delete in-code config section in LLM Obs docs (#23169)

* delete in-code config section

* Editorial review

* Fix broken shortcode

* Add SDK documentation link

* Tweak wording

* Fix quickstart headers

---------

Co-authored-by: lievan <[email protected]>
Co-authored-by: Jen Gilbert <[email protected]>

content/en/tracing/llm_observability/quickstart.md

@@ -9,28 +9,26 @@ LLM Observability is not available in the US1-FED site.
 
 <div class="alert alert-info">LLM Observability is in public beta.</a></div>
 
-Our quickstart docs make use of our Python SDK. For detailed usage, see [the SDK documentation][1]. If your application is written in another language, you can create traces by calling the [API][8] instead.
-
-## Command line quickstart
+Our quickstart docs make use of the LLM Observability SDK for Python. For detailed usage, see [the SDK documentation][1]. If your application is written in another language, you can create traces by calling the [API][8] instead.
 
 Use the steps below to run a simple Python script that generates an LLM Observability trace.
 
-### Prerequisites
+## Prerequisites
 
 - LLM Observability requires a Datadog API key (see [the instructions for creating an API key][7]).
 - The example script below uses OpenAI, but you can modify it to use a different provider. To run the script as written, you need:
     - An OpenAI API key stored in your environment as `OPENAI_API_KEY`. To create one, see [Account Setup][4] and [Set up your API key][6] in the OpenAI documentation.
     - The OpenAI Python library installed. See [Setting up Python][5] in the OpenAI documentation for instructions.
 
-### 1. Install the SDK
+## 1. Install the SDK
 
 Install the following `ddtrace` package hash:
 
 {{< code-block lang="shell" >}}
 pip install git+https://github.com/DataDog/dd-trace-py.git@main
 {{< /code-block >}}
 
-### 2. Create the script
+## 2. Create the script
 
 The Python script below makes a single OpenAI call. Save it as `quickstart.py`.
 
@@ -49,17 +47,19 @@ completion = oai_client.chat.completions.create(
 )
 {{< /code-block >}}
 
-### 3. Run the script
+## 3. Run the script
 
-Run the Python script with the following shell command, and a trace of the OpenAI call will be sent to Datadog:
+Run the Python script with the following shell command, sending a trace of the OpenAI call to Datadog:
 
 {{< code-block lang="shell" >}}
 DD_LLMOBS_ENABLED=1 DD_LLMOBS_APP_NAME=onboarding-quickstart \ 
-DD_API_KEY=<YOUR_DATADOG_API_KEY> DD_SITE={{< region-param key="dd_site" code="true" >}} \ 
+DD_API_KEY=<YOUR_DATADOG_API_KEY> DD_SITE=<YOUR_DATADOG_SITE> \ 
 DD_LLMOBS_NO_APM=1 ddtrace-run python quickstart.py
 {{< /code-block >}}
 
-### 4. View the trace
+For details on the required environment variables, see [the SDK documentation][9].
+
+## 4. View the trace
 
 A trace of your LLM call should appear in [the Traces tab][3] of LLM Observability in Datadog.
 
@@ -74,3 +74,4 @@ The trace you see is composed of a single LLM span. The `ddtrace-run` command au
 [6]: https://platform.openai.com/docs/quickstart/step-2-set-up-your-api-key
 [7]: /account_management/api-app-keys/#add-an-api-key-or-client-token
 [8]: /tracing/llm_observability/api
+[9]: /tracing/llm_observability/sdk/#command-line-setup

content/en/tracing/llm_observability/sdk.md

@@ -28,36 +28,14 @@ pip install git+https://github.com/DataDog/dd-trace-py.git@main
 
 2. LLM Observability requires a Datadog API key (see [the instructions for creating an API key][7]).
 
-#### In-code setup
-
-Enable LLM Observability through the `LLMOBs.enable()` function, as shown in the example below.
-
-- Use the `integrations` argument to turn on automatic tracing for supported LLM Observability integrations (OpenAI, Bedrock, and LangChain).
-
-- If you do not have Datadog APM set up, set `dd_llmobs_no_apm` to `True`. This configures the `ddtrace` library to not send any data that requires Datadog APM.
-
-- When choosing a value for `ml_app`, see [Application naming guidelines](#application-naming-guidelines) for allowed characters and other constraints.
-
-{{< code-block lang="python" >}}
-from ddtrace.llmobs import LLMObs
-
-LLMObs.enable(
-    ml_app="<YOUR_ML_APP_NAME>",
-    dd_api_key="<YOUR_DATADOG_API_KEY>",
-    dd_site="{{< region-param key="dd_site" code="true" >}}",
-    dd_llmobs_no_apm=True,
-    integrations=[LLMObs.openai, LLMObs.botocore, LLMObs.langchain],
-)
-{{< /code-block >}}
-
 #### Command-line setup
 
-You can also enable LLM Observability by running your application using the `ddtrace-run` command and specifying the required environment variables.
+Enable LLM Observability by running your application using the `ddtrace-run` command and specifying the required environment variables.
 
 **Note**: `ddtrace-run` automatically turns on all LLM Observability integrations.
 
 {{< code-block lang="shell">}}
-DD_SITE={{< region-param key="dd_site" code="true" >}} DD_API_KEY=<YOUR_API_KEY> DD_LLMOBS_ENABLED=1 \
+DD_SITE=<YOUR_DATADOG_SITE> DD_API_KEY=<YOUR_API_KEY> DD_LLMOBS_ENABLED=1 \
 DD_LLMOBS_APP_NAME=<YOUR_ML_APP_NAME> ddtrace-run <YOUR_APP_STARTUP_COMMAND>
 {{< /code-block >}}
 
@@ -83,7 +61,7 @@ DD_LLMOBS_APP_NAME=<YOUR_ML_APP_NAME> ddtrace-run <YOUR_APP_STARTUP_COMMAND>
 
 #### Application naming guidelines
 
-Your application name (the value of `ml_app` or `DD_LLMOBS_APP_NAME`) must start with a letter. It may contain the characters listed below:
+Your application name (the value of `DD_LLMOBS_APP_NAME`) must start with a letter. It may contain the characters listed below:
 
 - Alphanumerics
 - Underscores

content/en/tracing/llm_observability/trace_an_llm_application.md

@@ -39,9 +39,7 @@ Different span kinds also have different parent-child relationships. For details
 To trace an LLM application:
 
 1. [Install the LLM Observability SDK][1].
-1. Configure the SDK by doing one of the following:
-    - Add [setup code to your application][17] that provides the name of your application, your Datadog API key, and so on.
-    - [Start your application using `ddtrace-run`][5], providing the required environment variables.
+1. Configure the SDK by providing [the required environment variables][5] in your application startup command.
 1. In your code, use the SDK to create spans representing your application's tasks.
     - See the span creation example below.
     - For additional examples and detailed usage, see the [Quickstart][10] and the [SDK documentation for tracing spans][11].