dockerize

.dockerignore

@@ -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/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# 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 +1,13 @@
+FROM python:3.12-slim
+
+RUN pip install uv
+RUN uv venv
+
+COPY requirements.txt .
+RUN uv pip install -r requirements.txt
+
+COPY . .
+
+ENV GRADIO_SERVER_NAME="0.0.0.0"
+
+CMD .venv/bin/python main.py

docker-compose.yml

@@ -0,0 +1,8 @@
+services:
+  web:
+    build: .
+    ports:
+      - "8080:7860"
+    environment:
+      GEMINI_API_KEY: ${GEMINI_API_KEY}
+

main.py

@@ -1,4 +1,5 @@
 import io
+import os
 from typing import List, Literal
 
 import gradio as gr
@@ -9,8 +10,6 @@
 from pypdf import PdfReader
 
 
-
-
 class DialogueItem(BaseModel):
     text: str
     voice: Literal["alloy", "onyx", "fable"]
@@ -47,8 +46,11 @@ def generate_dialogue(text: str) -> Dialogue:
     Write your engaging, informative podcast dialogue based on the key points and creative ideas you came up with during the brainstorming session. Use a conversational tone and include any necessary context or explanations to make the content accessible to a general audience.
     """
 
-def get_mp3(text: str, voice: str) -> bytes:
-    client = OpenAI()
+
+def get_mp3(text: str, voice: str, api_key: str = None) -> bytes:
+    client = OpenAI(
+        api_key=api_key or os.getenv("OPENAI_API_KEY"),
+    )
 
     with client.audio.speech.with_streaming_response.create(
         model="tts-1",
@@ -61,9 +63,8 @@ def get_mp3(text: str, voice: str) -> bytes:
             return file.getvalue()
 
 
-def generate_audio(file: bytes) -> bytes:
+def generate_audio(file: bytes, openai_api_key: str) -> bytes:
 
-    # Read the PDF file
     reader = PdfReader(io.BytesIO(file))
     text = "\n\n".join([page.extract_text() for page in reader.pages])
 
@@ -73,12 +74,11 @@ def generate_audio(file: bytes) -> bytes:
     result = b""
     characters = 0
 
-    # Generate and play the dialogue
     for line in llm_output.dialogue:
         logger.info(line.text)
         logger.info(line.voice)
 
-        audio = get_mp3(line.text, line.voice)
+        audio = get_mp3(line.text, line.voice, openai_api_key)
         result += audio
         characters += len(line.text)
 
@@ -88,28 +88,24 @@ def generate_audio(file: bytes) -> bytes:
 
 
 demo = gr.Interface(
+    title="PDF to Podcast",
+    description="Convert any PDF document into an engaging podcast episode!",
     fn=generate_audio,
     inputs=[
         gr.File(
             label="Input PDF",
             type="binary",
-        )
-        # gr.Textbox(
-        #     label="Input Text",
-        #     placeholder="Enter text here",
-        # ),
-        # gr.Textbox(
-        #     label="Male Voice",
-        #     value="1m3E2x7boso3AU9J3woJ",
-        # ),
-        # gr.Textbox(
-        #     label="Female Voice",
-        #     value="uCGnCVg8g9Lwl9wocoHE",
-        # ),
+        ),
+        gr.Textbox(
+            label="OpenAI API Key",
+            placeholder="Enter your OpenAI API key here",
+        ),
     ],
     outputs=[
         gr.Audio(format="mp3"),
     ],
 )
 
-demo.launch()
+demo.launch(
+    show_api=False,
+)