initial commits

.dockerignore

@@ -0,0 +1,164 @@
+# 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/
+
+gradio_cached_examples/

.gitignore

@@ -0,0 +1,165 @@
+# 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/
+
+gradio_cached_examples/
+.DS_Store

Dockerfile

@@ -0,0 +1,11 @@
+FROM python:3.12-slim
+
+RUN pip install uv
+RUN uv venv
+
+COPY requirements.txt .
+RUN uv pip install -r requirements.txt
+
+COPY . .
+
+CMD .venv/bin/granian --interface asgi --port 8080 --host 0.0.0.0  app:app

LICENSE

@@ -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 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 2024 Stephan Fitzpatrick
+
+   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.

app.py

@@ -0,0 +1,371 @@
+import concurrent.futures as cf
+import glob
+import io
+import os
+import time
+from pathlib import Path
+from tempfile import NamedTemporaryFile
+from typing import List, Literal
+import requests
+
+import gradio as gr
+import sentry_sdk
+from fastapi import FastAPI
+from fastapi.staticfiles import StaticFiles
+from loguru import logger
+from openai import OpenAI
+from promptic import llm
+from pydantic import BaseModel, ValidationError
+from pypdf import PdfReader
+from tenacity import retry, retry_if_exception_type
+
+import pdfplumber
+import concurrent.futures
+# from docx import Document
+# from pptx import Presentation
+
+from langchain_openai import ChatOpenAI
+from langchain.chains.summarize import load_summarize_chain
+from langchain.docstore.document import Document
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_community.document_loaders.llmsherpa import LLMSherpaFileLoader
+from langchain_community.document_loaders import WebBaseLoader
+
+
+sentry_sdk.init(os.getenv("SENTRY_DSN"))
+
+app = FastAPI()
+
+app.mount("/static", StaticFiles(directory="static"), name="static")
+
+
+class DialogueItem(BaseModel):
+    text: str
+    speaker: Literal["female-1", "male-1", "female-2"]
+
+    @property
+    def voice(self):
+        return {
+            "female-1": "nova",
+            "male-1": "onyx",
+            "female-2": "shimmer",
+        }[self.speaker]
+
+
+class Dialogue(BaseModel):
+    scratchpad: str
+    dialogue: List[DialogueItem]
+
+
+@retry(retry=retry_if_exception_type(ValidationError))
+@llm(model="gpt-4o")
+def generate_dialogue(text: str) -> Dialogue:
+    """
+Your task is to take the input text provided and turn it into an engaging, informative podcast dialogue. The input text may be messy or unstructured, as it could come from a variety of sources like PDFs or web pages. Don't worry about the formatting issues or any irrelevant information; your goal is to extract the key points and interesting facts that could be fully discussed in a podcast.
+
+Here is the input text you will be working with:
+
+<input_text>
+{text}
+</input_text>
+
+First, carefully read through the input text and identify the main topics, key points, and any interesting facts or anecdotes. Think about how you could present this information in a fun, engaging way that would be suitable for an audio podcast.
+
+<scratchpad>
+Brainstorm creative ways to discuss the main topics and key points you identified in the input text. Consider using analogies, storytelling techniques, or hypothetical scenarios to make the content more relatable and engaging for listeners.
+Keep in mind that your podcast should be accessible to a general audience, so avoid using too much jargon or assuming prior knowledge of the topic. If necessary, think of ways to briefly explain any complex concepts in simple terms.
+
+Use your imagination to fill in any gaps in the input text or to come up with thought-provoking questions that could be explored in the podcast. The goal is to create an informative and entertaining dialogue, so feel free to be creative in your approach.
+
+Write your brainstorming ideas and a rough outline for the podcast dialogue here. Be sure to note the key insights and takeaways you want to reiterate at the end.
+</scratchpad>
+
+Now that you have brainstormed ideas and created a rough outline, it's time to write the actual podcast dialogue. Aim for a natural, conversational flow between the host and any guest speakers. Incorporate the best ideas from your brainstorming session and make sure to explain any complex topics in an easy-to-understand way.
+
+<podcast_dialogue>
+Write your engaging, informative podcast dialogue here, 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. Use made-up names for the hosts and guests to create a more engaging and immersive experience for listeners. Design your output to be read aloud -- it will be directly converted into audio.
+
+Make the dialogue sound like a natural conversation between Taiwanese people. Use colloquial language zh-hant, cultural references, and a friendly tone that reflects how people in Taiwan typically speak to each other. Incorporate local phrases and expressions to make the conversation authentic and relatable.
+
+Throughout the dialogue, sprinkle in new insights or interesting ideas that might arise naturally from the conversation. These could be personal anecdotes, hypothetical scenarios, or surprising facts that keep the listeners engaged.
+
+Include emotional cues to make the conversation more engaging, such as laughter, excitement, or surprise.
+
+Make the dialogue as long and detailed as possible, while still staying on topic and maintaining an engaging flow. Aim to use your full output capacity to create the longest podcast episode you can, while still communicating the key information from the input text in an entertaining way.
+
+At the end of the dialogue, have the host and guest speakers naturally summarize the main insights and takeaways from their discussion. This should flow organically from the conversation, reiterating the key points in a casual, conversational manner. Avoid making it sound like an obvious recap - the goal is to reinforce the central ideas one last time before signing off.
+</podcast_dialogue>
+    """
+
+
+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-hd",
+        voice=voice,
+        input=text,
+    ) as response:
+        with io.BytesIO() as file:
+            for chunk in response.iter_bytes():
+                file.write(chunk)
+            return file.getvalue()
+# def get_ppt_text(filename):
+#     prs = Presentation(filename)
+#     full_text = []
+#     for slide in prs.slides:
+#         for shape in slide.shapes:
+#             if hasattr(shape, "text"):
+#                 full_text.append(shape.text)
+#     return '\n'.join(full_text)
+
+
+# def get_doc_text(filename):
+#     doc = Document(filename)
+#     full_text = [para.text for para in doc.paragraphs]
+#     return '\n'.join(full_text)
+
+
+# def get_page_text(filename, page_num):
+#     with pdfplumber.open(filename) as pdf:
+#         page = pdf.pages[page_num]
+#         return page.extract_text()
+
+# def summarize_page(i, text):
+#     prompt = """Summarize the text in a detailed and concise manner."""
+#     # text = get_page_text(filename, page_num)
+#     client = OpenAI()
+#     # Check if text extraction was successful
+#     if text:
+#         response = client.chat.completions.create(
+#             model="gpt-4o",
+#             temperature=0.1,
+#             messages=[
+#                 {"role": "system", "content": prompt},
+#                 {"role": "user", "content": text}
+#             ]
+#         )
+#         return i, response.choices[0].message.content
+#     else:
+#         return i, "No text found on this page."
+
+# def summarize_large_text(texts):
+#     summary_parts = []
+#     num_pages = len(texts)
+#     with concurrent.futures.ThreadPoolExecutor() as executor:
+#         future_to_page = {executor.submit(summarize_page, i, texts[i]): i for i in range(num_pages)}
+#         for future in concurrent.futures.as_completed(future_to_page):
+#             i, page_summary = future.result()
+#             summary_parts.append((i, f"p{i+1}: {page_summary}"))
+
+#     # Sort the summary parts by page index and join them into a single string
+#     summary_parts.sort(key=lambda x: x[0])
+#     full_summary = "\n".join(part[1] for part in summary_parts)
+
+#     return full_summary
+
+# def summarize_pdf_parallel(filename):
+#     with pdfplumber.open(filename) as pdf:
+#         num_pages = len(pdf.pages)
+#         texts = [get_page_text(filename, i) for i in range(num_pages)]
+
+#     all_text = "\n".join(texts)
+
+#     if len(all_text) > 70000:
+#         return summarize_large_text(texts)
+#     else:
+#         return all_text
+
+# def summarize_file(filename):
+#     if filename.endswith(".pdf"):
+#         return summarize_pdf_parallel(filename)
+#     elif filename.endswith(".txt"):
+#         with open(filename, "r") as f:
+#             return f.read()
+#     elif filename.endswith(".docx"):
+#         return get_doc_text(filename)
+#     elif filename.endswith(".pptx"):
+#         return get_ppt_text(filename)
+#     else:
+#         raise ValueError("Unsupported file type")
+
+def summarize_chunk(chunk_text: str) -> str:
+    llm = ChatOpenAI(temperature=0, model_name="gpt-4o")
+    document = Document(page_content=chunk_text)
+    summarize_chain = load_summarize_chain(llm=llm)
+    summary = summarize_chain.invoke([document])
+    return summary["output_text"]
+
+# Function to read and extract text from a DOCX file
+def get_doc_text(filename: str) -> str:
+    from docx import Document as DocxDocument
+    doc = DocxDocument(filename)
+    full_text = [para.text for para in doc.paragraphs]
+    return '\n'.join(full_text)
+
+def get_pdf_text(filename: str) -> str:
+    full_text = []
+    with pdfplumber.open(filename) as pdf:
+        for page in pdf.pages:
+            text = page.extract_text()
+            if text:
+                full_text.append(text)
+    return '\n'.join(full_text)
+
+# Function to split text into smaller chunks
+def split_text(text: str, chunk_size: int = 1000, chunk_overlap: int = 200) -> List[str]:
+    text_splitter = RecursiveCharacterTextSplitter(
+        chunk_size=chunk_size,
+        chunk_overlap=chunk_overlap
+    )
+    chunks = text_splitter.split_text(text)
+    return chunks
+
+# Function to summarize a large document with text splitting in parallel
+def summarize_large_document(filename: str, chunk_size: int = 1000, chunk_overlap: int = 200) -> str:
+    if filename.endswith(".docx"):
+        text = get_doc_text(filename)
+    elif filename.endswith(".pdf"):
+        text = get_pdf_text(filename)
+    else:
+        raise ValueError("Unsupported file type")
+    chunks = split_text(text, chunk_size, chunk_overlap)
+    
+    summaries = []
+    with concurrent.futures.ThreadPoolExecutor() as executor:
+        futures = {executor.submit(summarize_chunk, chunk): chunk for chunk in chunks}
+        for future in concurrent.futures.as_completed(futures):
+            summaries.append(future.result())
+    
+    # Combine all summaries into one final summary
+    final_summary = "\n".join(summaries)
+    return final_summary
+
+
+def summarize_with_sherpa(url: str) -> str:
+    response = requests.head(url)
+    content_type = response.headers.get('content-type')
+    allowed_types = [
+        'application/vnd.openxmlformats-officedocument.wordprocessingml.document',  # DOCX
+        'application/vnd.openxmlformats-officedocument.presentationml.presentation',  # PPTX
+        'text/html',  # HTML
+        'text/plain',  # TXT
+        'application/xml',  # XML
+        'application/pdf', # PDF
+    ]
+    if content_type not in allowed_types:
+        loader = WebBaseLoader(url)
+        # print(content_type)
+    else:
+        loader = LLMSherpaFileLoader(
+            file_path=url,
+            new_indent_parser=True,
+            apply_ocr=True,
+            strategy="text",
+            llmsherpa_api_url="https://readers.llmsherpa.com/api/document/developer/parseDocument?renderFormat=all",
+        )
+    docs = loader.load()
+    return docs[0].page_content
+
+def generate_audio(file=None, url=None, openai_api_key: str = None) -> bytes:
+
+    if not os.getenv("OPENAI_API_KEY", openai_api_key):
+        raise gr.Error("OpenAI API key is required")
+
+    text = ""
+    if file:
+        try:
+            text = summarize_large_document(file)
+        except ValueError as e:
+            raise gr.Error(str(e))
+    elif url:
+        try:
+            text = summarize_with_sherpa(url)
+        except Exception as e:
+            raise gr.Error(str(e))
+
+    print(text)
+
+    llm_output = generate_dialogue(text)
+
+    audio = b""
+    transcript = ""
+
+    characters = 0
+
+    with cf.ThreadPoolExecutor() as executor:
+        futures = []
+        for line in llm_output.dialogue:
+            transcript_line = f"{line.speaker}: {line.text}"
+            future = executor.submit(get_mp3, line.text, line.voice, openai_api_key)
+            futures.append((future, transcript_line))
+            characters += len(line.text)
+
+        for future, transcript_line in futures:
+            audio_chunk = future.result()
+            audio += audio_chunk
+            transcript += transcript_line + "\n\n"
+
+    logger.info(f"Generated {characters} characters of audio")
+
+    temporary_directory = "./gradio_cached_examples/tmp/"
+    os.makedirs(temporary_directory, exist_ok=True)
+
+    # we use a temporary file because Gradio's audio component doesn't work with raw bytes in Safari
+    temporary_file = NamedTemporaryFile(
+        dir=temporary_directory,
+        delete=False,
+        suffix=".mp3",
+    )
+    temporary_file.write(audio)
+    temporary_file.close()
+
+    # Delete any files in the temp directory that end with .mp3 and are over a day old
+    for file in glob.glob(f"{temporary_directory}*.mp3"):
+        if os.path.isfile(file) and time.time() - os.path.getmtime(file) > 24 * 60 * 60:
+            os.remove(file)
+
+    return temporary_file.name, transcript
+
+
+demo = gr.Interface(
+    title="PDF to Podcast",
+    description=Path("description.md").read_text(),
+    fn=generate_audio,
+    examples=[],
+    inputs=[
+        gr.File(
+            label="PDF",
+        ),
+        gr.Textbox(
+            label="URL",
+            placeholder="Enter URL of a PDF, DOCX, or PPTX file",
+        ),
+        gr.Textbox(
+            label="OpenAI API Key",
+            visible=not os.getenv("OPENAI_API_KEY"),
+        ),
+    ],
+    outputs=[
+        gr.Audio(label="Audio", format="mp3"),
+        gr.Textbox(label="Transcript"),
+    ],
+    allow_flagging=False,
+    clear_btn=None,
+    head=os.getenv("HEAD", "") + Path("head.html").read_text(),
+    cache_examples="lazy",
+    api_name=False,
+)
+
+
+demo = demo.queue(
+    max_size=20,
+    default_concurrency_limit=20,
+)
+
+app = gr.mount_gradio_app(app, demo, path="/")
+
+if __name__ == "__main__":
+    demo.launch(show_api=False)

description.md

@@ -0,0 +1,3 @@
+<p style="text-align:center">
+  <strong>Convert any PDF into a podcast episode! Experience research papers, websites, and more in a whole new way.</strong>
+</p>

head.html

@@ -0,0 +1,49 @@
+<!-- Primary Meta Tags -->
+<title>PDF to Podcast - Convert Your Documents to Audio</title>
+<meta name="title" content="PDF to Podcast - Convert Your Documents to Audio" />
+<meta
+  name="description"
+  content="Easily convert your PDF documents into audio podcasts. Perfect for listening on the go and making content more accessible."
+/>
+
+<!-- Open Graph / Facebook -->
+<meta property="og:type" content="website" />
+<meta property="og:url" content="https://pdf-to-podcast.com/" />
+<meta
+  property="og:title"
+  content="PDF to Podcast - Convert Your Documents to Audio"
+/>
+<meta
+  property="og:description"
+  content="Easily convert your PDF documents into audio podcasts. Perfect for listening on the go and making content more accessible."
+/>
+<meta
+  property="og:image"
+  content="https://pdf-to-podcast.com/static/logo.png"
+/>
+
+<!-- Twitter -->
+<meta property="twitter:card" content="summary_large_image" />
+<meta property="twitter:url" content="https://pdf-to-podcast.com/" />
+<meta
+  property="twitter:title"
+  content="PDF to Podcast - Convert Your Documents to Audio"
+/>
+<meta
+  property="twitter:description"
+  content="Easily convert your PDF documents into audio podcasts. Perfect for listening on the go and making content more accessible."
+/>
+<meta
+  property="twitter:image"
+  content="https://pdf-to-podcast.com/static/logo.png"
+/>
+
+<!-- Additional Meta Tags -->
+<meta name="viewport" content="width=device-width, initial-scale=1" />
+<meta charset="UTF-8" />
+<meta name="author" content="Stephan Fitzpatrick" />
+<meta
+  name="keywords"
+  content="PDF to Podcast, PDF to audio, document to podcast, audio conversion, podcast creation, accessible content"
+/>
+<link rel="icon" href="/static/icon.png" type="image/png" />

requirements.txt

@@ -0,0 +1,19 @@
+gradio~=4.36
+promptic==0.7.5
+pydantic
+google-generativeai
+loguru~=0.7
+pypdf~=4.1
+tenacity~=8.3
+sentry-sdk~=2.5
+granian~=1.4
+# PyPDF2
+pdfplumber
+openai
+# docx
+# python-pptx
+llmsherpa
+langchain_openai
+langchain_community
+langchain
+bs4