From 453112d09fcfe487aac3edaf07713c4eeef183a8 Mon Sep 17 00:00:00 2001
From: amithkoujalgi <koujalgi.amith@gmail.com>
Date: Wed, 1 Oct 2025 01:14:21 +0530
Subject: [PATCH] Add metrics documentation for Ollama4j library

- Introduced a new `metrics.md` file detailing the metrics available in the Ollama4j library, including total requests, response time, error rate, and active sessions.
- Provided examples of accessing metrics in Java and integrating with monitoring tools like Prometheus and Grafana.
- Included a warning note indicating that the documentation is a work in progress.
---
 docs/docs/metrics.md | 71 ++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 71 insertions(+)
 create mode 100644 docs/docs/metrics.md

diff --git a/docs/docs/metrics.md b/docs/docs/metrics.md
new file mode 100644
index 0000000..a462691
--- /dev/null
+++ b/docs/docs/metrics.md
@@ -0,0 +1,71 @@
+---
+sidebar_position: 5
+
+title: Metrics
+---
+
+import CodeEmbed from '@site/src/components/CodeEmbed';
+
+# Metrics
+
+:::warning[Note]
+This is work in progress
+:::
+
+Monitoring and understanding the performance of your models and requests is crucial for optimizing and maintaining your
+applications. The Ollama4j library provides built-in support for collecting and exposing various metrics, such as
+request counts, response times, and error rates. These metrics can help you:
+
+- Track usage patterns and identify bottlenecks
+- Monitor the health and reliability of your services
+- Set up alerts for abnormal behavior
+- Gain insights for scaling and optimization
+
+## Available Metrics
+
+Ollama4j exposes several key metrics, including:
+
+- **Total Requests**: The number of requests processed by the model.
+- **Response Time**: The time taken to generate a response for each request.
+- **Error Rate**: The percentage of requests that resulted in errors.
+- **Active Sessions**: The number of concurrent sessions or users.
+
+These metrics can be accessed programmatically or integrated with monitoring tools such as Prometheus or Grafana for
+visualization and alerting.
+
+## Example Metrics Dashboard
+
+Below is an example of a metrics dashboard visualizing some of these key statistics:
+
+![Img](https://raw.githubusercontent.com/ollama4j/ollama4j/main/metrics.png)
+
+## Example: Accessing Metrics in Java
+
+You can easily access and display metrics in your Java application using Ollama4j.
+
+Make sure you have added the `simpleclient_httpserver` dependency in your app for the app to be able to expose the
+metrics via `/metrics` endpoint:
+
+```xml
+
+<dependency>
+    <groupId>io.prometheus</groupId>
+    <artifactId>simpleclient_httpserver</artifactId>
+    <version>0.16.0</version>
+</dependency>
+```
+
+Here is a sample code snippet demonstrating how to retrieve and print metrics:
+
+<CodeEmbed src="https://raw.githubusercontent.com/ollama4j/ollama4j-examples/refs/heads/main/src/main/java/io/github/ollama4j/examples/MetricsExample.java" />
+
+This will start a simple HTTP server with `/metrics` endpoint enabled. Metrics will now available
+at: http://localhost:8080/metrics
+
+## Integrating with Monitoring Tools
+
+To integrate Ollama4j metrics with external monitoring systems, you can export the metrics endpoint and configure your
+monitoring tool to scrape or collect the data. Refer to the [integration guide](../integration/monitoring.md) for
+detailed instructions.
+
+For more information on customizing and extending metrics, see the [API documentation](../api/metrics.md).