API Refactor & Model Manager

Dockerfile

@@ -12,7 +12,7 @@ ENV TZ=Europe/Amsterdam
 
 WORKDIR /usr/src/app
 
-COPY --chmod=0755 compile.sh .
+COPY --chmod=0755 scripts/compile.sh .
 
 # Install MongoDB and necessary tools
 RUN apt update && \
@@ -23,11 +23,7 @@ RUN apt update && \
     apt-get install -y mongodb-org && \
     git clone https://github.com/ggerganov/llama.cpp.git --branch master-d5850c5
 
-
-# copy & install python reqs
-COPY ./api/requirements.txt api/requirements.txt
-RUN pip install --upgrade pip && \
-    pip install --no-cache-dir -r ./api/requirements.txt
+RUN pip install --upgrade pip
 
 # Dev environment
 FROM base as dev
@@ -38,11 +34,7 @@ COPY --from=node_base /usr/local /usr/local
 COPY ./web/package*.json ./
 RUN npm ci
 
-# Copy the rest of the project files
-COPY web /usr/src/app/web
-COPY ./api /usr/src/app/api
-
-COPY --chmod=0755 dev.sh /usr/src/app/dev.sh
+COPY --chmod=0755 scripts/dev.sh /usr/src/app/dev.sh
 CMD ./dev.sh
 
 # Build frontend
@@ -64,6 +56,7 @@ WORKDIR /usr/src/app
 COPY --from=frontend_builder /usr/src/app/web/build /usr/src/app/api/static/
 COPY ./api /usr/src/app/api
 
-COPY --chmod=0755 deploy.sh /usr/src/app/deploy.sh
+RUN pip install ./api
 
+COPY --chmod=0755 scripts/deploy.sh /usr/src/app/deploy.sh
 CMD ./deploy.sh

README.md

@@ -22,7 +22,6 @@ cd serge
 docker compose up --build -d
 docker compose exec serge python3 /usr/src/app/api/utils/download.py tokenizer 7B
 ```
-Please note that the models occupy the following storage space: 7B requires 4.21G, 13B requires 8.14G, and 30B requires 20.3G
 
 #### Windows
 

api/.gitignore

@@ -0,0 +1,160 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

api/poetry.toml

@@ -0,0 +1,2 @@
+[virtualenvs]
+create = false

api/pyproject.toml

@@ -0,0 +1,66 @@
+[tool.poetry]
+name = "serge"
+description = "Serge API package"
+version = "0.1.0"
+license = "MIT"
+authors = [ 
+    "Nathan Sarrazin <contact@nsarrazin.com>"
+]
+
+packages = [
+    { include = "serge", from = "src" }
+]
+
+homepage = "https://serge.chat/"
+repository = "https://github.com/nsarrazin/serge"
+
+include = [{path="src"}]
+
+[build-system]
+requires = ["poetry-core>=1.0.0"]
+build-backend = "poetry.core.masonry.api"
+
+[tool.poetry.dependencies]
+python=">=3.10,<4.0"
+asyncio = "^3.4.3"
+packaging = "^23.0"
+pydantic = "^1.10.7"
+pymongo = "^4.3.3"
+python-dotenv = "^1.0.0"
+python-multipart = "^0.0.6"
+pyyaml = "^6.0"
+rfc3986 = "^2.0.0"
+sentencepiece = "^0.1.97"
+sniffio = "^1.3.0"
+sse-starlette = "^1.3.3"
+starlette = "^0.26.1"
+toml = "^0.10.2"
+tqdm = "^4.65.0"
+typing-extensions = "^4.5.0"
+ujson = "^5.7.0"
+urllib3 = "^1.26.15"
+uvicorn = "^0.21.1"
+uvloop = "^0.17.0"
+watchfiles = "^0.19.0"
+websockets = "^10.4"
+anyio = "^3.6.2"
+certifi = "^2022.12.7"
+charset-normalizer = "^3.1.0"
+click = "^8.1.3"
+email-validator = "^1.3.1"
+fastapi = "^0.95.0"
+filelock = "^3.10.7"
+h11 = "^0.14.0"
+httpcore = "^0.17.0"
+httptools = "^0.5.0"
+huggingface-hub = "^0.13.3"
+idna = "^3.4"
+itsdangerous = "^2.1.2"
+jinja2 = "^3.1.2"
+markupsafe = "^2.1.2"
+motor = "^3.1.1"
+orjson = "^3.8.8"
+beanie = "^1.17.0"
+dnspython = "^2.3.0"
+lazy-model = "^0.0.5"
+requests = "^2.28.2"

api/src/serge/dependencies.py

@@ -0,0 +1,8 @@
+from .utils.convert import convert_all
+import anyio
+
+
+async def convert_model_files():
+    await anyio.to_thread.run_sync(
+        convert_all, "/usr/src/app/weights/", "/usr/src/app/weights/tokenizer.model"
+    )