initial commit

.gitignore

@@ -0,0 +1,161 @@
+# 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/
+api_key.py

speech_to_text.py

@@ -0,0 +1,96 @@
+import openai
+import whisper
+from langchain import OpenAI, SQLDatabase, SQLDatabaseChain
+from langchain.llms import OpenAI
+from langchain.chains.summarize import load_summarize_chain
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from api_key import open_ai_key
+
+llm = OpenAI(temperature=0, openai_api_key='open_ai_key')
+
+
+
+#This is another alternative, but this block allows for the detection of the language and it also provides lowever-level access to the model
+
+def transcribe(aud_inp, whisper_lang):
+    if aud_inp is None:
+        return ''
+    model = whisper.load_audo('base')
+    #load audo and pad/trim it to fit 30seconds
+    audio = whisper.load_audio(aud_inp)
+    audio = whisper.pad_or_trim(audio)
+    #make log-Mel spectrogram and move to the same devcice as the model
+    mel = whisper.log_mel_spectogram(audio).to(model.device)
+    #detect the spoken language
+    _,probs = model.detect_language(mel)
+    print(f'Detected language: {max(probs, key=probs.get)}')
+    #decode the audio
+    options = whisper.DecodingOptions()
+    result = whisper.decode(model, mel, options)
+    print(result.text)
+    return result 
+#Function to convert speech to text
+
+#These two functions might need to go away but I am not entirely sure yet
+# def transcribe_audio(audio_file_path):
+#     #not sure what the path to the audio file will be so just putting a string as a place holder
+#     with open('audio file path') as audio_file:
+#         transcribtion = openai.Audio.transcribe('whisper-1', audio_file)
+#     return transcribtion['text']
+# #Save the transcribed text to a docx file
+# def save_as_doc(question, filename):
+#     doc=Document()
+#     for key, value in minutes.items():
+#         heading = ' '.join(word.capitalize() for word in key.split('_'))
+#         doc.add_heading(heading, level=1)
+#         doc.add_paragraph(value)
+#         doc.add_page_break()
+#     doc.save(f'{filename}.docx')
+#Not sure how the data will be stored, but my idea is that when a question or prompt is asked the audio file will be stored as text which then be fed into the llm 
+#to then query the database and return the answer. 
+
+#estbalish the question to be asked
+# question = transcribe
+
+# #I feel like I need another step here so that the model takes the question, goes to the db and knows that it needs to look for the answer to the question
+# # I am wondering if I need to setup an extraction algorithm here, but then how do I link the extraction algorithm to the database?
+# #Creating link to db
+# # I am also wondering if there should be an api for the model to call in order to access the database? Thinking that might be more better?
+# sqlite_db_path = 'sqlite:///database.db'
+# db = SQLDatabase.from_uri(f'sqlite:///{sqlite_db_path}')
+
+# db_chain = SQLDatabaseChain(llm-llm, database=db)
+
+# db_results = db_chain.run(transcribe)
+
+#After retrieving the data from the database, have llm summarize the data and return the answer to the question
+
+# with open(db_results) as file:
+#     text = file.read()
+
+
+# text_splitter = RecursiveCharacterTextSplitter(separators = ['\n\n', '\n'], chunk_size = 100, chunk_overlap = 0)
+# docs = text_splitter.create_documents([text])
+
+# chain = load_summarize_chain(llm=llm, chain_type = 'map_reduce')
+
+# output = chain.run(docs)
+
+# #Setup for the model to recevie a question and return the answer
+# context = output
+
+
+# answer = llm(context+question)
+
+
+# def save_as_doc(answer, filename):
+#     doc=Document()
+#     #not sure what the data will look like, as to what the keys and values will be, so just putting a place holder
+#     for key, value in minutes.items():
+#         heading = ' '.join(word.capitalize() for word in key.split('_'))
+#         doc.add_heading(heading, level=1)
+#         doc.add_paragraph(value)
+#         doc.add_page_break()
+#     doc.save(f'{filename}.docx')
+
+#Next part is to take the saved docx file and convert it to an audio file to be played back to the user