Add eval-base and eval-full extras

Signed-off-by: Anuradha Karuppiah <26330987+AnuradhaKaruppiah@users.noreply.github.com>

Author: AnuradhaKaruppiah

docs/source/get-started/installation.md

@@ -38,8 +38,9 @@ To install these first-party plugin libraries, you can use the full distribution
 - `nvidia-nat[agno]` or `nvidia-nat-agno` - [Agno](https://agno.com/)
 - `nvidia-nat[crewai]` or `nvidia-nat-crewai` - [CrewAI](https://www.crewai.com/) Conflicts with `nvidia-nat[openpipe-art]`.
 - `nvidia-nat[data-flywheel]` or `nvidia-nat-data-flywheel` - [NeMo DataFlywheel](https://github.com/NVIDIA-AI-Blueprints/data-flywheel)
-- `nvidia-nat[eval]` or `nvidia-nat-eval` - Evaluation package for ATIF-native and standalone custom evaluator workflows
+- `nvidia-nat[eval-base]` or `nvidia-nat-eval` - Evaluation package for ATIF-native and standalone custom evaluator workflows
 - `nvidia-nat[eval-full]` - Full evaluation runtime dependencies for config-driven `nat eval` workflows
+- `nvidia-nat[eval]` - Full evaluation runtime dependencies for config-driven `nat eval` workflows (backward-compatible alias of `eval-full`)
 - `nvidia-nat[langchain]` or `nvidia-nat-langchain` - [LangChain](https://www.langchain.com/), [LangGraph](https://www.langchain.com/langgraph)
 - `nvidia-nat[llama-index]` or `nvidia-nat-llama-index` - [LlamaIndex](https://www.llamaindex.ai/)
 - `nvidia-nat[mcp]` or `nvidia-nat-mcp` - [Model Context Protocol (MCP)](https://modelcontextprotocol.io/)

docs/source/reference/cli.md

@@ -555,9 +555,9 @@ nat serve --config_file=path/to/config --host 0.0.0.0 --port 8000
 The Swagger API docs will be available at: [http://localhost:8000/docs](http://localhost:8000/docs)
 
 ## Evaluation
-The `nat eval` command is provided by the `nvidia-nat-eval` package. For full config-driven `nat eval` runtime paths, install `pip install "nvidia-nat[eval-full]"` (recommended) or `pip install "nvidia-nat-eval[full]"`.
+The `nat eval` command is provided by the `nvidia-nat-eval` package. For full config-driven `nat eval` runtime paths, install `pip install "nvidia-nat[eval-full]"` or `pip install "nvidia-nat-eval[full]"`.
 
-For ATIF-native standalone custom-evaluator paths, install `pip install "nvidia-nat[eval]"` or `pip install nvidia-nat-eval`.
+For ATIF-native standalone custom-evaluator paths, install `pip install "nvidia-nat[eval-base]"` or `pip install nvidia-nat-eval`.
 
 The `nat eval` command provides access a set of evaluators designed to assessing the accuracy of NeMo Agent Toolkit workflows as
 well as instrumenting their performance characteristics. Please reference

docs/source/resources/migration-guide.md

@@ -58,16 +58,18 @@ This is a breaking change:
 
 To migrate:
 - Install both packages when using these evaluators:
+  - `pip install "nvidia-nat[eval]" nvidia-nat-langchain`
   - `pip install "nvidia-nat[eval-full]" nvidia-nat-langchain`
   - `pip install "nvidia-nat-eval[full]" nvidia-nat-langchain`
+  - Note: `nvidia-nat[eval]` is retained for backward compatibility; prefer `nvidia-nat[eval-full]` in new installs.
 - Install the RAGAS evaluator package when using `_type: ragas`:
   - `pip install nvidia-nat-ragas`
 - Install the profiler package when using performance evaluators or profiling workflows:
   - `pip install nvidia-nat-profiler`
   - Note: the previous dependency group name `nvidia-nat-profiling` is now `nvidia-nat-profiler`.
 - Keep evaluator config names unchanged (`trajectory`, `tunable_rag_evaluator`, `avg_llm_latency`, `avg_workflow_runtime`, `avg_num_llm_calls`, `avg_tokens_per_llm_end`).
 - Remove any `_type: swe_bench` evaluator entries from evaluation configurations.
-- If you only need custom evaluators, keep `nvidia-nat-eval` installed for evaluator contracts and do not rely on moved built-ins.
+- If you only need custom evaluators, use `nvidia-nat[eval-base]` (or `nvidia-nat-eval`) for the lightweight path and do not rely on moved built-ins.
 
 #### Eval Exporter Callback Split
 
@@ -91,6 +93,7 @@ CLI command ownership is now aligned to package domains:
 
 To migrate:
 - Install command-specific packages as needed:
+  - `pip install "nvidia-nat[eval]"`
   - `pip install "nvidia-nat[eval-full]"`
   - `pip install "nvidia-nat-eval[full]"`
   - `pip install nvidia-nat-profiler`

pyproject.toml

@@ -60,7 +60,9 @@ config-optimizer = ["nvidia-nat-config-optimizer == {version}"]
 core = ["nvidia-nat-core == {version}"]
 crewai = ["nvidia-nat-crewai == {version}"]
 data-flywheel = ["nvidia-nat-data-flywheel == {version}"]
-eval = ["nvidia-nat-eval == {version}"]
+# Backward-compatible alias: keep `eval` mapped to full runtime dependencies.
+eval = ["nvidia-nat-eval[full] == {version}"]
+eval-base = ["nvidia-nat-eval == {version}"]
 eval-full = ["nvidia-nat-eval[full] == {version}"]
 fastmcp = ["nvidia-nat-fastmcp == {version}"]
 langchain = ["nvidia-nat-langchain == {version}"]