model server build (#127)

* first commit to have model_server not be dependent on Docker

* making changes to fix the docker-compose file for archgw to set DNS_V4 and minor fixes with the build

* additional fixes for model server to be separated out in the build

* additional fixes for model server to be separated out in the build

* fix to get model_server to be built as a separate python process. TODO: fix the embeddings logs after cli completes

* fixing init to pull tempfile using the tempfile python package

---------

Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-261.local>
This commit is contained in:
Salman Paracha 2024-10-06 18:21:43 -07:00 committed by GitHub
parent 7d21359f5b
commit b60ceb9168
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
21 changed files with 3390 additions and 154 deletions

View file

@ -18,8 +18,8 @@ WORKDIR /src
ENV MODELS="BAAI/bge-large-en-v1.5"
COPY ./app ./app
COPY ./guard_model_config.yaml .
COPY ./openai_params.yaml .
COPY ./app/guard_model_config.yaml .
COPY ./app/openai_params.yaml .
# comment it out for now as we don't want to download the model every time we build the image
# we will mount host cache to docker image to avoid downloading the model every time