Merge branch 'main' into pagination

This commit is contained in:
Mike Fortman 2026-01-16 11:21:12 -06:00 committed by GitHub
commit cef21e500b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
49 changed files with 2280 additions and 20 deletions

155
.github/ISSUE_TEMPLATE/bug_report.yml vendored Normal file
View file

@ -0,0 +1,155 @@
name: Bug Report
description: Report a bug or unexpected behavior in OpenRAG
title: "[Bug]: "
labels: ["bug"]
body:
- type: markdown
attributes:
value: |
Thanks for taking the time to report a bug! Please fill out the form below to help us understand and fix the issue.
- type: input
id: openrag-version
attributes:
label: OpenRAG Version
description: What version of OpenRAG are you using? Run `openrag --version` or check your package version.
placeholder: "e.g., 0.1.0"
validations:
required: true
- type: dropdown
id: deployment-method
attributes:
label: Deployment Method
description: How are you running OpenRAG?
options:
- uvx (uvx openrag)
- uv add (installed in project)
- Docker
- Podman
- Local development (make dev)
- Other
validations:
required: true
- type: input
id: os
attributes:
label: Operating System
description: What operating system are you using?
placeholder: "e.g., macOS 14.0, Ubuntu 22.04, Windows 11"
validations:
required: true
- type: input
id: python-version
attributes:
label: Python Version
description: What Python version are you using? Run `python --version` to check.
placeholder: "e.g., 3.13.0"
validations:
required: false
- type: dropdown
id: affected-area
attributes:
label: Affected Area
description: Which area(s) of OpenRAG does this bug affect? Select all that apply.
multiple: true
options:
- Ingestion (document processing, upload, Docling)
- Retrieval (search, OpenSearch, hybrid search)
- Chat (chat interface, conversations, AI responses)
- Knowledge Filters (partitions, document filtering)
- Settings (configuration, model providers)
- TUI (Terminal User Interface)
- Connectors (Google Drive, OneDrive, SharePoint)
- Frontend (Next.js UI, components)
- Backend/API (Python/Starlette)
- Infrastructure (Docker, OpenSearch, Langflow)
- SDK (Python or TypeScript SDK)
- Onboarding (setup wizard, initial configuration)
- Authentication (OIDC, API keys)
- Other
validations:
required: true
- type: textarea
id: bug-description
attributes:
label: Bug Description
description: A clear and concise description of what the bug is.
placeholder: Describe the bug...
validations:
required: true
- type: textarea
id: steps-to-reproduce
attributes:
label: Steps to Reproduce
description: Steps to reproduce the behavior.
placeholder: |
1. Go to '...'
2. Click on '...'
3. Scroll down to '...'
4. See error
validations:
required: true
- type: textarea
id: expected-behavior
attributes:
label: Expected Behavior
description: A clear and concise description of what you expected to happen.
placeholder: What should have happened?
validations:
required: true
- type: textarea
id: actual-behavior
attributes:
label: Actual Behavior
description: A clear and concise description of what actually happened.
placeholder: What actually happened?
validations:
required: true
- type: textarea
id: logs
attributes:
label: Relevant Logs
description: |
Please copy and paste any relevant log output.
You can get logs using `make logs` for Docker deployments or check the terminal output.
This will be automatically formatted into code, so no need for backticks.
render: shell
validations:
required: false
- type: textarea
id: screenshots
attributes:
label: Screenshots
description: If applicable, add screenshots to help explain your problem.
validations:
required: false
- type: textarea
id: additional-context
attributes:
label: Additional Context
description: Add any other context about the problem here (e.g., browser version, specific document types, model provider being used).
validations:
required: false
- type: checkboxes
id: checklist
attributes:
label: Checklist
description: Please confirm the following before submitting.
options:
- label: I have searched existing issues to ensure this bug hasn't been reported before.
required: true
- label: I have provided all the requested information.
required: true

15
.github/ISSUE_TEMPLATE/config.yml vendored Normal file
View file

@ -0,0 +1,15 @@
blank_issues_enabled: false
contact_links:
- name: OpenRAG Documentation
url: https://docs.openr.ag/
about: Learn more about OpenRAG's features, installation, and configuration.
- name: Troubleshooting Guide
url: https://docs.openr.ag/support/troubleshoot
about: Check the troubleshooting guide for common issues and solutions.
- name: GitHub Discussions
url: https://github.com/langflow-ai/openrag/discussions
about: Ask questions and discuss ideas with the community.
- name: Contributing Guide
url: https://github.com/langflow-ai/openrag/blob/main/CONTRIBUTING.md
about: Learn how to contribute to OpenRAG development.

106
.github/ISSUE_TEMPLATE/documentation.yml vendored Normal file
View file

@ -0,0 +1,106 @@
name: Documentation Issue
description: Report an issue with documentation or request new documentation
title: "[Docs]: "
labels: ["documentation"]
body:
- type: markdown
attributes:
value: |
Thanks for helping improve OpenRAG's documentation! Please provide details about the issue or your request.
- type: dropdown
id: issue-type
attributes:
label: Issue Type
description: What type of documentation issue is this?
options:
- Incorrect information
- Missing documentation
- Outdated content
- Unclear or confusing
- Typo or grammatical error
- Broken links
- Request for new documentation
- Other
validations:
required: true
- type: dropdown
id: doc-area
attributes:
label: Documentation Area
description: Which area of documentation does this relate to?
multiple: true
options:
- Getting Started / Quickstart
- Installation (uvx, Docker, Podman)
- Configuration / Settings
- Ingestion & Document Processing
- Search & Retrieval
- Chat Interface
- Knowledge Filters
- Connectors (Google Drive, OneDrive, SharePoint)
- TUI (Terminal User Interface)
- API Reference
- SDK Documentation (Python/TypeScript)
- Troubleshooting
- Contributing Guide
- Other
validations:
required: true
- type: input
id: doc-url
attributes:
label: Documentation URL
description: If applicable, provide a link to the specific documentation page.
placeholder: "https://docs.openr.ag/..."
validations:
required: false
- type: textarea
id: current-content
attributes:
label: Current Content
description: If reporting an issue, what does the documentation currently say?
placeholder: Quote or describe the current documentation content.
validations:
required: false
- type: textarea
id: issue-description
attributes:
label: Issue Description
description: Describe the problem or what documentation you'd like to see added.
placeholder: |
For issues: Explain what's wrong or confusing about the current documentation.
For requests: Describe what topic you'd like documented and why it would be helpful.
validations:
required: true
- type: textarea
id: suggested-content
attributes:
label: Suggested Content
description: If you have suggestions for how to fix or improve the documentation, please share them.
placeholder: Provide suggested text, corrections, or an outline for new documentation.
validations:
required: false
- type: textarea
id: additional-context
attributes:
label: Additional Context
description: Add any other context, screenshots, or examples here.
validations:
required: false
- type: checkboxes
id: contribution
attributes:
label: Contribution
description: Would you be interested in contributing to fix this documentation issue?
options:
- label: I would be willing to submit a pull request to fix this issue.
required: false

View file

@ -0,0 +1,113 @@
name: Feature Request
description: Suggest a new feature or enhancement for OpenRAG
title: "[Feature]: "
labels: ["enhancement"]
body:
- type: markdown
attributes:
value: |
Thanks for suggesting a feature! Please provide as much detail as possible to help us understand your request.
- type: dropdown
id: feature-area
attributes:
label: Feature Area
description: Which area(s) of OpenRAG does this feature relate to?
multiple: true
options:
- Ingestion (document processing, upload, Docling)
- Retrieval (search, OpenSearch, hybrid search)
- Chat (chat interface, conversations, AI responses)
- Knowledge Filters (partitions, document filtering)
- Settings (configuration, model providers)
- TUI (Terminal User Interface)
- Connectors (Google Drive, OneDrive, SharePoint)
- Frontend (Next.js UI, components)
- Backend/API (Python/Starlette)
- Infrastructure (Docker, OpenSearch, Langflow)
- SDK (Python or TypeScript SDK)
- Onboarding (setup wizard, initial configuration)
- Authentication (OIDC, API keys)
- New Area
validations:
required: true
- type: textarea
id: problem-description
attributes:
label: Problem Description
description: Is your feature request related to a problem? Please describe.
placeholder: A clear and concise description of what the problem is. E.g., "I'm always frustrated when..."
validations:
required: true
- type: textarea
id: proposed-solution
attributes:
label: Proposed Solution
description: Describe the solution you'd like to see implemented.
placeholder: A clear and concise description of what you want to happen.
validations:
required: true
- type: textarea
id: use-case
attributes:
label: Use Case
description: Describe your use case and how this feature would benefit you or others.
placeholder: |
As a [type of user], I want [goal] so that [benefit].
Example: As a developer, I want to filter documents by custom metadata so that I can organize my knowledge base more effectively.
validations:
required: true
- type: textarea
id: alternatives
attributes:
label: Alternatives Considered
description: Describe any alternative solutions or features you've considered.
placeholder: What other approaches have you thought about? Why wouldn't they work as well?
validations:
required: false
- type: dropdown
id: priority
attributes:
label: Priority
description: How important is this feature to your workflow?
options:
- Nice to have
- Would improve my workflow
- Critical for my use case
validations:
required: true
- type: textarea
id: additional-context
attributes:
label: Additional Context
description: Add any other context, mockups, screenshots, or examples about the feature request here.
validations:
required: false
- type: checkboxes
id: contribution
attributes:
label: Contribution
description: Would you be interested in contributing to this feature?
options:
- label: I would be willing to help implement this feature.
required: false
- label: I can help test this feature once implemented.
required: false
- type: checkboxes
id: checklist
attributes:
label: Checklist
description: Please confirm the following before submitting.
options:
- label: I have searched existing issues and discussions to ensure this feature hasn't been requested before.
required: true

View file

@ -206,7 +206,7 @@ jobs:
uses: actions/checkout@v4
- name: Set up Python
uses: actions/setup-python@v5
uses: actions/setup-python@v6
with:
python-version: '3.13'

View file

@ -45,7 +45,7 @@ jobs:
- uses: actions/checkout@v4
- name: Setup Python
uses: actions/setup-python@v5
uses: actions/setup-python@v6
with:
python-version: '3.11'

View file

@ -23,7 +23,7 @@ jobs:
- name: Setup Node.js
uses: actions/setup-node@v4
with:
node-version: 20
node-version: 20.20.0
cache: npm
cache-dependency-path: ./docs/package-lock.json

View file

@ -16,7 +16,7 @@ jobs:
- uses: actions/checkout@v4
- uses: actions/setup-node@v4
with:
node-version: 20
node-version: 20.20.0
cache: npm
cache-dependency-path: ./docs/package-lock.json

View file

@ -21,7 +21,7 @@ jobs:
uses: actions/checkout@v4
- name: Set up Python
uses: actions/setup-python@v5
uses: actions/setup-python@v6
with:
python-version: '3.12'

View file

@ -20,7 +20,7 @@ jobs:
token: ${{ secrets.GITHUB_TOKEN }}
- name: Set up Python
uses: actions/setup-python@v5
uses: actions/setup-python@v6
with:
python-version: '3.13'

View file

@ -1,4 +1,4 @@
FROM node:18-slim
FROM node:20.20.0-slim
# Set working directory
WORKDIR /app

View file

@ -0,0 +1,5 @@
GPU acceleration isn't required for most use cases.
OpenRAG's CPU-only deployment doesn't prevent you from using GPU acceleration in external services, such as Ollama servers.
GPU acceleration is required only for specific use cases, typically involving customization of the ingestion flows or ingestion logic.
For example, writing alternate ingest logic in OpenRAG that uses GPUs directly in the container, or customizing the ingestion flows to use Langflow's Docling component with GPU acceleration instead of OpenRAG's `docling serve` service.

View file

@ -15,4 +15,6 @@ If a provider offers only one type, you must select two providers.
<PartialOllamaModels />
:::
* Optional: Install GPU support with an NVIDIA GPU, [CUDA](https://docs.nvidia.com/cuda/) support, and compatible NVIDIA drivers on the OpenRAG host machine. If you don't have GPU capabilities, OpenRAG provides an alternate CPU-only deployment.
* Optional: Install GPU support with an NVIDIA GPU, [CUDA](https://docs.nvidia.com/cuda/) support, and compatible NVIDIA drivers on the OpenRAG host machine.
If you don't have GPU capabilities, OpenRAG provides an alternate CPU-only deployment that is suitable for most use cases.
The default CPU-only deployment doesn't prevent you from using GPU acceleration in external services, such as Ollama servers.

View file

@ -12,6 +12,7 @@ import PartialPrereqWindows from '@site/docs/_partial-prereq-windows.mdx';
import PartialPrereqPython from '@site/docs/_partial-prereq-python.mdx';
import PartialInstallNextSteps from '@site/docs/_partial-install-next-steps.mdx';
import PartialOllamaModels from '@site/docs/_partial-ollama-models.mdx';
import PartialGpuModeTip from '@site/docs/_partial-gpu-mode-tip.mdx';
To manage your own OpenRAG services, deploy OpenRAG with Docker or Podman.
@ -116,7 +117,17 @@ The following variables are required or recommended:
3. Deploy the OpenRAG containers locally using the appropriate Docker Compose configuration for your environment:
* **GPU-accelerated deployment**: If your host machine has an NVIDIA GPU with CUDA support and compatible NVIDIA drivers, use the base `docker-compose.yml` file with the `docker-compose.gpu.yml` override.
* **CPU-only deployment** (default, recommended): If your host machine doesn't have NVIDIA GPU support, use the base `docker-compose.yml` file:
```bash title="Docker"
docker compose up -d
```
```bash title="Podman"
podman compose up -d
```
* **GPU-accelerated deployment**: If your host machine has an NVIDIA GPU with CUDA support and compatible NVIDIA drivers, use the base `docker-compose.yml` file with the `docker-compose.gpu.yml` override:
```bash title="Docker"
docker compose -f docker-compose.yml -f docker-compose.gpu.yml up -d
@ -126,15 +137,9 @@ The following variables are required or recommended:
podman compose -f docker-compose.yml -f docker-compose.gpu.yml up -d
```
* **CPU-only deployment** (default): If your host machine doesn't have NVIDIA GPU support, use the base `docker-compose.yml` file.
```bash title="Docker"
docker compose up -d
```
```bash title="Podman"
podman compose up -d
```
:::tip
<PartialGpuModeTip />
:::
4. Wait for the OpenRAG containers to start, and then confirm that all containers are running:

View file

@ -3,6 +3,8 @@ title: Use the TUI
slug: /tui
---
import PartialGpuModeTip from '@site/docs/_partial-gpu-mode-tip.mdx';
The OpenRAG Terminal User Interface (TUI) provides a simplified and guided experience for configuring, managing, and monitoring your OpenRAG deployment directly from the terminal.
![OpenRAG TUI Interface](@site/static/img/openrag_tui_dec_2025.png)
@ -36,6 +38,10 @@ In the TUI, click **Status**, and then click **Switch to GPU Mode** or **Switch
This change requires restarting all OpenRAG services because each mode has its own `docker-compose` file.
:::tip
<PartialGpuModeTip />
:::
## Exit the OpenRAG TUI
To exit the OpenRAG TUI, press <kbd>q</kbd> on the TUI main page.

View file

@ -26,7 +26,7 @@
"typescript": "~5.9.3"
},
"engines": {
"node": ">=18.0"
"node": ">=20.20.0"
}
},
"node_modules/@ai-sdk/gateway": {

View file

@ -46,6 +46,6 @@
]
},
"engines": {
"node": ">=18.0"
"node": ">=20.20.0"
}
}

View file

@ -2,6 +2,9 @@
"name": "frontend",
"version": "0.1.0",
"private": true,
"engines": {
"node": ">=20.20.0"
},
"scripts": {
"dev": "next dev",
"build": "next build",

18
helm/openrag/Chart.yaml Normal file
View file

@ -0,0 +1,18 @@
apiVersion: v2
name: openrag
description: A Helm chart for deploying OpenRAG - an open-source agentic RAG platform
type: application
version: 0.1.0
appVersion: "0.1.52"
keywords:
- openrag
- rag
- langflow
- opensearch
- ai
- llm
home: https://github.com/langflow-ai/openrag
sources:
- https://github.com/langflow-ai/openrag
maintainers:
- name: OpenRAG Team

View file

@ -0,0 +1,80 @@
OpenRAG has been deployed successfully!
{{- if .Values.global.tenant.name }}
Tenant: {{ .Values.global.tenant.name }}
Namespace: {{ include "openrag.namespace" . }}
{{- end }}
=== Services Deployed ===
{{- if .Values.langflow.enabled }}
Langflow:
- Internal URL: http://{{ include "openrag.fullname" . }}-langflow:{{ .Values.langflow.service.port }}
{{- if and .Values.ingress.enabled .Values.ingress.hosts.langflow.enabled .Values.ingress.hosts.langflow.host }}
- External URL: http{{ if .Values.ingress.tls.enabled }}s{{ end }}://{{ .Values.ingress.hosts.langflow.host }}
{{- end }}
{{- end }}
{{- if .Values.backend.enabled }}
Backend API:
- Internal URL: http://{{ include "openrag.fullname" . }}-backend:{{ .Values.backend.service.port }}
{{- if and .Values.ingress.enabled .Values.ingress.hosts.backend.host }}
- External URL: http{{ if .Values.ingress.tls.enabled }}s{{ end }}://{{ .Values.ingress.hosts.backend.host }}
{{- end }}
{{- end }}
{{- if .Values.frontend.enabled }}
Frontend UI:
- Internal URL: http://{{ include "openrag.fullname" . }}-frontend:{{ .Values.frontend.service.port }}
{{- if and .Values.ingress.enabled .Values.ingress.hosts.frontend.host }}
- External URL: http{{ if .Values.ingress.tls.enabled }}s{{ end }}://{{ .Values.ingress.hosts.frontend.host }}
{{- end }}
{{- end }}
{{- if .Values.dashboards.enabled }}
OpenSearch Dashboards:
- Internal URL: http://{{ include "openrag.fullname" . }}-dashboards:{{ .Values.dashboards.service.port }}
{{- if and .Values.ingress.enabled .Values.ingress.hosts.dashboards.enabled .Values.ingress.hosts.dashboards.host }}
- External URL: http{{ if .Values.ingress.tls.enabled }}s{{ end }}://{{ .Values.ingress.hosts.dashboards.host }}
{{- end }}
{{- end }}
=== External Dependencies ===
OpenSearch (External SaaS):
- Host: {{ .Values.global.opensearch.host }}
- Port: {{ .Values.global.opensearch.port }}
- Scheme: {{ .Values.global.opensearch.scheme }}
=== Credentials ===
To retrieve the Langflow superuser credentials:
kubectl get secret {{ include "openrag.fullname" . }}-langflow -n {{ include "openrag.namespace" . }} -o jsonpath='{.data.superuser}' | base64 -d
kubectl get secret {{ include "openrag.fullname" . }}-langflow -n {{ include "openrag.namespace" . }} -o jsonpath='{.data.superuser-password}' | base64 -d
=== Quick Start ===
{{- if and .Values.ingress.enabled .Values.ingress.hosts.frontend.host }}
1. Access the OpenRAG UI at: http{{ if .Values.ingress.tls.enabled }}s{{ end }}://{{ .Values.ingress.hosts.frontend.host }}
{{- else }}
1. Port-forward the frontend service:
kubectl port-forward svc/{{ include "openrag.fullname" . }}-frontend {{ .Values.frontend.service.port }}:{{ .Values.frontend.service.port }} -n {{ include "openrag.namespace" . }}
Then access: http://localhost:{{ .Values.frontend.service.port }}
{{- end }}
2. Upload documents to your knowledge base
3. Start chatting with your documents using the AI-powered chat interface
=== Troubleshooting ===
Check pod status:
kubectl get pods -n {{ include "openrag.namespace" . }} -l app.kubernetes.io/instance={{ .Release.Name }}
Check pod logs:
kubectl logs -n {{ include "openrag.namespace" . }} -l app.kubernetes.io/component=langflow
kubectl logs -n {{ include "openrag.namespace" . }} -l app.kubernetes.io/component=backend
kubectl logs -n {{ include "openrag.namespace" . }} -l app.kubernetes.io/component=frontend
For more information, visit: https://github.com/langflow-ai/openrag

View file

@ -0,0 +1,163 @@
{{/*
Expand the name of the chart.
*/}}
{{- define "openrag.name" -}}
{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" }}
{{- end }}
{{/*
Create a default fully qualified app name.
If tenant name is provided, prefix with tenant name.
*/}}
{{- define "openrag.fullname" -}}
{{- if .Values.fullnameOverride }}
{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" }}
{{- else }}
{{- $name := default .Chart.Name .Values.nameOverride }}
{{- if .Values.global.tenant.name }}
{{- printf "%s-%s" .Values.global.tenant.name $name | trunc 63 | trimSuffix "-" }}
{{- else }}
{{- printf "%s" $name | trunc 63 | trimSuffix "-" }}
{{- end }}
{{- end }}
{{- end }}
{{/*
Create the namespace name.
Uses tenant namespace if specified, otherwise tenant name, otherwise release namespace.
*/}}
{{- define "openrag.namespace" -}}
{{- if .Values.global.tenant.namespace }}
{{- .Values.global.tenant.namespace }}
{{- else if .Values.global.tenant.name }}
{{- .Values.global.tenant.name }}
{{- else }}
{{- .Release.Namespace }}
{{- end }}
{{- end }}
{{/*
Create chart name and version as used by the chart label.
*/}}
{{- define "openrag.chart" -}}
{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" }}
{{- end }}
{{/*
Common labels
*/}}
{{- define "openrag.labels" -}}
helm.sh/chart: {{ include "openrag.chart" . }}
{{ include "openrag.selectorLabels" . }}
{{- if .Chart.AppVersion }}
app.kubernetes.io/version: {{ .Chart.AppVersion | quote }}
{{- end }}
app.kubernetes.io/managed-by: {{ .Release.Service }}
{{- if .Values.global.tenant.name }}
openrag.io/tenant: {{ .Values.global.tenant.name }}
{{- end }}
{{- end }}
{{/*
Selector labels
*/}}
{{- define "openrag.selectorLabels" -}}
app.kubernetes.io/name: {{ include "openrag.name" . }}
app.kubernetes.io/instance: {{ .Release.Name }}
{{- end }}
{{/*
Create the name of the service account to use
*/}}
{{- define "openrag.serviceAccountName" -}}
{{- if .Values.serviceAccount.create }}
{{- default (include "openrag.fullname" .) .Values.serviceAccount.name }}
{{- else }}
{{- default "default" .Values.serviceAccount.name }}
{{- end }}
{{- end }}
{{/*
Langflow component labels
*/}}
{{- define "openrag.langflow.labels" -}}
{{ include "openrag.labels" . }}
app.kubernetes.io/component: langflow
{{- end }}
{{/*
Langflow selector labels
*/}}
{{- define "openrag.langflow.selectorLabels" -}}
{{ include "openrag.selectorLabels" . }}
app.kubernetes.io/component: langflow
{{- end }}
{{/*
Backend component labels
*/}}
{{- define "openrag.backend.labels" -}}
{{ include "openrag.labels" . }}
app.kubernetes.io/component: backend
{{- end }}
{{/*
Backend selector labels
*/}}
{{- define "openrag.backend.selectorLabels" -}}
{{ include "openrag.selectorLabels" . }}
app.kubernetes.io/component: backend
{{- end }}
{{/*
Frontend component labels
*/}}
{{- define "openrag.frontend.labels" -}}
{{ include "openrag.labels" . }}
app.kubernetes.io/component: frontend
{{- end }}
{{/*
Frontend selector labels
*/}}
{{- define "openrag.frontend.selectorLabels" -}}
{{ include "openrag.selectorLabels" . }}
app.kubernetes.io/component: frontend
{{- end }}
{{/*
Dashboards component labels
*/}}
{{- define "openrag.dashboards.labels" -}}
{{ include "openrag.labels" . }}
app.kubernetes.io/component: dashboards
{{- end }}
{{/*
Dashboards selector labels
*/}}
{{- define "openrag.dashboards.selectorLabels" -}}
{{ include "openrag.selectorLabels" . }}
app.kubernetes.io/component: dashboards
{{- end }}
{{/*
Generate the Langflow service URL
*/}}
{{- define "openrag.langflow.url" -}}
http://{{ include "openrag.fullname" . }}-langflow:{{ .Values.langflow.service.port }}
{{- end }}
{{/*
Generate the Backend service URL
*/}}
{{- define "openrag.backend.url" -}}
http://{{ include "openrag.fullname" . }}-backend:{{ .Values.backend.service.port }}
{{- end }}
{{/*
Generate the OpenSearch URL
*/}}
{{- define "openrag.opensearch.url" -}}
{{ .Values.global.opensearch.scheme }}://{{ .Values.global.opensearch.host }}:{{ .Values.global.opensearch.port }}
{{- end }}

View file

@ -0,0 +1,273 @@
{{- if .Values.backend.enabled }}
apiVersion: apps/v1
kind: Deployment
metadata:
name: {{ include "openrag.fullname" . }}-backend
namespace: {{ include "openrag.namespace" . }}
labels:
{{- include "openrag.backend.labels" . | nindent 4 }}
spec:
replicas: 1 # Single pod for vertical scaling
strategy:
type: Recreate # Required for RWO PVCs
selector:
matchLabels:
{{- include "openrag.backend.selectorLabels" . | nindent 6 }}
template:
metadata:
labels:
{{- include "openrag.backend.selectorLabels" . | nindent 8 }}
annotations:
checksum/secret-opensearch: {{ include (print $.Template.BasePath "/secrets/opensearch-secret.yaml") . | sha256sum }}
checksum/secret-langflow: {{ include (print $.Template.BasePath "/secrets/langflow-secret.yaml") . | sha256sum }}
checksum/config-flows: {{ include (print $.Template.BasePath "/configmaps/flow-ids-configmap.yaml") . | sha256sum }}
checksum/config-app: {{ include (print $.Template.BasePath "/configmaps/app-config-configmap.yaml") . | sha256sum }}
spec:
serviceAccountName: {{ include "openrag.serviceAccountName" . }}
{{- with .Values.podSecurityContext }}
securityContext:
{{- toYaml . | nindent 8 }}
{{- end }}
{{- with .Values.global.imagePullSecrets }}
imagePullSecrets:
{{- toYaml . | nindent 8 }}
{{- end }}
{{- if .Values.langflow.enabled }}
initContainers:
- name: wait-for-langflow
image: busybox:1.36
command:
- sh
- -c
- |
echo "Waiting for Langflow to be ready..."
until nc -z {{ include "openrag.fullname" . }}-langflow {{ .Values.langflow.service.port }}; do
echo "Langflow not ready, sleeping 5s..."
sleep 5
done
echo "Langflow is ready!"
{{- end }}
containers:
- name: backend
image: "{{ .Values.backend.image.repository }}:{{ .Values.backend.image.tag | default .Values.global.imageTag }}"
imagePullPolicy: {{ .Values.global.imagePullPolicy }}
{{- with .Values.securityContext }}
securityContext:
{{- toYaml . | nindent 12 }}
{{- end }}
ports:
- name: http
containerPort: 8000
protocol: TCP
env:
# OpenSearch connection (external SaaS)
- name: OPENSEARCH_HOST
value: {{ .Values.global.opensearch.host | quote }}
- name: OPENSEARCH_PORT
value: {{ .Values.global.opensearch.port | quote }}
- name: OPENSEARCH_USERNAME
value: {{ .Values.global.opensearch.username | quote }}
{{- if .Values.global.opensearch.password }}
- name: OPENSEARCH_PASSWORD
valueFrom:
secretKeyRef:
name: {{ include "openrag.fullname" . }}-opensearch
key: password
{{- end }}
# Langflow connection
- name: LANGFLOW_URL
value: {{ include "openrag.langflow.url" . | quote }}
{{- if .Values.backend.langflowPublicUrl }}
- name: LANGFLOW_PUBLIC_URL
value: {{ .Values.backend.langflowPublicUrl | quote }}
{{- end }}
- name: LANGFLOW_AUTO_LOGIN
value: {{ .Values.langflow.auth.autoLogin | quote }}
- name: LANGFLOW_SUPERUSER
valueFrom:
secretKeyRef:
name: {{ include "openrag.fullname" . }}-langflow
key: superuser
- name: LANGFLOW_SUPERUSER_PASSWORD
valueFrom:
secretKeyRef:
name: {{ include "openrag.fullname" . }}-langflow
key: superuser-password
# Flow IDs from ConfigMap
- name: LANGFLOW_CHAT_FLOW_ID
valueFrom:
configMapKeyRef:
name: {{ include "openrag.fullname" . }}-flow-ids
key: chat-flow-id
- name: LANGFLOW_INGEST_FLOW_ID
valueFrom:
configMapKeyRef:
name: {{ include "openrag.fullname" . }}-flow-ids
key: ingest-flow-id
- name: LANGFLOW_URL_INGEST_FLOW_ID
valueFrom:
configMapKeyRef:
name: {{ include "openrag.fullname" . }}-flow-ids
key: url-ingest-flow-id
- name: NUDGES_FLOW_ID
valueFrom:
configMapKeyRef:
name: {{ include "openrag.fullname" . }}-flow-ids
key: nudges-flow-id
# Feature flags
- name: DISABLE_INGEST_WITH_LANGFLOW
value: {{ .Values.backend.features.disableIngestWithLangflow | quote }}
# LLM Provider keys
{{- if .Values.llmProviders.openai.enabled }}
- name: OPENAI_API_KEY
valueFrom:
secretKeyRef:
name: {{ include "openrag.fullname" . }}-llm-providers
key: openai-api-key
{{- end }}
{{- if .Values.llmProviders.anthropic.enabled }}
- name: ANTHROPIC_API_KEY
valueFrom:
secretKeyRef:
name: {{ include "openrag.fullname" . }}-llm-providers
key: anthropic-api-key
{{- end }}
{{- if .Values.llmProviders.watsonx.enabled }}
- name: WATSONX_API_KEY
valueFrom:
secretKeyRef:
name: {{ include "openrag.fullname" . }}-llm-providers
key: watsonx-api-key
- name: WATSONX_ENDPOINT
valueFrom:
secretKeyRef:
name: {{ include "openrag.fullname" . }}-llm-providers
key: watsonx-endpoint
- name: WATSONX_PROJECT_ID
valueFrom:
secretKeyRef:
name: {{ include "openrag.fullname" . }}-llm-providers
key: watsonx-project-id
{{- end }}
{{- if .Values.llmProviders.ollama.enabled }}
- name: OLLAMA_ENDPOINT
value: {{ .Values.llmProviders.ollama.endpoint | quote }}
{{- end }}
# OAuth credentials
{{- if .Values.global.oauth.google.enabled }}
- name: GOOGLE_OAUTH_CLIENT_ID
valueFrom:
secretKeyRef:
name: {{ include "openrag.fullname" . }}-oauth
key: google-client-id
- name: GOOGLE_OAUTH_CLIENT_SECRET
valueFrom:
secretKeyRef:
name: {{ include "openrag.fullname" . }}-oauth
key: google-client-secret
{{- end }}
{{- if .Values.global.oauth.microsoft.enabled }}
- name: MICROSOFT_GRAPH_OAUTH_CLIENT_ID
valueFrom:
secretKeyRef:
name: {{ include "openrag.fullname" . }}-oauth
key: microsoft-client-id
- name: MICROSOFT_GRAPH_OAUTH_CLIENT_SECRET
valueFrom:
secretKeyRef:
name: {{ include "openrag.fullname" . }}-oauth
key: microsoft-client-secret
{{- end }}
# AWS credentials
{{- if .Values.backend.aws.enabled }}
- name: AWS_ACCESS_KEY_ID
valueFrom:
secretKeyRef:
name: {{ include "openrag.fullname" . }}-aws
key: access-key-id
- name: AWS_SECRET_ACCESS_KEY
valueFrom:
secretKeyRef:
name: {{ include "openrag.fullname" . }}-aws
key: secret-access-key
{{- end }}
# Webhook configuration
{{- if .Values.backend.webhook.enabled }}
- name: WEBHOOK_BASE_URL
value: {{ .Values.backend.webhook.baseUrl | quote }}
{{- end }}
volumeMounts:
{{- if .Values.backend.persistence.documents.enabled }}
- name: documents
mountPath: {{ .Values.backend.persistence.documents.mountPath }}
{{- end }}
{{- if .Values.backend.persistence.keys.enabled }}
- name: keys
mountPath: {{ .Values.backend.persistence.keys.mountPath }}
{{- end }}
{{- if .Values.backend.persistence.config.enabled }}
- name: config
mountPath: {{ .Values.backend.persistence.config.mountPath }}
{{- end }}
{{- if .Values.langflow.persistence.enabled }}
- name: flows
mountPath: /app/flows
subPath: {{ .Values.langflow.persistence.flowsSubPath }}
readOnly: true
{{- end }}
resources:
{{- toYaml .Values.backend.resources | nindent 12 }}
{{- if .Values.backend.livenessProbe.enabled }}
livenessProbe:
httpGet:
path: /health
port: http
initialDelaySeconds: {{ .Values.backend.livenessProbe.initialDelaySeconds }}
periodSeconds: {{ .Values.backend.livenessProbe.periodSeconds }}
timeoutSeconds: {{ .Values.backend.livenessProbe.timeoutSeconds }}
failureThreshold: {{ .Values.backend.livenessProbe.failureThreshold }}
{{- end }}
{{- if .Values.backend.readinessProbe.enabled }}
readinessProbe:
httpGet:
path: /health
port: http
initialDelaySeconds: {{ .Values.backend.readinessProbe.initialDelaySeconds }}
periodSeconds: {{ .Values.backend.readinessProbe.periodSeconds }}
timeoutSeconds: {{ .Values.backend.readinessProbe.timeoutSeconds }}
failureThreshold: {{ .Values.backend.readinessProbe.failureThreshold }}
{{- end }}
volumes:
{{- if .Values.backend.persistence.documents.enabled }}
- name: documents
persistentVolumeClaim:
claimName: {{ include "openrag.fullname" . }}-documents
{{- end }}
{{- if .Values.backend.persistence.keys.enabled }}
- name: keys
persistentVolumeClaim:
claimName: {{ include "openrag.fullname" . }}-keys
{{- end }}
{{- if .Values.backend.persistence.config.enabled }}
- name: config
persistentVolumeClaim:
claimName: {{ include "openrag.fullname" . }}-config
{{- end }}
{{- if .Values.langflow.persistence.enabled }}
- name: flows
persistentVolumeClaim:
claimName: {{ include "openrag.fullname" . }}-langflow
{{- end }}
{{- with .Values.nodeSelector }}
nodeSelector:
{{- toYaml . | nindent 8 }}
{{- end }}
{{- with .Values.affinity }}
affinity:
{{- toYaml . | nindent 8 }}
{{- end }}
{{- with .Values.tolerations }}
tolerations:
{{- toYaml . | nindent 8 }}
{{- end }}
{{- end }}

View file

@ -0,0 +1,18 @@
{{- if .Values.backend.enabled }}
apiVersion: v1
kind: Service
metadata:
name: {{ include "openrag.fullname" . }}-backend
namespace: {{ include "openrag.namespace" . }}
labels:
{{- include "openrag.backend.labels" . | nindent 4 }}
spec:
type: {{ .Values.backend.service.type }}
ports:
- port: {{ .Values.backend.service.port }}
targetPort: http
protocol: TCP
name: http
selector:
{{- include "openrag.backend.selectorLabels" . | nindent 4 }}
{{- end }}

View file

@ -0,0 +1,39 @@
apiVersion: v1
kind: ConfigMap
metadata:
name: {{ include "openrag.fullname" . }}-app-config
namespace: {{ include "openrag.namespace" . }}
labels:
{{- include "openrag.labels" . | nindent 4 }}
data:
config.yaml: |
agent:
llm_model: {{ .Values.appConfig.agent.llmModel | quote }}
llm_provider: {{ .Values.appConfig.agent.llmProvider | quote }}
{{- if .Values.appConfig.agent.systemPrompt }}
system_prompt: {{ .Values.appConfig.agent.systemPrompt | quote }}
{{- end }}
edited: false
knowledge:
chunk_overlap: {{ .Values.appConfig.knowledge.chunkOverlap }}
chunk_size: {{ .Values.appConfig.knowledge.chunkSize }}
embedding_model: {{ .Values.appConfig.knowledge.embeddingModel | quote }}
embedding_provider: {{ .Values.appConfig.knowledge.embeddingProvider | quote }}
ocr: {{ .Values.appConfig.knowledge.ocr }}
picture_descriptions: {{ .Values.appConfig.knowledge.pictureDescriptions }}
table_structure: {{ .Values.appConfig.knowledge.tableStructure }}
providers:
anthropic:
configured: {{ .Values.llmProviders.anthropic.enabled }}
ollama:
configured: {{ .Values.llmProviders.ollama.enabled }}
{{- if .Values.llmProviders.ollama.endpoint }}
endpoint: {{ .Values.llmProviders.ollama.endpoint | quote }}
{{- end }}
openai:
configured: {{ .Values.llmProviders.openai.enabled }}
watsonx:
configured: {{ .Values.llmProviders.watsonx.enabled }}
{{- if .Values.llmProviders.watsonx.endpoint }}
endpoint: {{ .Values.llmProviders.watsonx.endpoint | quote }}
{{- end }}

View file

@ -0,0 +1,14 @@
{{- if .Values.langflow.enabled }}
apiVersion: v1
kind: ConfigMap
metadata:
name: {{ include "openrag.fullname" . }}-flow-ids
namespace: {{ include "openrag.namespace" . }}
labels:
{{- include "openrag.labels" . | nindent 4 }}
data:
chat-flow-id: {{ .Values.langflow.flows.chatFlowId | quote }}
ingest-flow-id: {{ .Values.langflow.flows.ingestFlowId | quote }}
url-ingest-flow-id: {{ .Values.langflow.flows.urlIngestFlowId | quote }}
nudges-flow-id: {{ .Values.langflow.flows.nudgesFlowId | quote }}
{{- end }}

View file

@ -0,0 +1,12 @@
{{- if .Values.langflow.flows.loadDefaults }}
apiVersion: v1
kind: ConfigMap
metadata:
name: {{ include "openrag.fullname" . }}-flow-agent
namespace: {{ include "openrag.namespace" . }}
labels:
{{- include "openrag.labels" . | nindent 4 }}
data:
openrag_agent.json: |-
{{ .Files.Get "flows/openrag_agent.json" | indent 4 }}
{{- end }}

View file

@ -0,0 +1,12 @@
{{- if .Values.langflow.flows.loadDefaults }}
apiVersion: v1
kind: ConfigMap
metadata:
name: {{ include "openrag.fullname" . }}-flow-ingestion
namespace: {{ include "openrag.namespace" . }}
labels:
{{- include "openrag.labels" . | nindent 4 }}
data:
ingestion_flow.json: |-
{{ .Files.Get "flows/ingestion_flow.json" | indent 4 }}
{{- end }}

View file

@ -0,0 +1,12 @@
{{- if .Values.langflow.flows.loadDefaults }}
apiVersion: v1
kind: ConfigMap
metadata:
name: {{ include "openrag.fullname" . }}-flow-nudges
namespace: {{ include "openrag.namespace" . }}
labels:
{{- include "openrag.labels" . | nindent 4 }}
data:
openrag_nudges.json: |-
{{ .Files.Get "flows/openrag_nudges.json" | indent 4 }}
{{- end }}

View file

@ -0,0 +1,12 @@
{{- if .Values.langflow.flows.loadDefaults }}
apiVersion: v1
kind: ConfigMap
metadata:
name: {{ include "openrag.fullname" . }}-flow-url
namespace: {{ include "openrag.namespace" . }}
labels:
{{- include "openrag.labels" . | nindent 4 }}
data:
openrag_url_mcp.json: |-
{{ .Files.Get "flows/openrag_url_mcp.json" | indent 4 }}
{{- end }}

View file

@ -0,0 +1,81 @@
{{- if .Values.dashboards.enabled }}
apiVersion: apps/v1
kind: Deployment
metadata:
name: {{ include "openrag.fullname" . }}-dashboards
namespace: {{ include "openrag.namespace" . }}
labels:
{{- include "openrag.dashboards.labels" . | nindent 4 }}
spec:
replicas: {{ .Values.dashboards.replicaCount }}
selector:
matchLabels:
{{- include "openrag.dashboards.selectorLabels" . | nindent 6 }}
template:
metadata:
labels:
{{- include "openrag.dashboards.selectorLabels" . | nindent 8 }}
annotations:
checksum/secret: {{ include (print $.Template.BasePath "/secrets/opensearch-secret.yaml") . | sha256sum }}
spec:
serviceAccountName: {{ include "openrag.serviceAccountName" . }}
{{- with .Values.podSecurityContext }}
securityContext:
{{- toYaml . | nindent 8 }}
{{- end }}
{{- with .Values.global.imagePullSecrets }}
imagePullSecrets:
{{- toYaml . | nindent 8 }}
{{- end }}
containers:
- name: dashboards
image: "{{ .Values.dashboards.image.repository }}:{{ .Values.dashboards.image.tag }}"
imagePullPolicy: {{ .Values.global.imagePullPolicy }}
ports:
- name: http
containerPort: 5601
protocol: TCP
env:
# OpenSearch connection (external SaaS)
- name: OPENSEARCH_HOSTS
value: '["{{ include "openrag.opensearch.url" . }}"]'
- name: OPENSEARCH_USERNAME
value: {{ .Values.global.opensearch.username | quote }}
{{- if .Values.global.opensearch.password }}
- name: OPENSEARCH_PASSWORD
valueFrom:
secretKeyRef:
name: {{ include "openrag.fullname" . }}-opensearch
key: password
{{- end }}
resources:
{{- toYaml .Values.dashboards.resources | nindent 12 }}
{{- if .Values.dashboards.livenessProbe.enabled }}
livenessProbe:
httpGet:
path: /api/status
port: http
initialDelaySeconds: {{ .Values.dashboards.livenessProbe.initialDelaySeconds }}
periodSeconds: {{ .Values.dashboards.livenessProbe.periodSeconds }}
{{- end }}
{{- if .Values.dashboards.readinessProbe.enabled }}
readinessProbe:
httpGet:
path: /api/status
port: http
initialDelaySeconds: {{ .Values.dashboards.readinessProbe.initialDelaySeconds }}
periodSeconds: {{ .Values.dashboards.readinessProbe.periodSeconds }}
{{- end }}
{{- with .Values.nodeSelector }}
nodeSelector:
{{- toYaml . | nindent 8 }}
{{- end }}
{{- with .Values.affinity }}
affinity:
{{- toYaml . | nindent 8 }}
{{- end }}
{{- with .Values.tolerations }}
tolerations:
{{- toYaml . | nindent 8 }}
{{- end }}
{{- end }}

View file

@ -0,0 +1,18 @@
{{- if .Values.dashboards.enabled }}
apiVersion: v1
kind: Service
metadata:
name: {{ include "openrag.fullname" . }}-dashboards
namespace: {{ include "openrag.namespace" . }}
labels:
{{- include "openrag.dashboards.labels" . | nindent 4 }}
spec:
type: {{ .Values.dashboards.service.type }}
ports:
- port: {{ .Values.dashboards.service.port }}
targetPort: http
protocol: TCP
name: http
selector:
{{- include "openrag.dashboards.selectorLabels" . | nindent 4 }}
{{- end }}

View file

@ -0,0 +1,80 @@
{{- if .Values.frontend.enabled }}
apiVersion: apps/v1
kind: Deployment
metadata:
name: {{ include "openrag.fullname" . }}-frontend
namespace: {{ include "openrag.namespace" . }}
labels:
{{- include "openrag.frontend.labels" . | nindent 4 }}
spec:
{{- if not .Values.frontend.autoscaling.enabled }}
replicas: {{ .Values.frontend.replicaCount }}
{{- end }}
selector:
matchLabels:
{{- include "openrag.frontend.selectorLabels" . | nindent 6 }}
template:
metadata:
labels:
{{- include "openrag.frontend.selectorLabels" . | nindent 8 }}
spec:
serviceAccountName: {{ include "openrag.serviceAccountName" . }}
{{- with .Values.podSecurityContext }}
securityContext:
{{- toYaml . | nindent 8 }}
{{- end }}
{{- with .Values.global.imagePullSecrets }}
imagePullSecrets:
{{- toYaml . | nindent 8 }}
{{- end }}
containers:
- name: frontend
image: "{{ .Values.frontend.image.repository }}:{{ .Values.frontend.image.tag | default .Values.global.imageTag }}"
imagePullPolicy: {{ .Values.global.imagePullPolicy }}
{{- with .Values.securityContext }}
securityContext:
{{- toYaml . | nindent 12 }}
{{- end }}
ports:
- name: http
containerPort: 3000
protocol: TCP
env:
# Backend connection (uses internal service name)
- name: OPENRAG_BACKEND_HOST
value: "{{ include "openrag.fullname" . }}-backend"
resources:
{{- toYaml .Values.frontend.resources | nindent 12 }}
{{- if .Values.frontend.livenessProbe.enabled }}
livenessProbe:
httpGet:
path: /
port: http
initialDelaySeconds: {{ .Values.frontend.livenessProbe.initialDelaySeconds }}
periodSeconds: {{ .Values.frontend.livenessProbe.periodSeconds }}
timeoutSeconds: {{ .Values.frontend.livenessProbe.timeoutSeconds }}
failureThreshold: {{ .Values.frontend.livenessProbe.failureThreshold }}
{{- end }}
{{- if .Values.frontend.readinessProbe.enabled }}
readinessProbe:
httpGet:
path: /
port: http
initialDelaySeconds: {{ .Values.frontend.readinessProbe.initialDelaySeconds }}
periodSeconds: {{ .Values.frontend.readinessProbe.periodSeconds }}
timeoutSeconds: {{ .Values.frontend.readinessProbe.timeoutSeconds }}
failureThreshold: {{ .Values.frontend.readinessProbe.failureThreshold }}
{{- end }}
{{- with .Values.nodeSelector }}
nodeSelector:
{{- toYaml . | nindent 8 }}
{{- end }}
{{- with .Values.affinity }}
affinity:
{{- toYaml . | nindent 8 }}
{{- end }}
{{- with .Values.tolerations }}
tolerations:
{{- toYaml . | nindent 8 }}
{{- end }}
{{- end }}

View file

@ -0,0 +1,33 @@
{{- if and .Values.frontend.enabled .Values.frontend.autoscaling.enabled }}
apiVersion: autoscaling/v2
kind: HorizontalPodAutoscaler
metadata:
name: {{ include "openrag.fullname" . }}-frontend
namespace: {{ include "openrag.namespace" . }}
labels:
{{- include "openrag.frontend.labels" . | nindent 4 }}
spec:
scaleTargetRef:
apiVersion: apps/v1
kind: Deployment
name: {{ include "openrag.fullname" . }}-frontend
minReplicas: {{ .Values.frontend.autoscaling.minReplicas }}
maxReplicas: {{ .Values.frontend.autoscaling.maxReplicas }}
metrics:
{{- if .Values.frontend.autoscaling.targetCPUUtilizationPercentage }}
- type: Resource
resource:
name: cpu
target:
type: Utilization
averageUtilization: {{ .Values.frontend.autoscaling.targetCPUUtilizationPercentage }}
{{- end }}
{{- if .Values.frontend.autoscaling.targetMemoryUtilizationPercentage }}
- type: Resource
resource:
name: memory
target:
type: Utilization
averageUtilization: {{ .Values.frontend.autoscaling.targetMemoryUtilizationPercentage }}
{{- end }}
{{- end }}

View file

@ -0,0 +1,18 @@
{{- if .Values.frontend.enabled }}
apiVersion: v1
kind: Service
metadata:
name: {{ include "openrag.fullname" . }}-frontend
namespace: {{ include "openrag.namespace" . }}
labels:
{{- include "openrag.frontend.labels" . | nindent 4 }}
spec:
type: {{ .Values.frontend.service.type }}
ports:
- port: {{ .Values.frontend.service.port }}
targetPort: http
protocol: TCP
name: http
selector:
{{- include "openrag.frontend.selectorLabels" . | nindent 4 }}
{{- end }}

View file

@ -0,0 +1,104 @@
{{- if .Values.ingress.enabled }}
apiVersion: networking.k8s.io/v1
kind: Ingress
metadata:
name: {{ include "openrag.fullname" . }}
namespace: {{ include "openrag.namespace" . }}
labels:
{{- include "openrag.labels" . | nindent 4 }}
{{- with .Values.ingress.annotations }}
annotations:
{{- toYaml . | nindent 4 }}
{{- end }}
{{- if .Values.ingress.tls.certManager.enabled }}
cert-manager.io/cluster-issuer: {{ .Values.ingress.tls.certManager.issuerRef.name }}
{{- end }}
spec:
{{- if .Values.ingress.className }}
ingressClassName: {{ .Values.ingress.className }}
{{- end }}
{{- if .Values.ingress.tls.enabled }}
tls:
{{- if .Values.ingress.hosts.frontend.host }}
- hosts:
- {{ .Values.ingress.hosts.frontend.host }}
secretName: {{ .Values.ingress.tls.secretName | default (printf "%s-frontend-tls" (include "openrag.fullname" .)) }}
{{- end }}
{{- if .Values.ingress.hosts.backend.host }}
- hosts:
- {{ .Values.ingress.hosts.backend.host }}
secretName: {{ .Values.ingress.tls.secretName | default (printf "%s-backend-tls" (include "openrag.fullname" .)) }}
{{- end }}
{{- if and .Values.ingress.hosts.langflow.enabled .Values.ingress.hosts.langflow.host }}
- hosts:
- {{ .Values.ingress.hosts.langflow.host }}
secretName: {{ .Values.ingress.tls.secretName | default (printf "%s-langflow-tls" (include "openrag.fullname" .)) }}
{{- end }}
{{- if and .Values.dashboards.enabled .Values.ingress.hosts.dashboards.enabled .Values.ingress.hosts.dashboards.host }}
- hosts:
- {{ .Values.ingress.hosts.dashboards.host }}
secretName: {{ .Values.ingress.tls.secretName | default (printf "%s-dashboards-tls" (include "openrag.fullname" .)) }}
{{- end }}
{{- end }}
rules:
{{- if .Values.ingress.hosts.frontend.host }}
# Frontend ingress rule
- host: {{ .Values.ingress.hosts.frontend.host }}
http:
paths:
{{- range .Values.ingress.hosts.frontend.paths }}
- path: {{ .path }}
pathType: {{ .pathType }}
backend:
service:
name: {{ include "openrag.fullname" $ }}-frontend
port:
number: {{ $.Values.frontend.service.port }}
{{- end }}
{{- end }}
{{- if .Values.ingress.hosts.backend.host }}
# Backend API ingress rule
- host: {{ .Values.ingress.hosts.backend.host }}
http:
paths:
{{- range .Values.ingress.hosts.backend.paths }}
- path: {{ .path }}
pathType: {{ .pathType }}
backend:
service:
name: {{ include "openrag.fullname" $ }}-backend
port:
number: {{ $.Values.backend.service.port }}
{{- end }}
{{- end }}
{{- if and .Values.ingress.hosts.langflow.enabled .Values.ingress.hosts.langflow.host }}
# Optional Langflow direct access
- host: {{ .Values.ingress.hosts.langflow.host }}
http:
paths:
{{- range .Values.ingress.hosts.langflow.paths }}
- path: {{ .path }}
pathType: {{ .pathType }}
backend:
service:
name: {{ include "openrag.fullname" $ }}-langflow
port:
number: {{ $.Values.langflow.service.port }}
{{- end }}
{{- end }}
{{- if and .Values.dashboards.enabled .Values.ingress.hosts.dashboards.enabled .Values.ingress.hosts.dashboards.host }}
# Optional Dashboards access
- host: {{ .Values.ingress.hosts.dashboards.host }}
http:
paths:
{{- range .Values.ingress.hosts.dashboards.paths }}
- path: {{ .path }}
pathType: {{ .pathType }}
backend:
service:
name: {{ include "openrag.fullname" $ }}-dashboards
port:
number: {{ $.Values.dashboards.service.port }}
{{- end }}
{{- end }}
{{- end }}

View file

@ -0,0 +1,247 @@
{{- if .Values.langflow.enabled }}
apiVersion: apps/v1
kind: Deployment
metadata:
name: {{ include "openrag.fullname" . }}-langflow
namespace: {{ include "openrag.namespace" . }}
labels:
{{- include "openrag.langflow.labels" . | nindent 4 }}
spec:
replicas: 1 # Always 1 for SQLite-based Langflow
strategy:
type: Recreate # Required for RWO PVC
selector:
matchLabels:
{{- include "openrag.langflow.selectorLabels" . | nindent 6 }}
template:
metadata:
labels:
{{- include "openrag.langflow.selectorLabels" . | nindent 8 }}
annotations:
checksum/secret: {{ include (print $.Template.BasePath "/secrets/langflow-secret.yaml") . | sha256sum }}
checksum/config: {{ include (print $.Template.BasePath "/configmaps/flow-ids-configmap.yaml") . | sha256sum }}
spec:
serviceAccountName: {{ include "openrag.serviceAccountName" . }}
{{- with .Values.podSecurityContext }}
securityContext:
{{- toYaml . | nindent 8 }}
{{- end }}
{{- with .Values.global.imagePullSecrets }}
imagePullSecrets:
{{- toYaml . | nindent 8 }}
{{- end }}
{{- if .Values.langflow.flows.loadDefaults }}
initContainers:
- name: load-default-flows
image: busybox:1.36
command:
- /bin/sh
- -c
- |
FLOWS_DIR="{{ .Values.langflow.persistence.mountPath }}/{{ .Values.langflow.persistence.flowsSubPath }}"
mkdir -p "$FLOWS_DIR"
if [ -z "$(ls -A $FLOWS_DIR 2>/dev/null)" ]; then
echo "Loading default flows..."
cp /default-flows/*.json "$FLOWS_DIR/"
echo "Flows loaded: $(ls $FLOWS_DIR)"
else
echo "Flows already exist, skipping."
fi
volumeMounts:
- name: langflow-data
mountPath: {{ .Values.langflow.persistence.mountPath }}
- name: default-flows
mountPath: /default-flows
{{- end }}
containers:
- name: langflow
image: "{{ .Values.langflow.image.repository }}:{{ .Values.langflow.image.tag | default .Values.global.imageTag }}"
imagePullPolicy: {{ .Values.global.imagePullPolicy }}
{{- with .Values.securityContext }}
securityContext:
{{- toYaml . | nindent 12 }}
{{- end }}
ports:
- name: http
containerPort: 7860
protocol: TCP
env:
# Langflow core settings
- name: LANGFLOW_LOAD_FLOWS_PATH
value: {{ .Values.langflow.persistence.mountPath }}/{{ .Values.langflow.persistence.flowsSubPath }}
- name: LANGFLOW_DATABASE_URL
value: "sqlite:///{{ .Values.langflow.persistence.mountPath }}/{{ .Values.langflow.persistence.dbSubPath }}"
- name: LANGFLOW_DEACTIVATE_TRACING
value: {{ .Values.langflow.deactivateTracing | quote }}
- name: LANGFLOW_LOG_LEVEL
value: {{ .Values.langflow.logLevel | quote }}
- name: HIDE_GETTING_STARTED_PROGRESS
value: "true"
# Auth settings
- name: LANGFLOW_AUTO_LOGIN
value: {{ .Values.langflow.auth.autoLogin | quote }}
- name: LANGFLOW_NEW_USER_IS_ACTIVE
value: {{ .Values.langflow.auth.newUserIsActive | quote }}
- name: LANGFLOW_ENABLE_SUPERUSER_CLI
value: {{ .Values.langflow.auth.enableSuperuserCli | quote }}
# Variables to expose to flows
- name: LANGFLOW_VARIABLES_TO_GET_FROM_ENVIRONMENT
value: {{ .Values.langflow.variablesToGetFromEnvironment | quote }}
# Flow context variables (defaults for flow execution)
- name: JWT
value: "None"
- name: OWNER
value: "None"
- name: OWNER_NAME
value: "None"
- name: OWNER_EMAIL
value: "None"
- name: CONNECTOR_TYPE
value: "system"
- name: CONNECTOR_TYPE_URL
value: "url"
- name: OPENRAG-QUERY-FILTER
value: "{}"
- name: FILENAME
value: "None"
- name: MIMETYPE
value: "None"
- name: FILESIZE
value: "0"
- name: SELECTED_EMBEDDING_MODEL
value: ""
# Secrets from langflow secret
- name: LANGFLOW_SECRET_KEY
valueFrom:
secretKeyRef:
name: {{ include "openrag.fullname" . }}-langflow
key: secret-key
- name: LANGFLOW_SUPERUSER
valueFrom:
secretKeyRef:
name: {{ include "openrag.fullname" . }}-langflow
key: superuser
- name: LANGFLOW_SUPERUSER_PASSWORD
valueFrom:
secretKeyRef:
name: {{ include "openrag.fullname" . }}-langflow
key: superuser-password
# OpenSearch password (for flows)
{{- if .Values.global.opensearch.password }}
- name: OPENSEARCH_PASSWORD
valueFrom:
secretKeyRef:
name: {{ include "openrag.fullname" . }}-opensearch
key: password
{{- end }}
# LLM Provider keys
{{- if .Values.llmProviders.openai.enabled }}
- name: OPENAI_API_KEY
valueFrom:
secretKeyRef:
name: {{ include "openrag.fullname" . }}-llm-providers
key: openai-api-key
{{- else }}
- name: OPENAI_API_KEY
value: "None"
{{- end }}
{{- if .Values.llmProviders.anthropic.enabled }}
- name: ANTHROPIC_API_KEY
valueFrom:
secretKeyRef:
name: {{ include "openrag.fullname" . }}-llm-providers
key: anthropic-api-key
{{- else }}
- name: ANTHROPIC_API_KEY
value: "None"
{{- end }}
{{- if .Values.llmProviders.watsonx.enabled }}
- name: WATSONX_API_KEY
valueFrom:
secretKeyRef:
name: {{ include "openrag.fullname" . }}-llm-providers
key: watsonx-api-key
- name: WATSONX_ENDPOINT
valueFrom:
secretKeyRef:
name: {{ include "openrag.fullname" . }}-llm-providers
key: watsonx-endpoint
- name: WATSONX_PROJECT_ID
valueFrom:
secretKeyRef:
name: {{ include "openrag.fullname" . }}-llm-providers
key: watsonx-project-id
{{- else }}
- name: WATSONX_API_KEY
value: "None"
- name: WATSONX_ENDPOINT
value: "None"
- name: WATSONX_PROJECT_ID
value: "None"
{{- end }}
{{- if .Values.llmProviders.ollama.enabled }}
- name: OLLAMA_BASE_URL
value: {{ .Values.llmProviders.ollama.endpoint | quote }}
{{- else }}
- name: OLLAMA_BASE_URL
value: "None"
{{- end }}
volumeMounts:
- name: langflow-data
mountPath: {{ .Values.langflow.persistence.mountPath }}
resources:
{{- toYaml .Values.langflow.resources | nindent 12 }}
{{- if .Values.langflow.livenessProbe.enabled }}
livenessProbe:
httpGet:
path: /health
port: http
initialDelaySeconds: {{ .Values.langflow.livenessProbe.initialDelaySeconds }}
periodSeconds: {{ .Values.langflow.livenessProbe.periodSeconds }}
timeoutSeconds: {{ .Values.langflow.livenessProbe.timeoutSeconds }}
failureThreshold: {{ .Values.langflow.livenessProbe.failureThreshold }}
{{- end }}
{{- if .Values.langflow.readinessProbe.enabled }}
readinessProbe:
httpGet:
path: /health
port: http
initialDelaySeconds: {{ .Values.langflow.readinessProbe.initialDelaySeconds }}
periodSeconds: {{ .Values.langflow.readinessProbe.periodSeconds }}
timeoutSeconds: {{ .Values.langflow.readinessProbe.timeoutSeconds }}
failureThreshold: {{ .Values.langflow.readinessProbe.failureThreshold }}
{{- end }}
volumes:
- name: langflow-data
{{- if .Values.langflow.persistence.enabled }}
persistentVolumeClaim:
claimName: {{ include "openrag.fullname" . }}-langflow
{{- else }}
emptyDir: {}
{{- end }}
{{- if .Values.langflow.flows.loadDefaults }}
- name: default-flows
projected:
sources:
- configMap:
name: {{ include "openrag.fullname" . }}-flow-ingestion
- configMap:
name: {{ include "openrag.fullname" . }}-flow-agent
- configMap:
name: {{ include "openrag.fullname" . }}-flow-nudges
- configMap:
name: {{ include "openrag.fullname" . }}-flow-url
{{- end }}
{{- with .Values.nodeSelector }}
nodeSelector:
{{- toYaml . | nindent 8 }}
{{- end }}
{{- with .Values.affinity }}
affinity:
{{- toYaml . | nindent 8 }}
{{- end }}
{{- with .Values.tolerations }}
tolerations:
{{- toYaml . | nindent 8 }}
{{- end }}
{{- end }}

View file

@ -0,0 +1,18 @@
{{- if .Values.langflow.enabled }}
apiVersion: v1
kind: Service
metadata:
name: {{ include "openrag.fullname" . }}-langflow
namespace: {{ include "openrag.namespace" . }}
labels:
{{- include "openrag.langflow.labels" . | nindent 4 }}
spec:
type: {{ .Values.langflow.service.type }}
ports:
- port: {{ .Values.langflow.service.port }}
targetPort: http
protocol: TCP
name: http
selector:
{{- include "openrag.langflow.selectorLabels" . | nindent 4 }}
{{- end }}

View file

@ -0,0 +1,13 @@
{{- if .Values.backend.aws.enabled }}
apiVersion: v1
kind: Secret
metadata:
name: {{ include "openrag.fullname" . }}-aws
namespace: {{ include "openrag.namespace" . }}
labels:
{{- include "openrag.labels" . | nindent 4 }}
type: Opaque
stringData:
access-key-id: {{ .Values.backend.aws.accessKeyId | quote }}
secret-access-key: {{ .Values.backend.aws.secretAccessKey | quote }}
{{- end }}

View file

@ -0,0 +1,14 @@
{{- if .Values.langflow.enabled }}
apiVersion: v1
kind: Secret
metadata:
name: {{ include "openrag.fullname" . }}-langflow
namespace: {{ include "openrag.namespace" . }}
labels:
{{- include "openrag.labels" . | nindent 4 }}
type: Opaque
stringData:
secret-key: {{ .Values.langflow.auth.secretKey | default (randAlphaNum 32) | quote }}
superuser: {{ .Values.langflow.auth.superuser | quote }}
superuser-password: {{ .Values.langflow.auth.superuserPassword | default (randAlphaNum 16) | quote }}
{{- end }}

View file

@ -0,0 +1,22 @@
{{- if or .Values.llmProviders.openai.enabled .Values.llmProviders.anthropic.enabled .Values.llmProviders.watsonx.enabled }}
apiVersion: v1
kind: Secret
metadata:
name: {{ include "openrag.fullname" . }}-llm-providers
namespace: {{ include "openrag.namespace" . }}
labels:
{{- include "openrag.labels" . | nindent 4 }}
type: Opaque
stringData:
{{- if .Values.llmProviders.openai.enabled }}
openai-api-key: {{ .Values.llmProviders.openai.apiKey | quote }}
{{- end }}
{{- if .Values.llmProviders.anthropic.enabled }}
anthropic-api-key: {{ .Values.llmProviders.anthropic.apiKey | quote }}
{{- end }}
{{- if .Values.llmProviders.watsonx.enabled }}
watsonx-api-key: {{ .Values.llmProviders.watsonx.apiKey | quote }}
watsonx-endpoint: {{ .Values.llmProviders.watsonx.endpoint | quote }}
watsonx-project-id: {{ .Values.llmProviders.watsonx.projectId | quote }}
{{- end }}
{{- end }}

View file

@ -0,0 +1,19 @@
{{- if or .Values.global.oauth.google.enabled .Values.global.oauth.microsoft.enabled }}
apiVersion: v1
kind: Secret
metadata:
name: {{ include "openrag.fullname" . }}-oauth
namespace: {{ include "openrag.namespace" . }}
labels:
{{- include "openrag.labels" . | nindent 4 }}
type: Opaque
stringData:
{{- if .Values.global.oauth.google.enabled }}
google-client-id: {{ .Values.global.oauth.google.clientId | quote }}
google-client-secret: {{ .Values.global.oauth.google.clientSecret | quote }}
{{- end }}
{{- if .Values.global.oauth.microsoft.enabled }}
microsoft-client-id: {{ .Values.global.oauth.microsoft.clientId | quote }}
microsoft-client-secret: {{ .Values.global.oauth.microsoft.clientSecret | quote }}
{{- end }}
{{- end }}

View file

@ -0,0 +1,13 @@
{{- if .Values.global.opensearch.password }}
apiVersion: v1
kind: Secret
metadata:
name: {{ include "openrag.fullname" . }}-opensearch
namespace: {{ include "openrag.namespace" . }}
labels:
{{- include "openrag.labels" . | nindent 4 }}
type: Opaque
stringData:
password: {{ .Values.global.opensearch.password | quote }}
username: {{ .Values.global.opensearch.username | quote }}
{{- end }}

View file

@ -0,0 +1,13 @@
{{- if .Values.serviceAccount.create }}
apiVersion: v1
kind: ServiceAccount
metadata:
name: {{ include "openrag.serviceAccountName" . }}
namespace: {{ include "openrag.namespace" . }}
labels:
{{- include "openrag.labels" . | nindent 4 }}
{{- with .Values.serviceAccount.annotations }}
annotations:
{{- toYaml . | nindent 4 }}
{{- end }}
{{- end }}

View file

@ -0,0 +1,18 @@
{{- if and .Values.backend.enabled .Values.backend.persistence.config.enabled }}
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: {{ include "openrag.fullname" . }}-config
namespace: {{ include "openrag.namespace" . }}
labels:
{{- include "openrag.backend.labels" . | nindent 4 }}
spec:
accessModes:
- {{ .Values.backend.persistence.config.accessMode }}
{{- if .Values.backend.persistence.config.storageClass }}
storageClassName: {{ .Values.backend.persistence.config.storageClass | quote }}
{{- end }}
resources:
requests:
storage: {{ .Values.backend.persistence.config.size }}
{{- end }}

View file

@ -0,0 +1,18 @@
{{- if and .Values.backend.enabled .Values.backend.persistence.documents.enabled }}
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: {{ include "openrag.fullname" . }}-documents
namespace: {{ include "openrag.namespace" . }}
labels:
{{- include "openrag.backend.labels" . | nindent 4 }}
spec:
accessModes:
- {{ .Values.backend.persistence.documents.accessMode }}
{{- if .Values.backend.persistence.documents.storageClass }}
storageClassName: {{ .Values.backend.persistence.documents.storageClass | quote }}
{{- end }}
resources:
requests:
storage: {{ .Values.backend.persistence.documents.size }}
{{- end }}

View file

@ -0,0 +1,18 @@
{{- if and .Values.backend.enabled .Values.backend.persistence.keys.enabled }}
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: {{ include "openrag.fullname" . }}-keys
namespace: {{ include "openrag.namespace" . }}
labels:
{{- include "openrag.backend.labels" . | nindent 4 }}
spec:
accessModes:
- {{ .Values.backend.persistence.keys.accessMode }}
{{- if .Values.backend.persistence.keys.storageClass }}
storageClassName: {{ .Values.backend.persistence.keys.storageClass | quote }}
{{- end }}
resources:
requests:
storage: {{ .Values.backend.persistence.keys.size }}
{{- end }}

View file

@ -0,0 +1,18 @@
{{- if and .Values.langflow.enabled .Values.langflow.persistence.enabled }}
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: {{ include "openrag.fullname" . }}-langflow
namespace: {{ include "openrag.namespace" . }}
labels:
{{- include "openrag.langflow.labels" . | nindent 4 }}
spec:
accessModes:
- {{ .Values.langflow.persistence.accessMode }}
{{- if .Values.langflow.persistence.storageClass }}
storageClassName: {{ .Values.langflow.persistence.storageClass | quote }}
{{- end }}
resources:
requests:
storage: {{ .Values.langflow.persistence.size }}
{{- end }}

408
helm/openrag/values.yaml Normal file
View file

@ -0,0 +1,408 @@
# OpenRAG Helm Chart Values
# This chart deploys OpenRAG with external OpenSearch SaaS connection
# Override names
nameOverride: ""
fullnameOverride: ""
# Global settings
global:
# Tenant identification - used for resource naming and namespace
tenant:
name: "" # Required for multi-tenant: tenant identifier (e.g., "acme")
namespace: "" # Optional: override namespace (defaults to tenant name or release namespace)
# Image settings
imageRegistry: "langflowai"
imagePullPolicy: IfNotPresent
imageTag: "latest" # Override with specific version in production
imagePullSecrets: []
# External OpenSearch SaaS connection (OpenSearch is NOT deployed by this chart)
opensearch:
host: "" # Required: OpenSearch SaaS endpoint (e.g., "my-cluster.us-east-1.es.amazonaws.com")
port: 443 # Default HTTPS port for managed OpenSearch
scheme: "https" # https for production SaaS
username: "admin" # OpenSearch username
password: "" # OpenSearch password (stored in secret)
# Shared OAuth credentials (same across all tenants)
oauth:
google:
enabled: false
clientId: "" # Google OAuth client ID
clientSecret: "" # Google OAuth client secret
microsoft:
enabled: false
clientId: "" # Microsoft Graph OAuth client ID
clientSecret: "" # Microsoft Graph OAuth client secret
# ============================================================================
# Langflow Configuration
# ============================================================================
langflow:
enabled: true
image:
repository: langflowai/openrag-langflow
tag: "" # Uses global.imageTag if empty
# Single pod - vertical scaling only (SQLite requires single writer)
replicaCount: 1
# Resource requests/limits for vertical scaling
resources:
requests:
cpu: "500m"
memory: "1Gi"
limits:
cpu: "4"
memory: "8Gi"
# Persistence for SQLite DB and flows
persistence:
enabled: true
storageClass: "" # Empty uses cluster default
accessMode: ReadWriteOnce
size: 10Gi
mountPath: /app/data
flowsSubPath: flows
dbSubPath: langflow.db
# Flow configuration (UUIDs for Langflow workflows)
flows:
loadDefaults: true # Load default OpenRAG flows on first deployment
chatFlowId: "1098eea1-6649-4e1d-aed1-b77249fb8dd0"
ingestFlowId: "5488df7c-b93f-4f87-a446-b67028bc0813"
urlIngestFlowId: "72c3d17c-2dac-4a73-b48a-6518473d7830"
nudgesFlowId: "ebc01d31-1976-46ce-a385-b0240327226c"
loadPath: /app/flows
# Authentication settings
auth:
autoLogin: false
superuser: "admin" # Langflow superuser username
superuserPassword: "" # Langflow superuser password (stored in secret)
secretKey: "" # Langflow secret key for JWT (stored in secret)
newUserIsActive: false
enableSuperuserCli: false
# Runtime settings
deactivateTracing: true
logLevel: "INFO" # DEBUG, INFO, WARNING, ERROR
# Variables to expose to flows
variablesToGetFromEnvironment: "JWT,OPENRAG-QUERY-FILTER,OPENSEARCH_PASSWORD,OWNER,OWNER_NAME,OWNER_EMAIL,CONNECTOR_TYPE,FILENAME,MIMETYPE,FILESIZE,SELECTED_EMBEDDING_MODEL,OPENAI_API_KEY,ANTHROPIC_API_KEY,WATSONX_API_KEY,WATSONX_ENDPOINT,WATSONX_PROJECT_ID,OLLAMA_BASE_URL"
# Probes
livenessProbe:
enabled: true
initialDelaySeconds: 60
periodSeconds: 30
timeoutSeconds: 10
failureThreshold: 3
readinessProbe:
enabled: true
initialDelaySeconds: 30
periodSeconds: 10
timeoutSeconds: 5
failureThreshold: 3
# Service configuration
service:
type: ClusterIP
port: 7860
# ============================================================================
# OpenRAG Backend Configuration
# ============================================================================
backend:
enabled: true
image:
repository: langflowai/openrag-backend
tag: "" # Uses global.imageTag if empty
# Single pod for vertical scaling
replicaCount: 1
# Resource requests/limits
resources:
requests:
cpu: "500m"
memory: "2Gi"
limits:
cpu: "4"
memory: "16Gi"
# Persistence for documents, keys, and config
persistence:
documents:
enabled: true
storageClass: ""
accessMode: ReadWriteOnce
size: 50Gi
mountPath: /app/openrag-documents
keys:
enabled: true
storageClass: ""
accessMode: ReadWriteOnce
size: 1Gi
mountPath: /app/keys
config:
enabled: true
storageClass: ""
accessMode: ReadWriteOnce
size: 1Gi
mountPath: /app/config
# Feature flags
features:
disableIngestWithLangflow: false # Set true to use traditional processor instead of Langflow
# Langflow public URL (for UI links to Langflow)
langflowPublicUrl: "" # e.g., "https://langflow.example.com"
# Webhook configuration for continuous ingestion
webhook:
enabled: false
baseUrl: "" # DNS routable URL for webhooks (e.g., ngrok URL)
# AWS credentials for S3 integration
aws:
enabled: false
accessKeyId: ""
secretAccessKey: ""
# Probes
livenessProbe:
enabled: true
initialDelaySeconds: 30
periodSeconds: 30
timeoutSeconds: 10
failureThreshold: 3
readinessProbe:
enabled: true
initialDelaySeconds: 15
periodSeconds: 10
timeoutSeconds: 5
failureThreshold: 3
# Service configuration
service:
type: ClusterIP
port: 8000
# ============================================================================
# OpenRAG Frontend Configuration
# ============================================================================
frontend:
enabled: true
image:
repository: langflowai/openrag-frontend
tag: "" # Uses global.imageTag if empty
# Can be multiple replicas (stateless)
replicaCount: 2
# Resource requests/limits
resources:
requests:
cpu: "100m"
memory: "256Mi"
limits:
cpu: "1"
memory: "1Gi"
# Horizontal Pod Autoscaler
autoscaling:
enabled: false
minReplicas: 2
maxReplicas: 10
targetCPUUtilizationPercentage: 70
targetMemoryUtilizationPercentage: 80
# Probes
livenessProbe:
enabled: true
initialDelaySeconds: 30
periodSeconds: 10
timeoutSeconds: 5
failureThreshold: 3
readinessProbe:
enabled: true
initialDelaySeconds: 10
periodSeconds: 5
timeoutSeconds: 3
failureThreshold: 3
# Service configuration
service:
type: ClusterIP
port: 3000
# ============================================================================
# OpenSearch Dashboards Configuration (Optional)
# ============================================================================
dashboards:
enabled: false # Enable only if dashboards available in OS SaaS
image:
repository: opensearchproject/opensearch-dashboards
tag: "3.0.0"
replicaCount: 1
# Resource requests/limits
resources:
requests:
cpu: "100m"
memory: "512Mi"
limits:
cpu: "1"
memory: "2Gi"
# Probes
livenessProbe:
enabled: true
initialDelaySeconds: 60
periodSeconds: 30
readinessProbe:
enabled: true
initialDelaySeconds: 30
periodSeconds: 10
# Service configuration
service:
type: ClusterIP
port: 5601
# ============================================================================
# Ingress Configuration
# ============================================================================
ingress:
enabled: true
className: "nginx" # nginx, alb, traefik, etc.
# Annotations for ingress controller
annotations: {}
# For nginx:
# nginx.ingress.kubernetes.io/proxy-body-size: "100m"
# nginx.ingress.kubernetes.io/proxy-read-timeout: "300"
# For AWS ALB:
# alb.ingress.kubernetes.io/scheme: internet-facing
# alb.ingress.kubernetes.io/target-type: ip
# Host configuration
hosts:
frontend:
host: "" # e.g., "openrag.example.com"
paths:
- path: /
pathType: Prefix
backend:
host: "" # e.g., "api.openrag.example.com"
paths:
- path: /
pathType: Prefix
langflow:
enabled: false # Optional: expose Langflow directly
host: "" # e.g., "langflow.openrag.example.com"
paths:
- path: /
pathType: Prefix
dashboards:
enabled: false # Only if dashboards.enabled is true
host: ""
paths:
- path: /
pathType: Prefix
# TLS configuration
tls:
enabled: false
# Use existing secret:
# secretName: "openrag-tls"
# Or use cert-manager:
certManager:
enabled: false
issuerRef:
name: "letsencrypt-prod"
kind: "ClusterIssuer"
# ============================================================================
# LLM Provider API Keys
# ============================================================================
llmProviders:
openai:
enabled: false
apiKey: "" # OpenAI API key (stored in secret)
anthropic:
enabled: false
apiKey: "" # Anthropic API key (stored in secret)
watsonx:
enabled: false
apiKey: "" # WatsonX API key (stored in secret)
endpoint: "https://us-south.ml.cloud.ibm.com"
projectId: "" # WatsonX project ID
ollama:
enabled: false
endpoint: "" # Ollama endpoint URL (e.g., "http://ollama:11434")
# ============================================================================
# Application Config (config.yaml contents)
# ============================================================================
appConfig:
agent:
llmModel: "claude-sonnet-4-5-20250929"
llmProvider: "anthropic"
# System prompt can be customized here
systemPrompt: "" # Leave empty to use default
knowledge:
chunkOverlap: 200
chunkSize: 1000
embeddingModel: "text-embedding-3-large"
embeddingProvider: "openai"
ocr: false
pictureDescriptions: false
tableStructure: true
# ============================================================================
# Service Account
# ============================================================================
serviceAccount:
create: true
name: ""
annotations: {}
# ============================================================================
# Pod Security
# ============================================================================
podSecurityContext:
fsGroup: 1000
runAsNonRoot: true
securityContext:
allowPrivilegeEscalation: false
readOnlyRootFilesystem: false
runAsUser: 1000
runAsGroup: 1000
# ============================================================================
# Node Placement
# ============================================================================
nodeSelector: {}
tolerations: []
affinity: {}
# ============================================================================
# Pod Disruption Budgets
# ============================================================================
podDisruptionBudget:
enabled: false
minAvailable: 1
# maxUnavailable: 1

View file

@ -21,6 +21,7 @@ from functools import partial
from starlette.applications import Starlette
from starlette.routing import Route
from starlette.responses import JSONResponse
# Set multiprocessing start method to 'spawn' for CUDA compatibility
multiprocessing.set_start_method("spawn", force=True)
@ -456,6 +457,24 @@ async def _ingest_default_documents_langflow(services, file_paths):
file_count=len(file_paths),
)
async def opensearch_health_ready(request):
"""Readiness probe: verifies OpenSearch dependency is reachable."""
try:
# Fast check that the cluster is reachable/auth works
await asyncio.wait_for(clients.opensearch.info(), timeout=5.0)
return JSONResponse(
{"status": "ready", "dependencies": {"opensearch": "up"}},
status_code=200,
)
except Exception as e:
return JSONResponse(
{
"status": "not_ready",
"dependencies": {"opensearch": "down"},
"error": str(e),
},
status_code=503,
)
async def _ingest_default_documents_openrag(services, file_paths):
"""Ingest default documents using traditional OpenRAG processor."""
@ -1148,6 +1167,11 @@ async def create_app():
),
methods=["GET"],
),
Route(
"/search/health",
opensearch_health_ready,
methods=["GET"],
),
# Models endpoints
Route(
"/models/openai",