Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 3 additions & 0 deletions deploy/helm/semantic-router/templates/deployment.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -70,6 +70,9 @@ spec:
env:
- name: HF_HUB_CACHE
value: /tmp/hf_cache
{{- with .Values.initContainer.env }}
{{- toYaml . | nindent 10 }}
{{- end }}
resources:
{{- toYaml .Values.initContainer.resources | nindent 10 }}
volumeMounts:
Expand Down
12 changes: 12 additions & 0 deletions deploy/helm/semantic-router/values.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@
# Declare variables to be passed into your templates.

# Global settings
global:

Check warning on line 6 in deploy/helm/semantic-router/values.yaml

View workflow job for this annotation

GitHub Actions / Run Validation Script

6:1 [document-start] missing document start "---"
# -- Namespace for all resources (if not specified, uses Release.Namespace)
namespace: ""

Expand Down Expand Up @@ -42,7 +42,7 @@

# Pod security context
podSecurityContext: {}
# fsGroup: 2000

Check warning on line 45 in deploy/helm/semantic-router/values.yaml

View workflow job for this annotation

GitHub Actions / Run Validation Script

45:3 [comments-indentation] comment not indented like content

# Container security context
securityContext:
Expand Down Expand Up @@ -95,7 +95,7 @@
className: ""
# -- Ingress annotations
annotations: {}
# kubernetes.io/ingress.class: nginx

Check warning on line 98 in deploy/helm/semantic-router/values.yaml

View workflow job for this annotation

GitHub Actions / Run Validation Script

98:5 [comments-indentation] comment not indented like content
# kubernetes.io/tls-acme: "true"
# -- Ingress hosts configuration
hosts:
Expand Down Expand Up @@ -135,6 +135,18 @@
requests:
memory: "1Gi"
cpu: "500m"
# -- Additional environment variables for the init container.
# For example, to use a private Hugging Face model, you can pass a token
# and specify an endpoint using a pre-existing Kubernetes secret.
# env:
# - name: HF_TOKEN
# valueFrom:
# secretKeyRef:
# name: my-hf-secret
# key: token
# - name: HF_ENDPOINT
# value: "https://huggingface.co"
env: []
# -- Models to download
models:
- name: all-MiniLM-L12-v2
Expand All @@ -146,7 +158,7 @@
- name: jailbreak_classifier_modernbert-base_model
repo: LLM-Semantic-Router/jailbreak_classifier_modernbert-base_model
- name: pii_classifier_modernbert-base_presidio_token_model
repo: LLM-Semantic-Router/pii_classifier_modernbert-base_presidio_token_model

Check failure on line 161 in deploy/helm/semantic-router/values.yaml

View workflow job for this annotation

GitHub Actions / Run Validation Script

161:81 [line-length] line too long (83 > 80 characters)

# Autoscaling configuration
autoscaling:
Expand Down Expand Up @@ -208,7 +220,7 @@
size: 10Gi
# -- Annotations for PVC
annotations: {}
# -- Existing claim name (if provided, will use existing PVC instead of creating new one)

Check failure on line 223 in deploy/helm/semantic-router/values.yaml

View workflow job for this annotation

GitHub Actions / Run Validation Script

223:81 [line-length] line too long (91 > 80 characters)
existingClaim: ""

# Application configuration
Expand Down Expand Up @@ -243,7 +255,7 @@
model_id: "models/jailbreak_classifier_modernbert-base_model"
threshold: 0.7
use_cpu: true
jailbreak_mapping_path: "models/jailbreak_classifier_modernbert-base_model/jailbreak_type_mapping.json"

Check failure on line 258 in deploy/helm/semantic-router/values.yaml

View workflow job for this annotation

GitHub Actions / Run Validation Script

258:81 [line-length] line too long (107 > 80 characters)

# vLLM endpoints configuration
vllm_endpoints:
Expand All @@ -267,30 +279,30 @@
use_modernbert: true
threshold: 0.6
use_cpu: true
category_mapping_path: "models/category_classifier_modernbert-base_model/category_mapping.json"

Check failure on line 282 in deploy/helm/semantic-router/values.yaml

View workflow job for this annotation

GitHub Actions / Run Validation Script

282:81 [line-length] line too long (101 > 80 characters)
pii_model:
model_id: "models/pii_classifier_modernbert-base_presidio_token_model"
use_modernbert: true
threshold: 0.7
use_cpu: true
pii_mapping_path: "models/pii_classifier_modernbert-base_presidio_token_model/pii_type_mapping.json"

Check failure on line 288 in deploy/helm/semantic-router/values.yaml

View workflow job for this annotation

GitHub Actions / Run Validation Script

288:81 [line-length] line too long (106 > 80 characters)

# Categories configuration
categories:
- name: business
system_prompt: "You are a senior business consultant and strategic advisor with expertise in corporate strategy, operations management, financial analysis, marketing, and organizational development. Provide practical, actionable business advice backed by proven methodologies and industry best practices. Consider market dynamics, competitive landscape, and stakeholder interests in your recommendations."

Check failure on line 293 in deploy/helm/semantic-router/values.yaml

View workflow job for this annotation

GitHub Actions / Run Validation Script

293:81 [line-length] line too long (411 > 80 characters)
model_scores:
- model: qwen3
score: 0.7
use_reasoning: false
- name: law
system_prompt: "You are a knowledgeable legal expert with comprehensive understanding of legal principles, case law, statutory interpretation, and legal procedures across multiple jurisdictions. Provide accurate legal information and analysis while clearly stating that your responses are for informational purposes only and do not constitute legal advice. Always recommend consulting with qualified legal professionals for specific legal matters."

Check failure on line 299 in deploy/helm/semantic-router/values.yaml

View workflow job for this annotation

GitHub Actions / Run Validation Script

299:81 [line-length] line too long (454 > 80 characters)
model_scores:
- model: qwen3
score: 0.4
use_reasoning: false
- name: psychology
system_prompt: "You are a psychology expert with deep knowledge of cognitive processes, behavioral patterns, mental health, developmental psychology, social psychology, and therapeutic approaches. Provide evidence-based insights grounded in psychological research and theory. When discussing mental health topics, emphasize the importance of professional consultation and avoid providing diagnostic or therapeutic advice."

Check failure on line 305 in deploy/helm/semantic-router/values.yaml

View workflow job for this annotation

GitHub Actions / Run Validation Script

305:81 [line-length] line too long (428 > 80 characters)
semantic_cache_enabled: true
semantic_cache_similarity_threshold: 0.92
model_scores:
Expand All @@ -298,13 +310,13 @@
score: 0.6
use_reasoning: false
- name: biology
system_prompt: "You are a biology expert with comprehensive knowledge spanning molecular biology, genetics, cell biology, ecology, evolution, anatomy, physiology, and biotechnology. Explain biological concepts with scientific accuracy, use appropriate terminology, and provide examples from current research. Connect biological principles to real-world applications and emphasize the interconnectedness of biological systems."

Check failure on line 313 in deploy/helm/semantic-router/values.yaml

View workflow job for this annotation

GitHub Actions / Run Validation Script

313:81 [line-length] line too long (432 > 80 characters)
model_scores:
- model: qwen3
score: 0.9
use_reasoning: false
- name: chemistry
system_prompt: "You are a chemistry expert specializing in chemical reactions, molecular structures, and laboratory techniques. Provide detailed, step-by-step explanations."

Check failure on line 319 in deploy/helm/semantic-router/values.yaml

View workflow job for this annotation

GitHub Actions / Run Validation Script

319:81 [line-length] line too long (179 > 80 characters)
model_scores:
- model: qwen3
score: 0.6
Expand Down
Loading