docs: rewrite tracing.md (prioritize open source solution), fix misle…

…ading info

docs/tracing.md

@@ -13,7 +13,17 @@ The `project` field under the `[tracing]` section sets the name for your tracing
 > [!NOTE]  
 > Project name is currently only used by LangSmith. Langfuse will upload traces to the default project.
 
-### LangSmith
+### Langfuse (open-source)
+
+[Langfuse](https://langfuse.com/) is an open-source observability & analytics platform for LLM applications.
+
+To enable Langfuse tracing:
+
+1. Set `use_langfuse = true` in the `config.toml` file.
+2. Set the `LANGFUSE_PUBLIC_KEY` and `LANGFUSE_SECRET_KEY` environment variables with your Langfuse credentials.
+3. Optionally, you can specify a custom Langfuse host by modifying the `host` field under `[tracing.langfuse]`.
+
+### LangSmith (closed-source, paid)
 
 [LangSmith](https://www.langchain.com/langsmith) is a platform for debugging, testing, and monitoring LangChain applications.
 
@@ -22,23 +32,26 @@ To enable LangSmith tracing:
 1. Set `use_langsmith = true` in the `config.toml` file.
 2. Set the `LANGCHAIN_API_KEY` environment variable with your LangSmith API key.
 
-When enabled, LangSmith tracing will automatically be set up with the following environment variables:
-
-### Langfuse
+## Usage
 
-[Langfuse](https://langfuse.com/) is an open-source observability & analytics platform for LLM applications.
+To enable tracing in your RAI application, you need to import the get_tracing_callbacks() function and add it to the configuration when invoking your agent or model. Here's how to do it:
 
-To enable Langfuse tracing:
+1. First, import the get_tracing_callbacks() function:
 
-1. Set `use_langfuse = true` in the `config.toml` file.
-2. Set the `LANGFUSE_PUBLIC_KEY` and `LANGFUSE_SECRET_KEY` environment variables with your Langfuse credentials.
-3. Optionally, you can specify a custom Langfuse host by modifying the `host` field under `[tracing.langfuse]`.
+```python
+from rai.utils.model_initialization import get_tracing_callbacks
+```
 
-## Usage
+2. Then, add it to the configuration when invoking your agent or model:
 
-The tracing configuration is automatically loaded and applied when initializing models in RAI. The `get_tracing_callbacks()` function in `model_initialization.py` sets up the appropriate callbacks based on your configuration:
+```python
+response = agent.invoke(
+    input_dict,
+    config={"callbacks": get_tracing_callbacks()}
+)
+```
 
-This function returns a list of callback handlers that can be used with LangChain.
+By adding the get_tracing_callbacks() to the config parameter, you enable tracing for that specific invocation. The get_tracing_callbacks() function returns a list of callback handlers based on your configuration in config.toml.
 
 ## Troubleshooting