---
description: Explore the capabilities of Phoenix with notebooks
---
# Examples
## Tutorials
## Application Examples
Example full-stack applications instrumented using OpenInference and observed via phoenix server instances.
## Agent Demos
## LLM Traces
Trace through the execution of your LLM application to understand its internal structure and to troubleshoot issues with retrieval, tool execution, LLM calls, and more.
| Title | Topics | Links |
| -------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| Tracing an OpenAI App | | [](https://colab.research.google.com/github/Arize-ai/phoenix/blob/main/tutorials/hosted_phoenix/hosted_phoenix_openai_tutorial.ipynb) |
| Tracing a LlamaIndex App | | [](https://colab.research.google.com/github/Arize-ai/phoenix/blob/main/tutorials/hosted_phoenix/hosted_phoenix_llamaindex_tutorial.ipynb) |
| Retrieval Example with Evaluations: Fast UI Viz | | [](https://colab.research.google.com/github/Arize-ai/phoenix/blob/main/tutorials/llm_application_tracing_evaluating_and_analysis.ipynb) |
| Tracing and Evaluating a LlamaIndex + OpenAI RAG Application | - LlamaIndex
- OpenAI
- retrieval-augmented generation
| [](https://colab.research.google.com/github/Arize-ai/phoenix/blob/main/tutorials/tracing/llama_index_tracing_tutorial.ipynb) [](https://github.com/Arize-ai/phoenix/blob/main/tutorials/tracing/llama_index_tracing_tutorial.ipynb) |
| Tracing and Evaluating a LlamaIndex OpenAI Agent | - LlamaIndex
- OpenAI
- agents
- function calling
| [](https://colab.research.google.com/github/Arize-ai/phoenix/blob/main/tutorials/tracing/llama_index_openai_agent_tracing_tutorial.ipynb) [](https://github.com/Arize-ai/phoenix/blob/main/tutorials/tracing/llama_index_openai_agent_tracing_tutorial.ipynb) |
| Tracing and Evaluating a Structured Data Extraction Application with OpenAI Function Calling | - OpenAI
- structured data extraction
- function calling
| [](https://colab.research.google.com/github/Arize-ai/phoenix/blob/main/tutorials/tracing/openai_tracing_tutorial.ipynb) [](https://github.com/Arize-ai/phoenix/blob/main/tutorials/tracing/openai_tracing_tutorial.ipynb) |
| Tracing and Evaluating a LangChain + OpenAI RAG Application | - LangChain
- OpenAI
- retrieval-augmented generation
| [](https://colab.research.google.com/github/Arize-ai/phoenix/blob/main/tutorials/tracing/langchain_tracing_tutorial.ipynb) [](https://github.com/Arize-ai/phoenix/blob/main/tutorials/tracing/langchain_tracing_tutorial.ipynb) |
| Tracing and Evaluating a LangChain Agent | - LangChain
- OpenAI
- agents
- function calling
| [](https://colab.research.google.com/github/Arize-ai/phoenix/blob/main/tutorials/tracing/langchain_agent_tracing_tutorial.ipynb) [](https://github.com/Arize-ai/phoenix/blob/main/tutorials/tracing/langchain_agent_tracing_tutorial.ipynb) |
| Tracing and Evaluation a DSPy Application | - LangChain
- Google PaLM
- retrieval-augmented generation
| [](https://colab.research.google.com/github/Arize-ai/phoenix/blob/main/tutorials/tracing/dspy_tracing_tutorial.ipynb) [](https://github.com/Arize-ai/phoenix/blob/main/tutorials/tracing/dspy_tracing_tutorial.ipynb) |
| Tracing a LlamaIndex app with Sessions | - LlamaIndex
- Tracing
- Sessions
| 

|
| Tracing an OpenAI app with Sessions | | 

|
| Tracing an OpenAI app with Sessions (JS/TS) | | [](https://github.com/Arize-ai/phoenix/blob/main/js/examples/notebooks/tracing_openai_sessions_tutorial.ipynb) |
## Datasets and Experiments
Iteratively improve your LLM task by building datasets, running experiments, and evaluating performance using code and LLM-as-a-judge.
| Title | Topics | Links |
| ----------------------------------------------------- | ----------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Quickstart: Datasets and Experiments | | [](https://colab.research.google.com/github/Arize-ai/phoenix/blob/main/tutorials/experiments/datasets_and_experiments_quickstart.ipynb) |
| Text2SQL | | [](https://colab.research.google.com/github/Arize-ai/phoenix/blob/main/tutorials/experiments/txt2sql.ipynb) |
| Prompt Template Iteration for a Summarization Service | | [](https://colab.research.google.com/github/Arize-ai/phoenix/blob/main/tutorials/experiments/summarization.ipynb) |
| Answer Relevancy and Context Relevancy Evaluation | | [](https://colab.research.google.com/github/Arize-ai/phoenix/blob/main/tutorials/experiments/llama-index/answer_and_context_relevancy.ipynb) |
| Guideline Eval | | [](https://colab.research.google.com/github/Arize-ai/phoenix/blob/main/tutorials/experiments/llama-index/guideline_eval.ipynb) |
| Pairwise Eval | | [](https://colab.research.google.com/github/Arize-ai/phoenix/blob/main/tutorials/experiments/llama-index/pairwise_eval.ipynb) |
| LlamaIndex RAG with Reranker | | [](https://colab.research.google.com/github/Arize-ai/phoenix/blob/main/tutorials/experiments/run_experiments_with_llama_index.ipynb) |
| LangChain Email Extraction | | [](https://colab.research.google.com/github/Arize-ai/phoenix/blob/main/tutorials/experiments/langchain_email_extraction.ipynb) |
## LLM Evals
Leverage the power of large language models to evaluate your generative model or application for hallucinations, toxicity, relevance of retrieved documents, and more.
| Title | Topics | Links |
|---|
| Evaluating Hallucinations | |  |
| Evaluating Toxicity | |  |
| Evaluating Relevance of Retrieved Documents | |  |
| Evaluating Question-Answering | |  |
| Evaluating Summarization | |  |
| Evaluating Code Readability | |  |
## Retrieval-Augmented Generation Analysis
Visualize your generative application's retrieval process to surface failed retrievals and to find topics not addressed by your knowledge base.
| Title | Topics | Links |
| ---------------------------------------------------------- | ---------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Evaluating and Improving Search and Retrieval Applications | - LlamaIndex
- retrieval-augmented generation
| [](https://colab.research.google.com/github/Arize-ai/phoenix/blob/main/tutorials/llama_index_search_and_retrieval_tutorial.ipynb) [](https://github.com/Arize-ai/phoenix/blob/main/tutorials/llama_index_search_and_retrieval_tutorial.ipynb) |
| Evaluating and Improving Search and Retrieval Applications | - LlamaIndex
- Milvus
- retrieval-augmented generation
| [](https://colab.research.google.com/github/Arize-ai/phoenix/blob/main/tutorials/milvus_llamaindex_search_and_retrieval_tutorial.ipynb) [](https://github.com/Arize-ai/phoenix/blob/main/tutorials/milvus_llamaindex_search_and_retrieval_tutorial.ipynb) |
## Embedding Analysis
Explore lower-dimensional representations of your embedding data to identify clusters of high-drift and performance degradation.
| Title | Topics | Links |
| ----------------------------------------------------------------- | ---------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Active Learning for a Drifting Image Classification Model | - image classification
- fine-tuning
| [](https://colab.research.google.com/github/Arize-ai/phoenix/blob/main/tutorials/image_classification_tutorial.ipynb) [](https://github.com/Arize-ai/phoenix/blob/main/tutorials/image_classification_tutorial.ipynb) |
| Root-Cause Analysis for a Drifting Sentiment Classification Model | - NLP
- sentiment classification
| [](https://colab.research.google.com/github/Arize-ai/phoenix/blob/main/tutorials/sentiment_classification_tutorial.ipynb) [](https://github.com/Arize-ai/phoenix/blob/main/tutorials/sentiment_classification_tutorial.ipynb) |
| Troubleshooting an LLM Summarization Task | | [](https://colab.research.google.com/github/Arize-ai/phoenix/blob/main/tutorials/llm_summarization_tutorial.ipynb) [](https://github.com/Arize-ai/phoenix/blob/main/tutorials/llm_summarization_tutorial.ipynb) |
| Collect Chats with GPT | | [](https://colab.research.google.com/github/Arize-ai/phoenix/blob/main/tutorials/llm_generative_gpt_4.ipynb) [](https://github.com/Arize-ai/phoenix/blob/main/tutorials/llm_generative_gpt_4.ipynb) |
| Find Clusters, Export, and Explore with GPT | - LLMs
- exploratory data analysis
| [](https://colab.research.google.com/github/Arize-ai/phoenix/blob/main/tutorials/find_cluster_export_and_explore_with_gpt.ipynb) [](https://github.com/Arize-ai/phoenix/blob/main/tutorials/find_cluster_export_and_explore_with_gpt.ipynb) |
## Structured Data Analysis
Statistically analyze your structured data to perform A/B analysis, temporal drift analysis, and more.
| Title | Topics | Links |
| --------------------------------------- | -------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Detecting Fraud with Tabular Embeddings | - tabular data
- anomaly detection
| [](https://colab.research.google.com/github/Arize-ai/phoenix/blob/main/tutorials/credit_card_fraud_tutorial.ipynb) [](https://github.com/Arize-ai/phoenix/blob/main/tutorials/credit_card_fraud_tutorial.ipynb) |