File size: 6,086 Bytes
d1eebad
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
# syntax=docker/dockerfile:1
# Initialize device type args
# use build args in the docker build commmand with --build-arg="BUILDARG=true"
ARG USE_CUDA=false
ARG USE_OLLAMA=false
# Tested with cu117 for CUDA 11 and cu121 for CUDA 12 (default)
ARG USE_CUDA_VER=cu121
# any sentence transformer model; models to use can be found at https://huggingface.co/models?library=sentence-transformers
# Leaderboard: https://huggingface.co/spaces/mteb/leaderboard 
# for better performance and multilangauge support use "intfloat/multilingual-e5-large" (~2.5GB) or "intfloat/multilingual-e5-base" (~1.5GB)
# IMPORTANT: If you change the embedding model (sentence-transformers/all-MiniLM-L6-v2) and vice versa, you aren't able to use RAG Chat with your previous documents loaded in the WebUI! You need to re-embed them.
ARG USE_EMBEDDING_MODEL=sentence-transformers/all-MiniLM-L6-v2
ARG USE_RERANKING_MODEL=""
ARG BUILD_HASH=dev-build
# Override at your own risk - non-root configurations are untested
ARG UID=0
ARG GID=0

######## WebUI frontend ########
FROM --platform=$BUILDPLATFORM node:21-alpine3.19 as build
ARG BUILD_HASH

WORKDIR /app

COPY package.json package-lock.json ./
RUN npm ci

COPY . .
ENV APP_BUILD_HASH=${BUILD_HASH}
RUN npm run build

######## WebUI backend ########
FROM python:3.11-slim-bookworm as base

# Use args
ARG USE_CUDA
ARG USE_OLLAMA
ARG USE_CUDA_VER
ARG USE_EMBEDDING_MODEL
ARG USE_RERANKING_MODEL
ARG UID
ARG GID

## Basis ##
ENV ENV=prod \
    PORT=8080 \
    # pass build args to the build
    USE_OLLAMA_DOCKER=${USE_OLLAMA} \
    USE_CUDA_DOCKER=${USE_CUDA} \
    USE_CUDA_DOCKER_VER=${USE_CUDA_VER} \
    USE_EMBEDDING_MODEL_DOCKER=${USE_EMBEDDING_MODEL} \
    USE_RERANKING_MODEL_DOCKER=${USE_RERANKING_MODEL}

## Basis URL Config ##
ENV OLLAMA_BASE_URL="/ollama" \
    OPENAI_API_BASE_URL=""

## API Key and Security Config ##
ENV OPENAI_API_KEY="" \
    WEBUI_SECRET_KEY="" \
    SCARF_NO_ANALYTICS=true \
    DO_NOT_TRACK=true \
    ANONYMIZED_TELEMETRY=false

#### Other models #########################################################
## whisper TTS model settings ##
ENV WHISPER_MODEL="base" \
    WHISPER_MODEL_DIR="/app/backend/data/cache/whisper/models"

## RAG Embedding model settings ##
ENV RAG_EMBEDDING_MODEL="$USE_EMBEDDING_MODEL_DOCKER" \
    RAG_RERANKING_MODEL="$USE_RERANKING_MODEL_DOCKER" \
    SENTENCE_TRANSFORMERS_HOME="/app/backend/data/cache/embedding/models"

## Hugging Face download cache ##
ENV HF_HOME="/app/backend/data/cache/embedding/models"
#### Other models ##########################################################

WORKDIR /app/backend

ENV HOME /root
# Create user and group if not root
RUN if [ $UID -ne 0 ]; then \
    if [ $GID -ne 0 ]; then \
    addgroup --gid $GID app; \
    fi; \
    adduser --uid $UID --gid $GID --home $HOME --disabled-password --no-create-home app; \
    fi

RUN mkdir -p $HOME/.cache/chroma
RUN echo -n 00000000-0000-0000-0000-000000000000 > $HOME/.cache/chroma/telemetry_user_id

# Make sure the user has access to the app and root directory
RUN chown -R $UID:$GID /app $HOME

RUN if [ "$USE_OLLAMA" = "true" ]; then \
    apt-get update && \
    # Install pandoc and netcat
    apt-get install -y --no-install-recommends pandoc netcat-openbsd curl && \
    apt-get install -y --no-install-recommends gcc python3-dev && \
    # for RAG OCR
    apt-get install -y --no-install-recommends ffmpeg libsm6 libxext6 && \
    # install helper tools
    apt-get install -y --no-install-recommends curl jq && \
    # install ollama
    curl -fsSL https://ollama.com/install.sh | sh && \
    # cleanup
    rm -rf /var/lib/apt/lists/*; \
    else \
    apt-get update && \
    # Install pandoc, netcat and gcc
    apt-get install -y --no-install-recommends pandoc gcc netcat-openbsd curl jq && \
    apt-get install -y --no-install-recommends gcc python3-dev && \
    # for RAG OCR
    apt-get install -y --no-install-recommends ffmpeg libsm6 libxext6 && \
    # cleanup
    rm -rf /var/lib/apt/lists/*; \
    fi

# install python dependencies
COPY --chown=$UID:$GID ./backend/requirements.txt ./requirements.txt

RUN pip3 install uv && \
    if [ "$USE_CUDA" = "true" ]; then \
    # If you use CUDA the whisper and embedding model will be downloaded on first use
    pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/$USE_CUDA_DOCKER_VER --no-cache-dir && \
    uv pip install --system -r requirements.txt --no-cache-dir && \
    python -c "import os; from sentence_transformers import SentenceTransformer; SentenceTransformer(os.environ['RAG_EMBEDDING_MODEL'], device='cpu')" && \
    python -c "import os; from faster_whisper import WhisperModel; WhisperModel(os.environ['WHISPER_MODEL'], device='cpu', compute_type='int8', download_root=os.environ['WHISPER_MODEL_DIR'])"; \
    else \
    pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu --no-cache-dir && \
    uv pip install --system -r requirements.txt --no-cache-dir && \
    python -c "import os; from sentence_transformers import SentenceTransformer; SentenceTransformer(os.environ['RAG_EMBEDDING_MODEL'], device='cpu')" && \
    python -c "import os; from faster_whisper import WhisperModel; WhisperModel(os.environ['WHISPER_MODEL'], device='cpu', compute_type='int8', download_root=os.environ['WHISPER_MODEL_DIR'])"; \
    fi; \
    chown -R $UID:$GID /app/backend/data/



# copy embedding weight from build
# RUN mkdir -p /root/.cache/chroma/onnx_models/all-MiniLM-L6-v2
# COPY --from=build /app/onnx /root/.cache/chroma/onnx_models/all-MiniLM-L6-v2/onnx

# copy built frontend files
COPY --chown=$UID:$GID --from=build /app/build /app/build
COPY --chown=$UID:$GID --from=build /app/CHANGELOG.md /app/CHANGELOG.md
COPY --chown=$UID:$GID --from=build /app/package.json /app/package.json

# copy backend files
COPY --chown=$UID:$GID ./backend .

EXPOSE 8080

HEALTHCHECK CMD curl --silent --fail http://localhost:8080/health | jq -e '.status == true' || exit 1

USER $UID:$GID

ARG BUILD_HASH
ENV WEBUI_BUILD_VERSION=${BUILD_HASH}

CMD [ "bash", "start.sh"]