values.yaml

# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0

# Default values for agent.
# This is a YAML-formatted file.
# Declare variables to be passed into your templates.

tgi:
  enabled: false
  LLM_MODEL_ID: "meta-llama/Meta-Llama-3.1-70B-Instruct"
  MAX_INPUT_LENGTH: "4096"
  MAX_TOTAL_TOKENS: "8192"

vllm:
  enabled: false
  LLM_MODEL_ID: "mistralai/Mistral-7B-Instruct-v0.3"
  extraCmdArgs: ["--tensor-parallel-size", "1", "--block-size", "128", "--max-num-seqs", "4096", "--max-seq_len-to-capture", "8192", "--enable-auto-tool-choice", "--tool-call-parser", "mistral"]

replicaCount: 1
llm_endpoint_url: ""
model: "meta-llama/Meta-Llama-3.1-70B-Instruct"
max_new_tokens: "4096"
llm_engine: "tgi"
strategy: "react_langchain"
recursion_limit: "15"
require_human_feedback: "false"

# Set it as a non-null string, such as true, if you want to enable logging facility,
# otherwise, keep it as "" to disable it.
LOGFLAG: "True"

image:
  repository: opea/agent-langchain
  # Uncomment the following line to set desired image pull policy if needed, as one of Always, IfNotPresent, Never.
  # pullPolicy: ""
  # Overrides the image tag whose default is the chart appVersion.
  tag: "latest"

imagePullSecrets: []
nameOverride: ""
fullnameOverride: ""

serviceAccount:
  # Specifies whether a service account should be created
  create: false
  # Automatically mount a ServiceAccount's API credentials?
  automount: true
  # Annotations to add to the service account
  annotations: {}
  # The name of the service account to use.
  # If not set and create is true, a name is generated using the fullname template
  name: ""

podAnnotations: {}

podSecurityContext: {}
  # fsGroup: 2000

securityContext:
  readOnlyRootFilesystem: false
  allowPrivilegeEscalation: false
  runAsNonRoot: true
  runAsUser: 1000
  capabilities:
    drop:
    - ALL
  seccompProfile:
    type: RuntimeDefault

service:
  type: ClusterIP
  # The default port for agent service is 9090
  port: 9090

resources: {}
  # We usually recommend not to specify default resources and to leave this as a conscious
  # choice for the user. This also increases chances charts run on environments with little
  # resources, such as Minikube. If you do want to specify resources, uncomment the following
  # lines, adjust them as necessary, and remove the curly braces after 'resources:'.
  # limits:
  #   cpu: 100m
  #   memory: 128Mi
  # requests:
  #   cpu: 100m
  #   memory: 128Mi

livenessProbe:
  httpGet:
    path: v1/health_check
    port: agent
  initialDelaySeconds: 5
  periodSeconds: 5
  failureThreshold: 24
readinessProbe:
  httpGet:
    path: v1/health_check
    port: agent
  initialDelaySeconds: 5
  periodSeconds: 5
startupProbe:
  httpGet:
    path: v1/health_check
    port: agent
  initialDelaySeconds: 5
  periodSeconds: 5
  failureThreshold: 120

nodeSelector: {}

tolerations: []

affinity: {}

global:
  http_proxy: ""
  https_proxy: ""
  no_proxy: ""
  HUGGINGFACEHUB_API_TOKEN: "insert-your-huggingface-token-here"
  # service account name to be shared with all parent/child charts.
  # If set, it will overwrite serviceAccount.name.
  # If set, and serviceAccount.create is false, it will assume this service account is already created by others.
  sharedSAName: ""

  # Install Prometheus serviceMonitor for service
  monitoring: false

  # Prometheus Helm install release name for serviceMonitor
  prometheusRelease: prometheus-stack