docs: sync for 1.3 (#1833)

* docs: update default value of variable in run_relevance_eval (GITBOOK-368)

* docs: No subject (GITBOOK-369)

* docs: Environment documentation (GITBOOK-370)

* docs: Explanations (GITBOOK-371)

---------

Co-authored-by: Xander Song <xsong@arize.com>
Co-authored-by: Jason Lopatecki <jason@arize.com>

docs/SUMMARY.md

@@ -2,6 +2,7 @@
 
 * [Phoenix: AI Observability & Evaluation](README.md)
 * [Example Notebooks](notebooks.md)
+* [Environments](environments.md)
 
 ## 🔑 Quickstart
 
@@ -28,6 +29,7 @@
   * [Code Generation Eval](llm-evals/running-pre-tested-evals/code-generation-eval.md)
   * [Summarization Eval](llm-evals/running-pre-tested-evals/summarization-eval.md)
   * [Reference Link Evals](llm-evals/running-pre-tested-evals/reference-link-evals.md)
+* [Evals With Explanations](llm-evals/evals-with-explanations.md)
 * [Building Your Own Evals](llm-evals/building-your-own-evals.md)
 * [Benchmarking Retrieval (RAG)](llm-evals/benchmarking-retrieval-rag.md)
 

docs/api/evals.md

@@ -113,7 +113,7 @@ def run_relevance_eval(
     template: Union[ClassificationPromptTemplate, PromptTemplate, str] = RAG_RELEVANCY_PROMPT_TEMPLATE,
     rails: List[str] = list(RAG_RELEVANCY_PROMPT_RAILS_MAP.values()),
     system_instruction: Optional[str] = None,
-    query_column_name: str = "query",
+    query_column_name: str = "input",
     document_column_name: str = "reference",
 ) -> List[List[str]]:
 ```

docs/environments.md

@@ -0,0 +1,73 @@
+---
+description: >-
+  The Phoenix app can be run in various notebook environments such as colab and
+  SageMaker as well as be served via the terminal or a docker container
+---
+
+# Environments
+
+Phoenix app is first and foremost an application that can be run just in in your notebook! This makes it an extremely flexible app since it can be accessed directly as you iterate on your AI-powered app!\
+
+
+### Notebooks
+
+Currently phoenix supports local, colab, and SageMaker notebooks.
+
+{% hint style="warning" %}
+Note, phoenix only supports running the phoenix server via the notebook for SageMaker notebooks. It cannot setup proxy requests for SageMaker studio since there is no support of jupyter-server-proxy
+{% endhint %}
+
+#### SageMaker
+
+With SageMaker notebooks, phoenix leverages the [jupyter-server-proy](https://github.com/jupyterhub/jupyter-server-proxy) to host the server under `proxy/6006.`Note, that phoenix will automatically try to detect that you are running in SageMaker but you can declare the notebook runtime via a parameter to `launch_app` or an environment variable
+
+{% tabs %}
+{% tab title="Environment Variable" %}
+```python
+import os
+
+os.envoron["PHOENIX_NOTEBOOK_ENV"] = "sagemaker"
+```
+{% endtab %}
+
+{% tab title="Launch Parameter" %}
+```python
+import phoenix as px
+
+px.launch_app(notebook_environment="sagemaker")
+```
+{% endtab %}
+{% endtabs %}
+
+### Container
+
+{% hint style="info" %}
+Container images are still actively being worked on. If you are interested in hosted phoenix, please get in touch!
+{% endhint %}
+
+Phoenix server images are now available via [Docker Hub](https://hub.docker.com/r/arizephoenix/phoenix). The hosted phoenix server runs as a trace collector and can be used if you want observability for LLM traces via docker compose or simply want a long-running phoenix instance.
+
+If you deploy the phoenix server (collector) to a remote machine, you will have to make sure to configure the remote endpoint as the collector endpoint. (This feature is only available after phoenix **1.3.x**)
+
+{% tabs %}
+{% tab title="Environment Variable" %}
+```python
+import os
+
+os.envoron["PHOENIX_COLLECTOR_ENDPOINT"] = "https://my-phoenix.io"
+```
+{% endtab %}
+
+{% tab title="Second Tab" %}
+```python
+from phoenix.trace.tracer import Tracer
+from phoenix.trace.exporter import HttpExporter
+from phoenix.trace.openai.instrumentor import OpenAIInstrumentor
+
+
+tracer = Tracer(exporter=HttpExporter(endpoint="https://my-phoenix.io"))
+OpenAIInstrumentor(tracer).instrument()
+```
+{% endtab %}
+{% endtabs %}
+

docs/llm-evals/evals-with-explanations.md

@@ -0,0 +1,42 @@
+# Evals With Explanations
+
+{% embed url="https://colab.research.google.com/github/Arize-ai/phoenix/blob/main/tutorials/evals/evaluate_relevance_classifications.ipynb?#scrollTo=zUtDrplhZZJu&uniqifier=1" %}
+See "Classifications with Explanations Section"
+{% endembed %}
+
+It can be hard to understand in many cases why an LLM responds in a specific way. The explanation feature of Phoneix allows you to get a Eval output and an explanation from the LLM at the same time. We have found this incredibly useful for debugging LLM Evals.
+
+<pre class="language-python"><code class="lang-python">from phoenix.experimental.evals import (
+    RAG_RELEVANCY_PROMPT_RAILS_MAP,
+    RAG_RELEVANCY_PROMPT_TEMPLATE,
+    OpenAIModel,
+    download_benchmark_dataset,
+    llm_classify,
+)
+
+model = OpenAIModel(
+    model_name="gpt-4",
+    temperature=0.0,
+)
+
+#The rails is used to hold the output to specific values based on the template
+#It will remove text such as ",,," or "..."
+#Will ensure the binary value expected from the template is returned
+rails = list(RAG_RELEVANCY_PROMPT_RAILS_MAP.values())
+relevance_classifications = llm_classify(
+    dataframe=df,
+    template=RAG_RELEVANCY_PROMPT_TEMPLATE,
+    model=model,
+    rails=rails,
+    <a data-footnote-ref href="#user-content-fn-1">provide_explanation=True</a>
+)
+#relevance_classifications is a Dataframe with columns 'label' and 'explanation'
+</code></pre>
+
+The flag above can be set with any of the templates or your own custom templates. The example below is from a relevance Evaluation.&#x20;
+
+<figure><img src="../.gitbook/assets/explanation.png" alt=""><figcaption></figcaption></figure>
+
+
+
+[^1]: set to get an explanation out