Dockerize

.dockerignore

@@ -0,0 +1,169 @@
+ragna.toml
+ragna/_version.py
+
+# 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/
+
+# MacOS
+**/.DS_Store
+
+# VSCode
+.vscode/

Dockerfile

@@ -0,0 +1,28 @@
+FROM python:3.11
+
+WORKDIR /opt/ragna
+
+COPY requirements.txt .
+RUN pip wheel --progress-bar=off --requirement requirements.txt
+
+COPY ragna ./ragna
+COPY pyproject.toml .
+# Since we don't copy the .git folder, but still use setuptools-scm as build-backend
+# we need to make two manual changes:
+# 1. With setuptools-scm all files that are tracked by git are automatically included in
+#    the built wheel. Since we have corresponding .dockerignore file to our .gitignore,
+#    the ragna folder only includes files that we are tracking. Thus, we just include
+#    everything manually.
+# 2. We need to pass the version expliclitly as
+#    --build-arg SETUPTOOLS_SCM_PRETEND_VERSION_FOR_RAGNA=...,
+#    since setuptools-scm cannot infer the version
+RUN echo '[tool.setuptools.package-data]\n"*" = ["*"]' >> pyproject.toml
+ARG SETUPTOOLS_SCM_PRETEND_VERSION_FOR_RAGNA
+RUN pip install --progress-bar=off .[vectordb]
+
+WORKDIR /var/ragna
+COPY ragna-docker.toml ragna.toml
+ENV RAGNA_CONFIG=/var/ragna/ragna.toml
+
+ENTRYPOINT []
+CMD ["ragna", "--help"]

compose.yml

@@ -0,0 +1,50 @@
+version: "3"
+
+services:
+  api.localhost:
+    build:
+      context: .
+      dockerfile: Dockerfile
+      args:
+        - SETUPTOOLS_SCM_PRETEND_VERSION_FOR_RAGNA=0.0.0
+    env_file: .env
+    environment: # overrides config in ragna-docker.toml
+      - "RAGNA_API_URL=http://0.0.0.0:31476"
+      - 'RAGNA_API_ORIGINS=["http://localhost:31477", "http://ui:31477"]'
+    command:
+      - ragna
+      - api
+    ports:
+      - "31476:31476"
+    healthcheck:
+      test: ["CMD", "curl", "http://0.0.0.0:31476"]
+      interval: 5s
+      timeout: 2s
+      retries: 6
+#    volumes:
+#      - "/tmp/ragna/documents:/var/ragna/documents"
+
+  ui:
+    build:
+      context: .
+      dockerfile: Dockerfile
+      args:
+        - SETUPTOOLS_SCM_PRETEND_VERSION_FOR_RAGNA=0.0.0
+    depends_on:
+      api.localhost:
+        condition: service_healthy
+    environment: # overrides config in ragna-docker.toml
+      - "RAGNA_API_URL=http://api.localhost:31476"
+      - "RAGNA_UI_URL=http://0.0.0.0:31477"
+      - 'RAGNA_UI_ORIGINS=["http://localhost:31477"]'
+    env_file: .env
+    command:
+      - ragna
+      - ui
+    ports:
+      - "31477:31477"
+    healthcheck:
+      test: ["CMD", "curl", "http://0.0.0.0:31477/health"]
+      interval: 5s
+      timeout: 2s
+      retries: 6

pyproject.toml

@@ -52,13 +52,18 @@ Repository = "https://github.com/Quansight/ragna"
 
 [project.optional-dependencies]
 # to update the array below, run scripts/update_optional_dependencies.py
-all = [
+vectordb = [
     "chromadb>=0.4.13",
+    "tiktoken",
+]
+lancedb = [
     "lancedb>=0.2",
     "pyarrow",
+]
+pdf = [
     "pymupdf>=1.23.6",
-    "tiktoken",
 ]
+all = ["ragna[vectordb,lancedb,pdf]"]
 
 [tool.setuptools_scm]
 write_to = "ragna/_version.py"

ragna-docker.toml

@@ -0,0 +1,16 @@
+local_cache_root = "/var/ragna"
+document = "ragna.core.LocalDocument"
+authentication = "ragna.deploy._authentication.RagnaDemoAuthentication"
+
+[components]
+source_storages = ["ragna.source_storages.Chroma"]
+assistants = ["ragna.assistants.Gpt4", "ragna.assistants.Gpt35Turbo16k"]
+
+[api]
+url = "http://0.0.0.0:31476"
+origins = ["http://localhost:31477"]
+database_url = "sqlite:////var/ragna/ragna.db"
+
+[ui]
+url = "http://0.0.0.0:31477"
+origins = ["http://localhost:31477"]