[docs] Make RAG example self-contained (#962)

Before the patch, the example could not be executed verbatim without
copy-pasting client function from the inference example. I think it's
better to have examples self-contained, especially in a getting started
guide.

Signed-off-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>

# What does this PR do?

See above.

## Test Plan

Confirmed example can now be executed verbatim.

## Sources

Please link relevant resources if necessary.


## Before submitting

- [x] This PR fixes a typo or improves the docs (you can dismiss the
other checks if that's the case).
- [x] Ran pre-commit to handle lint / formatting issues.
- [ ] Read the [contributor
guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md),
      Pull Request section?
- [ ] Updated relevant documentation.
- [ ] Wrote necessary unit or integration tests.

Signed-off-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>

docs/source/getting_started/index.md

@@ -163,6 +163,23 @@ from llama_stack_client.lib.agents.event_logger import EventLogger
 from llama_stack_client.types.agent_create_params import AgentConfig
 from llama_stack_client.types import Document
 
+
+def create_http_client():
+    from llama_stack_client import LlamaStackClient
+
+    return LlamaStackClient(
+        base_url=f"http://localhost:{os.environ['LLAMA_STACK_PORT']}"
+    )
+
+
+def create_library_client(template="ollama"):
+    from llama_stack import LlamaStackAsLibraryClient
+
+    client = LlamaStackAsLibraryClient(template)
+    client.initialize()
+    return client
+
+
 client = (
     create_library_client()
 )  # or create_http_client() depending on the environment you picked