PyPi package install README updates

README.md

@@ -81,13 +81,13 @@ pip install nvidia-nat
 NeMo Agent Toolkit has many optional dependencies which can be installed with the core package. Optional dependencies are grouped by framework and can be installed with the core package. For example, to install the LangChain/LangGraph plugin, run the following:
 
 ```bash
-pip install nvidia-nat[langchain]
+pip install "nvidia-nat[langchain]"
 ```
 
 Or for all optional dependencies:
 
 ```bash
-pip install nvidia-nat[all]
+pip install "nvidia-nat[all]"
 ```
 
 The full list of optional dependencies can be found [here](./docs/source/quick-start/installing.md#framework-integrations).

docs/source/extend/telemetry-exporters.md

@@ -266,14 +266,14 @@ Before creating a custom exporter, check if your observability service is alread
 | Service | Type | Installation | Configuration |
 |---------|------|-------------|---------------|
 | **File** | `file` | `pip install nvidia-nat` | local file or directory |
-| **Langfuse** | `langfuse` | `pip install nvidia-nat[opentelemetry]` | endpoint + API keys |
-| **LangSmith** | `langsmith` | `pip install nvidia-nat[opentelemetry]` | endpoint + API key |
-| **OpenTelemetry Collector** | `otelcollector` | `pip install nvidia-nat[opentelemetry]` | endpoint + headers |
-| **Patronus** | `patronus` | `pip install nvidia-nat[opentelemetry]` | endpoint + API key |
-| **Galileo** | `galileo` | `pip install nvidia-nat[opentelemetry]` | endpoint + API key |
-| **Phoenix** | `phoenix` | `pip install nvidia-nat[phoenix]` | endpoint |
-| **RagaAI/Catalyst** | `catalyst` | `pip install nvidia-nat[ragaai]` | API key + project |
-| **Weave** | `weave` | `pip install nvidia-nat[weave]` | project name |
+| **Langfuse** | `langfuse` | `pip install "nvidia-nat[opentelemetry]"` | endpoint + API keys |
+| **LangSmith** | `langsmith` | `pip install "nvidia-nat[opentelemetry]"` | endpoint + API key |
+| **OpenTelemetry Collector** | `otelcollector` | `pip install "nvidia-nat[opentelemetry]"` | endpoint + headers |
+| **Patronus** | `patronus` | `pip install "nvidia-nat[opentelemetry]"` | endpoint + API key |
+| **Galileo** | `galileo` | `pip install "nvidia-nat[opentelemetry]"` | endpoint + API key |
+| **Phoenix** | `phoenix` | `pip install "nvidia-nat[phoenix]"` | endpoint |
+| **RagaAI/Catalyst** | `catalyst` | `pip install "nvidia-nat[ragaai]"` | API key + project |
+| **Weave** | `weave` | `pip install "nvidia-nat[weave]"` | project name |
 
 ### Simple Configuration Example
 
@@ -412,7 +412,7 @@ class CustomSpanExporter(SpanExporter[Span, dict]):
 > **Note**: OpenTelemetry exporters require the `nvidia-nat-opentelemetry` subpackage. Install it with:
 
 > ```bash
-> pip install nvidia-nat[opentelemetry]
+> pip install "nvidia-nat[opentelemetry]"
 > ```
 
 For most OTLP-compatible services, use the pre-built `OTLPSpanAdapterExporter`:

docs/source/quick-start/installing.md

@@ -92,13 +92,13 @@ pip install nvidia-nat
 NeMo Agent toolkit has many optional dependencies which can be installed with the core package. Optional dependencies are grouped by framework and can be installed with the core package. For example, to install the LangChain/LangGraph plugin, run the following:
 
 ```bash
-pip install nvidia-nat[langchain]
+pip install "nvidia-nat[langchain]"
 ```
 
 Or for all optional dependencies:
 
 ```bash
-pip install nvidia-nat[all]
+pip install "nvidia-nat[all]"
 ```
 
 The full list of optional dependencies can be found [here](../quick-start/installing.md#framework-integrations).

docs/source/reference/api-server-endpoints.md

@@ -61,7 +61,7 @@ result back to the client. The transaction schema is defined by the workflow.
 ## Asynchronous Generate
 The asynchronous generate endpoint allows clients to submit a workflow to run in the background and return a response immediately with a unique identifier for the workflow. This can be used to query the status and results of the workflow at a later time. This is useful for long-running workflows, which would otherwise cause the client to time out.
 
-This endpoint is only available when the `async_endpoints` optional dependency extra is installed. For users installing from source, this can be done by running `uv pip install -e '.[async_endpoints]'` from the root directory of the NeMo Agent toolkit library. Similarly, for users installing from PyPI, this can be done by running `pip install 'nvidia-nat[async_endpoints]'`.
+This endpoint is only available when the `async_endpoints` optional dependency extra is installed. For users installing from source, this can be done by running `uv pip install -e '.[async_endpoints]'` from the root directory of the NeMo Agent toolkit library. Similarly, for users installing from PyPI, this can be done by running `pip install "nvidia-nat[async_endpoints]"`.
 
 Asynchronous jobs are managed using [Dask](https://docs.dask.org/en/stable/). By default, a local Dask cluster is created at start time, however you can also configure the server to connect to an existing Dask scheduler by setting the `scheduler_address` configuration parameter. The Dask scheduler is used to manage the execution of asynchronous jobs, and can be configured to run on a single machine or across a cluster of machines. Job history and metadata is stored in a SQL database using [SQLAlchemy](https://www.sqlalchemy.org/). By default, a temporary SQLite database is created at start time, however you can also configure the server to use a persistent database by setting the `db_url` configuration parameter. Refer to the [SQLAlchemy documentation](https://docs.sqlalchemy.org/en/20/core/engines.html#database-urls) for the format of the `db_url` parameter. Any database supported by [SQLAlchemy's Asynchronous I/O extension](https://docs.sqlalchemy.org/en/20/orm/extensions/asyncio.html) can be used. Refer to [SQLAlchemy's Dialects](https://docs.sqlalchemy.org/en/20/dialects/index.html) for a complete list (many but not all of these support Asynchronous I/O).
 

docs/source/reference/evaluate-api.md

@@ -20,7 +20,7 @@ limitations under the License.
 It is recommended that the [Evaluating NeMo Agent toolkit Workflows](./evaluate.md) guide be read before proceeding with this detailed documentation.
 :::
 
-The evaluation endpoint can be used to start evaluation jobs on a remote NeMo Agent toolkit server. This endpoint is only available when the `async_endpoints` optional dependency extra is installed. For users installing from source, this can be done by running `uv pip install -e '.[async_endpoints]'` from the root directory of the NeMo Agent toolkit library. Similarly, for users installing from PyPI, this can be done by running `pip install 'nvidia-nat[async_endpoints]'`.
+The evaluation endpoint can be used to start evaluation jobs on a remote NeMo Agent toolkit server. This endpoint is only available when the `async_endpoints` optional dependency extra is installed. For users installing from source, this can be done by running `uv pip install -e '.[async_endpoints]'` from the root directory of the NeMo Agent toolkit library. Similarly, for users installing from PyPI, this can be done by running `pip install "nvidia-nat[async_endpoints]"`.
 
 ## Evaluation Endpoint Overview
 ```{mermaid}

docs/source/workflows/evaluate.md

@@ -34,7 +34,7 @@ uv pip install -e '.[profiling]'
 
 If you are installing from a package, you can install the sub-package by running the following command:
 ```bash
-uv pip install nvidia-nat[profiling]
+uv pip install "nvidia-nat[profiling]"
 ```
 
 ## Evaluating a Workflow

docs/source/workflows/mcp/index.md

@@ -21,7 +21,7 @@ NeMo Agent toolkit [Model Context Protocol (MCP)](https://modelcontextprotocol.i
 * An [MCP client](./mcp-client.md) to connect to and use tools served by remote MCP servers.
 * An [MCP server](./mcp-server.md) to publish tools using MCP to be used by any MCP client.
 
-**Note:** MCP client functionality requires the `nvidia-nat-mcp` package. Install it with `uv pip install nvidia-nat[mcp]`.
+**Note:** MCP client functionality requires the `nvidia-nat-mcp` package. Install it with `uv pip install "nvidia-nat[mcp]"`.
 
 
 ```{toctree}

docs/source/workflows/mcp/mcp-client.md

@@ -28,7 +28,7 @@ This guide will cover how to use a NeMo Agent toolkit workflow as a MCP host wit
 MCP client functionality requires the `nvidia-nat-mcp` package. Install it with:
 
 ```bash
-uv pip install nvidia-nat[mcp]
+uv pip install "nvidia-nat[mcp]"
 ```
 ## Accessing Protected MCP Servers
 NeMo Agent toolkit can access protected MCP servers via the MCP client auth provider. For more information, see the [MCP Authentication](./mcp-auth.md) documentation.

docs/source/workflows/mcp/mcp-server.md

@@ -62,7 +62,7 @@ nat mcp serve --config_file examples/getting_started/simple_calculator/configs/c
 
 To list the tools published by the MCP server you can use the `nat mcp client tool list` command. This command acts as an MCP client and connects to the MCP server running on the specified URL (defaults to `http://localhost:9901/mcp` for streamable-http, with backwards compatibility for `http://localhost:9901/sse`).
 
-**Note:** The `nat mcp client` commands require the `nvidia-nat-mcp` package. If you encounter an error about missing MCP client functionality, install it with `uv pip install nvidia-nat[mcp]`.
+**Note:** The `nat mcp client` commands require the `nvidia-nat-mcp` package. If you encounter an error about missing MCP client functionality, install it with `uv pip install "nvidia-nat[mcp]"`.
 
 ```bash
 nat mcp client tool list

docs/source/workflows/profiler.md

@@ -41,7 +41,7 @@ uv pip install -e ".[profiling]"
 
 If you are installing from a package, you need to install the `nvidia-nat[profiling]` package by running the following command:
 ```bash
-uv pip install nvidia-nat[profiling]
+uv pip install "nvidia-nat[profiling]"
 ```
 
 ## Current Profiler Architecture

examples/MCP/simple_auth_mcp/README.md

@@ -26,7 +26,7 @@ It is recommended to read the [MCP Authentication](../../../docs/source/workflow
 1. **Agent toolkit**: Ensure you have the Agent toolkit installed. If you have not already done so, follow the instructions in the [Install Guide](../../../docs/source/quick-start/installing.md#install-from-source) to create the development environment and install NeMo Agent Toolkit.
 2. **MCP Server**: Access to an MCP server that requires authentication (e.g., corporate Jira system)
 
-**Note**: If you installed NeMo Agent toolkit from source, MCP client functionality is already included. If you installed from PyPI, you may need to install the MCP client package separately with `uv pip install nvidia-nat[mcp]`.
+**Note**: If you installed NeMo Agent toolkit from source, MCP client functionality is already included. If you installed from PyPI, you may need to install the MCP client package separately with `uv pip install "nvidia-nat[mcp]"`.
 
 ## Install this Workflow
 

examples/RAG/simple_rag/configs/milvus_memory_rag_tools_config.yml

@@ -13,7 +13,6 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-
 memory:
   saas_memory:
     _type: mem0_memory
@@ -56,7 +55,7 @@ functions:
       The question should be about user preferences which will help you format your response.
       For example: "How does the user like responses formatted?"
 
-  # To use these tools you will need to install the nvidia-nat[langchain] package
+  # To use these tools you will need to install the "nvidia-nat[langchain]" package
   web_search_tool:
     _type: tavily_internet_search
     max_results: 5
@@ -85,11 +84,11 @@ embedders:
 workflow:
   _type: react_agent
   tool_names:
-   - cuda_retriever_tool
-   - mcp_retriever_tool
-   - add_memory
-   - get_memory
-   - web_search_tool
-   - code_generation_tool
+    - cuda_retriever_tool
+    - mcp_retriever_tool
+    - add_memory
+    - get_memory
+    - web_search_tool
+    - code_generation_tool
   verbose: true
   llm_name: nim_llm

examples/RAG/simple_rag/configs/milvus_rag_tools_config.yml

@@ -13,7 +13,6 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-
 retrievers:
   cuda_retriever:
     _type: milvus_retriever
@@ -38,7 +37,7 @@ functions:
     retriever: mcp_retriever
     topic: Retrieve information about Model Context Protocol (MCP)
 
-  # To use these tools you will need to install the nvidia-nat[langchain] package
+  # To use these tools you will need to install the "nvidia-nat[langchain]" package
   web_search_tool:
     _type: tavily_internet_search
     max_results: 5
@@ -67,10 +66,10 @@ embedders:
 workflow:
   _type: react_agent
   tool_names:
-   - cuda_retriever_tool
-   - mcp_retriever_tool
-   - web_search_tool
-   - code_generation_tool
+    - cuda_retriever_tool
+    - mcp_retriever_tool
+    - web_search_tool
+    - code_generation_tool
   verbose: true
   llm_name: nim_llm
   additional_instructions: "If a tool call results in code or other artifacts being returned, you MUST include that in your thoughts and response."

pyproject.toml

@@ -66,7 +66,7 @@ maintainers = [{ name = "NVIDIA Corporation" }]
 
 
 [project.optional-dependencies]
-# Optional dependencies are things that users would want to install with NAT. i.e. `uv pip install nvidia-nat[langchain]`
+# Optional dependencies are things that users would want to install with NAT. i.e. `uv pip install "nvidia-nat[langchain]"`
 # Keep sorted!!!
 all = ["nvidia-nat-all"] # meta-package
 adk = ["nvidia-nat-adk"]

src/nat/agent/prompt_optimizer/register.py

@@ -21,7 +21,8 @@
 from nat.cli.register_workflow import register_function
 from nat.data_models.component_ref import LLMRef
 from nat.data_models.function import FunctionBaseConfig
-from nat.profiler.parameter_optimization.prompt_optimizer import PromptOptimizerInputSchema
+from nat.profiler.parameter_optimization.prompt_optimizer import \
+    PromptOptimizerInputSchema
 
 
 class PromptOptimizerConfig(FunctionBaseConfig, name="prompt_init"):
@@ -51,7 +52,7 @@ async def prompt_optimizer_function(config: PromptOptimizerConfig, builder: Buil
         from .prompt import mutator_prompt
     except ImportError as exc:
         raise ImportError("langchain-core is not installed. Please install it to use MultiLLMPlanner.\n"
-                          "This error can be resolve by installing nvidia-nat[langchain]") from exc
+                          "This error can be resolve by installing \"nvidia-nat[langchain]\".") from exc
 
     llm = await builder.get_llm(config.optimizer_llm, wrapper_type=LLMFrameworkEnum.LANGCHAIN)
 
@@ -111,7 +112,7 @@ async def prompt_recombiner_function(config: PromptRecombinerConfig, builder: Bu
         from langchain_core.prompts import PromptTemplate
     except ImportError as exc:
         raise ImportError("langchain-core is not installed. Please install it to use MultiLLMPlanner.\n"
-                          "This error can be resolve by installing nvidia-nat[langchain].") from exc
+                          "This error can be resolve by installing \"nvidia-nat[langchain]\".") from exc
 
     llm = await builder.get_llm(config.optimizer_llm, wrapper_type=LLMFrameworkEnum.LANGCHAIN)
 

src/nat/profiler/decorators/framework_wrapper.py

@@ -17,8 +17,7 @@
 
 import functools
 import logging
-from collections.abc import AsyncIterator
-from collections.abc import Callable
+from collections.abc import AsyncIterator, Callable
 from contextlib import AbstractAsyncContextManager as AsyncContextManager
 from contextlib import asynccontextmanager
 from contextvars import ContextVar
@@ -72,13 +71,15 @@ async def wrapper(workflow_config, builder):
             if LLMFrameworkEnum.LANGCHAIN in frameworks:
                 # Always set a fresh handler in the current context so callbacks
                 # route to the active run. Only register the hook once globally.
-                from nat.profiler.callbacks.langchain_callback_handler import LangchainProfilerHandler
+                from nat.profiler.callbacks.langchain_callback_handler import \
+                    LangchainProfilerHandler
 
                 handler = LangchainProfilerHandler()
                 callback_handler_var.set(handler)
 
                 if not _library_instrumented["langchain"]:
-                    from langchain_core.tracers.context import register_configure_hook
+                    from langchain_core.tracers.context import \
+                        register_configure_hook
                     register_configure_hook(callback_handler_var, inheritable=True)
                     _library_instrumented["langchain"] = True
                     logger.debug("LangChain/LangGraph callback hook registered")
@@ -87,30 +88,34 @@ async def wrapper(workflow_config, builder):
                 from llama_index.core import Settings
                 from llama_index.core.callbacks import CallbackManager
 
-                from nat.profiler.callbacks.llama_index_callback_handler import LlamaIndexProfilerHandler
+                from nat.profiler.callbacks.llama_index_callback_handler import \
+                    LlamaIndexProfilerHandler
 
                 handler = LlamaIndexProfilerHandler()
                 Settings.callback_manager = CallbackManager([handler])
                 logger.debug("LlamaIndex callback handler registered")
 
             if LLMFrameworkEnum.CREWAI in frameworks and not _library_instrumented["crewai"]:
-                from nat.plugins.crewai.crewai_callback_handler import CrewAIProfilerHandler
+                from nat.plugins.crewai.crewai_callback_handler import \
+                    CrewAIProfilerHandler
 
                 handler = CrewAIProfilerHandler()
                 handler.instrument()
                 _library_instrumented["crewai"] = True
                 logger.debug("CrewAI callback handler registered")
 
             if LLMFrameworkEnum.SEMANTIC_KERNEL in frameworks and not _library_instrumented["semantic_kernel"]:
-                from nat.profiler.callbacks.semantic_kernel_callback_handler import SemanticKernelProfilerHandler
+                from nat.profiler.callbacks.semantic_kernel_callback_handler import \
+                    SemanticKernelProfilerHandler
 
                 handler = SemanticKernelProfilerHandler(workflow_llms=workflow_llms)
                 handler.instrument()
                 _library_instrumented["semantic_kernel"] = True
                 logger.debug("SemanticKernel callback handler registered")
 
             if LLMFrameworkEnum.AGNO in frameworks and not _library_instrumented["agno"]:
-                from nat.profiler.callbacks.agno_callback_handler import AgnoProfilerHandler
+                from nat.profiler.callbacks.agno_callback_handler import \
+                    AgnoProfilerHandler
 
                 handler = AgnoProfilerHandler()
                 handler.instrument()
@@ -119,11 +124,12 @@ async def wrapper(workflow_config, builder):
 
             if LLMFrameworkEnum.ADK in frameworks and not _library_instrumented["adk"]:
                 try:
-                    from nat.plugins.adk.adk_callback_handler import ADKProfilerHandler
+                    from nat.plugins.adk.adk_callback_handler import \
+                        ADKProfilerHandler
                 except ImportError as e:
                     logger.warning(
                         "ADK profiler not available. " +
-                        "Install NAT with ADK extras: pip install 'nvidia-nat[adk]'. Error: %s",
+                        "Install NAT with ADK extras: pip install \"nvidia-nat[adk]\". Error: %s",
                         e)
                 else:
                     handler = ADKProfilerHandler()

src/nat/profiler/forecasting/models/linear_model.py

@@ -17,8 +17,10 @@
 
 import numpy as np
 
-from nat.profiler.forecasting.models.forecasting_base_model import ForecastingBaseModel
-from nat.profiler.intermediate_property_adapter import IntermediatePropertyAdaptor
+from nat.profiler.forecasting.models.forecasting_base_model import \
+    ForecastingBaseModel
+from nat.profiler.intermediate_property_adapter import \
+    IntermediatePropertyAdaptor
 
 logger = logging.getLogger(__name__)
 
@@ -36,7 +38,7 @@ def __init__(self):
         except ImportError:
             logger.error(
                 "scikit-learn is not installed. Please install scikit-learn to use the LinearModel "
-                "profiling model or install `nvidia-nat[profiler]` to install all necessary profiling packages.")
+                "profiling model or install \"nvidia-nat[profiler]\" to install all necessary profiling packages.")
 
             raise