doc: add initial prometheus docs

docs/configuration/holmesgpt/builtin_toolsets.rst

@@ -9,12 +9,14 @@ Builtin Toolsets
    toolsets/argocd
    toolsets/aws
    toolsets/confluence
+   toolsets/datetime
    toolsets/docker
    toolsets/grafana
    toolsets/helm
    toolsets/internet
    toolsets/kubernetes
    toolsets/opensearch
+   toolsets/prometheus
    toolsets/robusta
    toolsets/slab
 
@@ -48,6 +50,11 @@ by the user by providing credentials or API keys to external systems.
         :link: toolsets/confluence
         :link-type: doc
 
+    .. grid-item-card:: :octicon:`cpu;1em;` Datetime
+        :class-card: sd-bg-light sd-bg-text-light
+        :link: toolsets/datetime
+        :link-type: doc
+
     .. grid-item-card:: :octicon:`cpu;1em;` Docker
         :class-card: sd-bg-light sd-bg-text-light
         :link: toolsets/docker
@@ -72,11 +79,17 @@ by the user by providing credentials or API keys to external systems.
         :class-card: sd-bg-light sd-bg-text-light
         :link: toolsets/kubernetes
         :link-type: doc
+
     .. grid-item-card:: :octicon:`cpu;1em;` OpenSearch
         :class-card: sd-bg-light sd-bg-text-light
         :link: toolsets/opensearch
         :link-type: doc
 
+    .. grid-item-card:: :octicon:`cpu;1em;` Prometheus
+        :class-card: sd-bg-light sd-bg-text-light
+        :link: toolsets/prometheus
+        :link-type: doc
+
     .. grid-item-card:: :octicon:`cpu;1em;` Robusta
         :class-card: sd-bg-light sd-bg-text-light
         :link: toolsets/robusta

docs/configuration/holmesgpt/toolsets/datetime.rst

@@ -0,0 +1,33 @@
+Datetime :checkmark:`_`
+=======================
+.. include:: ./_toolset_enabled_by_default.inc.rst
+
+By enabling this toolset, HolmesGPT will be able to get the current UTC date and time.
+This feature works well with other toolsets. For example, the :doc:`prometheus <prometheus>`
+toolset needs ``start`` and ``end`` time parameters to properly create and execute
+PromQL queries.
+
+Configuration
+-------------
+
+.. code-block:: yaml
+
+    holmes:
+        toolsets:
+            datetime:
+                enabled: true
+
+.. include:: ./_toolset_configuration.inc.rst
+
+Capabilities
+------------
+.. include:: ./_toolset_capabilities.inc.rst
+
+.. list-table::
+   :header-rows: 1
+   :widths: 30 70
+
+   * - Tool Name
+     - Description
+   * - get_current_time
+     - Return current time information. Useful to build queries that require a time information

docs/configuration/holmesgpt/toolsets/prometheus.rst

@@ -0,0 +1,58 @@
+Prometheus
+==========
+
+By enabling this toolset, HolmesGPT will be able to analyze prometheus metrics and generate graphs from these metrics.
+This gives HolmesGPT the ability to detect memory leak patterns, CPU throttling, high latency for your APIs, etc.
+
+Configuration
+-------------
+
+
+.. code-block:: yaml
+
+    holmes:
+        toolsets:
+            opensearch/status:
+                enabled: true
+            config:
+                prometheus_url: http://robusta-kube-prometheus-st-prometheus.default.svc.cluster.local:9090
+
+It is also possible to set the ``PROMETHEUS_URL`` environment variable instead of the above ``prometheus_url`` config key.
+
+.. include:: ./_toolset_configuration.inc.rst
+
+Prior to generating a PromQL query, HolmesQPT tends to list the available metrics. This is done to ensure the metrics used
+in PromQL are actually available. The result of the request to fetch the labels available for each metric is cached. The
+request and the caching behaviour (TTL) can be tweaked:
+
+.. code-block:: yaml
+
+    holmes:
+        toolsets:
+            opensearch/status:
+                enabled: true
+            config:
+                prometheus_url: ...
+                metrics_labels_time_window_hrs: 48 # default value
+                metrics_labels_cache_duration_hrs: 12 # default value
+
+
+- **metrics_labels_time_window_hrs** Represents the time window, in hours, over which labels are fetched. This avoids fetching obsolete labels. Set it to ``null`` to let HolmesGPT fetch labels regardless of when they were generated.
+- **metrics_labels_cache_duration_hrs** How long are labels cached, in hours. Set it to ``null`` to disable caching.
+
+Capabilities
+------------
+.. include:: ./_toolset_capabilities.inc.rst
+
+.. list-table::
+   :header-rows: 1
+   :widths: 30 70
+
+   * - Tool Name
+     - Description
+   * - list_available_metrics
+     - List all the available metrics to query from prometheus, including their types (counter, gauge, histogram, summary) and available labels.
+   * - execute_prometheus_instant_query
+     - Execute an instant PromQL query
+   * - execute_prometheus_range_query
+     - Execute a PromQL range query