version 0.3.35

Dockerfile.local

@@ -35,7 +35,7 @@ ENV APP_BUILD_HASH=${BUILD_HASH}
 RUN npm run build
 
 ######## WebUI backend ########
-FROM python:3.11-slim-bookworm as base
+FROM python:3.11-slim-bookworm AS base
 
 # Use args
 ARG USE_CUDA
@@ -187,7 +187,7 @@ RUN pip3 install uv && \
     echo "========Installing CUDA version======" && \
     pip3 install torch torchvision torchaudio --no-cache-dir && \
     # Install requirements.txt
-    uv pip install -r requirements.txt --no-cache-dir && \
+    pip3 install -r requirements.txt --no-cache-dir && \
     # Verify imports and model loading
     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'])"; \
@@ -215,6 +215,11 @@ COPY --chown=$UID:$GID --from=build /app/package.json /app/package.json
 # Copy backend files
 COPY --chown=$UID:$GID ./backend .
 
+# provide group with same permissions as user
+# allows running in OpenShift
+RUN chmod -R g=u /app $HOME
+
+
 EXPOSE 8080
 
 HEALTHCHECK CMD curl --silent --fail http://localhost:${PORT:-8080}/health | jq -ne 'input.status == true' || exit 1

backend/open_webui/apps/retrieval/main.py

@@ -175,37 +175,37 @@
 app.state.config.RAG_WEB_SEARCH_CONCURRENT_REQUESTS = RAG_WEB_SEARCH_CONCURRENT_REQUESTS
 
 
-# def update_embedding_model(
-#     embedding_model: str,
-#     auto_update: bool = False,
-# ):
-#     if embedding_model and app.state.config.RAG_EMBEDDING_ENGINE == "":
-#         from sentence_transformers import SentenceTransformer
-
-#         app.state.sentence_transformer_ef = SentenceTransformer(
-#             get_model_path(embedding_model, auto_update),
-#             device=DEVICE_TYPE,
-#             trust_remote_code=RAG_EMBEDDING_MODEL_TRUST_REMOTE_CODE,
-#         )
-#     else:
-#         app.state.sentence_transformer_ef = None
-
-# reverting to old version of this function
 def update_embedding_model(
     embedding_model: str,
     auto_update: bool = False,
 ):
     if embedding_model and app.state.config.RAG_EMBEDDING_ENGINE == "":
-        import sentence_transformers
+        from sentence_transformers import SentenceTransformer
 
-        app.state.sentence_transformer_ef = sentence_transformers.SentenceTransformer(
+        app.state.sentence_transformer_ef = SentenceTransformer(
             get_model_path(embedding_model, auto_update),
             device=DEVICE_TYPE,
             trust_remote_code=RAG_EMBEDDING_MODEL_TRUST_REMOTE_CODE,
         )
     else:
         app.state.sentence_transformer_ef = None
 
+# reverting to old version of this function
+# def update_embedding_model(
+#     embedding_model: str,
+#     auto_update: bool = False,
+# ):
+#     if embedding_model and app.state.config.RAG_EMBEDDING_ENGINE == "":
+#         import sentence_transformers
+
+#         app.state.sentence_transformer_ef = sentence_transformers.SentenceTransformer(
+#             get_model_path(embedding_model, auto_update),
+#             device=DEVICE_TYPE,
+#             trust_remote_code=RAG_EMBEDDING_MODEL_TRUST_REMOTE_CODE,
+#         )
+#     else:
+#         app.state.sentence_transformer_ef = None
+
 def update_reranking_model(
     reranking_model: str,
     auto_update: bool = False,

docker-compose-myCustomizations.yaml

@@ -40,7 +40,7 @@ services:
       - OPENAI_API_BASE_URL=http://pipelines:9099
       - OPENAI_API_KEY=0p3n-w3bu!
       - TIKTOKEN_ENCODING_NAME=cl100k_base
-      - RAG_EMBEDDING_MODEL=sentence-transformers/all-MiniLM-L6-v2
+      - RAG_EMBEDDING_MODEL=intfloat/multilingual-e5-large
       - WHISPER_MODEL=ivrit-ai/faster-whisper-v2-d3-e3
       - WHISPER_MODEL_DIR=/app/backend/data/cache/whisper/models
       - SENTENCE_TRANSFORMERS_HOME=/app/backend/data/cache/embedding/models