Docs for Gradio UI. Bumped version to 0.2.0

evandempsey · Nov 22, 2024 · 4d69a34 · 4d69a34
1 parent 9efeae7
commit 4d69a34
Show file tree

Hide file tree

Showing 6 changed files with 51 additions and 1 deletion.
diff --git a/README.md b/README.md
@@ -22,6 +22,7 @@ An intelligent system that automatically generates engaging podcast conversation
 - High-quality text-to-speech synthesis using Google Cloud or ElevenLabs
 - Checkpoint system to save progress and resume generation
 - Configurable voices and audio settings
+- Gradio UI
 
 ## Examples
 
@@ -48,6 +49,10 @@ Listen to sample podcasts generated using Podcast-LLM:
 [![Play Podcast Sample](https://img.shields.io/badge/Play%20Podcast-brightgreen?style=for-the-badge&logo=soundcloud)](https://soundcloud.com/evan-dempsey-153309617/robotic-process-automation-google-voices)
 
 
+## Web Interface
+
+![Gradio Web Interface](assets/images/gradio_ui.png)
+
 ## Installation
 
 1. Install using pip:
@@ -92,6 +97,21 @@ Listen to sample podcasts generated using Podcast-LLM:
 
 3. Customize voices and other settings in `config/config.yaml`
 
+4. Launch the Gradio web interface:
+   ```bash
+   # Start the web UI
+   podcast-llm-gui
+   ```
+
+   This launches a user-friendly web interface where you can:
+   - Enter a podcast topic
+   - Choose between research and context modes
+   - Upload source files and URLs for context mode
+   - Configure Q&A rounds and checkpointing
+   - Specify output paths for text and audio
+   - Monitor generation progress in real-time
+
+
 ## License
 
 This project is licensed under Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)

diff --git a/assets/images/gradio_ui.png b/assets/images/gradio_ui.png
diff --git a/docs/source/index.rst b/docs/source/index.rst
@@ -23,6 +23,7 @@ Welcome to Podcast LLM's documentation!
    modules/extractors_web
    modules/extractors_youtube
    modules/generate
+   modules/gui
    modules/models
    modules/outline
    modules/research

diff --git a/docs/source/modules/gui.rst b/docs/source/modules/gui.rst
@@ -0,0 +1,7 @@
+podcast_llm.gui
+===============
+
+.. automodule:: podcast_llm.gui
+   :members:
+   :undoc-members:
+   :show-inheritance: 
diff --git a/docs/source/usage.rst b/docs/source/usage.rst
@@ -32,7 +32,27 @@ Here's how to use the Podcast LLM system:
       # Generate Markdown output
       podcast-llm "Machine Learning" --text-output podcast.md
 
+
 Configuration
 ------------
 
 The system can be configured using the ``config.yaml`` file:
+
+
+Launching the Web Interface
+-------------------------
+
+You can launch the Gradio web interface using:
+
+.. code-block:: bash
+
+   podcast-llm-gui
+
+This launches a user-friendly web interface where you can:
+
+- Enter a podcast topic
+- Choose between research and context modes  
+- Upload source files and URLs for context mode
+- Configure Q&A rounds and checkpointing
+- Specify output paths for text and audio
+- Monitor generation progress in real-time
diff --git a/pyproject.toml b/pyproject.toml
@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "podcast-llm"
-version = "0.1.2"
+version = "0.2.0"
 description = "An intelligent system that automatically generates engaging podcast conversations using LLMs and text-to-speech technology."
 authors = ["Evan Dempsey <[email protected]>"]
 license = "Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)"
@@ -49,6 +49,8 @@ sphinxcontrib-napoleon = "^0.7"
 
 [tool.poetry.scripts]
 podcast-llm = "podcast_llm.generate:main"
+podcast-llm-gui = "podcast_llm.gui:main"
+
 
 [build-system]
 requires = ["poetry-core"]