Build models and all downloads directly into docker containers

backend/Dockerfile

@@ -42,6 +42,12 @@ RUN apt-get remove -y --allow-remove-essential perl-base xserver-common xvfb cma
     rm -rf /var/lib/apt/lists/* && \
     rm /usr/local/lib/python3.11/site-packages/tornado/test/test.key
 
+# Pre-downloading NLTK for setups with limited egress
+RUN python -c "import nltk; \
+nltk.download('stopwords', quiet=True); \
+nltk.download('wordnet', quiet=True); \
+nltk.download('punkt', quiet=True);"
+
 # Set up application files
 WORKDIR /app
 COPY ./danswer /app/danswer

backend/Dockerfile.model_server

@@ -17,6 +17,16 @@ RUN pip install --no-cache-dir --upgrade -r /tmp/requirements.txt
 RUN apt-get remove -y --allow-remove-essential perl-base && \
     apt-get autoremove -y
 
+# Pre-downloading models for setups with limited egress
+RUN python -c "from transformers import AutoModel, AutoTokenizer, TFDistilBertForSequenceClassification; \
+from huggingface_hub import snapshot_download; \
+AutoTokenizer.from_pretrained('danswer/intent-model'); \
+AutoTokenizer.from_pretrained('intfloat/e5-base-v2'); \
+AutoTokenizer.from_pretrained('mixedbread-ai/mxbai-rerank-xsmall-v1'); \
+snapshot_download('danswer/intent-model'); \
+snapshot_download('intfloat/e5-base-v2'); \
+snapshot_download('mixedbread-ai/mxbai-rerank-xsmall-v1')"
+
 WORKDIR /app
 
 # Utils used by model server