update back dockerfile and vit config

Dockerfile

@@ -1,103 +1,176 @@
 # syntax=docker/dockerfile:1
-
-# Аргументы сборки
+# Initialize device type args
+# use build args in the docker build command 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_TIKTOKEN_ENCODING_NAME=cl100k_base
+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
 
-# Этап сборки фронтенда
-FROM node:22-alpine3.20 AS build
+######## WebUI frontend ########
+FROM --platform=$BUILDPLATFORM node:22-alpine3.20 AS build
 ARG BUILD_HASH
 
 WORKDIR /app
+
 COPY package.json package-lock.json ./
-RUN npm ci --production --ignore-scripts --prefer-offline && \
-    npm cache clean --force
+RUN npm ci
 
 COPY . .
 ENV APP_BUILD_HASH=${BUILD_HASH}
-RUN npm run build -- --max-workers=2 && \
-    rm -rf /app/src /root/.npm
+RUN npm run build
 
-# Основной этап сборки бэкенда
+######## 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} \
-    RAG_EMBEDDING_MODEL=${USE_EMBEDDING_MODEL} \
-    WHISPER_MODEL="base" \
-    WHISPER_MODEL_DIR="/app/backend/data/cache/whisper/models" \
-    SENTENCE_TRANSFORMERS_HOME="/app/backend/data/cache/embedding/models" \
-    TIKTOKEN_ENCODING_NAME=${USE_TIKTOKEN_ENCODING_NAME} \
-    TIKTOKEN_CACHE_DIR="/app/backend/data/cache/tiktoken" \
-    HF_HOME="/app/backend/data/cache/embedding/models" \
-    OLLAMA_BASE_URL="/ollama" \
-    OPENAI_API_BASE_URL="" \
-    OPENAI_API_KEY="" \
+    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"
+
+## 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 ##########################################################
+
 WORKDIR /app/backend
-ENV HOME=/root
 
-# Создание пользователя, если не root
-RUN if [ "$UID" -ne 0 ]; then \
-    if [ "$GID" -ne 0 ]; then addgroup --gid $GID app; fi; \
+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
 
-# Установка базовых зависимостей
-RUN apt-get update && \
-    apt-get install -y --no-install-recommends git build-essential pandoc gcc netcat-openbsd curl jq && \
-    apt-get install -y --no-install-recommends python3-dev ffmpeg libsm6 libxext6 && \
-    rm -rf /var/lib/apt/lists/*
+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
 
-# Установка Ollama, если требуется
 RUN if [ "$USE_OLLAMA" = "true" ]; then \
-    curl -fsSL https://ollama.com/install.sh | sh; \
+    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
 
-# Установка Python-зависимостей
+# install python dependencies
 COPY --chown=$UID:$GID ./backend/requirements.txt ./requirements.txt
-RUN pip3 install uv && \
-    pip3 install torch==2.0.0+cpu torchvision==0.15.0+cpu torchaudio==2.0.0+cpu --index-url https://download.pytorch.org/whl/cpu && \
-    uv pip install --system -r requirements.txt --no-deps && \
-    rm -rf /root/.cache/pip
 
-# Копирование собранного фронтенда
+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'])"; \
+    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'])"; \
+    python -c "import os; import tiktoken; tiktoken.get_encoding(os.environ['TIKTOKEN_ENCODING_NAME'])"; \
+    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
 
-# Копирование бэкенда
+# copy backend files
 COPY --chown=$UID:$GID ./backend .
 
-# Права доступа
-RUN mkdir -p $HOME/.cache/chroma && \
-    echo -n 00000000-0000-0000-0000-000000000000 > $HOME/.cache/chroma/telemetry_user_id && \
-    chown -R $UID:$GID /app $HOME
-
 EXPOSE 8080
+
+HEALTHCHECK CMD curl --silent --fail http://localhost:${PORT:-8080}/health | jq -ne 'input.status == true' || exit 1
+
 USER $UID:$GID
+
 ARG BUILD_HASH
-ENV WEBUI_BUILD_VERSION=${BUILD_HASH} \
-    DOCKER=true
+ENV WEBUI_BUILD_VERSION=${BUILD_HASH}
+ENV DOCKER=true
 
-CMD ["bash", "start.sh"]
+CMD [ "bash", "start.sh"]

vite.config.ts

@@ -35,21 +35,9 @@ export default defineConfig({
 		APP_BUILD_HASH: JSON.stringify(process.env.APP_BUILD_HASH || 'dev-build')
 	},
 	build: {
-    rollupOptions: {
-      maxParallelFileOps: 5, // Уменьшить количество параллельных операций
-      output: {
-        manualChunks: (id) => {
-          if (id.includes('node_modules')) {
-            return 'vendor'; // Разделить зависимости в отдельный чанк
-          }
-        },
-      },
-    },
-    minify: 'esbuild', // Быстрая минимизация
-    target: 'esnext', // Уменьшить объем трансформации
-  },
+		sourcemap: true
+	},
 	worker: {
 		format: 'es'
-	},
-	sourceMap: true
+	}
 });