Add Exa Search API support as internet search tool (#1846)

## Summary
- Add `exa_internet_search` tool using `langchain_exa.ExaSearchResults`, mirroring the existing `tavily_internet_search` tool
- Includes `ExaInternetSearchToolConfig` with configurable `max_results`, `search_type` (`Literal["auto", "neural", "keyword"]`), `livecrawl` (`Literal["always", "fallback", "never"]`), `max_query_length`, and `api_key` (via config or `EXA_API_KEY` env var)
- Client instantiated lazily inside the invocation path, only when a valid API key is present
- Adds `langchain-exa>=1.1.0,<2.0.0` dependency to `nvidia-nat-langchain`
- Updates tutorial documentation with an "Using Exa Search" section alongside the existing Tavily section

Closes #1848

## Test plan
- [x] Unit tests pass (12 tests in `test_exa_internet_search.py` — config validation, retries, truncation, empty results, empty key)
- [x] Existing Tavily tests still pass (no regressions)
- [x] Tool registers correctly in `GlobalTypeRegistry` and appears in `nat info components -t function`
- [x] `ruff check` passes on all new/modified files
- [x] Integration test with a valid `EXA_API_KEY` against live Exa API

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Authors:
  - Max Buckley (https://github.com/maxwbuckley)
  - Bryan Bednarski (https://github.com/bbednarski9)

Approvers:
  - Bryan Bednarski (https://github.com/bbednarski9)
  - https://github.com/Salonijain27

URL: #1846

Author: maxwbuckley

ci/vale/styles/config/vocabularies/nat/accept.txt

@@ -65,6 +65,7 @@ Dynatrace
 [Ee]ngineerable
 etcd
 [Ee]val
+Exa
 [Ee]xfiltration
 [Ee]xplainability
 Faiss

docs/source/get-started/tutorials/add-tools-to-a-workflow.md

@@ -109,7 +109,9 @@ Workflow Result:
 ```
 
 ## Alternate Method Using a Web Search Tool
-Adding individual web pages to a workflow can be cumbersome, especially when dealing with multiple web pages. An alternative method is to use a web search tool. One of the tools available in NeMo Agent Toolkit is the `tavily_internet_search` tool, which utilizes the [Tavily Search API](https://tavily.com/).
+Adding individual web pages to a workflow can be cumbersome, especially when dealing with multiple web pages. An alternative method is to use a web search tool. NeMo Agent Toolkit provides two web search tools: `tavily_internet_search` which utilizes the [Tavily Search API](https://tavily.com/), and `exa_internet_search` which utilizes the [Exa Search API](https://exa.ai/).
+
+### Using Tavily Search
 
 The `tavily_internet_search` tool is part of the `nvidia-nat[langchain]` package, to install the package run:
 ```bash
@@ -151,3 +153,46 @@ Which will then yield a slightly different result to the same question:
 Workflow Result:
 ['To trace only specific parts of a LangChain application, users can use the `@traceable` decorator to mark specific functions or methods as traceable. Additionally, users can configure the tracing functionality to log traces to a specific project, add metadata and tags to traces, and customize the run name and ID. Users can also use the `LangChainTracer` class to trace specific invocations or parts of their application. Furthermore, users can use the `tracing_v2_enabled` context manager to trace a specific block of code.']
 ```
+
+### Using Exa Search
+
+The `exa_internet_search` tool is also part of the `nvidia-nat[langchain]` package. If you haven't already installed it:
+```bash
+# local package install from source
+uv pip install -e ".[langchain]"
+```
+
+Prior to using the `exa_internet_search` tool, create an account at [`exa.ai`](https://exa.ai/) and obtain an API key. Once obtained, set the `EXA_API_KEY` environment variable to the API key:
+```bash
+export EXA_API_KEY=<YOUR_EXA_API_KEY>
+```
+
+You can use the `exa_internet_search` tool in the same way as `tavily_internet_search` by updating the `functions` section of the configuration file:
+```yaml
+functions:
+  internet_search:
+    _type: exa_internet_search
+  current_datetime:
+    _type: current_datetime
+```
+
+The `exa_internet_search` tool supports additional configuration options:
+```yaml
+functions:
+  internet_search:
+    _type: exa_internet_search
+    max_results: 5
+    search_type: neural  # 'auto', 'fast', 'deep', 'neural', or 'instant'
+    livecrawl: fallback  # 'always', 'fallback', or 'never'
+    max_retries: 3
+    max_query_length: 2000  # queries longer than this are truncated
+    highlights: true  # include highlights in results
+    max_content_length: 10000  # max chars of text per result; set to None to disable
+```
+
+Then ensure the tool is included in the workflow tool list:
+```yaml
+workflow:
+  _type: react_agent
+  tool_names: [internet_search, current_datetime]
+```