# Documentation
## Docs
- [What is Evidently?](https://docs.evidentlyai.com/introduction.md): Welcome to the Evidently documentation.
- [LLM Evaluation](https://docs.evidentlyai.com/quickstart_llm.md): Evaluate text outputs in under 5 minutes
- [Data and ML checks](https://docs.evidentlyai.com/quickstart_ml.md): Run a simple evaluation for tabular data
- [Tracing](https://docs.evidentlyai.com/quickstart_tracing.md): How to capture LLM inputs and outputs and evaluate them.
- [Installation](https://docs.evidentlyai.com/docs/setup/installation.md): How to install the open-source Python library.
- [Self-hosting](https://docs.evidentlyai.com/docs/setup/self-hosting.md): How to self-host the open-source Evidently UI service.
- [Introduction](https://docs.evidentlyai.com/docs/library/overview.md): Core concepts and components of the Evidently Python library.
- [Overview](https://docs.evidentlyai.com/docs/library/evaluations_overview.md): Core eval workflow using the Evidently library at a glance.
- [Data definition](https://docs.evidentlyai.com/docs/library/data_definition.md): How to map the input data.
- [Descriptors](https://docs.evidentlyai.com/docs/library/descriptors.md): How to run evaluations for text data.
- [Report](https://docs.evidentlyai.com/docs/library/report.md): How to generate Report.
- [Tests](https://docs.evidentlyai.com/docs/library/tests.md): How to run conditional checks.
- [Metric generators](https://docs.evidentlyai.com/docs/library/metric_generator.md): How to generate multiple metrics at once.
- [Output formats](https://docs.evidentlyai.com/docs/library/output_formats.md): How to export the evaluation results.
- [Add tags and metadata](https://docs.evidentlyai.com/docs/library/tags_metadata.md): How to add metadata to evaluations.
- [Prompt optimization](https://docs.evidentlyai.com/docs/library/prompt_optimization.md): [NEW] Automated prompt optimization.
- [Synthetic data generation](https://docs.evidentlyai.com/docs/library/synthetic_data_api.md): [NEW] Code-first synthetic data generation.
- [Introduction](https://docs.evidentlyai.com/docs/platform/overview.md): Evidently Platform at a glance.
- [Overview](https://docs.evidentlyai.com/docs/platform/projects_overview.md): Introduction to Projects.
- [Manage Projects](https://docs.evidentlyai.com/docs/platform/projects_manage.md): Set up an evaluation or monitoring Project.
- [Overview](https://docs.evidentlyai.com/docs/platform/datasets_overview.md): Introduction to Datasets.
- [Work with datasets](https://docs.evidentlyai.com/docs/platform/datasets_workflow.md): How to create, upload and manage Datasets.
- [Synthetic data](https://docs.evidentlyai.com/docs/platform/datasets_generate.md): Generating synthetic data.
- [Overview](https://docs.evidentlyai.com/docs/platform/tracing_overview.md): Introduction to Tracing.
- [Set up tracing](https://docs.evidentlyai.com/docs/platform/tracing_setup.md): How to collect data from a live LLM app.
- [Overview](https://docs.evidentlyai.com/docs/platform/evals_overview.md): Running evals on the platform.
- [Run evals via API](https://docs.evidentlyai.com/docs/platform/evals_api.md): How to run evals and log them on the platform
- [No code evals](https://docs.evidentlyai.com/docs/platform/evals_no_code.md): How to evaluate your data in a no-code interface.
- [Explore view](https://docs.evidentlyai.com/docs/platform/evals_explore.md): Reviewing the evaluation results on the Platform.
- [Overview](https://docs.evidentlyai.com/docs/platform/dashboard_overview.md): Introduction to Dashboard.
- [Add dashboard panels (API)](https://docs.evidentlyai.com/docs/platform/dashboard_add_panels.md): How to design your Dashboard with custom Panels.
- [Add dashboard panels (UI)](https://docs.evidentlyai.com/docs/platform/dashboard_add_panels_ui.md): How to design your Dashboard with custom Panels.
- [Overview](https://docs.evidentlyai.com/docs/platform/monitoring_overview.md): How production AI quality monitoring works.
- [Batch monitoring](https://docs.evidentlyai.com/docs/platform/monitoring_local_batch.md): How to run batch evaluation jobs.
- [Scheduled evals](https://docs.evidentlyai.com/docs/platform/monitoring_scheduled_evals.md): Running managed evaluations over traces on a platform.
- [Alerts](https://docs.evidentlyai.com/docs/platform/alerts.md): How to set up alerts.
- [Evaluations](https://docs.evidentlyai.com/metrics/introduction.md): Available metrics, tests and how to customize them.
- [All Metrics](https://docs.evidentlyai.com/metrics/all_metrics.md): Reference page for all dataset-level evals.
- [All Descriptors](https://docs.evidentlyai.com/metrics/all_descriptors.md): Reference page for all row-level text and LLM evals.
- [Overview](https://docs.evidentlyai.com/metrics/all_presets.md): All available Presets.
- [Text Evals](https://docs.evidentlyai.com/metrics/preset_text_evals.md): Overview of the Text Evals Preset.
- [Data Drift](https://docs.evidentlyai.com/metrics/preset_data_drift.md): Overview of the Data Drift Preset.
- [Data Summary](https://docs.evidentlyai.com/metrics/preset_data_summary.md): Overview of the Data Summary Preset.
- [Classification](https://docs.evidentlyai.com/metrics/preset_classification.md): Overview of the Classification Quality Preset
- [Regression](https://docs.evidentlyai.com/metrics/preset_regression.md): Overview of the Regression Quality Preset
- [Custom Text Descriptor](https://docs.evidentlyai.com/metrics/customize_descriptor.md): How to add a custom row-level text evaluator.
- [Configure LLM Judges](https://docs.evidentlyai.com/metrics/customize_llm_judge.md): How to run prompt-based evaluators for custom criteria.
- [Use HuggingFace models](https://docs.evidentlyai.com/metrics/customize_hf_descriptor.md): How to use models from HuggingFace as evaluators.
- [Customize Data Drift](https://docs.evidentlyai.com/metrics/customize_data_drift.md): How to change data drift detection methods and conditions.
- [Custom Metric](https://docs.evidentlyai.com/metrics/customize_metric.md): How to create a custom dataset or column-level Metric.
- [Data drift](https://docs.evidentlyai.com/metrics/explainer_drift.md): How data drift detection works
- [Ranking and RecSys metrics](https://docs.evidentlyai.com/metrics/explainer_recsys.md): Open-source metrics for ranking and recommendations.
- [Synthetic data](https://docs.evidentlyai.com/synthetic-data/introduction.md): Generating test cases and datasets.
- [Why synthetic data?](https://docs.evidentlyai.com/synthetic-data/why_synthetic.md): When do you need synthetic data in LLM evaluations.
- [RAG evaluation dataset](https://docs.evidentlyai.com/synthetic-data/rag_data.md): Synthetic data for RAG.
- [Adversarial testing](https://docs.evidentlyai.com/synthetic-data/adversarial_data.md): Synthetic edge cases and tricky inputs
- [Create synthetic inputs](https://docs.evidentlyai.com/synthetic-data/input_data.md): Generate input test cases.
- [Tutorials and guides](https://docs.evidentlyai.com/examples/introduction.md): End-to-end code examples.
- [RAG evals](https://docs.evidentlyai.com/examples/LLM_rag_evals.md): Metrics to evaluate a RAG system.
- [LLM as a judge](https://docs.evidentlyai.com/examples/LLM_judge.md): How to create and evaluate an LLM judge.
- [LLM-as-a-jury](https://docs.evidentlyai.com/examples/LLM_jury.md): Evaluate the LLM outputs with multiple LLMs.
- [Evidently and GitHub actions](https://docs.evidentlyai.com/examples/GitHub_actions.md): Testing LLM outputs as part of the CI/CD flow.
- [Frequently Asked Questions](https://docs.evidentlyai.com/faq/introduction.md): Popular questions.
- [Why Evidently?](https://docs.evidentlyai.com/faq/why_evidently.md): Why choose Evidently.
- [Open-source vs. Cloud](https://docs.evidentlyai.com/faq/oss_vs_cloud.md): Deployment options and feature overview.
- [Migration Guide](https://docs.evidentlyai.com/faq/migration.md): How to migrate to the new Evidently version?
- [Evidently Cloud v2](https://docs.evidentlyai.com/faq/cloud_v2.md): A new version of Evidently Cloud available starting April 10, 2025.
- [Telemetry](https://docs.evidentlyai.com/faq/telemetry.md): What data is collected when you use Evidently open-source.
- [Contact us](https://docs.evidentlyai.com/faq/contact.md): How to connect with Evidently team.
- [Product updates](https://docs.evidentlyai.com/changelog/changelog.md): Latest releases.
## OpenAPI Specs
- [openapi](https://docs.evidentlyai.com/api-reference/openapi.json)
## Optional
- [GitHub](https://github.com/evidentlyai/evidently)
- [Community](https://discord.gg/xZjKRaNp8b)
- [Old docs](https://docs-old.evidentlyai.com)
This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.
Measured from the saved file
Linked document
UTF-8 text size
8.6 KB8759 bytes
Token count
2165o200k_base encoding
Markdown links
7575 distinct URLs
Fenced code blocks
087 lines in the file
Size measures the captured UTF-8 text, not compressed transfer size. Tokens are counted with a named tokenizer; other models can count differently. Neither measure establishes context compatibility or answer quality.
Project H1
Documentation
Context architecture
How the content is divided
3 H2 sections organize 75 parsed Markdown links. 70 links point to .md or .markdown paths; 4 link occurrences use another hostname. Linked destinations have not been recursively validated.
H2 section
Links
UTF-8 bytes
Tokens
DocsLine 3
70
8375
2063
OpenAPI SpecsLine 76
1
71
20
OptionalLine 80 · Optional
4
259
71
Link counts exclude parsed fenced and inline code and resolve relative destinations against the final endpoint. Section sizes cover the text below each H2 until the next H2.
Embedded material
Code, installation and API examples
Fenced blocks
0 closed
Declared languages
No fenced blocks detected
Package-install commands
0 detected in fenced or inline code
Authentication examples
0 fenced lines match API-key, Authorization, Bearer, OAuth or access-token patterns
HTTP request examples
0 fenced lines match request-method patterns
Authentication links
0 links have authentication-related labels
Embedded example text and links to further documentation are counted separately. A code block does not establish that a sample runs or that an authentication flow succeeds.
Publisher prioritization
The Optional section
1 H2 section named “Optional” contain 4 parsed links. 71 links sit outside those sections. That puts 5.3% of the file’s parsed links under Optional.
The community proposal uses Optional by convention for secondary links that can be skipped for a shorter context. This label does not establish that everything outside it is critical, or that the material inside it is deprecated.
Machine-readable routes
MCP references and configuration text
No MCP or Model Context Protocol term was detected in the captured file. 0 links have MCP-related labels or paths. 0 fenced lines match mcpServers, mcp_servers or an mcp add command.
These are text and link observations. No MCP server connection, authentication or tool call was tested.
A verified text response establishes a companion at the checked URL. It does not prove the bundle contains all product documentation, that generation is automated, or that it fits an assistant’s context window.
Change evidence
What can be said about freshness
This capture establishes a baseline. Update frequency cannot be determined from one observation.
Linked release and migration material
2 links have release, changelog, deprecation or migration terms in their labels or paths. These provide places to investigate product changes separately.
File changes can reveal documentation edits or navigation changes. They do not by themselves measure product release velocity, accuracy, agent adoption or AI visibility.
Counts use a deterministic parser, not a spec-compliance grade. Unusual Markdown and indented code can fall outside its recognized patterns. See the llms.txt proposal and tokenizer implementation.