DSPy: The framework for programming—not prompting—language models
Python
Add 'DSPy in Production' page (#7760)
Yuki Watanabe8e85350e28b2
diff --git a/docs/docs/production/index.md b/docs/docs/production/index.mdnew file mode 100644index 000000000..b952efb1f--- /dev/null+++ b/docs/docs/production/index.md@@ -0,0 +1,53 @@+# Using DSPy in Production++<div class="grid cards" style="text-align: left;" markdown>++- :material-earth:{ .lg .middle } __Real-World Use Cases__++ ---++ DSPy is deployed in production by many enterprises and startups. Explore real-world case studies.++ [:octicons-arrow-right-24: Use Cases](../dspy-usecases.md)++- :material-magnify-expand:{ .lg .middle } __Monitoring & Observability__++ ---++ Monitor your DSPy programs using **MLflow Tracing**, based on OpenTelemetry.++ [:octicons-arrow-right-24: Set Up Observability](../tutorials/observability/#tracing)++- :material-ab-testing: __Reproducibility__++ ---++ Log programs, metrics, configs, and environments for full reproducibility with DSPy's native MLflow integration.++ [:octicons-arrow-right-24: MLflow Integration](https://mlflow.org/docs/latest/llms/dspy/index.html)++- :material-rocket-launch: __Deployment__++ ---++ When it's time to productionize, deploy your application easily with DSPy's integration with MLflow Model Serving.++ [:octicons-arrow-right-24: Deployment Guide](../tutorials/deployment)++- :material-arrow-up-right-bold: __Scalability__++ ---++ DSPy is designed with thread-safety in mind and offers native asynchronous execution support for high-throughput environments.++ [:octicons-arrow-right-24: Async Program](../api/utils/asyncify.md)++- :material-alert-rhombus: __Guardrails & Controllability__++ ---++ DSPy's **Signatures**, **Modules**, and **Optimizers** help you control and guide LM outputs.++ [:octicons-arrow-right-24: Learn Signature](../learn/programming/signatures.md)++</div>diff --git a/docs/docs/stylesheets/extra.css b/docs/docs/stylesheets/extra.cssindex 9a745886e..d0bef54c8 100644--- a/docs/docs/stylesheets/extra.css+++ b/docs/docs/stylesheets/extra.css@@ -51,6 +51,10 @@text-align: justify;}+/* Left-aligned text for grid cards */+.md-content__inner .grid.cards p {+ text-align: left;+}/* Base styling for the output area */.jp-Cell-outputWrapper .jp-OutputArea-output pre {diff --git a/docs/docs/tutorials/observability/index.md b/docs/docs/tutorials/observability/index.mdindex e7568107f..5b82796e9 100644--- a/docs/docs/tutorials/observability/index.md+++ b/docs/docs/tutorials/observability/index.md@@ -4,7 +4,7 @@ This guide demonstrates how to debug problems and improve observability in DSPy.However, as systems grow more sophisticated, the ability to **understand what your system is doing** becomes critical. Without transparency, the prediction process can easily become a black box, making failures or quality issues difficult to diagnose and production maintenance challenging.-By the end of this tutorial, you'll understand how to debug an issue and improve observability using [MLflow Tracing](#mlflow-tracing). You'll also explore how to build a custom logging solution using callbacks.+By the end of this tutorial, you'll understand how to debug an issue and improve observability using [MLflow Tracing](#tracing). You'll also explore how to build a custom logging solution using callbacks.diff --git a/docs/mkdocs.yml b/docs/mkdocs.ymlindex 9c195c474..bdb643217 100644--- a/docs/mkdocs.yml+++ b/docs/mkdocs.yml@@ -127,6 +127,8 @@ nav:- load: api/utils/load.md- streamify: api/utils/streamify.md+ - DSPy in Production: production/index.md+theme:name: materialcustom_dir: overrides@@ -231,6 +233,7 @@ markdown_extensions:- pymdownx.superfences- pymdownx.mark- attr_list+ - md_in_html- pymdownx.emoji:emoji_index: !!python/name:material.extensions.emoji.twemojiemoji_generator: !!python/name:materialx.emoji.to_svg