Files
ragflow/helm/values.yaml

235 lines
5.4 KiB
YAML
Raw Permalink Normal View History

# Based on docker compose .env file
# Global image pull secrets configuration
imagePullSecrets: []
env:
# The type of doc engine to use.
# Available options:
# - `elasticsearch` (default)
# - `infinity` (https://github.com/infiniflow/infinity)
# - `opensearch` (https://github.com/opensearch-project/OpenSearch)
# DOC_ENGINE: elasticsearch
DOC_ENGINE: infinity
# DOC_ENGINE: opensearch
# The version of Elasticsearch.
STACK_VERSION: "8.11.3"
# The password for Elasticsearch
ELASTIC_PASSWORD: infini_rag_flow_helm
# The password for OpenSearch.
# At least one uppercase letter, one lowercase letter, one digit, and one special character
OPENSEARCH_PASSWORD: infini_rag_flow_OS_01
# The password for MySQL
MYSQL_PASSWORD: infini_rag_flow_helm
# The database of the MySQL service to use
MYSQL_DBNAME: rag_flow
# The username for MinIO.
MINIO_ROOT_USER: rag_flow
# The password for MinIO
MINIO_PASSWORD: infini_rag_flow_helm
# The password for Redis
REDIS_PASSWORD: infini_rag_flow_helm
# The local time zone.
TZ: "Asia/Shanghai"
# Uncomment the following line if you have limited access to huggingface.co:
# HF_ENDPOINT: https://hf-mirror.com
# The maximum file size for each uploaded file, in bytes.
# You can uncomment this line and update the value if you wish to change 128M file size limit
# MAX_CONTENT_LENGTH: "134217728"
# After making the change, ensure you update `client_max_body_size` in nginx/nginx.conf correspondingly.
Feat: make document parsing and embedding batch sizes configurable via environment variables (#8266) ### Description This PR introduces two new environment variables, ‎`DOC_BULK_SIZE` and ‎`EMBEDDING_BATCH_SIZE`, to allow flexible tuning of batch sizes for document parsing and embedding vectorization in RAGFlow. By making these parameters configurable, users can optimize performance and resource usage according to their hardware capabilities and workload requirements. ### What problem does this PR solve? Previously, the batch sizes for document parsing and embedding were hardcoded, limiting the ability to adjust throughput and memory consumption. This PR enables users to set these values via environment variables (in ‎`.env`, Helm chart, or directly in the deployment environment), improving flexibility and scalability for both small and large deployments. - ‎`DOC_BULK_SIZE`: Controls how many document chunks are processed in a single batch during document parsing (default: 4). - ‎`EMBEDDING_BATCH_SIZE`: Controls how many text chunks are processed in a single batch during embedding vectorization (default: 16). This change updates the codebase, documentation, and configuration files to reflect the new options. ### Type of change - [ ] Bug Fix (non-breaking change which fixes an issue) - [x] New Feature (non-breaking change which adds functionality) - [x] Documentation Update - [ ] Refactoring - [x] Performance Improvement - [ ] Other (please describe): ### Additional context - Updated ‎`.env`, ‎`helm/values.yaml`, and documentation to describe the new variables. - Modified relevant code paths to use the environment variables instead of hardcoded values. - Users can now tune these parameters to achieve better throughput or reduce memory usage as needed. Before: Default value: <img width="643" alt="image" src="https://github.com/user-attachments/assets/086e1173-18f3-419d-a0f5-68394f63866a" /> After: 10x: <img width="777" alt="image" src="https://github.com/user-attachments/assets/5722bbc0-0bcb-4536-b928-077031e550f1" />
2025-06-16 13:40:47 +08:00
# The number of document chunks processed in a single batch during document parsing.
DOC_BULK_SIZE: 4
# The number of text chunks processed in a single batch during embedding vectorization.
EMBEDDING_BATCH_SIZE: 16
ragflow:
image:
repository: infiniflow/ragflow
tag: v0.22.1
pullPolicy: IfNotPresent
pullSecrets: []
# Optional service configuration overrides
# to be written to local.service_conf.yaml
# inside the RAGFlow container
# https://ragflow.io/docs/dev/configurations#service-configuration
service_conf:
# Optional yaml formatted override for the
# llm_factories.json file inside the RAGFlow
# container.
llm_factories:
# factory_llm_infos:
# - name: OpenAI-API-Compatible
# logo: ""
# tags: "LLM,TEXT EMBEDDING,SPEECH2TEXT,MODERATION"
# status: "1"
# llm:
# - llm_name: my-custom-llm
# tags: "LLM,CHAT,"
# max_tokens: 100000
# model_type: chat
# is_tools: false
# Kubernetes configuration
deployment:
strategy:
resources:
service:
# Use LoadBalancer to expose the web interface externally
type: ClusterIP
api:
service:
enabled: true
type: ClusterIP
infinity:
image:
repository: infiniflow/infinity
tag: v0.6.13
pullPolicy: IfNotPresent
pullSecrets: []
storage:
className:
capacity: 5Gi
deployment:
strategy:
resources:
service:
type: ClusterIP
elasticsearch:
image:
repository: elasticsearch
tag: "8.11.3"
pullPolicy: IfNotPresent
pullSecrets: []
initContainers:
alpine:
repository: alpine
tag: latest
pullPolicy: IfNotPresent
busybox:
repository: busybox
tag: latest
pullPolicy: IfNotPresent
storage:
className:
capacity: 20Gi
deployment:
strategy:
resources:
requests:
cpu: "4"
memory: "16Gi"
service:
type: ClusterIP
opensearch:
image:
repository: opensearchproject/opensearch
tag: 2.19.1
pullPolicy: IfNotPresent
pullSecrets: []
initContainers:
alpine:
repository: alpine
tag: latest
pullPolicy: IfNotPresent
busybox:
repository: busybox
tag: latest
pullPolicy: IfNotPresent
storage:
className:
capacity: 20Gi
deployment:
strategy:
resources:
requests:
cpu: "4"
memory: "16Gi"
service:
type: ClusterIP
minio:
image:
repository: quay.io/minio/minio
tag: RELEASE.2023-12-20T01-00-02Z
pullPolicy: IfNotPresent
pullSecrets: []
storage:
className:
capacity: 5Gi
deployment:
strategy:
resources:
service:
type: ClusterIP
mysql:
image:
repository: mysql
tag: 8.0.39
pullPolicy: IfNotPresent
pullSecrets: []
storage:
className:
capacity: 5Gi
deployment:
strategy:
resources:
service:
type: ClusterIP
redis:
image:
repository: valkey/valkey
tag: 8
pullPolicy: IfNotPresent
pullSecrets: []
storage:
className:
capacity: 5Gi
persistence:
enabled: true
# Set's the retention policy for the persistent storage (only available in k8s 1.32 or later)
# https://kubernetes.io/docs/concepts/workloads/controllers/statefulset/#persistentvolumeclaim-retention
# retentionPolicy:
# whenDeleted: Delete
# whenScaled: Delete
deployment:
strategy:
resources:
service:
type: ClusterIP
# This block is for setting up web service ingress. For more information, see:
# https://kubernetes.io/docs/concepts/services-networking/ingress/
ingress:
enabled: false
className: ""
annotations: {}
# kubernetes.io/ingress.class: nginx
# kubernetes.io/tls-acme: "true"
hosts:
- host: chart-example.local
paths:
- path: /
pathType: ImplementationSpecific
tls: []
# - secretName: chart-example-tls
# hosts:
# - chart-example.local