Clean up project

.dockerignore

@@ -0,0 +1,7 @@
+*.env
+models
+models/*
+data
+data/*
+notebooks
+notebooks/*

.env.template

@@ -0,0 +1,16 @@
+export ENV="dev"
+export PROJECT_PATH="/Users/<xx>/"
+export OPENSEARCH_URL="https://localhost:9200"
+
+export LOADER_CONFIG="file_loader" # defaults to s3_loader 
+export VECTOR_STORE_CONFIG="opensearch" # defaults to opensearch
+export LLM_MODEL="local_llm" # defaults to hosted_llm
+
+export SUMMARISE_API = "xxxxxxx"
+export SUMMARISE_URL = "https://xxxx.amazonaws.com/api"
+export FACTCHECK_API = "xxxxxxx"
+export FACTCHECK_URL = "https://xxxx.amazonaws.com/api"
+export GLOSSERY_API = "xxxxxxx"
+export GLOSSERY_URL = "https://xxxx.amazonaws.com/api"
+export CONVERSATION_API = "xxxxxxx"
+export CONVERSATION_URL = "https://xxxx.amazonaws.com/api"

.gitattributes

@@ -0,0 +1,3 @@
+*.ipynb filter=nbstripout
+*.zpln filter=nbstripout
+*.ipynb diff=ipynb

.github/workflows/black.yml

@@ -0,0 +1,10 @@
+name: Black
+
+on: [push, pull_request]
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - uses: psf/black@stable

.github/workflows/isort.yml

@@ -0,0 +1,10 @@
+name: isort
+on:
+  - push
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - uses: isort/isort-action@v1

.gitignore

@@ -0,0 +1,169 @@
+# 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
+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/
+
+#mac
+.DS_Store
+
+#models
+/models/*
+
+#data
+/data/*
+/vacancies

.isort.cfg

@@ -0,0 +1,2 @@
+[tool.isort]
+profile = "black"

.pre-commit-config.yaml

@@ -0,0 +1,15 @@
+repos:
+  - repo: https://github.com/psf/black
+    rev: 24.3.0
+    hooks:
+      - id: black
+  - repo: https://github.com/pycqa/isort
+    rev: 5.13.2
+    hooks:
+      - id: isort
+        name: isort (python)
+        args: ["--profile", "black"]
+  - repo: https://github.com/kynan/nbstripout
+    rev: 0.7.1
+    hooks:
+      - id: nbstripout

.python-version

@@ -0,0 +1 @@
+3.10.13

.venv

@@ -0,0 +1 @@
+hackathon

Dockerfile

@@ -0,0 +1,32 @@
+FROM python:3.10-slim as builder
+
+ENV PYTHONUNBUFFERED=1
+ENV PYTHONDONTWRITEBYTECODE=1
+ENV POETRY_VIRTUALENVS_CREATE=false
+
+WORKDIR /app
+
+RUN apt-get update -y && apt-get install -y gcc g++ && \
+    # Prevent apt-get cache from being persisted to this layer.
+    rm -rf /var/lib/apt/lists/*
+RUN pip install --upgrade pip && pip install poetry
+
+COPY poetry.lock* pyproject.toml /app/
+
+COPY . /app/
+
+RUN poetry install --no-interaction --only main --no-ansi
+#--no-root --sync
+
+# ---- Run Stage ----
+FROM python:3.10-slim as runner
+
+WORKDIR /app
+
+COPY --from=builder /app /app
+COPY --from=builder /usr/local/lib/python3.10/site-packages /usr/local/lib/python3.10/site-packages
+COPY --from=builder /usr/local/bin /usr/local/bin
+
+EXPOSE 8501
+
+CMD ["streamlit", "run", "app/home.py"]

README.md

@@ -1,7 +1,6 @@
 # hackathon
 
 
-
 ## Workflow
 
 ## How it works (for the hackathon)
@@ -12,11 +11,6 @@
 
 # Set up 
 
-https://python.langchain.com/docs/integrations/chat/llama2_chat
-https://python.langchain.com/docs/templates/llama2-functions
-https://huggingface.co/blog/llama2#how-to-prompt-llama-2 
-https://python.langchain.com/docs/integrations/llms/llamacpp#grammars
-
 ## 1. pyenv
 
 Install here: [https://github.com/pyenv/pyenv#homebrew-on-macos]
@@ -133,6 +127,14 @@ Pre commit hooks run after commit to fix up formatting and other issues. Install
 pre-commit install
 ```
 
+You can then run:
+
+```sh
+pre-commit run --all-files
+```
+
+and commit any changes made to files in the repo.
+
 ## 6. Add secrets into .env
 
 - Run `cp .env.template .env` and update the secrets.
@@ -199,9 +201,7 @@ docker-compose down
 
 check opensearch by visiting http://localhost:5601/app/login? or running `curl https://localhost:9200 -ku 'admin:admin'`
 
-## Sagemaker setup
-- Launch a SageMaker Notebook from SageMaker > Notebook > Notebook instances > Create notebook instance
-- Select `ml.g4dn.xlarge` instance type (see [https://aws.amazon.com/sagemaker/pricing/] for pricing)
+## Conda setup
 
 ### Install Python dependencies
 
@@ -211,11 +211,8 @@ Create a new terminal and run the following:
 # Switch to a bash shell
 bash
 
-# Change to the repo root
-cd ~/SageMaker/hackathon
 
-# Activate a Python 3.10 environment pre-configured with PyTorch
-conda create -n hackathon python=3.10.13
+# Activate a Python 3.10 environment 
 conda create -n hackathon python=$(cat .python-version)
 conda activate hackathon