tdpeuter/open-webui
tdpeuter/open-webui
1
Fork 0
forked from open-webui/open-webui
Code Issues Pull requests 1 Projects 1 Releases 2 Packages 1 Activity Actions

feat: hybrid search and reranking support

Browse source
This commit is contained in:
Steven Kreitzer 2024-04-22 18:36:46 -05:00
parent db801aee79
commit c0259aad67
10 changed files with 262 additions and 131 deletions
Download patch file Download diff file Expand all files Collapse all files

7
Dockerfile
View file

@ -10,7 +10,7 @@ ARG USE_CUDA_VER=cu121
# 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=BAAI/bge-reranker-base
ARG USE_RERANKING_MODEL=""
######## WebUI frontend ########
FROM --platform=$BUILDPLATFORM node:21-alpine3.19 as build
@ -67,6 +67,9 @@ ENV WHISPER_MODEL="base" \
ENV RAG_EMBEDDING_MODEL="$USE_EMBEDDING_MODEL_DOCKER" \
RAG_RERANKING_MODEL="$USE_RERANKING_MODEL_DOCKER" \
SENTENCE_TRANSFORMERS_HOME="/app/backend/data/cache/embedding/models"
## Hugging Face download cache ##
ENV HF_HOME="/app/backend/data/cache/embedding/models"
#### Other models ##########################################################
WORKDIR /app/backend
@ -102,13 +105,11 @@ RUN pip3 install uv && \
pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/$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 sentence_transformers import CrossEncoder; CrossEncoder(os.environ['RAG_RERANKING_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 sentence_transformers import CrossEncoder; CrossEncoder(os.environ['RAG_RERANKING_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