDk7VwVA5fRC4895VfHsRDfS1liHarw==",
+      "version": "0.2.21",
+      "resolved": "https://registry.npmjs.org/llama-stack-client/-/llama-stack-client-0.2.21.tgz",
+      "integrity": "sha512-rjU2Vx5xStxDYavU8K1An/SYXiQQjroLcK98B+p0Paz/a7OgRao2S0YwvThJjPUyChY4fO03UIXP9LpmHqlXWQ==",
       "license": "MIT",
       "dependencies": {
         "@types/node": "^18.11.18",

llama_stack/ui/package.json

@@ -23,7 +23,7 @@
     "class-variance-authority": "^0.7.1",
     "clsx": "^2.1.1",
     "framer-motion": "^12.23.12",
-    "llama-stack-client": "^0.2.20",
+    "llama-stack-client": "^0.2.21",
     "lucide-react": "^0.542.0",
     "next": "15.3.3",
     "next-auth": "^4.24.11",