Rework Dockerfile.scratch (#2525)

### What problem does this PR solve?

Rework Dockerfile.scratch
- Multiple stage Dockerfile
- Removed conda
- Replaced pip with poetry
- Added missing dependencies and fixed package version conflicts
- Added deepdoc models

### Type of change

- [x] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):

Dockerfile.scratch

@@ -1,56 +1,91 @@
-FROM ubuntu:22.04
+# base stage
+FROM ubuntu:24.04 AS base
 USER root
 
 WORKDIR /ragflow
 
-RUN apt-get update && apt-get install -y wget curl build-essential libopenmpi-dev
+RUN rm -f /etc/apt/apt.conf.d/docker-clean \
+    && echo 'Binary::apt::APT::Keep-Downloaded-Packages "true";' > /etc/apt/apt.conf.d/keep-cache
 
-RUN wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh -O ~/miniconda.sh && \
-    bash ~/miniconda.sh -b -p /root/miniconda3 && \
-    rm ~/miniconda.sh && ln -s /root/miniconda3/etc/profile.d/conda.sh /etc/profile.d/conda.sh && \
-    echo ". /root/miniconda3/etc/profile.d/conda.sh" >> ~/.bashrc && \
-    echo "conda activate base" >> ~/.bashrc
+RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
+    apt update && apt-get --no-install-recommends install -y ca-certificates
 
-ENV PATH /root/miniconda3/bin:$PATH
+# if you located in China, you can use tsinghua mirror to speed up apt
+RUN  sed -i 's|http://archive.ubuntu.com|https://mirrors.tuna.tsinghua.edu.cn|g' /etc/apt/sources.list.d/ubuntu.sources
 
-RUN conda create -y --name py11 python=3.11
+RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
+    apt update && apt install -y curl libpython3-dev nginx openmpi-bin openmpi-common libopenmpi-dev libglib2.0-0 libglx-mesa0 \
+    && rm -rf /var/lib/apt/lists/* \
+    && curl -sSL https://install.python-poetry.org | python3 -
 
-ENV CONDA_DEFAULT_ENV py11
-ENV CONDA_PREFIX /root/miniconda3/envs/py11
-ENV PATH $CONDA_PREFIX/bin:$PATH
+ENV PYTHONDONTWRITEBYTECODE=1 LD_LIBRARY_PATH=usr/lib/x86_64-linux-gnu/openmpi/lib:$LD_LIBRARY_PATH
 
-RUN curl -sL https://deb.nodesource.com/setup_14.x | bash -
-RUN apt-get install -y nodejs
+# Configure Poetry
+ENV POETRY_NO_INTERACTION=1
+ENV POETRY_VIRTUALENVS_IN_PROJECT=true
+ENV POETRY_VIRTUALENVS_CREATE=true
+ENV POETRY_REQUESTS_TIMEOUT=15
 
-RUN apt-get install -y nginx
+# builder stage
+FROM base AS builder
+USER root
+
+WORKDIR /ragflow
+
+RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
+    apt update && apt install -y nodejs npm && \
+    rm -rf /var/lib/apt/lists/*
+
+# if you located in China, you can use taobao registry to speed up npm and yarn
+RUN npm config set registry https://registry.npmmirror.com/
+
+# https://yarnpkg.com/getting-started/install
+COPY web web
+RUN cd web && npm install -g corepack && corepack enable && yarn install && yarn run build
 
-ADD ./web ./web
-ADD ./api ./api
-ADD ./conf ./conf
-ADD ./deepdoc ./deepdoc
-ADD ./rag ./rag
-ADD ./requirements.txt ./requirements.txt
-ADD ./agent ./agent
-ADD ./graphrag ./graphrag
+# install dependencies from poetry.lock file
+COPY pyproject.toml poetry.toml poetry.lock ./
+RUN --mount=type=cache,target=/root/.cache/pypoetry,sharing=locked \
+    /root/.local/bin/poetry install --sync --no-cache --no-root
 
-RUN apt install openmpi-bin openmpi-common libopenmpi-dev
-ENV LD_LIBRARY_PATH /usr/lib/x86_64-linux-gnu/openmpi/lib:$LD_LIBRARY_PATH
-RUN rm /root/miniconda3/envs/py11/compiler_compat/ld
-RUN cd ./web && npm i --force && npm run build
-RUN conda run -n py11 pip install -i https://mirrors.aliyun.com/pypi/simple/ -r ./requirements.txt
+# production stage
+FROM base AS production
+USER root
+
+WORKDIR /ragflow
 
-RUN apt-get update && \
-    apt-get install -y libglib2.0-0 libgl1-mesa-glx && \
+# Install python packages' dependencies
+# cv2 requires libGL.so.1
+RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
+    apt update && apt install -y --no-install-recommends nginx libgl1 vim less && \
     rm -rf /var/lib/apt/lists/*
 
-RUN conda run -n py11 pip install -i https://mirrors.aliyun.com/pypi/simple/ ollama
-RUN conda run -n py11 python -m nltk.downloader punkt
-RUN conda run -n py11 python -m nltk.downloader wordnet
+COPY web web
+COPY api api
+COPY conf conf
+COPY deepdoc deepdoc
+COPY rag rag
+COPY agent agent
+COPY graphrag graphrag
+COPY pyproject.toml poetry.toml poetry.lock ./
+
+# Copy compiled web pages
+COPY --from=builder /ragflow/web/dist /ragflow/web/dist
+
+# Copy Python environment and packages
+ENV VIRTUAL_ENV=/ragflow/.venv
+COPY --from=builder ${VIRTUAL_ENV} ${VIRTUAL_ENV}
+ENV PATH="${VIRTUAL_ENV}/bin:/root/.local/bin:${PATH}"
+
+# Download nltk data
+RUN python3 -m nltk.downloader wordnet punkt punkt_tab
+
+# Copy models downloaded via download_deps.sh
+COPY det.onnx layout.laws.onnx layout.manual.onnx layout.onnx layout.paper.onnx ocr.res rec.onnx tsr.onnx updown_concat_xgb.model /ragflow/rag/res/deepdoc/
 
 ENV PYTHONPATH=/ragflow/
-ENV HF_ENDPOINT=https://hf-mirror.com
 
-ADD docker/entrypoint.sh ./entrypoint.sh
+COPY docker/entrypoint.sh ./entrypoint.sh
 RUN chmod +x ./entrypoint.sh
 
 ENTRYPOINT ["./entrypoint.sh"]

api/ragflow_server.py

@@ -46,7 +46,7 @@ def update_progress():
 
 
 if __name__ == '__main__':
-    print("""
+    print(r"""
     ____                 ______ __               
    / __ \ ____ _ ____ _ / ____// /____  _      __
   / /_/ // __ `// __ `// /_   / // __ \| | /| / /

docker/.env

@@ -33,10 +33,13 @@ REDIS_PASSWORD=infini_rag_flow
 
 SVR_HTTP_PORT=9380
 
-RAGFLOW_VERSION=dev
+RAGFLOW_VERSION=poetry
 
 TIMEZONE='Asia/Shanghai'
 
+# Inside GFW, we need the following huggingface.co mirror:
+HF_ENDPOINT=https://hf-mirror.com
+
 ######## OS setup for ES ###########
 # sysctl vm.max_map_count
 # sudo sysctl -w vm.max_map_count=262144

docker/docker-compose.yml

@@ -15,6 +15,7 @@ services:
       - ${SVR_HTTP_PORT}:9380
       - 80:80
       - 443:443
+      - 5678:5678
     volumes:
       - ./service_conf.yaml:/ragflow/conf/service_conf.yaml
       - ./ragflow-logs:/ragflow/logs
@@ -23,7 +24,7 @@ services:
       - ./nginx/nginx.conf:/etc/nginx/nginx.conf
     environment:
       - TZ=${TIMEZONE}
-      - HF_ENDPOINT=https://huggingface.co
+      - HF_ENDPOINT=${HF_ENDPOINT}
       - MACOS=${MACOS}
     networks:
       - ragflow

download_deps.sh

@@ -0,0 +1,38 @@
+#!/usr/bin/env bash
+
+download()
+{
+    echo "download $1"
+    # https://stackoverflow.com/questions/3162385/how-to-split-a-string-in-shell-and-get-the-last-field
+    fn=${1##*/}
+    if [ ! -f $fn ] ; then
+        wget --no-check-certificate $1
+    fi
+}
+
+# https://stackoverflow.com/questions/24628076/convert-multiline-string-to-array
+names="https://huggingface.co/InfiniFlow/deepdoc/resolve/main/det.onnx
+https://huggingface.co/InfiniFlow/deepdoc/resolve/main/layout.laws.onnx
+https://huggingface.co/InfiniFlow/deepdoc/resolve/main/layout.manual.onnx
+https://huggingface.co/InfiniFlow/deepdoc/resolve/main/layout.onnx
+https://huggingface.co/InfiniFlow/deepdoc/resolve/main/layout.paper.onnx
+https://huggingface.co/InfiniFlow/deepdoc/resolve/main/ocr.res
+https://huggingface.co/InfiniFlow/deepdoc/resolve/main/rec.onnx
+https://huggingface.co/InfiniFlow/deepdoc/resolve/main/tsr.onnx
+https://huggingface.co/InfiniFlow/text_concat_xgb_v1.0/resolve/main/updown_concat_xgb.model"
+
+SAVEIFS=$IFS   # Save current IFS (Internal Field Separator)
+IFS=$'\n'      # Change IFS to newline char
+names=($names) # split the `names` string into an array by the same name
+IFS=$SAVEIFS   # Restore original IFS
+
+find . -size 0 | xargs rm -f
+# https://stackoverflow.com/questions/15466808/shell-iterate-over-array
+for ((i=0; i<${#names[@]}; i+=1)); do
+    url="${names[$i]}"
+    download $url
+    if [ $? != 0 ]; then
+	exit -1
+    fi
+done
+find . -size 0 | xargs rm -f

poetry.toml

@@ -0,0 +1,4 @@
+[virtualenvs]
+in-project = true
+create = true
+prefer-active-python = true

pyproject.toml

@@ -0,0 +1,129 @@
+[tool.poetry]
+name = "ragflow"
+version = "0.11.0"
+description = "[RAGFlow](https://ragflow.io/) is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding. It offers a streamlined RAG workflow for businesses of any scale, combining LLM (Large Language Models) to provide truthful question-answering capabilities, backed by well-founded citations from various complex formatted data."
+authors = ["Your Name <you@example.com>"]
+license = "https://github.com/infiniflow/ragflow/blob/main/LICENSE"
+readme = "README.md"
+package-mode = false
+
+[tool.poetry.dependencies]
+python = ">=3.12,<3.13"
+datrie = "0.8.2"
+akshare = "1.14.72"
+azure-storage-blob = "12.22.0"
+azure-identity = "1.17.1"
+azure-storage-file-datalake = "12.16.0"
+anthropic = "=0.34.1"
+arxiv = "2.1.3"
+aspose-slides = "24.8.0"
+bcembedding = "0.1.3"
+bio = "1.7.1"
+boto3 = "1.34.140"
+botocore = "1.34.140"
+cachetools = "5.3.3"
+chardet = "5.2.0"
+cn2an = "0.5.22"
+cohere = "5.6.2"
+dashscope = "1.14.1"
+deepl = "1.18.0"
+demjson3 = "3.0.6"
+discord-py = "2.3.2"
+duckduckgo-search = "6.1.9"
+editdistance = "0.8.1"
+elastic-transport = "8.12.0"
+elasticsearch = "8.12.1"
+elasticsearch-dsl = "8.12.0"
+fastembed = "^0.3.6"
+fasttext = "0.9.3"
+filelock = "3.15.4"
+flagembedding = "1.2.10"
+flask = "3.0.3"
+flask-cors = "5.0.0"
+flask-login = "0.6.3"
+flask-session = "0.8.0"
+google-search-results = "2.4.2"
+groq = "0.9.0"
+hanziconv = "0.3.2"
+html-text = "0.6.2"
+httpx = "0.27.0"
+huggingface-hub = "^0.25.0"
+infinity-emb = "0.0.51"
+itsdangerous = "2.1.2"
+markdown = "3.6"
+markdown-to-json = "2.1.1"
+minio = "7.2.4"
+mistralai = "0.4.2"
+nltk = "3.9.1"
+numpy = "1.26.4"
+ollama = "0.2.1"
+onnxruntime = "1.17.3"
+onnxruntime-gpu = "1.17.1"
+openai = "1.12.0"
+opencv-python = "4.9.0.80"
+opencv-python-headless = "4.9.0.80"
+openpyxl = "3.1.2"
+ormsgpack = "1.5.0"
+pandas = "2.2.2"
+pdfplumber = "0.10.4"
+peewee = "3.17.1"
+pillow = "10.3.0"
+protobuf = "5.27.2"
+psycopg2-binary = "2.9.9"
+pyclipper = "1.3.0.post5"
+pycryptodomex = "3.20.0"
+pypdf = "^5.0.0"
+pytest = "8.2.2"
+python-dotenv = "1.0.1"
+python-dateutil = "2.8.2"
+python-pptx = "0.6.23"
+pywencai = "0.12.2"
+qianfan = "0.4.6"
+ranx = "0.3.20"
+readability-lxml = "0.8.1"
+redis = "5.0.3"
+requests = "2.32.2"
+replicate = "0.31.0"
+roman-numbers = "1.0.2"
+ruamel-base = "1.0.0"
+scholarly = "1.7.11"
+scikit-learn = "1.5.0"
+selenium = "4.22.0"
+setuptools = "70.0.0"
+shapely = "2.0.5"
+six = "1.16.0"
+strenum = "0.4.15"
+tabulate = "0.9.0"
+tencentcloud-sdk-python = "3.0.1215"
+tika = "2.6.0"
+tiktoken = "0.6.0"
+torch = "2.3.0"
+transformers = "4.38.1"
+umap = "0.1.1"
+vertexai = "1.64.0"
+volcengine = "1.0.146"
+voyageai = "0.2.3"
+webdriver-manager = "4.0.1"
+werkzeug = "3.0.3"
+wikipedia = "1.4.0"
+word2number = "1.1"
+xgboost = "2.1.0"
+xpinyin = "0.7.6"
+yfinance = "0.1.96"
+zhipuai = "2.0.1"
+ruamel-yaml = "^0.18.6"
+google-generativeai = "^0.8.1"
+python-docx = "^1.1.2"
+pypdf2 = "^3.0.1"
+graspologic = "^3.4.1"
+pymysql = "^1.1.1"
+
+
+[[tool.poetry.source]]
+name = "tsinghua"
+url = "https://pypi.tuna.tsinghua.edu.cn/simple/"
+priority = "primary"
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"

requirements.txt

@@ -4,7 +4,7 @@ azure-identity==1.17.1
 azure-storage-file-datalake==12.16.0
 anthropic===0.34.1
 arxiv==2.1.3
-Aspose.Slides==24.2.0
+Aspose.Slides==24.8.0
 BCEmbedding==0.1.3
 Bio==1.7.1
 boto3==1.34.140
@@ -43,7 +43,7 @@ Markdown==3.6
 markdown_to_json==2.1.1
 minio==7.2.4
 mistralai==0.4.2
-nltk==3.9
+nltk==3.9.1
 numpy==1.26.4
 ollama==0.2.1
 onnxruntime==1.17.3
@@ -57,7 +57,6 @@ pandas==2.2.2
 pdfplumber==0.10.4
 peewee==3.17.1
 Pillow==10.3.0
-pipreqs==0.5.0
 protobuf==5.27.2
 psycopg2-binary==2.9.9
 pyclipper==1.3.0.post5

ubuntu.sources

@@ -0,0 +1,39 @@
+Types: deb
+URIs: https://mirrors.tuna.tsinghua.edu.cn/ubuntu
+Suites: noble noble-updates noble-backports
+Components: main restricted universe multiverse
+Signed-By: /usr/share/keyrings/ubuntu-archive-keyring.gpg
+
+# 默认注释了源码镜像以提高 apt update 速度，如有需要可自行取消注释
+# Types: deb-src
+# URIs: https://mirrors.tuna.tsinghua.edu.cn/ubuntu
+# Suites: noble noble-updates noble-backports
+# Components: main restricted universe multiverse
+# Signed-By: /usr/share/keyrings/ubuntu-archive-keyring.gpg
+
+# 以下安全更新软件源包含了官方源与镜像站配置，如有需要可自行修改注释切换
+Types: deb
+URIs: https://mirrors.tuna.tsinghua.edu.cn/ubuntu
+Suites: noble-security
+Components: main restricted universe multiverse
+Signed-By: /usr/share/keyrings/ubuntu-archive-keyring.gpg
+
+# Types: deb-src
+# URIs: https://mirrors.tuna.tsinghua.edu.cn/ubuntu
+# Suites: noble-security
+# Components: main restricted universe multiverse
+# Signed-By: /usr/share/keyrings/ubuntu-archive-keyring.gpg
+
+# 预发布软件源，不建议启用
+
+# Types: deb
+# URIs: https://mirrors.tuna.tsinghua.edu.cn/ubuntu
+# Suites: noble-proposed
+# Components: main restricted universe multiverse
+# Signed-By: /usr/share/keyrings/ubuntu-archive-keyring.gpg
+
+# # Types: deb-src
+# # URIs: https://mirrors.tuna.tsinghua.edu.cn/ubuntu
+# # Suites: noble-proposed
+# # Components: main restricted universe multiverse
+# # Signed-By: /usr/share/keyrings/ubuntu-archive-keyring.gpg

web/package.json

@@ -8,7 +8,7 @@
     "lint": "umi lint --eslint-only",
     "prepare": "cd .. && husky web/.husky",
     "setup": "umi setup",
-    "start": "npm run dev",
+    "start": "yarn dev",
     "test": "jest --no-cache --coverage"
   },
   "lint-staged": {