mirror of
https://github.com/danswer-ai/danswer.git
synced 2025-03-28 18:52:31 +01:00
463340b8a1
* remove title for slack * initial working code * simplification * improvements * name change to information_content_model * avoid boost_score > 1.0 * nit * EL comments and improvements Improvements: - proper import of information content model from cache or HF - warm up for information content model Other: - EL PR review comments * nit * requirements version update * fixed docker file * new home for model_server configs * default off * small updates * YS comments - pt 1 * renaming to chunk_boost & chunk table def * saving and deleting chunk stats in new table * saving and updating chunk stats * improved dict score update * create columns for individual boost factors * RK comments * Update migration * manual import reordering
62 lines
2.4 KiB
Docker
62 lines
2.4 KiB
Docker
FROM python:3.11.7-slim-bookworm
|
|
|
|
LABEL com.danswer.maintainer="founders@onyx.app"
|
|
LABEL com.danswer.description="This image is for the Onyx model server which runs all of the \
|
|
AI models for Onyx. This container and all the code is MIT Licensed and free for all to use. \
|
|
You can find it at https://hub.docker.com/r/onyx/onyx-model-server. For more details, \
|
|
visit https://github.com/onyx-dot-app/onyx."
|
|
|
|
# Default ONYX_VERSION, typically overriden during builds by GitHub Actions.
|
|
ARG ONYX_VERSION=0.0.0-dev
|
|
ENV ONYX_VERSION=${ONYX_VERSION} \
|
|
DANSWER_RUNNING_IN_DOCKER="true"
|
|
|
|
|
|
RUN echo "ONYX_VERSION: ${ONYX_VERSION}"
|
|
|
|
COPY ./requirements/model_server.txt /tmp/requirements.txt
|
|
RUN pip install --no-cache-dir --upgrade \
|
|
--retries 5 \
|
|
--timeout 30 \
|
|
-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
|
|
# Download tokenizers, distilbert for the Onyx model
|
|
# Download model weights
|
|
# Run Nomic to pull in the custom architecture and have it cached locally
|
|
RUN python -c "from transformers import AutoTokenizer; \
|
|
AutoTokenizer.from_pretrained('distilbert-base-uncased'); \
|
|
AutoTokenizer.from_pretrained('mixedbread-ai/mxbai-rerank-xsmall-v1'); \
|
|
from huggingface_hub import snapshot_download; \
|
|
snapshot_download(repo_id='onyx-dot-app/hybrid-intent-token-classifier'); \
|
|
snapshot_download(repo_id='onyx-dot-app/information-content-model'); \
|
|
snapshot_download('nomic-ai/nomic-embed-text-v1'); \
|
|
snapshot_download('mixedbread-ai/mxbai-rerank-xsmall-v1'); \
|
|
from sentence_transformers import SentenceTransformer; \
|
|
SentenceTransformer(model_name_or_path='nomic-ai/nomic-embed-text-v1', trust_remote_code=True);"
|
|
|
|
# In case the user has volumes mounted to /root/.cache/huggingface that they've downloaded while
|
|
# running Onyx, don't overwrite it with the built in cache folder
|
|
RUN mv /root/.cache/huggingface /root/.cache/temp_huggingface
|
|
|
|
WORKDIR /app
|
|
|
|
# Utils used by model server
|
|
COPY ./onyx/utils/logger.py /app/onyx/utils/logger.py
|
|
|
|
# Place to fetch version information
|
|
COPY ./onyx/__init__.py /app/onyx/__init__.py
|
|
|
|
# Shared between Onyx Backend and Model Server
|
|
COPY ./shared_configs /app/shared_configs
|
|
|
|
# Model Server main code
|
|
COPY ./model_server /app/model_server
|
|
|
|
ENV PYTHONPATH=/app
|
|
|
|
CMD ["uvicorn", "model_server.main:app", "--host", "0.0.0.0", "--port", "9000"]
|