Dockerfile modification
This commit is contained in:
l.gabrysiak
parent
65850c568b
commit
1fb23b189d
135
Dockerfile
135
Dockerfile
|
|
@ -1,27 +1,20 @@
|
|||
# syntax=docker/dockerfile:1
|
||||
# Initialize device type args
|
||||
# use build args in the docker build command with --build-arg="BUILDARG=true"
|
||||
|
||||
# Argumenty budowania
|
||||
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=""
|
||||
|
||||
# Tiktoken encoding name; models to use can be found at https://huggingface.co/models?library=tiktoken
|
||||
ARG USE_TIKTOKEN_ENCODING_NAME="cl100k_base"
|
||||
|
||||
ARG BUILD_HASH=dev-build
|
||||
# Override at your own risk - non-root configurations are untested
|
||||
ARG UID=0
|
||||
ARG GID=0
|
||||
|
||||
######## WebUI frontend ########
|
||||
# Etap budowania frontendu
|
||||
FROM --platform=$BUILDPLATFORM node:22-alpine3.20 AS build
|
||||
ARG TARGETPLATFORM
|
||||
ARG BUILDPLATFORM
|
||||
ARG BUILD_HASH
|
||||
|
||||
WORKDIR /app
|
||||
|
|
@ -33,10 +26,11 @@ COPY . .
|
|||
ENV APP_BUILD_HASH=${BUILD_HASH}
|
||||
RUN npm run build
|
||||
|
||||
######## WebUI backend ########
|
||||
FROM --platform=$BUILDPLATFORM python:3.11-slim-bookworm AS base
|
||||
# Etap budowania backendu
|
||||
FROM --platform=$TARGETPLATFORM python:3.11-slim-bookworm AS base
|
||||
|
||||
# Use args
|
||||
# Użyj argumentów
|
||||
ARG TARGETPLATFORM
|
||||
ARG USE_CUDA
|
||||
ARG USE_OLLAMA
|
||||
ARG USE_CUDA_VER
|
||||
|
|
@ -45,53 +39,35 @@ ARG USE_RERANKING_MODEL
|
|||
ARG UID
|
||||
ARG GID
|
||||
|
||||
## Basis ##
|
||||
# Ustawienia środowiskowe
|
||||
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=${USE_RERANKING_MODEL}
|
||||
|
||||
## Basis URL Config ##
|
||||
ENV OLLAMA_BASE_URL="/ollama" \
|
||||
OPENAI_API_BASE_URL=""
|
||||
|
||||
## API Key and Security Config ##
|
||||
ENV OPENAI_API_KEY="" \
|
||||
USE_RERANKING_MODEL_DOCKER=${USE_RERANKING_MODEL} \
|
||||
OLLAMA_BASE_URL="/ollama" \
|
||||
OPENAI_API_BASE_URL="" \
|
||||
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"
|
||||
|
||||
## Tiktoken model settings ##
|
||||
ENV TIKTOKEN_ENCODING_NAME="cl100k_base" \
|
||||
TIKTOKEN_CACHE_DIR="/app/backend/data/cache/tiktoken"
|
||||
|
||||
## Hugging Face download cache ##
|
||||
ENV HF_HOME="/app/backend/data/cache/embedding/models"
|
||||
|
||||
## Torch Extensions ##
|
||||
# ENV TORCH_EXTENSIONS_DIR="/.cache/torch_extensions"
|
||||
|
||||
#### Other models ##########################################################
|
||||
ANONYMIZED_TELEMETRY=false \
|
||||
WHISPER_MODEL="base" \
|
||||
WHISPER_MODEL_DIR="/app/backend/data/cache/whisper/models" \
|
||||
RAG_EMBEDDING_MODEL="$USE_EMBEDDING_MODEL" \
|
||||
RAG_RERANKING_MODEL="$USE_RERANKING_MODEL" \
|
||||
SENTENCE_TRANSFORMERS_HOME="/app/backend/data/cache/embedding/models" \
|
||||
TIKTOKEN_ENCODING_NAME="cl100k_base" \
|
||||
TIKTOKEN_CACHE_DIR="/app/backend/data/cache/tiktoken" \
|
||||
HF_HOME="/app/backend/data/cache/embedding/models"
|
||||
|
||||
WORKDIR /app/backend
|
||||
|
||||
ENV HOME=/root
|
||||
# Create user and group if not root
|
||||
|
||||
# Tworzenie użytkownika i grupy, jeśli nie root
|
||||
RUN if [ $UID -ne 0 ]; then \
|
||||
if [ $GID -ne 0 ]; then \
|
||||
addgroup --gid $GID app; \
|
||||
|
|
@ -102,65 +78,40 @@ RUN if [ $UID -ne 0 ]; then \
|
|||
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
|
||||
# Upewnij się, że użytkownik ma dostęp do katalogów
|
||||
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 git build-essential 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 git build-essential 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
|
||||
# Instalacja zależności systemowych
|
||||
RUN apt-get update && \
|
||||
apt-get install -y --no-install-recommends \
|
||||
git build-essential pandoc gcc netcat-openbsd curl jq \
|
||||
python3-dev ffmpeg libsm6 libxext6 && \
|
||||
if [ "$USE_OLLAMA" = "true" ]; then \
|
||||
curl -fsSL https://ollama.com/install.sh | sh; \
|
||||
fi && \
|
||||
rm -rf /var/lib/apt/lists/*
|
||||
|
||||
# install python dependencies
|
||||
# Instalacja zależności Pythona
|
||||
COPY --chown=$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/$USE_CUDA_DOCKER_VER --no-cache-dir && \
|
||||
uv pip install --system -r requirements.txt --no-cache-dir && \
|
||||
python -c "import os; from sentence_transformers import SentenceTransformer; SentenceTransformer(os.environ['RAG_EMBEDDING_MODEL'], device='cpu')" && \
|
||||
python -c "import os; from faster_whisper import WhisperModel; WhisperModel(os.environ['WHISPER_MODEL'], device='cpu', compute_type='int8', download_root=os.environ['WHISPER_MODEL_DIR'])"; \
|
||||
python -c "import os; import tiktoken; tiktoken.get_encoding(os.environ['TIKTOKEN_ENCODING_NAME'])"; \
|
||||
pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/$USE_CUDA_DOCKER_VER --no-cache-dir; \
|
||||
else \
|
||||
pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu --no-cache-dir && \
|
||||
pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu --no-cache-dir; \
|
||||
fi && \
|
||||
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'])"; \
|
||||
python -c "import os; import tiktoken; tiktoken.get_encoding(os.environ['TIKTOKEN_ENCODING_NAME'])"; \
|
||||
fi; \
|
||||
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'])" && \
|
||||
python -c "import os; import tiktoken; tiktoken.get_encoding(os.environ['TIKTOKEN_ENCODING_NAME'])" && \
|
||||
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
|
||||
# Kopiowanie plików frontendowych
|
||||
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
|
||||
# Kopiowanie plików backendowych
|
||||
COPY --chown=$UID:$GID ./backend .
|
||||
|
||||
EXPOSE 8080
|
||||
|
|
|
|||
Loading…
Reference in New Issue