Merge pull request #5756 from Arize-ai/docs

chore: sync docs
Arize-ai · Dec 17, 2024 · 26e83b1 · 26e83b1
2 parents 4569db9 + 71718ec
commit 26e83b1
Show file tree

Hide file tree

Showing 96 changed files with 2,686 additions and 1,166 deletions.
diff --git a/docs/.gitbook/assets/Screenshot 2024-10-29 at 2.26.50 PM.png b/docs/.gitbook/assets/Screenshot 2024-10-29 at 2.26.50 PM.png
diff --git a/docs/.gitbook/assets/Screenshot 2024-10-29 at 2.28.28 PM.png b/docs/.gitbook/assets/Screenshot 2024-10-29 at 2.28.28 PM.png
diff --git a/docs/.gitbook/assets/Screenshot 2024-10-29 at 2.51.24 PM.png b/docs/.gitbook/assets/Screenshot 2024-10-29 at 2.51.24 PM.png
diff --git a/docs/.gitbook/assets/Screenshot 2024-10-29 at 3.52.49 PM.png b/docs/.gitbook/assets/Screenshot 2024-10-29 at 3.52.49 PM.png
diff --git a/docs/.gitbook/assets/Screenshot 2024-12-02 at 9.55.26 AM.png b/docs/.gitbook/assets/Screenshot 2024-12-02 at 9.55.26 AM.png
diff --git a/docs/.gitbook/assets/Screenshot 2024-12-09 at 10.39.41 AM.png b/docs/.gitbook/assets/Screenshot 2024-12-09 at 10.39.41 AM.png
diff --git a/docs/.gitbook/assets/Screenshot 2024-12-09 at 10.42.07 AM (1).png b/docs/.gitbook/assets/Screenshot 2024-12-09 at 10.42.07 AM (1).png
diff --git a/docs/.gitbook/assets/Screenshot 2024-12-09 at 10.42.07 AM.png b/docs/.gitbook/assets/Screenshot 2024-12-09 at 10.42.07 AM.png
diff --git a/docs/.gitbook/assets/Screenshot 2024-12-09 at 10.49.57 AM.png b/docs/.gitbook/assets/Screenshot 2024-12-09 at 10.49.57 AM.png
diff --git a/docs/.gitbook/assets/Screenshot 2024-12-09 at 10.51.07 AM.png b/docs/.gitbook/assets/Screenshot 2024-12-09 at 10.51.07 AM.png
diff --git a/docs/.gitbook/assets/Screenshot 2024-12-09 at 11.29.18 AM.png b/docs/.gitbook/assets/Screenshot 2024-12-09 at 11.29.18 AM.png
diff --git a/docs/.gitbook/assets/Screenshot 2024-12-09 at 11.34.54 AM.png b/docs/.gitbook/assets/Screenshot 2024-12-09 at 11.34.54 AM.png
diff --git a/docs/.gitbook/assets/Screenshot 2024-12-09 at 11.37.34 AM.png b/docs/.gitbook/assets/Screenshot 2024-12-09 at 11.37.34 AM.png
diff --git a/docs/.gitbook/assets/image (32).png b/docs/.gitbook/assets/image (32).png
diff --git a/docs/.gitbook/assets/news-article-summaries-2024-11-04 11_08_10.csv b/docs/.gitbook/assets/news-article-summaries-2024-11-04 11_08_10.csv
diff --git a/docs/README.md b/docs/README.md
@@ -18,7 +18,7 @@ In your Jupyter or Colab environment, run the following command to install.
 pip install arize-phoenix
 ```
 
-For full details on how to run phoenix in various environments such as Databricks, consult our [environments guide.](setup/environments.md)
+For full details on how to run phoenix in various environments such as Databricks, consult our [environments guide.](deployment/environments.md)
 {% endtab %}
 
 {% tab title="Using conda" %}
@@ -34,18 +34,32 @@ Phoenix can also run via a container. The image can be found at:
 Images for phoenix are published to dockerhub
 {% endembed %}
 
-Checkout the [environments section](setup/environments.md) and [deployment guide](deployment/deploying-phoenix.md) for details.
+Checkout the [environments section](deployment/environments.md) and [deployment guide](deployment/deploying-phoenix.md) for details.
 {% endtab %}
 {% endtabs %}
 
 Phoenix works with OpenTelemetry and [OpenInference](https://github.com/Arize-ai/openinference) instrumentation. If you are looking to deploy phoenix as a service rather than a library, see [deployment](deployment/ "mention")
 
+
+
 ## Quickstarts
 
 Running Phoenix for the first time? Select a quickstart below.
 
 <table data-card-size="large" data-view="cards"><thead><tr><th align="center"></th><th data-hidden data-card-target data-type="content-ref"></th><th data-hidden data-card-cover data-type="files"></th></tr></thead><tbody><tr><td align="center"><strong>Tracing</strong></td><td><a href="tracing/llm-traces-1.md">llm-traces-1.md</a></td><td><a href=".gitbook/assets/Screenshot 2023-09-27 at 1.51.45 PM.png">Screenshot 2023-09-27 at 1.51.45 PM.png</a></td></tr><tr><td align="center"><strong>Evaluation</strong></td><td><a href="evaluation/evals.md">evals.md</a></td><td><a href=".gitbook/assets/evals.png">evals.png</a></td></tr><tr><td align="center"><strong>Inferences</strong></td><td><a href="inferences/phoenix-inferences.md">phoenix-inferences.md</a></td><td><a href=".gitbook/assets/Screenshot 2023-09-27 at 1.53.06 PM.png">Screenshot 2023-09-27 at 1.53.06 PM.png</a></td></tr><tr><td align="center"><strong>Datasets and Experiments</strong></td><td><a href="datasets-and-experiments/quickstart-datasets.md">quickstart-datasets.md</a></td><td><a href=".gitbook/assets/experiments_preview.png">experiments_preview.png</a></td></tr></tbody></table>
 
+## Available Packages
+
+The main Phoenix package is arize-phoenix. We offer several helper packages below for specific use cases.
+
+| Package                            | What It's For                                                                                                                                                                                                                                                                                                                        | Pypi                                                                                                                   |
+| ---------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ---------------------------------------------------------------------------------------------------------------------- |
+| arize-phoenix                      | <p>Running and connecting to the Phoenix client. Used:<br>- Self-hosting Phoenix<br>- Connecting to a Phoenix client (either Phoenix Developer Edition or self-hosted) to query spans, run evaluations, generate datasets, etc.<br><br><em>*arize-phoenix automatically includes arize-phoenix-otel and arize-phoenix evals</em></p> | <img src="https://img.shields.io/pypi/v/arize-phoenix" alt="PyPI - Version" data-size="original">                      |
+| arize-phoenix-otel                 | Sending OpenTelemetry traces to a Phoenix instance                                                                                                                                                                                                                                                                                   | <img src="https://img.shields.io/pypi/v/arize-phoenix-otel" alt="PyPI - Version" data-size="original">                 |
+| arize-phoenix-evals                | Running evaluations in your  environment                                                                                                                                                                                                                                                                                             | <img src="https://img.shields.io/pypi/v/arize-phoenix-evals" alt="PyPI - Version" data-size="original">                |
+| openinference-semantic-conventions | Our semantic layer to add LLM telemetry to OpenTelemetry                                                                                                                                                                                                                                                                             | <img src="https://img.shields.io/pypi/v/openinference-semantic-conventions" alt="PyPI - Version" data-size="original"> |
+| openinference-instrumentation-xxxx | Automatically instrumenting popular packages.                                                                                                                                                                                                                                                                                        | See [integrations-tracing](tracing/integrations-tracing/ "mention")                                                    |
+
 ## Next Steps
 
 ### [Try our Tutorials](notebooks.md)

diff --git a/docs/SUMMARY.md b/docs/SUMMARY.md
@@ -4,26 +4,29 @@
 * [Quickstart](quickstart.md)
 * [User Guide](user-guide.md)
 * [Examples](notebooks.md)
-* [Setup](setup/README.md)
-  * [Environments](setup/environments.md)
-  * [Configuration](setup/configuration.md)
-  * [Authentication](setup/authentication.md)
-* [Deployment](deployment/README.md)
+* [Self-hosting](deployment/README.md)
   * [Quickstart: Deployment](deployment/deploying-phoenix.md)
-  * [Hosted Phoenix](deployment/hosted-phoenix.md)
+  * [Environments](deployment/environments.md)
   * [Docker](deployment/docker.md)
-  * [Persistence](deployment/persistence.md)
   * [Kubernetes](deployment/kubernetes.md)
-  * [FAQs: Deployment](deployment/faqs-deployment.md)
+  * [Authentication](deployment/authentication.md)
+  * [Persistence](deployment/persistence.md)
+  * [Configuration](deployment/configuration.md)
 
 ## 🔭 Tracing
 
-* [Overview: Tracing](tracing/llm-traces.md)
+* [Overview: Tracing](tracing/llm-traces/README.md)
+  * [Traces](tracing/llm-traces/what-are-traces.md)
+  * [How Tracing Works](tracing/llm-traces/how-does-tracing-work.md)
+  * [Annotating Traces](tracing/llm-traces/how-to-annotate-traces.md)
+  * [FAQs: Tracing](tracing/llm-traces/faqs-tracing.md)
 * [Quickstart: Tracing](tracing/llm-traces-1.md)
 * [Integrations: Tracing](tracing/integrations-tracing/README.md)
   * [OpenAI](tracing/integrations-tracing/openai.md)
   * [LlamaIndex](tracing/integrations-tracing/llamaindex.md)
+  * [LlamaIndex Workflows](tracing/integrations-tracing/llamaindex-1.md)
   * [LangChain](tracing/integrations-tracing/langchain.md)
+  * [LangGraph](tracing/integrations-tracing/langgraph.md)
   * [Haystack](tracing/integrations-tracing/haystack.md)
   * [Anthropic](tracing/integrations-tracing/anthropic.md)
   * [Groq](tracing/integrations-tracing/groq.md)
@@ -40,37 +43,32 @@
   * [OpenAI Node SDK](tracing/integrations-tracing/openai-node-sdk.md)
   * [LangChain.js](tracing/integrations-tracing/langchain.js.md)
   * [Vercel AI SDK](tracing/integrations-tracing/vercel-ai-sdk.md)
-* [Concepts: Tracing](tracing/concepts-tracing/README.md)
-  * [Traces](tracing/concepts-tracing/what-are-traces.md)
-  * [How Tracing Works](tracing/concepts-tracing/how-does-tracing-work.md)
-  * [Annotating Traces](tracing/concepts-tracing/how-to-annotate-traces.md)
 * [How-to: Tracing](tracing/how-to-tracing/README.md)
   * [Setup Tracing](tracing/how-to-tracing/setup-tracing/README.md)
     * [Setup Tracing: Python](tracing/how-to-tracing/setup-tracing/setup-tracing-python/README.md)
       * [Using OTEL Python Directly](tracing/how-to-tracing/setup-tracing/setup-tracing-python/using-otel-python-directly.md)
     * [Setup Tracing: TS](tracing/how-to-tracing/setup-tracing/setup-tracing-ts.md)
-  * [Tracing Core Concepts](tracing/how-to-tracing/tracing-core-concepts.md)
-  * [Customize Traces](tracing/how-to-tracing/customize-traces.md)
-  * [Customize Spans](tracing/how-to-tracing/customize-spans/README.md)
+  * [Customize Tracing](tracing/how-to-tracing/customize-spans/README.md)
     * [Instrumenting Prompt Templates and Prompt Variables](tracing/how-to-tracing/customize-spans/instrumenting-prompt-templates-and-prompt-variables.md)
+    * [Masking Span Attributes](tracing/how-to-tracing/customize-spans/masking-span-attributes.md)
+    * [Filtering Spans](tracing/how-to-tracing/customize-spans/filtering-spans.md)
   * [Auto Instrumentation](tracing/how-to-tracing/instrumentation/README.md)
     * [Auto Instrument: Python](tracing/how-to-tracing/instrumentation/auto-instrument-python.md)
     * [Auto Instrument: TS](tracing/how-to-tracing/instrumentation/auto-instrument-ts.md)
   * [Manual Instrumentation](tracing/how-to-tracing/manual-instrumentation/README.md)
     * [Instrument: Python](tracing/how-to-tracing/manual-instrumentation/custom-spans.md)
     * [Instrument: TS](tracing/how-to-tracing/manual-instrumentation/javascript.md)
   * [Multimodal Tracing](tracing/how-to-tracing/multimodal-tracing.md)
-  * [Querying Spans](tracing/how-to-tracing/extract-data-from-spans.md)
   * [Log Evaluation Results](tracing/how-to-tracing/llm-evaluations.md)
+  * [Capture Feedback](tracing/how-to-tracing/capture-feedback.md)
+  * [Querying Spans](tracing/how-to-tracing/extract-data-from-spans.md)
   * [Importing Existing Traces](tracing/how-to-tracing/importing-existing-traces.md)
   * [Save and Load Traces](tracing/how-to-tracing/save-and-load-traces.md)
-  * [Capture Feedback](tracing/how-to-tracing/capture-feedback.md)
+  * [Setup Sessions](tracing/how-to-tracing/setup-sessions.md)
   * [Trace a Deployed App](tracing/how-to-tracing/trace-a-deployed-app.md)
-  * [Configure Tracing](tracing/how-to-tracing/configure-tracing.md)
 * [Use Cases: Tracing](tracing/use-cases-tracing/README.md)
   * [Evaluate RAG](tracing/use-cases-tracing/rag-evaluation.md)
   * [Structured Data Extraction](tracing/use-cases-tracing/structured-extraction.md)
-* [FAQs: Tracing](tracing/faqs-tracing.md)
 
 ## 🧠 Evaluation
 
@@ -100,6 +98,12 @@
   * [Evaluating Phoenix Traces](evaluation/how-to-evals/evaluating-phoenix-traces.md)
 * [Evaluation Models](evaluation/evaluation-models.md)
 
+## 📃 Prompt Engineering
+
+* [Overview: Prompts](prompt-engineering/overview-prompts.md)
+* [Quickstart: Prompts](prompt-engineering/quickstart-prompts.md)
+* [Concepts: Prompts](prompt-engineering/concepts-prompts.md)
+
 ## 🗄️ Datasets & Experiments
 
 * [Overview: Datasets](datasets-and-experiments/overview-datasets.md)

diff --git a/docs/api/client.md b/docs/api/client.md
@@ -34,13 +34,13 @@ A client for making HTTP requests to the Phoenix server for extracting/downloadi
 
 ## _**get\_spans\_dataframe**_
 
-\-> Optional\[pandas.DataFrame]
+-> Optional\[pandas.DataFrame]
 
 ```python
 px.Client(endpoint="http://127.0.0.1:6006").get_spans_dataframe()
 ```
 
-Returns spans in a pandas.dataframe. Filters can be applied. See [LLM Traces](../tracing/llm-traces.md) for more about tracing your LLM application.\
+Returns spans in a pandas.dataframe. Filters can be applied. See [LLM Traces](../tracing/llm-traces/) for more about tracing your LLM application.\
 \
 **Parameters**
 
@@ -52,7 +52,7 @@ Returns spans in a pandas.dataframe. Filters can be applied. See [LLM Traces](..
 
 ## _**query\_spans**_
 
-\-> Optional\[Union\[pandas.DataFrame, List\[pandas.DataFrame]]\
+-> Optional\[Union\[pandas.DataFrame, List\[pandas.DataFrame]]\
 \
 Extract values from spans in a pandas.dataframe. See [extract-data-from-spans.md](../tracing/how-to-tracing/extract-data-from-spans.md "mention")for more details.\
 \
@@ -66,7 +66,7 @@ Extract values from spans in a pandas.dataframe. See [extract-data-from-spans.md
 
 ## _**get\_evaluations**_
 
-\-> List\[Evaluations]
+-> List\[Evaluations]
 
 ```python
 px.Client(endpoint="http://127.0.0.1:6006").get_evaluations()
@@ -80,7 +80,7 @@ Extract evaluations if any. Otherwise returns empty List. See [llm-evaluations.m
 
 ## _**get\_trace\_dataset**_
 
-\-> Optional\[TraceDataset]
+-> Optional\[TraceDataset]
 
 ```python
 px.Client(endpoint="http://127.0.0.1:6006").get_trace_dataset()
@@ -94,7 +94,7 @@ Returns the trace dataset containing spans and evaluations.\
 
 ## _**log\_evaluations**_
 
-\-> None\
+-> None\
 \
 Send evaluations to Phoenix. See [#logging-multiple-evaluation-dataframes](../tracing/how-to-tracing/llm-evaluations.md#logging-multiple-evaluation-dataframes "mention")for usage.\
 \
@@ -105,7 +105,7 @@ Send evaluations to Phoenix. See [#logging-multiple-evaluation-dataframes](../tr
 
 ## _**get\_dataset\_versions**_
 
-\-> pandas.DataFrame\
+-> pandas.DataFrame\
 \
 Get dataset versions as pandas DataFrame.\
 \
@@ -116,7 +116,7 @@ Get dataset versions as pandas DataFrame.\
 
 ## _**upload\_dataset**_
 
-\-> Dataset\
+-> Dataset\
 \
 Upload a dataset to Phoenix. See [Usage](client.md#usage) below for examples. It can upload a pandas dataframe, a CSV text file, or a series of dictionary objects, and only one of these options should be specified.\
 \
@@ -133,9 +133,9 @@ Upload a dataset to Phoenix. See [Usage](client.md#usage) below for examples. It
 * **outputs** (Iterable\[Mapping\[str, Any]]): When uploading a series of dictionary objects, this specifies the list of dictionaries object for inputs.
 * **metadata** (Iterable\[Mapping\[str, Any]]): When uploading a series of dictionary objects, this specifies the list of dictionaries object for inputs.
 
-## _**append\_dataset**_
+## _**append\_to\_dataset**_
 
-\-> Dataset\
+-> Dataset\
 \
 Method signature is identical to that of the _upload\_dataset_ method. If dataset doesn't already exist on the Phoenix server, it will be created.
 

diff --git a/docs/api/inference-and-schema.md b/docs/api/inference-and-schema.md
@@ -136,18 +136,18 @@ class TraceDataset(
 )
 ```
 
-Wraps a dataframe that is a flattened representation of spans and traces. Note that it does not require a Schema. See [LLM Traces](../tracing/llm-traces.md) on how to monitor your LLM application using traces. Because Phoenix can also receive traces from your LLM application directly in real time, `TraceDataset` is mostly used for loading trace data that has been previously saved to file.
+Wraps a dataframe that is a flattened representation of spans and traces. Note that it does not require a Schema. See [LLM Traces](../tracing/llm-traces/) on how to monitor your LLM application using traces. Because Phoenix can also receive traces from your LLM application directly in real time, `TraceDataset` is mostly used for loading trace data that has been previously saved to file.
 
 **\[**[**source**](https://github.com/Arize-ai/phoenix/blob/main/src/phoenix/trace/trace\_dataset.py)**]**
 
 ### **Parameters**
 
-* **dataframe** (pandas.dataframe): a dataframe each row of which is a flattened representation of a span. See [LLM Traces](../tracing/llm-traces.md) for more on traces and spans.
+* **dataframe** (pandas.dataframe): a dataframe each row of which is a flattened representation of a span. See [LLM Traces](../tracing/llm-traces/) for more on traces and spans.
 * **name** (str): The name used to identify the dataset in the application. If not provided, a random name will be generated.
 
 ### Attributes
 
-* **dataframe** (pandas.dataframe): a dataframe each row of which is a flattened representation of a span. See [LLM Traces](../tracing/llm-traces.md) for more on traces and spans.
+* **dataframe** (pandas.dataframe): a dataframe each row of which is a flattened representation of a span. See [LLM Traces](../tracing/llm-traces/) for more on traces and spans.
 * **name** (Optional\[str]): The name used to identify the dataset in the application.
 
 ### Usage