From df30014c5d8e55f85ec16bc1d5bf747d0e4e5dda Mon Sep 17 00:00:00 2001
From: Yuhong Sun <yuhongsun96@gmail.com>
Date: Tue, 16 Apr 2024 23:39:12 -0700
Subject: [PATCH] Build models and all downloads directly into docker
 containers

---
 backend/Dockerfile              |  6 ++++++
 backend/Dockerfile.model_server | 10 ++++++++++
 2 files changed, 16 insertions(+)

diff --git a/backend/Dockerfile b/backend/Dockerfile
index a61864fa2c0..09114aa4598 100644
--- a/backend/Dockerfile
+++ b/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
diff --git a/backend/Dockerfile.model_server b/backend/Dockerfile.model_server
index 365a553c9f1..89f24e2ac26 100644
--- a/backend/Dockerfile.model_server
+++ b/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