First commit

.gitignore

@@ -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/#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
+.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/
+
+.streamlit/secrets.toml

app.py

@@ -0,0 +1,98 @@
+# Original code
+# https://www.youtube.com/watch?app=desktop&v=_j7JEDWuqLE&ab_channel=AIJason
+
+# OpenAI break 
+# https://github.com/langchain-ai/langchain/issues/12949
+
+import os
+import requests
+from transformers import pipeline
+#from langchain import PromptTemplate, LLMChain, OpenAI
+from langchain.prompts import PromptTemplate
+from langchain.chains import LLMChain
+from langchain.llms import OpenAI
+import streamlit as st
+
+#from huggingface_hub import HfApi
+HUGGING_FACE_API_TOKEN = st.secrets["HUGGING_FACE_API_TOKEN"]
+
+#api = HfApi()
+#if api.is_authenticated():
+#    print('HF server')
+#    HUGGING_FACE_API_TOKEN = os.environ("HUGGING_FACE_API_TOKEN")
+#else:
+#    print('Local machine')
+#    HUGGING_FACE_API_TOKEN = st.secrets("HUGGING_FACE_API_TOKEN")
+
+# img2text
+def img2text(url):
+    image_to_text = pipeline("image-to-text", model="Salesforce/blip-image-captioning-base")
+
+    text = image_to_text(url)[0]["generated_text"]
+
+    print(text)
+    return text
+
+# llm
+def generate_story(scenario):
+    template = """
+    You are a story teller;
+    You can generate a short story based on a simple narrative, the story should be no more than 20 words;
+
+    CONTEXT: {scenario}
+    STORY:
+    """
+
+    prompt = PromptTemplate(template=template, input_variables=["scenario"])
+
+    story_llm = LLMChain(llm=OpenAI(
+        model_name="gpt-3.5-turbo", temperature=1), prompt=prompt, verbose=True)
+    
+    story = story_llm.predict(scenario=scenario)
+
+    print(story)
+    return story
+
+# text to speech
+def text2speech(message):
+    API_URL = "https://api-inference.huggingface.co/models/espnet/kan-bayashi_ljspeech_vits"
+    headers = {"Authorization": f"Bearer {HUGGING_FACE_API_TOKEN}"}
+    payloads = {
+        "inputs": message
+    }
+
+    response = requests.post(API_URL, headers=headers, json=payloads)
+    with open('audio.flac', 'wb') as file:
+        file.write(response.content)
+
+def main():
+
+    st.set_page_config(page_title="img 2 audio story", page_icon="A")
+
+    st.header("Turn img into audio story")
+    uploaded_file = st.file_uploader("Chose an image...", type="jpg")
+
+    if uploaded_file is not None:
+        bytes_data = uploaded_file.getvalue()
+        with open(uploaded_file.name, "wb") as file:
+            file.write(bytes_data)
+        st.image(uploaded_file, caption="Uploaded Image.",
+                 use_column_width=True)
+        scenario = img2text(uploaded_file.name)
+        story = generate_story(scenario)
+        text2speech(story)
+
+        with st.expander("scenario"):
+            st.write(scenario)
+        with st.expander("story"):
+            st.write(story)
+
+        st.audio("audio.flac")
+
+if __name__ == '__main__':
+    main()
+
+# Debug
+#scenario = img2text("photo.jpg")
+#story = generate_story(scenario)
+#text2speech(story)

requests.txt

@@ -0,0 +1,5 @@
+requests
+python-dotenv
+transformers
+openai == 0.28.1 
+langchain == 0.0.330