Refactor code to improve performance and readability

.gitignore

@@ -0,0 +1,162 @@
+# 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/
+
+ignore*

app.py

@@ -0,0 +1,58 @@
+"""
+streamlit run app.py --server.address 0.0.0.0
+"""
+
+from __future__ import annotations
+
+import os
+from time import time
+
+import faiss
+import pandas as pd
+import streamlit as st
+from open_clip import create_model_and_transforms
+from openai import OpenAI
+from qdrant_client import QdrantClient
+from qdrant_client.http import models
+
+if os.getenv("SPACE_ID"):
+    USE_HF_SPACE = True
+    os.environ["HF_HOME"] = "/data/.huggingface"
+    os.environ["HF_DATASETS_CACHE"] = "/data/.huggingface"
+else:
+    USE_HF_SPACE = False
+
+# for tokenizer
+os.environ["TOKENIZERS_PARALLELISM"] = "false"
+
+OPENAI_API_KEY = os.environ.get("OPENAI_API_KEY")
+QDRANT_API_ENDPOINT = os.environ.get("QDRANT_API_ENDPOINT")
+QDRANT_API_KEY = os.environ.get("QDRANT_API_KEY")
+
+if not QDRANT_API_ENDPOINT or not QDRANT_API_KEY:
+    raise ValueError("env: QDRANT_API_ENDPOINT or QDRANT_API_KEY is not set.")
+
+
+@st.cache_resource
+def get_model_preprocess():
+    model, _, preprocess = create_model_and_transforms(
+        "xlm-roberta-base-ViT-B-32", pretrained="laion5B-s13B-b90k"
+    )
+    return model, preprocess
+
+
+@st.cache_resource
+def get_qdrant_client():
+    qdrant_client = QdrantClient(
+        url=QDRANT_API_ENDPOINT,
+        api_key=QDRANT_API_KEY,
+    )
+    return qdrant_client
+
+
+def app():
+    st.title("secon.dev site search")
+
+
+if __name__ == "__main__":
+    app()

requirements.txt

@@ -0,0 +1,7 @@
+streamlit==1.29.0
+sentence-transformers==2.2.2
+sentencepiece==0.1.99
+transformers==4.35.2
+openai==1.3.3
+open_clip_torch==2.23.0
+qdrant_client==1.7.0