docs: improve haystack integration docs, add note that content tracing env must be set before importing LangfuseConnector

Author: marcklingen

cookbook/integration_haystack.ipynb

@@ -131,7 +131,9 @@
       "source": [
         "The following code snippet (based off of the Haystack [documentation](https://docs.haystack.deepset.ai/docs/get_started)) walks through building a basic retrieval-augmented generative (RAG) pipeline. First you'll load your data to the Document Store, then connect components together into a RAG pipeline, and finally ask a question.\n",
         "\n",
-        "First we build the pipeline. Add `LangfuseConnector` to the pipeline as a tracer. There's no need to connect it to any other component. The `LangfuseConnector` will automatically trace the operations and data flow within the pipeline. Then add the other components, like the text embedder, retriever, prompt builder and the model, and connect them together in the order they will be used in the pipeline."
+        "First we build the pipeline. Add `LangfuseConnector` to the pipeline as a tracer. There's no need to connect it to any other component. The `LangfuseConnector` will automatically trace the operations and data flow within the pipeline. Then add the other components, like the text embedder, retriever, prompt builder and the model, and connect them together in the order they will be used in the pipeline.\n",
+        "\n",
+        "**Note**: Make sure to set the `HAYSTACK_CONTENT_TRACING_ENABLED` environment variable before importing `LangfuseConnector`."
       ]
     },
     {
@@ -1610,7 +1612,9 @@
         "id": "YiuP6i7ncYUj"
       },
       "source": [
-        "Here is another example connecting a RAG pipeline to a chat generator. Using a component like Haystack's `DynamicChatPromptBuilder` is a great way to add a chat component to your application, which can add a level of personalization and interactivity to your program."
+        "Here is another example connecting a RAG pipeline to a chat generator. Using a component like Haystack's `DynamicChatPromptBuilder` is a great way to add a chat component to your application, which can add a level of personalization and interactivity to your program.\n",
+        "\n",
+        "**Note**: Make sure to set the `HAYSTACK_CONTENT_TRACING_ENABLED` environment variable before importing `LangfuseConnector`."
       ]
     },
     {

pages/docs/integrations/haystack/example-python.md

@@ -69,6 +69,8 @@ The following code snippet (based off of the Haystack [documentation](https://do
 
 First we build the pipeline. Add `LangfuseConnector` to the pipeline as a tracer. There's no need to connect it to any other component. The `LangfuseConnector` will automatically trace the operations and data flow within the pipeline. Then add the other components, like the text embedder, retriever, prompt builder and the model, and connect them together in the order they will be used in the pipeline.
 
+**Note**: Make sure to set the `HAYSTACK_CONTENT_TRACING_ENABLED` environment variable before importing `LangfuseConnector`.
+
 
 ```python
 from datasets import load_dataset
@@ -178,6 +180,8 @@ Learn more about tracing in the [docs](https://langfuse.com/docs/tracing).
 
 Here is another example connecting a RAG pipeline to a chat generator. Using a component like Haystack's `DynamicChatPromptBuilder` is a great way to add a chat component to your application, which can add a level of personalization and interactivity to your program.
 
+**Note**: Make sure to set the `HAYSTACK_CONTENT_TRACING_ENABLED` environment variable before importing `LangfuseConnector`.
+
 
 ```python
 from haystack import Pipeline

pages/docs/integrations/haystack/get-started.mdx

@@ -50,7 +50,7 @@ pip install haystack-ai langfuse-haystack langfuse
 ### Set Environment Variables
 
 1. Langfuse: You can find your Langfuse public and private API keys in the project settings.
-2. Haystack: Enable `HAYSTACK_CONTENT_TRACING_ENABLED`.
+2. Haystack: Enable `HAYSTACK_CONTENT_TRACING_ENABLED`. **You must set this variable before importing `LangfuseConnector`.**
 
 ```python
 import os
@@ -66,6 +66,24 @@ os.environ["LANGFUSE_HOST"] = "https://cloud.langfuse.com" # 🇪🇺 EU region
 os.environ["HAYSTACK_CONTENT_TRACING_ENABLED"] = "True"
 ```
 
+### Add `LangfuseConnector` to your pipeline
+
+Add `LangfuseConnector` to the pipeline as a tracer. There's no need to connect it to any other component. The LangfuseConnector will automatically trace the operations and data flow within the pipeline. Then add the other components, like the text embedder, retriever, prompt builder and the model, and connect them together in the order they will be used in the pipeline.
+
+```python
+from haystack import Pipeline
+from haystack_integrations.components.connectors.langfuse import LangfuseConnector
+
+# Example pipeline
+example_pipeline = Pipeline()
+
+# Add LangfuseConnector to the pipeline
+example_pipeline.add_component("tracer", LangfuseConnector("Example Pipeline"))
+
+# Add other components and use the pipeline
+# ...
+```
+
 </Steps>
 
 <Callout type="info" emoji="✨">
@@ -99,3 +117,7 @@ import { FileCode } from "lucide-react";
 ## Acknowledgement
 
 We're thrilled to collaborate with the Haystack team to give the best possible experience to devs when building complex RAG applications. Thanks to them for developing this intgeration.
+
+```
+
+```

pages/guides/cookbook/integration_haystack.md

@@ -69,6 +69,8 @@ The following code snippet (based off of the Haystack [documentation](https://do
 
 First we build the pipeline. Add `LangfuseConnector` to the pipeline as a tracer. There's no need to connect it to any other component. The `LangfuseConnector` will automatically trace the operations and data flow within the pipeline. Then add the other components, like the text embedder, retriever, prompt builder and the model, and connect them together in the order they will be used in the pipeline.
 
+**Note**: Make sure to set the `HAYSTACK_CONTENT_TRACING_ENABLED` environment variable before importing `LangfuseConnector`.
+
 
 ```python
 from datasets import load_dataset
@@ -178,6 +180,8 @@ Learn more about tracing in the [docs](https://langfuse.com/docs/tracing).
 
 Here is another example connecting a RAG pipeline to a chat generator. Using a component like Haystack's `DynamicChatPromptBuilder` is a great way to add a chat component to your application, which can add a level of personalization and interactivity to your program.
 
+**Note**: Make sure to set the `HAYSTACK_CONTENT_TRACING_ENABLED` environment variable before importing `LangfuseConnector`.
+
 
 ```python
 from haystack import Pipeline