llama_toolchain -> llama_stack

MANIFEST.in

@@ -1,4 +1,4 @@
 include requirements.txt
-include llama_toolchain/data/*.yaml
+include llama_stack/data/*.yaml
-include llama_toolchain/core/*.sh
+include llama_stack/core/*.sh
-include llama_toolchain/cli/scripts/*.sh
+include llama_stack/cli/scripts/*.sh

docs/cli_reference.md

@@ -276,16 +276,16 @@ The following command and specifications allows you to get started with building
 ```
 llama stack build <path/to/config>
 ```
-- You will be required to pass in a file path to the build.config file (e.g. `./llama_toolchain/configs/distributions/conda/local-conda-example-build.yaml`). We provide some example build config files for configuring different types of distributions in the `./llama_toolchain/configs/distributions/` folder.
+- You will be required to pass in a file path to the build.config file (e.g. `./llama_stack/configs/distributions/conda/local-conda-example-build.yaml`). We provide some example build config files for configuring different types of distributions in the `./llama_stack/configs/distributions/` folder.
 
 The file will be of the contents
 ```
-$ cat ./llama_toolchain/configs/distributions/conda/local-conda-example-build.yaml
+$ cat ./llama_stack/configs/distributions/conda/local-conda-example-build.yaml
 
 name: 8b-instruct
 distribution_spec:
   distribution_type: local
-  description: Use code from `llama_toolchain` itself to serve all llama stack APIs
+  description: Use code from `llama_stack` itself to serve all llama stack APIs
   docker_image: null
   providers:
     inference: meta-reference
@@ -311,7 +311,7 @@ After this step is complete, a file named `8b-instruct-build.yaml` will be gener
 To specify a different API provider, we can change the `distribution_spec` in our `<name>-build.yaml` config. For example, the following build spec allows you to build a distribution using TGI as the inference API provider.
 
 ```
-$ cat ./llama_toolchain/configs/distributions/conda/local-tgi-conda-example-build.yaml
+$ cat ./llama_stack/configs/distributions/conda/local-tgi-conda-example-build.yaml
 
 name: local-tgi-conda-example
 distribution_spec:
@@ -328,7 +328,7 @@ image_type: conda
 
 The following command allows you to build a distribution with TGI as the inference API provider, with the name `tgi`.
 ```
-llama stack build --config ./llama_toolchain/configs/distributions/conda/local-tgi-conda-example-build.yaml --name tgi
+llama stack build --config ./llama_stack/configs/distributions/conda/local-tgi-conda-example-build.yaml --name tgi
 ```
 
 We provide some example build configs to help you get started with building with different API providers.
@@ -337,11 +337,11 @@ We provide some example build configs to help you get started with building with
 To build a docker image, simply change the `image_type` to `docker` in our `<name>-build.yaml` file, and run `llama stack build --config <name>-build.yaml`.
 
 ```
-$ cat ./llama_toolchain/configs/distributions/docker/local-docker-example-build.yaml
+$ cat ./llama_stack/configs/distributions/docker/local-docker-example-build.yaml
 
 name: local-docker-example
 distribution_spec:
-  description: Use code from `llama_toolchain` itself to serve all llama stack APIs
+  description: Use code from `llama_stack` itself to serve all llama stack APIs
   docker_image: null
   providers:
     inference: meta-reference
@@ -354,7 +354,7 @@ image_type: docker
 
 The following command allows you to build a Docker image with the name `docker-local`
 ```
-llama stack build --config ./llama_toolchain/configs/distributions/docker/local-docker-example-build.yaml --name docker-local
+llama stack build --config ./llama_stack/configs/distributions/docker/local-docker-example-build.yaml --name docker-local
 
 Dockerfile created successfully in /tmp/tmp.I0ifS2c46A/DockerfileFROM python:3.10-slim
 WORKDIR /app
@@ -482,7 +482,7 @@ Once the server is setup, we can test it with a client to see the example output
 cd /path/to/llama-stack
 conda activate <env>  # any environment containing the llama-toolchain pip package will work
 
-python -m llama_toolchain.inference.client localhost 5000
+python -m llama_stack.inference.client localhost 5000
 ```
 
 This will run the chat completion client and query the distribution’s /inference/chat_completion API.
@@ -500,7 +500,7 @@ You know what's even more hilarious? People like you who think they can just Goo
 Similarly you can test safety (if you configured llama-guard and/or prompt-guard shields) by:
 
 ```
-python -m llama_toolchain.safety.client localhost 5000
+python -m llama_stack.safety.client localhost 5000
 ```
 
 You can find more example scripts with client SDKs to talk with the Llama Stack server in our [llama-stack-apps](https://github.com/meta-llama/llama-stack-apps/tree/main/sdk_examples) repo.

docs/getting_started.md

@@ -9,7 +9,7 @@ This guides allows you to quickly get started with building and running a Llama
 
 **`llama stack build`**
 ```
-llama stack build --config ./llama_toolchain/configs/distributions/conda/local-conda-example-build.yaml --name my-local-llama-stack
+llama stack build --config ./llama_stack/configs/distributions/conda/local-conda-example-build.yaml --name my-local-llama-stack
 ...
 ...
 Build spec configuration saved at ~/.llama/distributions/conda/my-local-llama-stack-build.yaml
@@ -97,16 +97,16 @@ The following command and specifications allows you to get started with building
 ```
 llama stack build <path/to/config>
 ```
-- You will be required to pass in a file path to the build.config file (e.g. `./llama_toolchain/configs/distributions/conda/local-conda-example-build.yaml`). We provide some example build config files for configuring different types of distributions in the `./llama_toolchain/configs/distributions/` folder.
+- You will be required to pass in a file path to the build.config file (e.g. `./llama_stack/configs/distributions/conda/local-conda-example-build.yaml`). We provide some example build config files for configuring different types of distributions in the `./llama_stack/configs/distributions/` folder.
 
 The file will be of the contents
 ```
-$ cat ./llama_toolchain/configs/distributions/conda/local-conda-example-build.yaml
+$ cat ./llama_stack/configs/distributions/conda/local-conda-example-build.yaml
 
 name: 8b-instruct
 distribution_spec:
   distribution_type: local
-  description: Use code from `llama_toolchain` itself to serve all llama stack APIs
+  description: Use code from `llama_stack` itself to serve all llama stack APIs
   docker_image: null
   providers:
     inference: meta-reference
@@ -132,7 +132,7 @@ After this step is complete, a file named `8b-instruct-build.yaml` will be gener
 To specify a different API provider, we can change the `distribution_spec` in our `<name>-build.yaml` config. For example, the following build spec allows you to build a distribution using TGI as the inference API provider.
 
 ```
-$ cat ./llama_toolchain/configs/distributions/conda/local-tgi-conda-example-build.yaml
+$ cat ./llama_stack/configs/distributions/conda/local-tgi-conda-example-build.yaml
 
 name: local-tgi-conda-example
 distribution_spec:
@@ -149,7 +149,7 @@ image_type: conda
 
 The following command allows you to build a distribution with TGI as the inference API provider, with the name `tgi`.
 ```
-llama stack build --config ./llama_toolchain/configs/distributions/conda/local-tgi-conda-example-build.yaml --name tgi
+llama stack build --config ./llama_stack/configs/distributions/conda/local-tgi-conda-example-build.yaml --name tgi
 ```
 
 We provide some example build configs to help you get started with building with different API providers.
@@ -158,11 +158,11 @@ We provide some example build configs to help you get started with building with
 To build a docker image, simply change the `image_type` to `docker` in our `<name>-build.yaml` file, and run `llama stack build --config <name>-build.yaml`.
 
 ```
-$ cat ./llama_toolchain/configs/distributions/docker/local-docker-example-build.yaml
+$ cat ./llama_stack/configs/distributions/docker/local-docker-example-build.yaml
 
 name: local-docker-example
 distribution_spec:
-  description: Use code from `llama_toolchain` itself to serve all llama stack APIs
+  description: Use code from `llama_stack` itself to serve all llama stack APIs
   docker_image: null
   providers:
     inference: meta-reference
@@ -175,7 +175,7 @@ image_type: docker
 
 The following command allows you to build a Docker image with the name `docker-local`
 ```
-llama stack build --config ./llama_toolchain/configs/distributions/docker/local-docker-example-build.yaml --name docker-local
+llama stack build --config ./llama_stack/configs/distributions/docker/local-docker-example-build.yaml --name docker-local
 
 Dockerfile created successfully in /tmp/tmp.I0ifS2c46A/DockerfileFROM python:3.10-slim
 WORKDIR /app
@@ -296,7 +296,7 @@ Once the server is setup, we can test it with a client to see the example output
 cd /path/to/llama-stack
 conda activate <env>  # any environment containing the llama-toolchain pip package will work
 
-python -m llama_toolchain.inference.client localhost 5000
+python -m llama_stack.inference.client localhost 5000
 ```
 
 This will run the chat completion client and query the distribution’s /inference/chat_completion API.
@@ -314,7 +314,7 @@ You know what's even more hilarious? People like you who think they can just Goo
 Similarly you can test safety (if you configured llama-guard and/or prompt-guard shields) by:
 
 ```
-python -m llama_toolchain.safety.client localhost 5000
+python -m llama_stack.safety.client localhost 5000
 ```
 
 You can find more example scripts with client SDKs to talk with the Llama Stack server in our [llama-stack-apps](https://github.com/meta-llama/llama-stack-apps/tree/main/sdk_examples) repo.

llama_stack/agentic_system/api/api.py

@@ -14,10 +14,10 @@ from pydantic import BaseModel, ConfigDict, Field
 from typing_extensions import Annotated
 
 from llama_models.llama3.api.datatypes import *  # noqa: F403
-from llama_toolchain.common.deployment_types import *  # noqa: F403
+from llama_stack.common.deployment_types import *  # noqa: F403
-from llama_toolchain.inference.api import *  # noqa: F403
+from llama_stack.inference.api import *  # noqa: F403
-from llama_toolchain.safety.api import *  # noqa: F403
+from llama_stack.safety.api import *  # noqa: F403
-from llama_toolchain.memory.api import *  # noqa: F403
+from llama_stack.memory.api import *  # noqa: F403
 
 
 @json_schema_type

llama_stack/agentic_system/client.py

@@ -16,7 +16,7 @@ from pydantic import BaseModel
 from termcolor import cprint
 
 from llama_models.llama3.api.datatypes import *  # noqa: F403
-from llama_toolchain.core.datatypes import RemoteProviderConfig
+from llama_stack.core.datatypes import RemoteProviderConfig
 
 from .api import *  # noqa: F403
 from .event_logger import EventLogger
@@ -186,7 +186,7 @@ async def run_rag(host: str, port: int):
     ]
 
     # Alternatively, you can pre-populate the memory bank with documents for example,
-    # using `llama_toolchain.memory.client`. Then you can grab the bank_id
+    # using `llama_stack.memory.client`. Then you can grab the bank_id
     # from the output of that run.
     tool_definitions = [
         MemoryToolDefinition(

llama_stack/agentic_system/event_logger.py

@@ -11,10 +11,7 @@ from llama_models.llama3.api.tool_utils import ToolUtils
 
 from termcolor import cprint
 
-from llama_toolchain.agentic_system.api import (
+from llama_stack.agentic_system.api import AgenticSystemTurnResponseEventType, StepType
-    AgenticSystemTurnResponseEventType,
-    StepType,
-)
 
 
 class LogEvent:

llama_stack/agentic_system/execute_with_custom_tools.py

@@ -7,14 +7,14 @@
 from typing import AsyncGenerator, List
 
 from llama_models.llama3.api.datatypes import *  # noqa: F403
-from llama_toolchain.agentic_system.api import *  # noqa: F403
+from llama_stack.agentic_system.api import *  # noqa: F403
-from llama_toolchain.memory.api import *  # noqa: F403
+from llama_stack.memory.api import *  # noqa: F403
-from llama_toolchain.safety.api import *  # noqa: F403
+from llama_stack.safety.api import *  # noqa: F403
 
-from llama_toolchain.agentic_system.api import (
+from llama_stack.agentic_system.api import (
     AgenticSystemTurnResponseEventType as EventType,
 )
-from llama_toolchain.tools.custom.datatypes import CustomTool
+from llama_stack.tools.custom.datatypes import CustomTool
 
 
 class AgentWithCustomToolExecutor:

llama_stack/agentic_system/meta_reference/__init__.py

@@ -6,7 +6,7 @@
 
 from typing import Dict
 
-from llama_toolchain.core.datatypes import Api, ProviderSpec
+from llama_stack.core.datatypes import Api, ProviderSpec
 
 from .config import MetaReferenceImplConfig
 

llama_stack/agentic_system/meta_reference/agent_instance.py

@@ -20,13 +20,13 @@ import httpx
 
 from termcolor import cprint
 
-from llama_toolchain.agentic_system.api import *  # noqa: F403
+from llama_stack.agentic_system.api import *  # noqa: F403
-from llama_toolchain.inference.api import *  # noqa: F403
+from llama_stack.inference.api import *  # noqa: F403
-from llama_toolchain.memory.api import *  # noqa: F403
+from llama_stack.memory.api import *  # noqa: F403
-from llama_toolchain.safety.api import *  # noqa: F403
+from llama_stack.safety.api import *  # noqa: F403
 
-from llama_toolchain.tools.base import BaseTool
+from llama_stack.tools.base import BaseTool
-from llama_toolchain.tools.builtin import (
+from llama_stack.tools.builtin import (
     interpret_content_as_attachment,
     SingleMessageBuiltinTool,
 )

llama_stack/agentic_system/meta_reference/agentic_system.py

@@ -10,17 +10,17 @@ import tempfile
 import uuid
 from typing import AsyncGenerator
 
-from llama_toolchain.inference.api import Inference
+from llama_stack.inference.api import Inference
-from llama_toolchain.memory.api import Memory
+from llama_stack.memory.api import Memory
-from llama_toolchain.safety.api import Safety
+from llama_stack.safety.api import Safety
-from llama_toolchain.agentic_system.api import *  # noqa: F403
+from llama_stack.agentic_system.api import *  # noqa: F403
-from llama_toolchain.tools.builtin import (
+from llama_stack.tools.builtin import (
     CodeInterpreterTool,
     PhotogenTool,
     SearchTool,
     WolframAlphaTool,
 )
-from llama_toolchain.tools.safety import with_safety
+from llama_stack.tools.safety import with_safety
 
 from .agent_instance import ChatAgent
 from .config import MetaReferenceImplConfig

llama_stack/agentic_system/meta_reference/rag/context_retriever.py

@@ -10,14 +10,14 @@ from jinja2 import Template
 from llama_models.llama3.api import *  # noqa: F403
 
 
-from llama_toolchain.agentic_system.api import (
+from llama_stack.agentic_system.api import (
     DefaultMemoryQueryGeneratorConfig,
     LLMMemoryQueryGeneratorConfig,
     MemoryQueryGenerator,
     MemoryQueryGeneratorConfig,
 )
 from termcolor import cprint  # noqa: F401
-from llama_toolchain.inference.api import *  # noqa: F403
+from llama_stack.inference.api import *  # noqa: F403
 
 
 async def generate_rag_query(

llama_stack/agentic_system/meta_reference/safety.py

@@ -9,7 +9,7 @@ from typing import List
 from llama_models.llama3.api.datatypes import Message, Role, UserMessage
 from termcolor import cprint
 
-from llama_toolchain.safety.api import (
+from llama_stack.safety.api import (
     OnViolationAction,
     RunShieldRequest,
     Safety,

llama_stack/agentic_system/providers.py

@@ -6,7 +6,7 @@
 
 from typing import List
 
-from llama_toolchain.core.datatypes import Api, InlineProviderSpec, ProviderSpec
+from llama_stack.core.datatypes import Api, InlineProviderSpec, ProviderSpec
 
 
 def available_providers() -> List[ProviderSpec]:
@@ -23,8 +23,8 @@ def available_providers() -> List[ProviderSpec]:
                 "torch",
                 "transformers",
             ],
-            module="llama_toolchain.agentic_system.meta_reference",
+            module="llama_stack.agentic_system.meta_reference",
-            config_class="llama_toolchain.agentic_system.meta_reference.MetaReferenceImplConfig",
+            config_class="llama_stack.agentic_system.meta_reference.MetaReferenceImplConfig",
             api_dependencies=[
                 Api.inference,
                 Api.safety,

llama_stack/batch_inference/api/api.py

@@ -11,7 +11,7 @@ from llama_models.schema_utils import json_schema_type, webmethod
 from pydantic import BaseModel, Field
 
 from llama_models.llama3.api.datatypes import *  # noqa: F403
-from llama_toolchain.inference.api import *  # noqa: F403
+from llama_stack.inference.api import *  # noqa: F403
 
 
 @json_schema_type

llama_stack/cli/download.py

@@ -20,7 +20,7 @@ from pydantic import BaseModel
 
 from termcolor import cprint
 
-from llama_toolchain.cli.subcommand import Subcommand
+from llama_stack.cli.subcommand import Subcommand
 
 
 class Download(Subcommand):
@@ -92,7 +92,7 @@ def _hf_download(
     from huggingface_hub import snapshot_download
     from huggingface_hub.utils import GatedRepoError, RepositoryNotFoundError
 
-    from llama_toolchain.common.model_utils import model_local_dir
+    from llama_stack.common.model_utils import model_local_dir
 
     repo_id = model.huggingface_repo
     if repo_id is None:
@@ -126,7 +126,7 @@ def _hf_download(
 def _meta_download(model: "Model", meta_url: str):
     from llama_models.sku_list import llama_meta_net_info
 
-    from llama_toolchain.common.model_utils import model_local_dir
+    from llama_stack.common.model_utils import model_local_dir
 
     output_dir = Path(model_local_dir(model.descriptor()))
     os.makedirs(output_dir, exist_ok=True)
@@ -188,7 +188,7 @@ class Manifest(BaseModel):
 
 
 def _download_from_manifest(manifest_file: str):
-    from llama_toolchain.common.model_utils import model_local_dir
+    from llama_stack.common.model_utils import model_local_dir
 
     with open(manifest_file, "r") as f:
         d = json.load(f)

llama_stack/cli/model/describe.py

@@ -9,12 +9,12 @@ import json
 
 from llama_models.sku_list import resolve_model
 
-from llama_toolchain.cli.subcommand import Subcommand
-from llama_toolchain.cli.table import print_table
-from llama_toolchain.common.serialize import EnumEncoder
-
 from termcolor import colored
 
+from llama_stack.cli.subcommand import Subcommand
+from llama_stack.cli.table import print_table
+from llama_stack.common.serialize import EnumEncoder
+
 
 class ModelDescribe(Subcommand):
     """Show details about a model"""

llama_stack/cli/model/download.py

@@ -6,7 +6,7 @@
 
 import argparse
 
-from llama_toolchain.cli.subcommand import Subcommand
+from llama_stack.cli.subcommand import Subcommand
 
 
 class ModelDownload(Subcommand):
@@ -19,6 +19,6 @@ class ModelDownload(Subcommand):
             formatter_class=argparse.RawTextHelpFormatter,
         )
 
-        from llama_toolchain.cli.download import setup_download_parser
+        from llama_stack.cli.download import setup_download_parser
 
         setup_download_parser(self.parser)

llama_stack/cli/model/list.py

@@ -8,8 +8,8 @@ import argparse
 
 from llama_models.sku_list import all_registered_models
 
-from llama_toolchain.cli.subcommand import Subcommand
+from llama_stack.cli.subcommand import Subcommand
-from llama_toolchain.cli.table import print_table
+from llama_stack.cli.table import print_table
 
 
 class ModelList(Subcommand):

llama_stack/cli/model/model.py

@@ -6,12 +6,12 @@
 
 import argparse
 
-from llama_toolchain.cli.model.describe import ModelDescribe
+from llama_stack.cli.model.describe import ModelDescribe
-from llama_toolchain.cli.model.download import ModelDownload
+from llama_stack.cli.model.download import ModelDownload
-from llama_toolchain.cli.model.list import ModelList
+from llama_stack.cli.model.list import ModelList
-from llama_toolchain.cli.model.template import ModelTemplate
+from llama_stack.cli.model.template import ModelTemplate
 
-from llama_toolchain.cli.subcommand import Subcommand
+from llama_stack.cli.subcommand import Subcommand
 
 
 class ModelParser(Subcommand):

llama_stack/cli/model/template.py

@@ -9,7 +9,7 @@ import textwrap
 
 from termcolor import colored
 
-from llama_toolchain.cli.subcommand import Subcommand
+from llama_stack.cli.subcommand import Subcommand
 
 
 class ModelTemplate(Subcommand):
@@ -75,7 +75,7 @@ class ModelTemplate(Subcommand):
             render_jinja_template,
         )
 
-        from llama_toolchain.cli.table import print_table
+        from llama_stack.cli.table import print_table
 
         if args.name:
             tool_prompt_format = self._prompt_type(args.format)

llama_stack/cli/stack/build.py

@@ -6,8 +6,8 @@
 
 import argparse
 
-from llama_toolchain.cli.subcommand import Subcommand
+from llama_stack.cli.subcommand import Subcommand
-from llama_toolchain.core.datatypes import *  # noqa: F403
+from llama_stack.core.datatypes import *  # noqa: F403
 from pathlib import Path
 
 import yaml
@@ -29,7 +29,7 @@ class StackBuild(Subcommand):
         self.parser.add_argument(
             "config",
             type=str,
-            help="Path to a config file to use for the build. You may find example configs in llama_toolchain/configs/distributions",
+            help="Path to a config file to use for the build. You may find example configs in llama_stack/configs/distributions",
         )
 
         self.parser.add_argument(
@@ -44,17 +44,17 @@ class StackBuild(Subcommand):
         import json
         import os
 
-        from llama_toolchain.common.config_dirs import DISTRIBS_BASE_DIR
+        from llama_stack.common.config_dirs import DISTRIBS_BASE_DIR
-        from llama_toolchain.common.serialize import EnumEncoder
+        from llama_stack.common.serialize import EnumEncoder
-        from llama_toolchain.core.package import ApiInput, build_image, ImageType
+        from llama_stack.core.package import ApiInput, build_image, ImageType
         from termcolor import cprint
 
         # save build.yaml spec for building same distribution again
         if build_config.image_type == ImageType.docker.value:
             # docker needs build file to be in the llama-stack repo dir to be able to copy over to the image
-            llama_toolchain_path = Path(os.path.relpath(__file__)).parent.parent.parent
+            llama_stack_path = Path(os.path.relpath(__file__)).parent.parent.parent
             build_dir = (
-                llama_toolchain_path / "configs/distributions" / build_config.image_type
+                llama_stack_path / "configs/distributions" / build_config.image_type
             )
         else:
             build_dir = DISTRIBS_BASE_DIR / build_config.image_type
@@ -74,12 +74,12 @@ class StackBuild(Subcommand):
         )
 
     def _run_stack_build_command(self, args: argparse.Namespace) -> None:
-        from llama_toolchain.common.prompt_for_config import prompt_for_config
+        from llama_stack.common.prompt_for_config import prompt_for_config
-        from llama_toolchain.core.dynamic import instantiate_class_type
+        from llama_stack.core.dynamic import instantiate_class_type
 
         if not args.config:
             self.parser.error(
-                "No config file specified. Please use `llama stack build /path/to/*-build.yaml`. Example config files can be found in llama_toolchain/configs/distributions"
+                "No config file specified. Please use `llama stack build /path/to/*-build.yaml`. Example config files can be found in llama_stack/configs/distributions"
             )
             return
 

llama_stack/cli/stack/configure.py

@@ -13,11 +13,11 @@ import pkg_resources
 import yaml
 from termcolor import cprint
 
-from llama_toolchain.cli.subcommand import Subcommand
+from llama_stack.cli.subcommand import Subcommand
-from llama_toolchain.common.config_dirs import BUILDS_BASE_DIR
+from llama_stack.common.config_dirs import BUILDS_BASE_DIR
 
-from llama_toolchain.common.exec import run_with_pty
+from llama_stack.common.exec import run_with_pty
-from llama_toolchain.core.datatypes import *  # noqa: F403
+from llama_stack.core.datatypes import *  # noqa: F403
 import os
 
 
@@ -49,7 +49,7 @@ class StackConfigure(Subcommand):
         )
 
     def _run_stack_configure_cmd(self, args: argparse.Namespace) -> None:
-        from llama_toolchain.core.package import ImageType
+        from llama_stack.core.package import ImageType
 
         docker_image = None
         build_config_file = Path(args.config)
@@ -66,7 +66,7 @@ class StackConfigure(Subcommand):
             os.makedirs(builds_dir, exist_ok=True)
 
             script = pkg_resources.resource_filename(
-                "llama_toolchain", "core/configure_container.sh"
+                "llama_stack", "core/configure_container.sh"
             )
             script_args = [script, docker_image, str(builds_dir)]
 
@@ -95,8 +95,8 @@ class StackConfigure(Subcommand):
         build_config: BuildConfig,
         output_dir: Optional[str] = None,
     ):
-        from llama_toolchain.common.serialize import EnumEncoder
+        from llama_stack.common.serialize import EnumEncoder
-        from llama_toolchain.core.configure import configure_api_providers
+        from llama_stack.core.configure import configure_api_providers
 
         builds_dir = BUILDS_BASE_DIR / build_config.image_type
         if output_dir:

llama_stack/cli/stack/list_apis.py

@@ -6,7 +6,7 @@
 
 import argparse
 
-from llama_toolchain.cli.subcommand import Subcommand
+from llama_stack.cli.subcommand import Subcommand
 
 
 class StackListApis(Subcommand):
@@ -25,8 +25,8 @@ class StackListApis(Subcommand):
         pass
 
     def _run_apis_list_cmd(self, args: argparse.Namespace) -> None:
-        from llama_toolchain.cli.table import print_table
+        from llama_stack.cli.table import print_table
-        from llama_toolchain.core.distribution import stack_apis
+        from llama_stack.core.distribution import stack_apis
 
         # eventually, this should query a registry at llama.meta.com/llamastack/distributions
         headers = [

llama_stack/cli/stack/list_providers.py

@@ -6,7 +6,7 @@
 
 import argparse
 
-from llama_toolchain.cli.subcommand import Subcommand
+from llama_stack.cli.subcommand import Subcommand
 
 
 class StackListProviders(Subcommand):
@@ -22,7 +22,7 @@ class StackListProviders(Subcommand):
         self.parser.set_defaults(func=self._run_providers_list_cmd)
 
     def _add_arguments(self):
-        from llama_toolchain.core.distribution import stack_apis
+        from llama_stack.core.distribution import stack_apis
 
         api_values = [a.value for a in stack_apis()]
         self.parser.add_argument(
@@ -33,8 +33,8 @@ class StackListProviders(Subcommand):
         )
 
     def _run_providers_list_cmd(self, args: argparse.Namespace) -> None:
-        from llama_toolchain.cli.table import print_table
+        from llama_stack.cli.table import print_table
-        from llama_toolchain.core.distribution import Api, api_providers
+        from llama_stack.core.distribution import Api, api_providers
 
         all_providers = api_providers()
         providers_for_api = all_providers[Api(args.api)]

llama_stack/cli/stack/run.py

@@ -11,8 +11,8 @@ from pathlib import Path
 import pkg_resources
 import yaml
 
-from llama_toolchain.cli.subcommand import Subcommand
+from llama_stack.cli.subcommand import Subcommand
-from llama_toolchain.core.datatypes import *  # noqa: F403
+from llama_stack.core.datatypes import *  # noqa: F403
 
 
 class StackRun(Subcommand):
@@ -47,7 +47,7 @@ class StackRun(Subcommand):
         )
 
     def _run_stack_run_cmd(self, args: argparse.Namespace) -> None:
-        from llama_toolchain.common.exec import run_with_pty
+        from llama_stack.common.exec import run_with_pty
 
         if not args.config:
             self.parser.error("Must specify a config file to run")
@@ -67,13 +67,13 @@ class StackRun(Subcommand):
 
         if config.docker_image:
             script = pkg_resources.resource_filename(
-                "llama_toolchain",
+                "llama_stack",
                 "core/start_container.sh",
             )
             run_args = [script, config.docker_image]
         else:
             script = pkg_resources.resource_filename(
-                "llama_toolchain",
+                "llama_stack",
                 "core/start_conda_env.sh",
             )
             run_args = [

llama_stack/cli/stack/stack.py

@@ -6,7 +6,7 @@
 
 import argparse
 
-from llama_toolchain.cli.subcommand import Subcommand
+from llama_stack.cli.subcommand import Subcommand
 
 from .build import StackBuild
 from .configure import StackConfigure

llama_stack/configs/distributions/conda/local-conda-example-build.yaml

@@ -1,6 +1,6 @@
 name: local-conda-example
 distribution_spec:
-  description: Use code from `llama_toolchain` itself to serve all llama stack APIs
+  description: Use code from `llama_stack` itself to serve all llama stack APIs
   providers:
     inference: meta-reference
     memory: meta-reference-faiss

llama_stack/configs/distributions/docker/local-docker-example-build.yaml

@@ -1,6 +1,6 @@
 name: local-docker-example
 distribution_spec:
-  description: Use code from `llama_toolchain` itself to serve all llama stack APIs
+  description: Use code from `llama_stack` itself to serve all llama stack APIs
   providers:
     inference: meta-reference
     memory: meta-reference-faiss

llama_stack/core/build_container.sh

@@ -90,7 +90,7 @@ add_to_docker <<EOF
 # This would be good in production but for debugging flexibility lets not add it right now
 # We need a more solid production ready entrypoint.sh anyway
 #
-# ENTRYPOINT ["python", "-m", "llama_toolchain.core.server"]
+# ENTRYPOINT ["python", "-m", "llama_stack.core.server"]
 
 EOF
 

llama_stack/core/configure.py

@@ -8,12 +8,12 @@ from typing import Any
 
 from pydantic import BaseModel
 
-from llama_toolchain.core.datatypes import *  # noqa: F403
+from llama_stack.core.datatypes import *  # noqa: F403
 from termcolor import cprint
 
-from llama_toolchain.common.prompt_for_config import prompt_for_config
+from llama_stack.common.prompt_for_config import prompt_for_config
-from llama_toolchain.core.distribution import api_providers, stack_apis
+from llama_stack.core.distribution import api_providers, stack_apis
-from llama_toolchain.core.dynamic import instantiate_class_type
+from llama_stack.core.dynamic import instantiate_class_type
 
 
 # These are hacks so we can re-use the `prompt_for_config` utility

llama_stack/core/datatypes.py

@@ -151,7 +151,7 @@ as being "Llama Stack compatible"
     def module(self) -> str:
         if self.adapter:
             return self.adapter.module
-        return f"llama_toolchain.{self.api.value}.client"
+        return f"llama_stack.{self.api.value}.client"
 
     @property
     def pip_packages(self) -> List[str]:
@@ -167,7 +167,7 @@ def remote_provider_spec(
     config_class = (
         adapter.config_class
         if adapter and adapter.config_class
-        else "llama_toolchain.core.datatypes.RemoteProviderConfig"
+        else "llama_stack.core.datatypes.RemoteProviderConfig"
     )
     provider_id = remote_provider_id(adapter.adapter_id) if adapter else "remote"
 

llama_stack/core/distribution.py

@@ -8,11 +8,11 @@ import importlib
 import inspect
 from typing import Dict, List
 
-from llama_toolchain.agentic_system.api import AgenticSystem
+from llama_stack.agentic_system.api import AgenticSystem
-from llama_toolchain.inference.api import Inference
+from llama_stack.inference.api import Inference
-from llama_toolchain.memory.api import Memory
+from llama_stack.memory.api import Memory
-from llama_toolchain.safety.api import Safety
+from llama_stack.safety.api import Safety
-from llama_toolchain.telemetry.api import Telemetry
+from llama_stack.telemetry.api import Telemetry
 
 from .datatypes import Api, ApiEndpoint, ProviderSpec, remote_provider_spec
 
@@ -67,7 +67,7 @@ def api_providers() -> Dict[Api, Dict[str, ProviderSpec]]:
     ret = {}
     for api in stack_apis():
         name = api.name.lower()
-        module = importlib.import_module(f"llama_toolchain.{name}.providers")
+        module = importlib.import_module(f"llama_stack.{name}.providers")
         ret[api] = {
             "remote": remote_provider_spec(api),
             **{a.provider_id: a for a in module.available_providers()},

llama_stack/core/dynamic.py

@@ -7,7 +7,7 @@
 import importlib
 from typing import Any, Dict
 
-from llama_toolchain.core.datatypes import *  # noqa: F403
+from llama_stack.core.datatypes import *  # noqa: F403
 
 
 def instantiate_class_type(fully_qualified_name):

llama_stack/core/package.py

@@ -12,12 +12,12 @@ from pydantic import BaseModel
 
 from termcolor import cprint
 
-from llama_toolchain.common.exec import run_with_pty
+from llama_stack.common.exec import run_with_pty
 
-from llama_toolchain.core.datatypes import *  # noqa: F403
+from llama_stack.core.datatypes import *  # noqa: F403
 from pathlib import Path
 
-from llama_toolchain.core.distribution import api_providers, SERVER_DEPENDENCIES
+from llama_stack.core.distribution import api_providers, SERVER_DEPENDENCIES
 
 
 class ImageType(Enum):
@@ -68,7 +68,7 @@ def build_image(build_config: BuildConfig, build_file_path: Path):
 
     if build_config.image_type == ImageType.docker.value:
         script = pkg_resources.resource_filename(
-            "llama_toolchain", "core/build_container.sh"
+            "llama_stack", "core/build_container.sh"
         )
         args = [
             script,
@@ -79,7 +79,7 @@ def build_image(build_config: BuildConfig, build_file_path: Path):
         ]
     else:
         script = pkg_resources.resource_filename(
-            "llama_toolchain", "core/build_conda_env.sh"
+            "llama_stack", "core/build_conda_env.sh"
         )
         args = [
             script,

llama_stack/core/server.py

@@ -39,13 +39,13 @@ from pydantic import BaseModel, ValidationError
 from termcolor import cprint
 from typing_extensions import Annotated
 
-from llama_toolchain.telemetry.tracing import (
+from llama_stack.telemetry.tracing import (
     end_trace,
     setup_logger,
     SpanStatus,
     start_trace,
 )
-from llama_toolchain.core.datatypes import *  # noqa: F403
+from llama_stack.core.datatypes import *  # noqa: F403
 
 from .distribution import api_endpoints, api_providers
 from .dynamic import instantiate_provider
@@ -309,7 +309,7 @@ async def resolve_impls(
 
             specs[api] = RouterProviderSpec(
                 api=api,
-                module=f"llama_toolchain.{api.value.lower()}.router",
+                module=f"llama_stack.{api.value.lower()}.router",
                 api_dependencies=[],
                 inner_specs=inner_specs,
             )

llama_stack/core/start_conda_env.sh

@@ -37,6 +37,6 @@ eval "$(conda shell.bash hook)"
 conda deactivate && conda activate "$env_name"
 
 $CONDA_PREFIX/bin/python \
-  -m llama_toolchain.core.server \
+  -m llama_stack.core.server \
   --yaml_config "$yaml_config" \
   --port "$port" "$@"

llama_stack/core/start_container.sh

@@ -38,6 +38,6 @@ podman run -it \
   -p $port:$port \
   -v "$yaml_config:/app/config.yaml" \
   $docker_image \
-  python -m llama_toolchain.core.server \
+  python -m llama_stack.core.server \
   --yaml_config /app/config.yaml \
   --port $port "$@"

llama_stack/evaluations/api/api.py

@@ -12,8 +12,8 @@ from llama_models.schema_utils import webmethod
 from pydantic import BaseModel
 
 from llama_models.llama3.api.datatypes import *  # noqa: F403
-from llama_toolchain.dataset.api import *  # noqa: F403
+from llama_stack.dataset.api import *  # noqa: F403
-from llama_toolchain.common.training_types import *  # noqa: F403
+from llama_stack.common.training_types import *  # noqa: F403
 
 
 class TextGenerationMetric(Enum):

llama_stack/inference/adapters/fireworks/fireworks.py

@@ -13,8 +13,8 @@ from llama_models.llama3.api.datatypes import Message, StopReason
 from llama_models.llama3.api.tokenizer import Tokenizer
 from llama_models.sku_list import resolve_model
 
-from llama_toolchain.inference.api import *  # noqa: F403
+from llama_stack.inference.api import *  # noqa: F403
-from llama_toolchain.inference.prepare_messages import prepare_messages
+from llama_stack.inference.prepare_messages import prepare_messages
 
 from .config import FireworksImplConfig
 

llama_stack/inference/adapters/ollama/__init__.py

@@ -4,7 +4,7 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from llama_toolchain.core.datatypes import RemoteProviderConfig
+from llama_stack.core.datatypes import RemoteProviderConfig
 
 
 async def get_adapter_impl(config: RemoteProviderConfig, _deps):

llama_stack/inference/adapters/ollama/ollama.py

@@ -14,8 +14,8 @@ from llama_models.llama3.api.tokenizer import Tokenizer
 from llama_models.sku_list import resolve_model
 from ollama import AsyncClient
 
-from llama_toolchain.inference.api import *  # noqa: F403
+from llama_stack.inference.api import *  # noqa: F403
-from llama_toolchain.inference.prepare_messages import prepare_messages
+from llama_stack.inference.prepare_messages import prepare_messages
 
 # TODO: Eventually this will move to the llama cli model list command
 # mapping of Model SKUs to ollama models

llama_stack/inference/adapters/tgi/tgi.py

@@ -13,8 +13,8 @@ from huggingface_hub import HfApi, InferenceClient
 from llama_models.llama3.api.chat_format import ChatFormat
 from llama_models.llama3.api.datatypes import StopReason
 from llama_models.llama3.api.tokenizer import Tokenizer
-from llama_toolchain.inference.api import *  # noqa: F403
+from llama_stack.inference.api import *  # noqa: F403
-from llama_toolchain.inference.prepare_messages import prepare_messages
+from llama_stack.inference.prepare_messages import prepare_messages
 
 from .config import TGIImplConfig
 

llama_stack/inference/adapters/together/together.py

@@ -13,8 +13,8 @@ from llama_models.llama3.api.tokenizer import Tokenizer
 from llama_models.sku_list import resolve_model
 from together import Together
 
-from llama_toolchain.inference.api import *  # noqa: F403
+from llama_stack.inference.api import *  # noqa: F403
-from llama_toolchain.inference.prepare_messages import prepare_messages
+from llama_stack.inference.prepare_messages import prepare_messages
 
 from .config import TogetherImplConfig
 

llama_stack/inference/client.py

@@ -10,11 +10,11 @@ from typing import Any, AsyncGenerator
 
 import fire
 import httpx
-
-from llama_toolchain.core.datatypes import RemoteProviderConfig
 from pydantic import BaseModel
 from termcolor import cprint
 
+from llama_stack.core.datatypes import RemoteProviderConfig
+
 from .api import (
     ChatCompletionRequest,
     ChatCompletionResponse,

llama_stack/inference/event_logger.py

@@ -4,11 +4,12 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from llama_toolchain.inference.api import (
+from termcolor import cprint
+
+from llama_stack.inference.api import (
     ChatCompletionResponseEventType,
     ChatCompletionResponseStreamChunk,
 )
-from termcolor import cprint
 
 
 class LogEvent:

llama_stack/inference/meta_reference/config.py

@@ -13,7 +13,7 @@ from llama_models.sku_list import all_registered_models, resolve_model
 
 from pydantic import BaseModel, Field, field_validator
 
-from llama_toolchain.inference.api import QuantizationConfig
+from llama_stack.inference.api import QuantizationConfig
 
 
 @json_schema_type

llama_stack/inference/meta_reference/generation.py

@@ -28,11 +28,11 @@ from llama_models.llama3.api.datatypes import Message, ToolPromptFormat
 from llama_models.llama3.api.tokenizer import Tokenizer
 from llama_models.llama3.reference_impl.model import Transformer
 from llama_models.sku_list import resolve_model
-
-from llama_toolchain.common.model_utils import model_local_dir
-from llama_toolchain.inference.api import QuantizationType
 from termcolor import cprint
 
+from llama_stack.common.model_utils import model_local_dir
+from llama_stack.inference.api import QuantizationType
+
 from .config import MetaReferenceImplConfig
 
 

llama_stack/inference/meta_reference/inference.py

@@ -11,7 +11,7 @@ from typing import AsyncIterator, Union
 from llama_models.llama3.api.datatypes import StopReason
 from llama_models.sku_list import resolve_model
 
-from llama_toolchain.inference.api import (
+from llama_stack.inference.api import (
     ChatCompletionRequest,
     ChatCompletionResponse,
     ChatCompletionResponseEvent,
@@ -21,13 +21,13 @@ from llama_toolchain.inference.api import (
     ToolCallDelta,
     ToolCallParseStatus,
 )
-from llama_toolchain.inference.prepare_messages import prepare_messages
+from llama_stack.inference.prepare_messages import prepare_messages
 
 from .config import MetaReferenceImplConfig
 from .model_parallel import LlamaModelParallelGenerator
 
 from llama_models.llama3.api.datatypes import *  # noqa: F403
-from llama_toolchain.inference.api import *  # noqa: F403
+from llama_stack.inference.api import *  # noqa: F403
 
 # there's a single model parallel process running serving the model. for now,
 # we don't support multiple concurrent requests to this process.

llama_stack/inference/prepare_messages.py

@@ -5,7 +5,7 @@
 # the root directory of this source tree.
 
 from llama_models.llama3.api.datatypes import *  # noqa: F403
-from llama_toolchain.inference.api import *  # noqa: F403
+from llama_stack.inference.api import *  # noqa: F403
 from llama_models.llama3.prompt_templates import (
     BuiltinToolGenerator,
     FunctionTagCustomToolGenerator,

llama_stack/inference/providers.py

@@ -6,7 +6,7 @@
 
 from typing import List
 
-from llama_toolchain.core.datatypes import *  # noqa: F403
+from llama_stack.core.datatypes import *  # noqa: F403
 
 
 def available_providers() -> List[ProviderSpec]:
@@ -24,15 +24,15 @@ def available_providers() -> List[ProviderSpec]:
                 "transformers",
                 "zmq",
             ],
-            module="llama_toolchain.inference.meta_reference",
+            module="llama_stack.inference.meta_reference",
-            config_class="llama_toolchain.inference.meta_reference.MetaReferenceImplConfig",
+            config_class="llama_stack.inference.meta_reference.MetaReferenceImplConfig",
         ),
         remote_provider_spec(
             api=Api.inference,
             adapter=AdapterSpec(
                 adapter_id="ollama",
                 pip_packages=["ollama"],
-                module="llama_toolchain.inference.adapters.ollama",
+                module="llama_stack.inference.adapters.ollama",
             ),
         ),
         remote_provider_spec(
@@ -40,8 +40,8 @@ def available_providers() -> List[ProviderSpec]:
             adapter=AdapterSpec(
                 adapter_id="tgi",
                 pip_packages=["huggingface_hub"],
-                module="llama_toolchain.inference.adapters.tgi",
+                module="llama_stack.inference.adapters.tgi",
-                config_class="llama_toolchain.inference.adapters.tgi.TGIImplConfig",
+                config_class="llama_stack.inference.adapters.tgi.TGIImplConfig",
             ),
         ),
         remote_provider_spec(
@@ -51,8 +51,8 @@ def available_providers() -> List[ProviderSpec]:
                 pip_packages=[
                     "fireworks-ai",
                 ],
-                module="llama_toolchain.inference.adapters.fireworks",
+                module="llama_stack.inference.adapters.fireworks",
-                config_class="llama_toolchain.inference.adapters.fireworks.FireworksImplConfig",
+                config_class="llama_stack.inference.adapters.fireworks.FireworksImplConfig",
             ),
         ),
         remote_provider_spec(
@@ -62,8 +62,8 @@ def available_providers() -> List[ProviderSpec]:
                 pip_packages=[
                     "together",
                 ],
-                module="llama_toolchain.inference.adapters.together",
+                module="llama_stack.inference.adapters.together",
-                config_class="llama_toolchain.inference.adapters.together.TogetherImplConfig",
+                config_class="llama_stack.inference.adapters.together.TogetherImplConfig",
             ),
         ),
     ]

llama_stack/inference/quantization/loader.py

@@ -14,9 +14,9 @@ import torch
 
 from fairscale.nn.model_parallel.mappings import reduce_from_model_parallel_region
 from llama_models.llama3.api.model import Transformer, TransformerBlock
-from llama_toolchain.inference.api import QuantizationType
+from llama_stack.inference.api import QuantizationType
 
-from llama_toolchain.inference.api.config import (
+from llama_stack.inference.api.config import (
     CheckpointQuantizationFormat,
     MetaReferenceImplConfig,
 )