🐛 fix(GenerationContext.py): fix import statements and add support for captioning engine

✨ feat(GenerationContext.py): add support for captioning engine in the GenerationContext class
The import statement for the `moviepy.editor` module is changed to `moviepy.editor as mp` to improve code readability. Additionally, the `gradio` module is imported as `gr` to improve code readability. The `GenerationContext` class now includes a `captioningengine` parameter and initializes a `captioningengine` attribute. The `setup_dir` method is modified to include a call to create a directory for the output files. The `get_file_path` method is modified to return the file path based on the output directory. The `process` method is modified to include additional steps for captioning. The `timed_script` attribute is added to store the result of the `ttsengine.synthesize` method. The `captioningengine` is used to generate captions and store them in the `captions` attribute. The final video is rendered using the `moviepy` library and saved as "final.mp4" in the output directory.

src/chore/GenerationContext.py

@@ -1,6 +1,7 @@
-import moviepy
+import moviepy.editor as mp
 import time
 import os
+import gradio as gr
 
 from .. import engines
 from ..utils.prompting import get_prompt
@@ -8,31 +9,64 @@ from ..utils.prompting import get_prompt
 
 class GenerationContext:
     def __init__(
-        self, powerfulllmengine, simplellmengine, scriptengine, ttsengine
+        self,
+        powerfulllmengine,
+        simplellmengine,
+        scriptengine,
+        ttsengine,
+        captioningengine,
     ) -> None:
-        self.powerfulllmengine: engines.LLMEngine.BaseLLMEngine = powerfulllmengine
+        self.powerfulllmengine: engines.LLMEngine.BaseLLMEngine = powerfulllmengine[0]
         self.powerfulllmengine.ctx = self
 
-        self.simplellmengine: engines.LLMEngine.BaseLLMEngine = simplellmengine
+        self.simplellmengine: engines.LLMEngine.BaseLLMEngine = simplellmengine[0]
         self.simplellmengine.ctx = self
 
-        self.scriptengine: engines.ScriptEngine.BaseScriptEngine = scriptengine
+        self.scriptengine: engines.ScriptEngine.BaseScriptEngine = scriptengine[0]
         self.scriptengine.ctx = self
 
-        self.ttsengine: engines.TTSEngine.BaseTTSEngine = ttsengine
+        self.ttsengine: engines.TTSEngine.BaseTTSEngine = ttsengine[0]
         self.ttsengine.ctx = self
 
+        self.captioningengine: engines.CaptioningEngine.BaseCaptioningEngine = (
+            captioningengine[0]
+        )
+        self.captioningengine.ctx = self
+
     def setup_dir(self):
         self.dir = f"output/{time.time()}"
         os.makedirs(self.dir)
-    
+
     def get_file_path(self, name: str) -> str:
         return os.path.join(self.dir, name)
 
     def process(self):
-        # IMPORTANT NOTE: All methods called here are expected to be defined as abstract methods in the base classes, if not there is an issue with the engine implementation.
+        # ⚠️ IMPORTANT NOTE: All methods called here are expected to be defined as abstract methods in the base classes, if not there is an issue with the engine implementation.
+
+        progress = gr.Progress()
+        self.width, self.height = (
+            1080,
+            1920,
+        )  # TODO: Add support for custom resolution, for now it's tiktok's resolution
         self.setup_dir()
 
-        script = self.scriptengine.generate()
+        self.script = self.scriptengine.generate()
 
-        timed_script = self.ttsengine.synthesize(script, self.get_file_path("tts.wav"))
+        self.timed_script = self.ttsengine.synthesize(
+            self.script, self.get_file_path("tts.wav")
+        )
+
+        if not isinstance(self.captioningengine, engines.NoneEngine):
+            self.captions = self.captioningengine.get_captions()
+        else:
+            self.captions = []
+
+        # add any other processing steps here
+
+        # we render to a file called final.mp4
+        # using moviepy CompositeVideoClip
+
+        clip = mp.CompositeVideoClip(self.captions, size=(self.width, self.height))
+        audio = mp.AudioFileClip(self.get_file_path("tts.wav"))
+        clip = clip.set_audio(audio)
+        clip.write_videofile(self.get_file_path("final.mp4"), fps=60)