youtube-short-generator:v1

.gitignore

@@ -0,0 +1,163 @@
+.env
+service_account_file.json
+venv/
+
+# 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
+.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/

app.py

@@ -0,0 +1,69 @@
+import streamlit as st
+import os
+import re
+from youtube_short_generator import YoutubeShortGenerator
+
+def main():
+    st.title("YouTube Shorts Generator 🎥")
+    st.write("Generate AI-powered YouTube Shorts by just entering a title!")
+    
+    # User Input
+    video_title = st.text_input("Enter Video Title:", "Top 3 Marvel Superheroes")
+    
+    if st.button("Generate Video"):
+        if video_title.strip():
+            # Validate that the title starts with "Top 3" or "Top 5" (case-insensitive)
+            pattern = r"^top\s*(3|5)\b"
+            if not re.match(pattern, video_title.strip(), re.IGNORECASE):
+                st.warning("Please start the title with 'Top 3' or 'Top 5'.")
+                return
+            
+            st.info("Starting video generation process...")
+            
+            try:
+                # Initialize Generator
+                yt_generator = YoutubeShortGenerator()
+                
+                with st.spinner("Analyzing title and extracting keywords..."):
+                    yt_generator.title_to_keywords(video_title)
+                    st.info("Keywords extracted successfully!")
+                
+                with st.spinner("Generating images..."):
+                    yt_generator.generate_images()
+                    st.info("Images generated successfully!")
+                
+                with st.spinner("Overlaying text on images..."):
+                    yt_generator.overlay_text_to_images()
+                    st.info("Text overlay completed!")
+                
+                with st.spinner("Generating audio clips..."):
+                    yt_generator.generate_audio_clips()
+                    st.info("Audio clips generated successfully!")
+                
+                with st.spinner("Combining images and audio into video..."):
+                    yt_generator.make_video()
+                    st.info("Video is being finalized!")
+                
+                # Get the generated video path
+                video_path = os.path.join(yt_generator.generated_video_dir, 'final_video.mp4')
+                
+                if os.path.exists(video_path):
+                    st.success("Video generated successfully!")
+                    
+                    # Provide a download link
+                    with open(video_path, "rb") as file:
+                        st.download_button(
+                            label="Download Video",
+                            data=file,
+                            file_name="youtube_short.mp4",
+                            mime="video/mp4"
+                        )
+                else:
+                    st.error("Error: Video file not found.")
+            except Exception as e:
+                st.error(f"An error occurred: {e}")
+        else:
+            st.warning("Please enter a valid title.")
+
+if __name__ == "__main__":
+    main()

constants.py

@@ -0,0 +1,40 @@
+import os
+from dotenv import load_dotenv
+
+load_dotenv()
+
+# API keys need to be configured in .env
+llm_api_keys = {
+        "openai": os.getenv('OPENAI_API_KEY'),
+        "groq": os.getenv('GROQ_API_KEY'),
+        "anthropic": os.getenv('ANTHROPIC_API_KEY')
+    }
+
+# optionally change providers
+CHOSEN_LLM_PROVIDER = os.getenv('CHOSEN_LLM_PROVIDER','groq')  
+CHOSEN_EMBEDDING_PROVIDER = os.getenv('CHOSEN_EMBEDDING_PROVIDER','ollama')  
+
+
+FONT_BASE_DIR = 'fonts'
+HF_TOKEN = os.getenv("HF_TOKEN", None)
+IMAGE_GENERATION_SPACE_NAME="habib926653/stabilityai-stable-diffusion-3.5-large-turbo"
+
+
+# LLM Models dictionary
+selected_llm_model = {
+        "openai": os.getenv('GPT_MODEL','gpt-4o-mini'),
+        "groq": os.getenv('GROQ_MODEL','llama-3.3-70b-versatile'),
+        "anthropic": os.getenv('ANTHROPIC_MODEL','claude-3-5-sonnet-latest'),
+        "ollama": os.getenv('OLLAMA_MODEL','llama3.1')
+
+    }
+
+
+# Embedding Model Models dictionary
+selected_embedding_model = {
+        "openai": os.getenv('GPT_EMBEDDING_MODEL'),
+        "groq": os.getenv('GROQ_EMBEDDING_MODEL'),
+        "anthropic": os.getenv('ANTHROPIC_EMBEDDING_MODEL'),
+        "ollama": os.getenv('OLLAMA_EMBEDDING_MODEL')
+
+    }

env.sample

@@ -0,0 +1,2 @@
+GROQ_API_KEY=GROQ_API_KEY
+HF_TOKEN=HF_TOKEN

fonts/Roboto/LICENSE.txt

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

function_wrap_center.py

@@ -0,0 +1,157 @@
+from PIL import Image, ImageDraw, ImageFont,ImageStat,ImageFilter,ImageEnhance
+from django.conf import settings
+import constants
+import os
+
+def wrap_text(draw, text, font, max_width):
+    words = text.split()
+    lines = []
+    current_line = words[0]
+
+    for word in words[1:]:
+        test_line = current_line + " " + word
+        if draw.textlength(test_line, font) <= max_width:
+            current_line = test_line
+        else:
+            lines.append(current_line)
+            current_line = word
+
+    lines.append(current_line)
+    return lines
+
+def draw_text_centered(draw, lines, position, font, max_width, padding, fill='yellow'):
+    y = position[1]
+
+    for line in lines:
+        text_width = draw.textlength(line, font)
+        x = position[0] + (max_width - text_width) // 2
+        draw.text((x, y), line, font=font, fill=fill)
+        y += font.getsize('hg')[1] + padding
+
+def get_wrapped_text_size(draw, lines, font, padding):
+    line_height = font.getsize('hg')[1]
+    total_height = len(lines) * (line_height + padding) - padding
+    max_line_width = max(draw.textlength(line, font) for line in lines)
+    return total_height, max_line_width
+
+def dynamically_adjust_font(draw, text, font, max_width, max_height, padding):
+    lines = wrap_text(draw, text, font, max_width)
+    total_height, _ = get_wrapped_text_size(draw, lines, font, padding)
+    while total_height > max_height and font.size > 10:
+        font = ImageFont.truetype(font.path, font.size - 1)
+        lines = wrap_text(draw, text, font, max_width)
+        total_height, _ = get_wrapped_text_size(draw, lines, font, padding)
+    return font, lines
+
+
+def is_image_dark(image,threshold=128):
+    """Determine if the image is predominantly dark, light or in the middle and return a suitable color for overlay"""
+    grayscale = image.convert('L')  # Convert to grayscale
+    stat = ImageStat.Stat(grayscale)
+    avg_brightness = stat.mean[0]
+
+    if avg_brightness < threshold:
+        return ('dark','yellow')
+    else:
+        return ('light','red')
+    
+
+def add_text_to_image(image_path, text, is_title=True, save_to=None):
+    # Load the image
+    image = Image.open(image_path)
+
+    # Resize the image
+    resized_image = image.resize((360, 740))
+
+    # Get resized image dimensions
+    image_width, image_height = resized_image.size
+
+    # check if the image is more darker or more lighter
+    image_brightness_level = is_image_dark(resized_image)
+
+    # Create a drawing object
+    draw = ImageDraw.Draw(resized_image)
+
+    # setting up font_paths
+    font_paths = {
+        "weaselic" : os.path.join(constants.FONT_BASE_DIR,'Weaselic.ttf'),
+        "black": os.path.join(constants.FONT_BASE_DIR,'Roboto/Roboto-Black.ttf'),
+        "bold": os.path.join(constants.FONT_BASE_DIR,'Roboto/Roboto-Bold.ttf'),
+        "medium": os.path.join(constants.FONT_BASE_DIR,'Roboto/Roboto-Medium.ttf'),
+        "light": os.path.join(constants.FONT_BASE_DIR,'Roboto/Roboto-Light.ttf'),
+        "thin": os.path.join(constants.FONT_BASE_DIR,'Roboto/Roboto-Thin.ttf')
+    }
+
+    # Define fonts
+    fonts = {
+        "weaselic" : ImageFont.truetype(font_paths['weaselic'], 43),
+        "black": ImageFont.truetype(font_paths['black'], 40),
+        "bold": ImageFont.truetype(font_paths['bold'], 35),
+        "medium": ImageFont.truetype(font_paths['medium'], 40),
+        "light": ImageFont.truetype(font_paths['light'], 30),
+        "thin": ImageFont.truetype(font_paths['thin'], 30)
+    }
+
+    padding = 5
+    margin_between = 50  # Margin between title and description
+    safe_margin = 10  # Margin from the image edges
+
+    if is_title:
+        font = fonts["bold"]
+        max_width = image_width - 2 * safe_margin
+        max_height = (image_height - 2 * safe_margin) // 2
+
+        # Dynamically adjust font size and wrap text
+        font, lines = dynamically_adjust_font(draw, text, font, max_width, max_height, padding)
+
+        # Calculate total text height
+        total_height, _ = get_wrapped_text_size(draw, lines, font, padding)
+
+        # Positioning
+        if total_height > image_height - 2 * safe_margin:
+            print("Text does not fit within the image boundaries.")
+        else:
+            position = (safe_margin, safe_margin + (image_height - total_height) // 2 - 120)
+
+            # Draw the rectangle behind the text
+            rect_x0 = safe_margin
+            rect_x1 = image_width - safe_margin
+            rect_y0 = position[1] - padding
+            rect_y1 = rect_y0 + total_height + 2 * padding
+            draw.rectangle([(rect_x0, rect_y0), (rect_x1, rect_y1)], fill="yellow")
+
+            # Draw wrapped and centered text
+            draw_text_centered(draw, lines, (safe_margin, rect_y0 + padding), font, rect_x1 - rect_x0, padding, fill='black')
+
+    else:
+        font = fonts["weaselic"]
+        max_width = image_width - 2 * safe_margin
+        max_height = (image_height - 2 * safe_margin) // 2
+
+        # Dynamically adjust font size and wrap text
+        font, lines = dynamically_adjust_font(draw, text, font, max_width, max_height, padding)
+
+        # Calculate total text height
+        total_height, _ = get_wrapped_text_size(draw, lines, font, padding)
+
+        # Positioning
+        if total_height > image_height - 2 * safe_margin:
+            print("Text does not fit within the image boundaries.")
+        else:
+            position = (safe_margin, safe_margin + (image_height - total_height) // 2)
+
+            # Draw wrapped and centered text
+            description_color =  image_brightness_level[1]
+            draw_text_centered(draw, lines, position, font, max_width, padding,fill = description_color)
+
+    # Save the image if save_to is provided
+    if save_to:
+        resized_image.save(save_to)
+
+# Example usage:
+if __name__ == '__main__':
+    title_text = "Top 5 mountains in the world"
+    description_text = "Mount Everest"
+
+    add_text_to_image('wow.png', title_text, is_title=True, save_to='output_title.png')
+    add_text_to_image('wow.png', description_text, is_title=False, save_to='output_description.png')

image_generator.py

@@ -0,0 +1,59 @@
+import pollinations
+import constants
+from PIL import Image
+from gradio_client import Client
+
+
+class ImageGenerator:
+    def __init__(self, model=pollinations.Image.flux(), seed="random", width=720, height=1280, enhance=False, nologo=True, private=True, safe=False, referrer="pollinations.py"):
+        # Initialize the image model with provided parameters
+        self.image_model = pollinations.Image(
+            model=model,
+            seed=seed,
+            width=width,
+            height=height,
+            enhance=False,
+            nologo=nologo,
+            private=private,
+            safe=safe,
+            referrer=referrer
+        )
+    
+    def generate_image_with_pollinations_ai(self, prompt):
+        # Generate image using the provided prompt
+        try:
+            image = self.image_model(prompt=prompt)
+            return image  # Return the generated image object
+        except Exception as e:
+            print(f"Error generating image: {e}")
+            return None  # Return None if there's an error
+        
+
+    def generate_image(self, prompt, path='test_image.png'):
+        try:
+            # Initialize the Gradio Client with Hugging Face token
+            client = Client(constants.IMAGE_GENERATION_SPACE_NAME, hf_token=constants.HF_TOKEN)
+
+            # Make the API request
+            result = client.predict(
+                param_0=prompt,  # Text prompt for image generation
+                api_name="/predict"
+            )
+
+            image = Image.open(result)
+            image.save(path)
+
+            # Return the result (which includes the URL or file path)
+            return result
+
+        except Exception as e:
+            print(f"Error during image generation: {e}")
+            return {"error": str(e)}
+
+
+# Example usage
+if __name__ == '__main__':
+    image_generator = ImageGenerator()  # You can pass custom params here if needed
+    result = image_generator.generate_image("A cat with flowers around it.",path='wow9.png')
+    
+    print(result)

structured_output.py

@@ -0,0 +1,119 @@
+from typing import Type, Optional
+from pydantic import BaseModel, Field
+from langgraph.graph import StateGraph, START, END
+import constants
+from typing import TypedDict
+
+
+
+# Define the State structure (similar to previous definition)
+class State(TypedDict):
+    messages: list
+    output: Optional[BaseModel]
+
+
+# Generic Pydantic model-based structured output extractor
+class StructuredOutputExtractor:
+    def __init__(self, response_schema: Type[BaseModel]):
+        """
+        Initializes the extractor for any given structured output model.
+        
+        :param response_schema: Pydantic model class used for structured output extraction
+        """
+        self.response_schema = response_schema
+
+        # Initialize language model (provider and API keys come from constants.py)
+        self.llm = self._choose_llm_provider(constants.CHOSEN_LLM_PROVIDER)
+        
+        # Bind the model with structured output capability
+        self.structured_llm = self.llm.with_structured_output(response_schema)
+        
+        # Build the graph for structured output
+        self._build_graph()
+
+    def _build_graph(self):
+        """
+        Build the LangGraph computational graph for structured extraction.
+        """
+        graph_builder = StateGraph(State)
+
+        # Add nodes and edges for structured output
+        graph_builder.add_node("extract", self._extract_structured_info)
+        graph_builder.add_edge(START, "extract")
+        graph_builder.add_edge("extract", END)
+
+        self.graph = graph_builder.compile()
+
+    def _extract_structured_info(self, state: dict):
+        """
+        Extract structured information using the specified response model.
+        
+        :param state: Current graph state
+        :return: Updated state with structured output
+        """
+        query = state['messages'][-1].content
+        print(f"Processing query: {query}")
+        try:
+            # Extract details using the structured model
+            output = self.structured_llm.invoke(query)
+            # Return the structured response
+            return {"output": output}
+        except Exception as e:
+            print(f"Error during extraction: {e}")
+            return {"output": None}
+
+    def extract(self, query: str) -> Optional[BaseModel]:
+        """
+        Public method to extract structured information.
+        
+        :param query: Input query for structured output extraction
+        :return: Structured model object or None
+        """
+        from langchain_core.messages import HumanMessage
+
+        result = self.graph.invoke({
+            "messages": [HumanMessage(content=query)]
+        })
+        # Return the structured model response, if available
+        result = result.get('output')
+        return result
+
+    def _choose_llm_provider(self, chosen_llm_provider):
+        """Dynamically imports and selects the LLM provider based on configuration, and asks to install the library if it's missing."""
+        api_key = constants.llm_api_keys.get(chosen_llm_provider)
+        if chosen_llm_provider == 'openai':
+            from langchain_openai import ChatOpenAI
+            return ChatOpenAI(model=constants.selected_llm_model.get('openai'), streaming=True, api_key=api_key)
+        elif chosen_llm_provider == 'ollama':
+            from langchain_ollama import ChatOllama
+            return ChatOllama(model=constants.selected_llm_model.get('ollama'))  # streaming is enabled by default
+        elif chosen_llm_provider == 'groq':
+            from langchain_groq import ChatGroq
+            return ChatGroq(model=constants.selected_llm_model.get('groq'), streaming=True, api_key=api_key)
+        elif chosen_llm_provider == 'anthropic':
+            from langchain_anthropic import ChatAnthropic
+            return ChatAnthropic(model=constants.selected_llm_model.get('anthropic'), streaming=True, api_key=api_key)
+        else:
+            raise ValueError(f"Unsupported LLM provider: {chosen_llm_provider}")
+
+
+if __name__ == '__main__':
+        
+        # Example Pydantic model (e.g., Movie)
+        class Movie(BaseModel):
+            title: str = Field(description="the title of the youtube video")
+            title_image: str = Field(description="highly detailed and descriptive image prompt for the Title")
+            items: list[str] = Field(description="top n number of requested items")
+            image_prompts: list[str] = Field(description="highly detailed and descriptive image prompts for each item ")
+
+
+
+        # Example usage with a generic structured extractor
+        extractor = StructuredOutputExtractor(response_schema=Movie)
+
+        query = "Top 5 Superheroes"
+
+        result = extractor.extract(query)
+        print(type(result))
+        if result:
+            print(result)

youtube_short_generator.py

@@ -0,0 +1,208 @@
+import os
+import uuid
+import shutil
+from image_generator import ImageGenerator
+from moviepy.editor import ImageClip, concatenate_videoclips,AudioFileClip
+from function_wrap_center import add_text_to_image
+from gtts import gTTS
+from structured_output import StructuredOutputExtractor
+from pydantic import BaseModel, Field
+
+
+class YoutubeShortGenerator:
+
+    def __init__(self):
+        self.video_title = None
+        self.result = None
+        self.media_dir = 'generated_media'
+        self.generated_video_dir = None
+        self.image_dir = None
+        self.audio_clips_dir = None
+        self.video_path = None
+
+        os.makedirs(self.media_dir,exist_ok=True)
+
+    def title_to_keywords(self, title):
+        # Define your data extraction model here
+        class TopN(BaseModel):
+            title: str = Field(description="the title of the youtube video")
+            title_image_prompt: str = Field(description="highly detailed and descriptive image prompt for the background image of Title")
+            items: list[str] = Field(description="top n number of requested items")
+            items_image_prompts: list[str] = Field(description="highly detailed and descriptive image prompts for each item ")
+
+        # Assuming StructuredOutputExtractor is defined and functional
+        extractor = StructuredOutputExtractor(response_schema=TopN)
+        result = extractor.extract(title)
+        self.result = result
+
+        # create main directory for saving  video related content  i.e images, audio_clips
+        video_title = self.result.title
+        unique_id = uuid.uuid4().hex
+        folder_path = f"{self.media_dir}/generated_{video_title}_{unique_id}"
+        self.generated_video_dir = folder_path
+
+        return self
+    
+    def generate_images(self):
+        if not self.result:
+            print("No data available. Call title_to_keywords first.")
+            return self
+        
+        print(self.result,'inside generate_images()')
+        
+        generator = ImageGenerator()  # Your custom image generator
+        folder_path = f"{self.generated_video_dir}/generated_images"  # Append unique ID
+        os.makedirs(folder_path, exist_ok=True)  # Ensure directory is created
+        self.image_dir = folder_path
+
+        # Generate Title Image
+        # generator.generate_image(self.result.title_image_prompt, path=f"{folder_path}/title.png")
+        print("Title Prompt: ",self.result.title_image_prompt)
+
+        # generate images using pollinations_ai
+        # title_image = generator.generate_image(self.result.title_image_prompt)
+        # title_image.save(f"{folder_path}/title.png")
+
+        # generate images using stable-diffusion-turbo
+        generator.generate_image(self.result.title_image_prompt, path=f"{folder_path}/title.png")
+
+
+        print("Generating Images...")
+        image_prompts = self.result.items_image_prompts
+        print("items image prompts: ", image_prompts)
+        image_prompts = reversed(image_prompts)
+        print("Image Prompts: ", image_prompts)  # Placeholder for actual image processing
+
+        # Generate and save images
+        for index, image_prompt in enumerate(image_prompts):
+            
+            # generate images using pollinations_ai
+            # image = generator.generate_image(image_prompt)  
+            # image.save(f"{folder_path}/{index}.png")
+            
+            # generate images using stable-diffusion-turbo
+            generator.generate_image(image_prompt, f"{folder_path}/{index}.png" )  
+            print(f"Image {index} saved.")
+
+        return self  # Return self for further chaining if needed
+    
+
+    def overlay_text_to_images(self):
+        if not self.result:
+            print("No data available. Call title_to_keywords first.")
+            return self
+        
+        title_text = self.result.title
+        text_items = reversed(self.result.items)
+        print("text_items ",text_items)
+
+        # add text to title image
+        add_text_to_image(text=title_text,image_path=f"{self.image_dir}/title.png", save_to=f"{self.image_dir}/title.png")
+        
+        # add text to other images
+        for index, text in enumerate(text_items):
+            image_path = f"{self.image_dir}/{index}.png"
+            add_text_to_image(text=text,image_path=image_path,is_title=False, save_to=image_path)
+
+        return self
+        
+        
+
+    
+    def generate_audio_clips(self):
+        if not self.result:
+            print("No data available. Call title_to_keywords first.")
+            return self
+        
+        print("Generating Title Audio...")
+        overlay_title = self.result.title
+        print("Title: ", overlay_title)
+
+        
+        print("Generating Audio Clips...")
+        overlay_text_items = reversed(self.result.items)
+        print("Overlay Text: ", overlay_text_items)  # Placeholder for actual text processing
+
+        folder_path = f"{self.generated_video_dir}/generated_audio_clips"  # Append unique ID
+        self.audio_clips_dir = folder_path
+
+        os.makedirs(folder_path, exist_ok=True)  # Ensure directory is created
+
+        # Generate title Audio
+        title_tts = gTTS(text=overlay_title)
+        title_tts.save(f"{folder_path}/title.mp3")
+        print(f"Title Audio clip title.mp3 saved.")
+
+        # Generate and save audio clips
+        for index, text_overlay in enumerate(overlay_text_items):
+            tts = gTTS(text=text_overlay)  # Generate audio clip
+            tts.save(f"{folder_path}/{index}.mp3")  # Save the audio as MP3
+            print(f"Audio clip {index} saved.")
+
+        return self  # Return self for further chaining if needed
+        
+
+    def make_video(self):
+        # Ensure title is included and sorted properly
+        audio_files = sorted(os.listdir(self.audio_clips_dir), key=lambda x: (x != "title.mp3", int(x.split(".")[0]) if x != "title.mp3" else -1))
+        image_files = sorted(os.listdir(self.image_dir), key=lambda x: (x != "title.png", int(x.split(".")[0]) if x != "title.png" else -1))
+
+        print("Sorted audio files:", audio_files)
+        print("Sorted image files:", image_files)
+
+        # Initialize audio clips
+        audio_clips = [AudioFileClip(os.path.join(self.audio_clips_dir, audio)) for audio in audio_files]
+
+        # Initialize image clips with matching durations
+        image_clips = [ImageClip(os.path.join(self.image_dir, image)).set_duration(audio.duration) 
+                    for image, audio in zip(image_files, audio_clips)]
+
+        # Attach audio to images
+        image_clips_with_audio = [image.set_audio(audio) for image, audio in zip(image_clips, audio_clips)]
+
+        # Concatenate all video clips
+        video_clip = concatenate_videoclips(image_clips_with_audio, method="compose")
+
+        # Save the final video
+        video_clip.write_videofile(
+            os.path.join(self.generated_video_dir, 'final_video.mp4'), 
+            codec='libx264', 
+            fps=24
+        )
+
+        self.remove_directory(self.image_dir)
+        self.remove_directory(self.audio_clips_dir)
+
+
+        existing_videos = sorted(
+            [os.path.join(self.media_dir, d) for d in os.listdir(self.media_dir) 
+             if os.path.isdir(os.path.join(self.media_dir, d))],
+            key=os.path.getctime  # Sort by creation time (oldest first)
+        )
+
+        if len(existing_videos) > 5:
+            for old_video_dir in existing_videos[:-5]:  # Keep last 5, delete the rest
+                if old_video_dir != self.generated_video_dir:  # Ensure we don't delete the current video
+                    self.remove_directory(old_video_dir)
+
+    @staticmethod
+    def remove_directory(dir_path):
+        """
+        Remove the specified directory and all its contents.
+        """
+        if os.path.isdir(dir_path):
+            shutil.rmtree(dir_path)
+            print(f"{dir_path} and its contents have been removed.")
+        else:
+            print(f"{dir_path} does not exist or is not a directory.")
+
+            
+
+    
+
+if __name__ == '__main__':
+    yt_short_generator = YoutubeShortGenerator()
+    result = yt_short_generator.title_to_keywords("top 3 Marvel Superheroes").generate_images().overlay_text_to_images().generate_audio_clips().make_video()
+
+
+