Add Mistral Guide and Assets

docs/content/guides/assets/mistral/graph.mmd

@@ -0,0 +1,34 @@
+flowchart LR
+subgraph root.0[<center>ConcurrencyScheduler<br/>1 selectors</center>]
+subgraph root.0_inports[ ]
+style root.0_inports fill:none,stroke:none
+root.0max_capacity[max_capacity]
+end
+subgraph root.0_outports[ ]
+style root.0_outports fill:none,stroke:none
+root.0accept_percentage[accept_percentage]
+end
+end
+root.0_max_capacity_FakeConstantout((2.00))
+subgraph root.1[<center>Decider<br/>gte for 0s</center>]
+subgraph root.1_inports[ ]
+style root.1_inports fill:none,stroke:none
+root.1lhs[lhs]
+root.1rhs[rhs]
+end
+subgraph root.1_outports[ ]
+style root.1_outports fill:none,stroke:none
+root.1output[output]
+end
+end
+root.1_rhs_FakeConstantout((90.00))
+subgraph root.2[<center>Alerter<br/>Too many inflight requests/...</center>]
+subgraph root.2_inports[ ]
+style root.2_inports fill:none,stroke:none
+root.2signal[signal]
+end
+end
+root.0accept_percentage --> |ACCEPT_PERCENTAGE| root.1lhs
+root.0_max_capacity_FakeConstantout --> root.0max_capacity
+root.1output --> |ACCEPT_PERCENTAGE_ALERT| root.2signal
+root.1_rhs_FakeConstantout --> root.1rhs

docs/content/guides/assets/mistral/graph.mmd.md5sum

@@ -0,0 +1 @@
+9ca1ad832dcce3be1db8edf82a0979c7

docs/content/guides/assets/mistral/mistral.mmd

@@ -0,0 +1,21 @@
+flowchart LR
+classDef Orange fill:#F8773D,stroke:#000000,stroke-width:2px;
+classDef Green fill:#56AE89,stroke:#000000,stroke-width:2px;
+classDef Red fill:#F13C15,stroke:#000000,stroke-width:1px;
+classDef Pink fill:#ffb6c1,stroke:#000000,stroke-width:1px;
+
+TC[\Token Counter/]
+class TC Orange
+
+Scheduler
+class Scheduler Orange
+
+SDK
+class SDK Green
+
+subgraph Aperture_Cloud ["Aperture Cloud"]
+    Scheduler -- "Counting" --> TC
+end
+class Aperture_Cloud Green
+
+SDK -- "Schedule Request" --> Scheduler

docs/content/guides/assets/mistral/mistral.mmd.md5sum

@@ -0,0 +1 @@
+5df63f64375615e3ec9761cb92b987af

docs/content/guides/assets/mistral/policy.yaml

@@ -0,0 +1,48 @@
+apiVersion: fluxninja.com/v1alpha1
+kind: Policy
+metadata:
+  labels:
+    fluxninja.com/validate: "true"
+  name: mistral-concurrency-scheduling
+spec:
+  circuit:
+    components:
+    - flow_control:
+        concurrency_scheduler:
+          concurrency_limiter:
+            limit_by_label_key: limit_by_label_key
+            max_inflight_duration: 60s
+          in_ports:
+            max_concurrency:
+              constant_signal:
+                value: 2
+          out_ports:
+            accept_percentage:
+              signal_name: ACCEPT_PERCENTAGE
+          scheduler:
+            priority_label_key: priority
+            tokens_label_key: tokens
+            workload_label_key: workload
+          selectors:
+          - control_point: mistral-prompt
+    - decider:
+        in_ports:
+          lhs:
+            signal_name: ACCEPT_PERCENTAGE
+          rhs:
+            constant_signal:
+              value: 90
+        operator: gte
+        out_ports:
+          output:
+            signal_name: ACCEPT_PERCENTAGE_ALERT
+    - alerter:
+        in_ports:
+          signal:
+            signal_name: ACCEPT_PERCENTAGE_ALERT
+        parameters:
+          alert_name: Too many inflight requests
+    evaluation_interval: 1s
+  resources:
+    flow_control:
+      classifiers: []

docs/content/guides/assets/mistral/validate.sh

@@ -0,0 +1,22 @@
+#!/usr/bin/env bash
+
+set -e
+
+git_root=$(git rev-parse --show-toplevel)
+
+# shellcheck disable=SC1091
+source "$git_root"/docs/tools/aperturectl/validate_common.sh
+
+generate_from_values \
+	values.yaml \
+	tmp
+
+# copy the generated policy and graph to this (assets) directory so that they can be used in the docs
+cp tmp/policies/mistral-concurrency-scheduling-cr.yaml policy.yaml
+cp tmp/graphs/mistral-concurrency-scheduling-cr.mmd graph.mmd
+
+# git add the generated policy and graph
+"$git_root"/scripts/git_add_safely.sh policy.yaml graph.mmd
+
+# remove the tmp directory
+rm -rf tmp

docs/content/guides/assets/mistral/values.yaml

@@ -0,0 +1,21 @@
+# yaml-language-server: $schema=../../../../../blueprints/concurrency-scheduling/base/gen/definitions.json
+blueprint: concurrency-scheduling/base
+uri: ../../../../../blueprints
+policy:
+  policy_name: "mistral-concurrency-scheduling"
+  components: []
+  concurrency_scheduler:
+    alerter:
+      alert_name: "Too many inflight requests"
+    concurrency_limiter:
+      max_inflight_duration: "60s"
+    max_concurrency: 2
+    scheduler:
+      priority_label_key: "priority"
+      tokens_label_key: "tokens"
+      workload_label_key: "workload"
+    selectors:
+      - control_point: "mistral-prompt"
+  resources:
+    flow_control:
+      classifiers: []