🎉 add repository files

.env.example

@@ -0,0 +1,59 @@
+# -- DEV MODE if true, log debugs and traces
+DEV_MODE=True
+
+# Ollama and ollamazure models to emulate openai or azure_openai
+# run make run-ollama or make run-ollamazure to emulate openai or azure_openai locally
+OLLAMA_MODEL_NAME="phi3:3.8b-mini-4k-instruct-q4_K_M"
+OLLAMA_EMBEDDING_MODEL_NAME="all-minilm:l6-v2"
+
+
+# LLM_PROVIDER : openai or azure_openai
+LLM_PROVIDER="openai"
+
+# if provider is OPENAI
+OPENAI_DEPLOYMENT_NAME="phi3:3.8b-mini-4k-instruct-q4_K_M" # or gpt-4o-mini if you use openai
+OPENAI_BASE_URL="http://localhost:11434/v1" # ollama endpoint or https://api.openai.com/v1 if use use openai
+OPENAI_API_KEY="t"
+# if provider is AZURE
+AZURE_OPENAI_DEPLOYMENT_NAME="phi3:3.8b-mini-4k-instruct-q4_K_M" # or your azure model name
+AZURE_OPENAI_API_KEY="t" #
+AZURE_OPENAI_BASE_URL="http://localhost:4041" # ollamazure endpoint or your azure endpoint
+AZURE_OPENAI_API_VERSION="2024-10-01-preview" # fake api version
+
+# -- FASTAPI
+FASTAPI_HOST="localhost"
+FASTAPI_PORT=8080
+# -- Streamlit
+STREAMLIT_PORT=8501
+
+####################### EVALUATION ############################
+# (Optional) If you want to use Promptfoo and ragas, the eval tool
+ENABLE_EVALUATION=false # if true, you need to set the following
+# LLMAAJ stands for LLM as a judge
+LLMAAJ_PROVIDER="openai" # or azure_openai
+#if openai
+LLMAAJ_OPENAI_DEPLOYMENT_NAME="phi3:3.8b-mini-4k-instruct-q4_K_M" # or gpt-4o-mini if you use openai
+LLMAAJ_OPENAI_BASE_URL="http://localhost:11434/v1" # ollama endpoint or https://api.openai.com/v1 if use use openai
+LLMAAJ_OPENAI_API_KEY="t"
+LLMAAJ_OPENAI_EMBEDDING_DEPLOYMENT_NAME="text-embedding-ada-002"
+#if azure_openai
+LLMAAJ_AZURE_OPENAI_DEPLOYMENT_NAME="phi3:3.8b-mini-4k-instruct-q4_K_M" # or your azure model name
+LLMAAJ_AZURE_OPENAI_API_KEY="t"
+LLMAAJ_AZURE_OPENAI_BASE_URL="http://localhost:4041" # ollamazure endpoint or your azure endpoint
+LLMAAJ_AZURE_OPENAI_API_VERSION="2024-10-01-preview"
+LLMAAJ_AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME="all-minilm:l6-v2" # or your azure embedding model name
+
+
+####################### AI SEARCH ############################
+# (Optional) If you want to use Azure Search AI
+ENABLE_AZURE_SEARCH=false # if true, you need to set the following
+AZURE_SEARCH_TOP_K=3
+AZURE_SEARCH_API_KEY=""
+AZURE_SEARCH_INDEX_NAME=""
+AZURE_SEARCH_INDEXER_NAME=""
+AZURE_SEARCH_SERVICE_ENDPOINT=""
+SEMENTIC_CONFIGURATION_NAME=""
+# -- AZURE BLOB STORAGE
+AZURE_STORAGE_ACCOUNT_NAME=""
+AZURE_STORAGE_ACCOUNT_KEY=""
+AZURE_CONTAINER_NAME=""

.github/workflows/ai_evaluation.yaml

@@ -0,0 +1,62 @@
+name: 'LLM Evaluation'
+
+on:
+  pull_request:
+  push:
+#on:
+#  pull_request:
+#    paths:
+#      - src/ml
+#      - src/evaluation
+
+env:
+  OLLAMA_MODEL_NAME: "phi3:3.8b-mini-4k-instruct-q4_K_M"
+  OLLAMA_EMBEDDING_MODEL_NAME: "all-minilm:l6-v2"
+  LLM_PROVIDER: "openai"
+  OPENAI_DEPLOYMENT_NAME: "phi3:3.8b-mini-4k-instruct-q4_K_M" # or gpt-4o-mini if you use openai
+  OPENAI_BASE_URL: "http://localhost:11434/v1" # ollama endpoint or https://api.openai.com/v1 if use use openai
+  OPENAI_API_KEY: "t"
+
+  ENABLE_EVALUATION: true # if true, you need to set the following
+  # LLMAAJ stands for LLM as a judge
+  LLMAAJ_PROVIDER: "openai" # or azure_openai
+  #if openai
+  LLMAAJ_OPENAI_DEPLOYMENT_NAME: "phi3:3.8b-mini-4k-instruct-q4_K_M" # or gpt-4o-mini if you use openai
+  LLMAAJ_OPENAI_BASE_URL: "http://localhost:11434/v1" # ollama endpoint or https://api.openai.com/v1 if use use openai
+  LLMAAJ_OPENAI_API_KEY: "t"
+  LLMAAJ_OPENAI_EMBEDDING_DEPLOYMENT_NAME: "text-embedding-ada-002"
+
+jobs:
+  evaluate:
+    runs-on: ubuntu-latest
+    container:
+      image: aminedjeghri/python3.11-nvm22.08:latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+#      - name: Install NVM
+#        shell: bash
+#        run : make install_nvm_node
+      - name: Install Python dependencies
+        shell: bash
+        run: |
+          make install-dev
+      - name: Install NPM dependencies
+        shell: bash
+        run: |
+          make install-npm-dependencies
+      - name: Download local models
+        shell: bash
+        run: |
+          make download-ollama-model
+      - name: Run tests
+        shell: bash
+        run: |
+          ollama serve &
+          make test
+#      - name: Run promptfoo evaluation
+#        shell: bash
+#        run: |
+#          source ${{ env.VENV_PATH }}/bin/activate
+#          make eval

.github/workflows/deploy-pages.yaml

@@ -0,0 +1,31 @@
+name: 'Deploy Github Pages'
+
+#on:
+#  pull_request:
+#  push:
+
+jobs:
+  # Build job
+  build:
+
+  # Deploy job
+  deploy:
+    # Add a dependency to the build job
+    needs: build
+
+    # Grant GITHUB_TOKEN the permissions required to make a Pages deployment
+    permissions:
+      pages: write      # to deploy to Pages
+      id-token: write   # to verify the deployment originates from an appropriate source
+
+    # Deploy to the github-pages environment
+    environment:
+      name: github-pages
+      url: ${{ steps.deployment.outputs.page_url }}
+
+    # Specify runner + deployment step
+    runs-on: ubuntu-latest
+    steps:
+      - name: Deploy to GitHub Pages
+        id: deployment
+        uses: actions/deploy-pages@v4 # or specific "vX.X.X" version tag for this action

.github/workflows/pre-commit.yaml

@@ -0,0 +1,15 @@
+name: pre-commit
+
+on:
+  pull_request:
+  push:
+
+jobs:
+  pre-commit:
+    runs-on: ubuntu-22.04
+    steps:
+      - uses: actions/checkout@v3
+      - uses: actions/setup-python@v4
+        with:
+          python-version: '3.11'
+      - uses: pre-commit/[email protected]

.gitignore

@@ -0,0 +1,192 @@
+# 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
+.envd
+.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/
+
+# environment var
+.env
+*.secrets
+
+# node
+node_modules/
+
+# github actions local
+bin/act
+
+#gitlab ci local
+.gitlab-ci-local/
+.gitlab-ci-local-env
+.gitlab-ci-local.yml
+
+# Windows specific files
+*Zone.Identifier
+
+
+.cache*
+
+**/*tmp*.py
+**/*temp*.py
+
+
+
+src/evaluation/data/*
+!src/evaluation/data/test_json.csv
+!src/evaluation/data/test_simple.csv