ragflow/helm/values.yaml

168 lines
4.0 KiB
YAML
Raw Normal View History

# Based on docker compose .env file
env:
# The type of doc engine to use.
# Available options:
# - `elasticsearch` (default)
# - `infinity` (https://github.com/infiniflow/infinity)
# DOC_ENGINE: elasticsearch
DOC_ENGINE: infinity
# The version of Elasticsearch.
STACK_VERSION: "8.11.3"
# The password for Elasticsearch
ELASTIC_PASSWORD: infini_rag_flow_helm
# 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 RAGFlow Docker image to download.
# Defaults to the v0.19.1-slim edition, which is the RAGFlow Docker image without embedding models.
RAGFLOW_IMAGE: infiniflow/ragflow:v0.19.1-slim
#
# To download the RAGFlow Docker image with embedding models, uncomment the following line instead:
# RAGFLOW_IMAGE: infiniflow/ragflow:v0.19.1
#
# The Docker image of the v0.19.1 edition includes:
# - Built-in embedding models:
# - BAAI/bge-large-zh-v1.5
# - BAAI/bge-reranker-v2-m3
# - maidalun1020/bce-embedding-base_v1
# - maidalun1020/bce-reranker-base_v1
# - Embedding models that will be downloaded once you select them in the RAGFlow UI:
# - BAAI/bge-base-en-v1.5
# - BAAI/bge-large-en-v1.5
# - BAAI/bge-small-en-v1.5
# - BAAI/bge-small-zh-v1.5
# - jinaai/jina-embeddings-v2-base-en
# - jinaai/jina-embeddings-v2-small-en
# - nomic-ai/nomic-embed-text-v1.5
# - sentence-transformers/all-MiniLM-L6-v2
#
#
# The local time zone.
TIMEZONE: "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:
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: v0.6.0-dev3
storage:
className:
capacity: 5Gi
deployment:
strategy:
resources:
service:
type: ClusterIP
elasticsearch:
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
storage:
className:
capacity: 5Gi
deployment:
strategy:
resources:
service:
type: ClusterIP
mysql:
image:
repository: mysql
tag: 8.0.39
storage:
className:
capacity: 5Gi
deployment:
strategy:
resources:
service:
type: ClusterIP
redis:
image:
repository: valkey/valkey
tag: 8
storage:
className:
capacity: 5Gi
persistence:
enabled: true
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