jie yang
commited on
Commit
·
67dea7a
1
Parent(s):
d5f7f73
build ragflow image from scratch (#376)
Browse files### What problem does this PR solve?
issue: #205
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
- Dockerfile +20 -20
- Dockerfile.scratch +54 -0
- deepdoc/parser/resume/step_two.py +2 -2
- requirements.txt +1 -1
Dockerfile
CHANGED
@@ -1,20 +1,20 @@
|
|
1 |
-
FROM swr.cn-north-4.myhuaweicloud.com/infiniflow/ragflow-base:v1.0
|
2 |
-
USER root
|
3 |
-
|
4 |
-
WORKDIR /ragflow
|
5 |
-
|
6 |
-
ADD ./web ./web
|
7 |
-
RUN cd ./web && npm i && npm run build
|
8 |
-
|
9 |
-
ADD ./api ./api
|
10 |
-
ADD ./conf ./conf
|
11 |
-
ADD ./deepdoc ./deepdoc
|
12 |
-
ADD ./rag ./rag
|
13 |
-
|
14 |
-
ENV PYTHONPATH=/ragflow/
|
15 |
-
ENV HF_ENDPOINT=https://hf-mirror.com
|
16 |
-
|
17 |
-
ADD docker/entrypoint.sh ./entrypoint.sh
|
18 |
-
RUN chmod +x ./entrypoint.sh
|
19 |
-
|
20 |
-
ENTRYPOINT ["./entrypoint.sh"]
|
|
|
1 |
+
FROM swr.cn-north-4.myhuaweicloud.com/infiniflow/ragflow-base:v1.0
|
2 |
+
USER root
|
3 |
+
|
4 |
+
WORKDIR /ragflow
|
5 |
+
|
6 |
+
ADD ./web ./web
|
7 |
+
RUN cd ./web && npm i && npm run build
|
8 |
+
|
9 |
+
ADD ./api ./api
|
10 |
+
ADD ./conf ./conf
|
11 |
+
ADD ./deepdoc ./deepdoc
|
12 |
+
ADD ./rag ./rag
|
13 |
+
|
14 |
+
ENV PYTHONPATH=/ragflow/
|
15 |
+
ENV HF_ENDPOINT=https://hf-mirror.com
|
16 |
+
|
17 |
+
ADD docker/entrypoint.sh ./entrypoint.sh
|
18 |
+
RUN chmod +x ./entrypoint.sh
|
19 |
+
|
20 |
+
ENTRYPOINT ["./entrypoint.sh"]
|
Dockerfile.scratch
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
FROM ubuntu:22.04
|
2 |
+
USER root
|
3 |
+
|
4 |
+
WORKDIR /ragflow
|
5 |
+
|
6 |
+
RUN apt-get update && apt-get install -y wget curl build-essential libopenmpi-dev
|
7 |
+
|
8 |
+
RUN wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh -O ~/miniconda.sh && \
|
9 |
+
bash ~/miniconda.sh -b -p /root/miniconda3 && \
|
10 |
+
rm ~/miniconda.sh && ln -s /root/miniconda3/etc/profile.d/conda.sh /etc/profile.d/conda.sh && \
|
11 |
+
echo ". /root/miniconda3/etc/profile.d/conda.sh" >> ~/.bashrc && \
|
12 |
+
echo "conda activate base" >> ~/.bashrc
|
13 |
+
|
14 |
+
ENV PATH /root/miniconda3/bin:$PATH
|
15 |
+
|
16 |
+
RUN conda create -y --name py11 python=3.11
|
17 |
+
|
18 |
+
ENV CONDA_DEFAULT_ENV py11
|
19 |
+
ENV CONDA_PREFIX /root/miniconda3/envs/py11
|
20 |
+
ENV PATH $CONDA_PREFIX/bin:$PATH
|
21 |
+
|
22 |
+
RUN curl -sL https://deb.nodesource.com/setup_14.x | bash -
|
23 |
+
RUN apt-get install -y nodejs
|
24 |
+
|
25 |
+
RUN apt-get install -y nginx
|
26 |
+
|
27 |
+
ADD ./web ./web
|
28 |
+
ADD ./api ./api
|
29 |
+
ADD ./conf ./conf
|
30 |
+
ADD ./deepdoc ./deepdoc
|
31 |
+
ADD ./rag ./rag
|
32 |
+
ADD ./requirements.txt ./requirements.txt
|
33 |
+
|
34 |
+
RUN apt install openmpi-bin openmpi-common libopenmpi-dev
|
35 |
+
ENV LD_LIBRARY_PATH /usr/lib/x86_64-linux-gnu/openmpi/lib:$LD_LIBRARY_PATH
|
36 |
+
RUN rm /root/miniconda3/envs/py11/compiler_compat/ld
|
37 |
+
RUN cd ./web && npm i && npm run build
|
38 |
+
RUN conda run -n py11 pip install -i https://mirrors.aliyun.com/pypi/simple/ -r ./requirements.txt
|
39 |
+
|
40 |
+
RUN apt-get update && \
|
41 |
+
apt-get install -y libglib2.0-0 libgl1-mesa-glx && \
|
42 |
+
rm -rf /var/lib/apt/lists/*
|
43 |
+
|
44 |
+
RUN conda run -n py11 pip install -i https://mirrors.aliyun.com/pypi/simple/ ollama
|
45 |
+
RUN conda run -n py11 python -m nltk.downloader punkt
|
46 |
+
RUN conda run -n py11 python -m nltk.downloader wordnet
|
47 |
+
|
48 |
+
ENV PYTHONPATH=/ragflow/
|
49 |
+
ENV HF_ENDPOINT=https://hf-mirror.com
|
50 |
+
|
51 |
+
ADD docker/entrypoint.sh ./entrypoint.sh
|
52 |
+
RUN chmod +x ./entrypoint.sh
|
53 |
+
|
54 |
+
ENTRYPOINT ["./entrypoint.sh"]
|
deepdoc/parser/resume/step_two.py
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
# -*- coding: utf-8 -*-
|
2 |
-
import re, copy, time, datetime,
|
3 |
traceback, signal
|
4 |
import numpy as np
|
5 |
from deepdoc.parser.resume.entities import degrees, schools, corporations
|
@@ -197,7 +197,7 @@ def forProj(cv):
|
|
197 |
|
198 |
|
199 |
def json_loads(line):
|
200 |
-
return
|
201 |
|
202 |
|
203 |
def forWork(cv):
|
|
|
1 |
# -*- coding: utf-8 -*-
|
2 |
+
import re, copy, time, datetime, demjson3, \
|
3 |
traceback, signal
|
4 |
import numpy as np
|
5 |
from deepdoc.parser.resume.entities import degrees, schools, corporations
|
|
|
197 |
|
198 |
|
199 |
def json_loads(line):
|
200 |
+
return demjson3.decode(re.sub(r": *(True|False)", r": '\1'", line))
|
201 |
|
202 |
|
203 |
def forWork(cv):
|
requirements.txt
CHANGED
@@ -19,7 +19,7 @@ cryptography==42.0.5
|
|
19 |
dashscope==1.14.1
|
20 |
datasets==2.17.1
|
21 |
datrie==0.8.2
|
22 |
-
|
23 |
dill==0.3.8
|
24 |
distro==1.9.0
|
25 |
elastic-transport==8.12.0
|
|
|
19 |
dashscope==1.14.1
|
20 |
datasets==2.17.1
|
21 |
datrie==0.8.2
|
22 |
+
demjson3==3.0.6
|
23 |
dill==0.3.8
|
24 |
distro==1.9.0
|
25 |
elastic-transport==8.12.0
|