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

Browse source
This commit is contained in:
Steven Kreitzer 2024-04-22 15:49:58 -05:00 • committed by Steven Kreitzer
parent f3e5700d49
commit 4e0b32b505
7 changed files with 406 additions and 110 deletions
Download patch file Download diff file Expand all files Collapse all files

11
Dockerfile
View file

@ -8,8 +8,9 @@ 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 default 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.
# 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
######## WebUI frontend ########
FROM --platform=$BUILDPLATFORM node:21-alpine3.19 as build
@ -30,6 +31,7 @@ ARG USE_CUDA
ARG USE_OLLAMA
ARG USE_CUDA_VER
ARG USE_EMBEDDING_MODEL
ARG USE_RERANKING_MODEL
## Basis ##
ENV ENV=prod \
@ -38,7 +40,8 @@ ENV ENV=prod \
USE_OLLAMA_DOCKER=${USE_OLLAMA} \
USE_CUDA_DOCKER=${USE_CUDA} \
USE_CUDA_DOCKER_VER=${USE_CUDA_VER} \
USE_EMBEDDING_MODEL_DOCKER=${USE_EMBEDDING_MODEL}
USE_EMBEDDING_MODEL_DOCKER=${USE_EMBEDDING_MODEL} \
USE_RERANKING_MODEL_DOCKER=${USE_RERANKING_MODEL}
## Basis URL Config ##
ENV OLLAMA_BASE_URL="/ollama" \
@ -62,7 +65,7 @@ ENV WHISPER_MODEL="base" \
## RAG Embedding model settings ##
ENV RAG_EMBEDDING_MODEL="$USE_EMBEDDING_MODEL_DOCKER" \
RAG_EMBEDDING_MODEL_DIR="/app/backend/data/cache/embedding/models" \
RAG_RERANKING_MODEL="$USE_RERANKING_MODEL_DOCKER" \
SENTENCE_TRANSFORMERS_HOME="/app/backend/data/cache/embedding/models"
#### Other models ##########################################################
@ -99,11 +102,13 @@ RUN pip3 install uv && \
pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/$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