init

.gitignore

@@ -1,11 +1,224 @@
-# Python-generated files
+# Byte-compiled / optimized / DLL files
 __pycache__/
-*.py[oc]
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
 build/
+develop-eggs/
 dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
 wheels/
-*.egg-info
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
 
-# Virtual environments
-.venv
+# 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
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+uv.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
+#poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+#pdm.lock
+#pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+#pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# 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
+.envrc
+.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/
+
+# Abstra
+# Abstra is an AI-powered process automation framework.
+# Ignore directories containing user credentials, local state, and settings.
+# Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#  Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#  that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#  and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#  you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Cursor
+#  Cursor is an AI-powered code editor. `.cursorignore` specifies files/directories to
+#  exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
+#  refer to https://docs.cursor.com/context/ignore-files
+.cursorignore
+.cursorindexingignore
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+tests/
+checkpoints/
+playground.ipynb
+.history/
+upload_checkpoints.sh
+checkpoints.7z
+README_old.md
+discord_bot/
+feishu_bot/
+tmp*
+torchinductor_root/
+scripts/
+checkpoints_legacy/
+lora_output/
+datasets/
+python_embeded/
+checkpoints_pack/

Dockerfile

@@ -0,0 +1,53 @@
+FROM python:3.11-slim
+
+# Set environment variables
+ENV PYTHONDONTWRITEBYTECODE=1 \
+    PYTHONUNBUFFERED=1 \
+    DEBIAN_FRONTEND=noninteractive \
+    TORCHAUDIO_USE_TORCHCODEC=0
+
+# Install system dependencies
+# build-essential is required for triton to compile CUDA kernels
+# ffmpeg and libav* dev packages are required for torchaudio's ffmpeg backend
+# Note: torchaudio's ffmpeg backend needs shared libraries, not just the ffmpeg binary
+RUN apt-get update && \
+    apt-get install -y --no-install-recommends git libsndfile1 build-essential && \
+    apt-get install -y ffmpeg libavcodec-dev libavformat-dev libavutil-dev libswresample-dev && \
+    rm -rf /var/lib/apt/lists/*
+
+# Set up a new user named "user" with user ID 1000 (HuggingFace Space requirement)
+RUN useradd -m -u 1000 user
+
+# Create /data directory with proper permissions for persistent storage
+RUN mkdir -p /data && chown user:user /data && chmod 755 /data
+
+# Set environment variables for user
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:$PATH \
+    GRADIO_SERVER_NAME=0.0.0.0 \
+    GRADIO_SERVER_PORT=7860
+
+# Set the working directory
+WORKDIR $HOME/app
+
+# Copy requirements first for better Docker layer caching
+COPY --chown=user:user requirements.txt .
+
+# Copy the local nano-vllm package
+COPY --chown=user:user acestep/third_parts/nano-vllm ./acestep/third_parts/nano-vllm
+
+# Switch to user before installing packages
+USER user
+
+# Install dependencies from requirements.txt (includes PyTorch with CUDA from --extra-index-url)
+RUN pip install --no-cache-dir --user -r requirements.txt
+
+
+# Copy the rest of the application
+COPY --chown=user:user . .
+
+# Expose port
+EXPOSE 7860
+
+# Run the application
+CMD ["python", "app.py"]

README.md

@@ -3,10 +3,9 @@ title: HF Vector Search
 emoji: 🚀
 colorFrom: blue
 colorTo: indigo
-sdk: gradio
-sdk_version: 4.19.2
-app_file: app.py
-pinned: true
+sdk: docker
+app_port: 7860
+pinned: false
 ---
 
 # HF Vector Search

app.py

@@ -132,4 +132,11 @@ import gradio as gr
 with gr.Blocks(title="Qdrant Vector DB Demo") as demo:
     gr.Markdown("# 🚀 Demo Qdrant Vector Search")
     gr.Markdown("Tool test nhanh khả năng thêm dữ liệu và tìm kiếm ngữ nghĩa (Semantic Search).")
-demo.launch()
+    
+print("Launching server on 0.0.0.0:7860...")
+demo.launch(
+    server_name="0.0.0.0",
+    server_port=7860,
+    share=False,
+    show_error=True,
+)