Merge pull request #1 from dockhardman/feature_web_app_init

Feature web app init

.dockerignore

@@ -0,0 +1,164 @@
+# Custom
+.git
+qdrant_storage
+
+# 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/

Dockerfile

@@ -0,0 +1,14 @@
+FROM python:3.8-slim
+
+LABEL maintainer="dockhardman <f1470891079@gmail.com>"
+
+# Install Dependencies
+WORKDIR /
+COPY ./requirements.txt ./requirements.txt
+RUN pip install -r /requirements.txt
+
+# Application
+WORKDIR /app/
+COPY ./app /app
+
+CMD ["bash", "/app/start.sh"]

Makefile

@@ -0,0 +1,14 @@
+# Developing
+logs:
+	docker logs -f --tail 300 wiki-retrieval-service
+
+install_all:
+	poetry install --with dev --no-root
+
+update_dependencies:
+	poetry update
+	poetry export --without-hashes -f requirements.txt --output requirements.txt
+	poetry export --without-hashes -f requirements.txt --with dev --output requirements-dev.txt
+
+format:
+	poetry run black .

app/app/config.py

@@ -0,0 +1,49 @@
+import os
+import copy
+import logging
+from typing import Text
+
+from rich.console import Console
+
+
+console = Console()
+
+
+class Settings:
+    def __init__(self, **kwargs):
+        environ = copy.deepcopy(os.environ)
+        environ.update(**kwargs)
+
+        # General
+        self.APP_NAME: Text = environ.get("APP_NAME", "wiki-retrieval-service")
+        self.APP_VERSION: Text = environ.get("APP_VERSION", "0.1.0")
+        self.APP_TIMEZONE: Text = environ.get("APP_TIMEZONE", "Asia/Taipei")
+
+        # Logging Config
+        self.APP_LOGGER_NAME: Text = environ.get("APP_LOGGER_NAME", "sanic.root")
+        self.LOG_DIR: Text = "log"
+        self.LOG_ACCESS_FILENAME: Text = environ.get(
+            "LOG_ACCESS_FILENAME", "access.log"
+        )
+        self.LOG_ERROR_FILENAME: Text = environ.get("LOG_ERROR_FILENAME", "error.log")
+        self.LOG_SERVICE_FILENAME: Text = environ.get(
+            "LOG_SERVICE_FILENAME", "service.log"
+        )
+
+        # OpenAI Config
+        self.OPENAI_API_KEY = environ.get("OPENAI_API_KEY")
+
+        # Retrieval Config
+        self.VECTOR_SIZE = int(environ.get("VECTOR_SIZE", "1536"))
+        self.DATASTORE = environ.get("DATASTORE", "qdrant")
+        self.BEARER_TOKEN = environ.get("BEARER_TOKEN")
+        self.QDRANT_URL = environ.get("QDRANT_URL", "wiki-qdrant-service")
+        self.QDRANT_PORT = int(environ.get("QDRANT_PORT", "6333"))
+        self.QDRANT_GRPC_PORT = int(environ.get("QDRANT_GRPC_PORT", "6334"))
+        self.QDRANT_API_KEY = environ.get("QDRANT_API_KEY")
+        self.QDRANT_COLLECTION = environ.get("QDRANT_COLLECTION", "wiki_documents")
+
+
+settings = Settings()
+
+logger = logging.getLogger(settings.APP_LOGGER_NAME)

app/app/deps/__init__.py

@@ -0,0 +1,5 @@
+from .document_store import get_document_store
+from .timer import click_timer
+
+
+__all__ = ["click_timer", "get_document_store"]

app/app/deps/document_store.py

@@ -0,0 +1,7 @@
+from sanic.request import Request
+
+from app.document_store import QdrantDocumentStore
+
+
+def get_document_store(request: Request) -> "QdrantDocumentStore":
+    return request.app.ctx.document_store

app/app/deps/timer.py

@@ -0,0 +1,8 @@
+from pyassorted.datetime import Timer
+from sanic.request import Request
+
+
+def click_timer(request: Request) -> "Timer":
+    timer = Timer()
+    timer.click()
+    return timer

app/app/document_store/__init__.py

@@ -0,0 +1,5 @@
+from .abc import DocumentStore
+from .qdrant import QdrantDocumentStore
+
+
+__all__ = ["DocumentStore", "QdrantDocumentStore"]

app/app/document_store/abc.py

@@ -0,0 +1,52 @@
+from abc import ABC, abstractmethod
+from typing import Dict, List, Optional, Text
+
+from app.schema.models import (
+    Document,
+    DocumentChunk,
+    DocumentMetadataFilter,
+    Query,
+    QueryResult,
+    QueryWithEmbedding,
+)
+
+
+class DocumentStore(ABC):
+    @property
+    def host(self) -> str:
+        raise NotImplementedError
+
+    @property
+    def port(self) -> int:
+        raise NotImplementedError
+
+    @abstractmethod
+    async def touch(self) -> bool:
+        raise NotImplementedError
+
+    @abstractmethod
+    async def upsert(
+        self, documents: List[Document], chunk_token_size: Optional[int] = None
+    ) -> List[Text]:
+        raise NotImplementedError
+
+    @abstractmethod
+    async def _upsert(self, chunks: Dict[str, List[DocumentChunk]]) -> List[Text]:
+        raise NotImplementedError
+
+    @abstractmethod
+    async def query(self, queries: List[Query]) -> List[QueryResult]:
+        raise NotImplementedError
+
+    @abstractmethod
+    async def _query(self, queries: List[QueryWithEmbedding]) -> List[QueryResult]:
+        raise NotImplementedError
+
+    @abstractmethod
+    async def delete(
+        self,
+        ids: Optional[List[Text]] = None,
+        filter: Optional[DocumentMetadataFilter] = None,
+        delete_all: Optional[bool] = None,
+    ) -> bool:
+        raise NotImplementedError

app/app/document_store/factory.py

@@ -0,0 +1,7 @@
+from typing import Text
+
+from .qdrant import QdrantDocumentStore
+
+
+def get_document_store(collection_name: Text) -> "QdrantDocumentStore":
+    return QdrantDocumentStore(collection_name=collection_name)