Merge pull request #1 from teddy-ambona/feat/add-chatbot

Added chatbot

.github/workflows/cicd.yml

@@ -0,0 +1,93 @@
+---
+name: Application code CICD Pipeline
+on: [push]
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v2
+      - name: Check for code styling, static code issues
+        run: |
+          pip install pre-commit
+          pre-commit install
+          pre-commit run --all-files -v
+
+  image-misconfiguration:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v2
+
+      - name: Run Trivy misconfiguration scanner
+        uses: aquasecurity/trivy-action@master
+        with:
+          scan-type: config
+
+          # File to scan
+          scan-ref: Dockerfile
+          format: table
+          exit-code: 1
+          vuln-type: security-check
+          severity: CRITICAL,HIGH
+
+  build:
+    # Build Docker image and upload it to the pipeline artifacts.
+    # The image will be re-used in the downstream jobs
+    needs: [lint, image-misconfiguration]
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v2
+
+      - name: Build image tag
+        id: build_image_tag
+        run: |
+          echo "::set-output name=IMAGE_TAG::$(make app-get-version)"
+          echo "::set-output name=ACT::${ACT}"
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v1
+
+      - name: Build and push
+        uses: docker/build-push-action@v2
+        with:
+          context: .
+          file: ./Dockerfile
+          tags: ${{ steps.build_image_tag.outputs.IMAGE_TAG }}
+          outputs: type=docker,dest=/tmp/openai-rag-chatbot-app.tar
+
+      - name: Upload artifact
+        uses: actions/upload-artifact@v2
+        with:
+          name: openai-rag-chatbot-app
+          path: /tmp/openai-rag-chatbot-app.tar
+    outputs:
+      SUFFIX: ${{ steps.build_image_tag.outputs.SUFFIX }}
+      IMAGE_TAG: ${{ steps.build_image_tag.outputs.IMAGE_TAG }}
+      ACT: ${{ steps.build_image_tag.outputs.ACT }}
+
+  image-vulnerabilities:
+    needs: [build]
+    runs-on: ubuntu-latest
+    steps:
+      - name: Download artifact
+        uses: actions/download-artifact@v2
+        with:
+          name: openai-rag-chatbot-app
+          path: /tmp
+
+      - name: Load Docker image
+        run: |
+          docker load --input /tmp/openai-rag-chatbot-app.tar
+          docker image ls -a
+
+      - name: Run Trivy vulnerability scanner
+        uses: aquasecurity/trivy-action@master
+        with:
+          image-ref: ${{ needs.build.outputs.IMAGE_TAG }}
+          format: table
+          exit-code: 1
+          ignore-unfixed: true
+          vuln-type: library
+          severity: CRITICAL,HIGH

.gitignore

@@ -0,0 +1,95 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+env/
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# 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/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# DotEnv configuration
+.env
+
+# Database
+*.db
+*.rdb
+
+# Pycharm
+.idea
+
+# VS Code
+.vscode/
+
+# Spyder
+.spyproject/
+
+# Jupyter NB Checkpoints
+.ipynb_checkpoints/
+
+# Mac OS-specific storage files
+.DS_Store
+
+# vim
+*.swp
+*.swo
+
+# Mypy cache
+.mypy_cache/
+
+# Secrets variables
+/secrets/
+
+# Python virtual environment
+/venv/
+
+# milvus volumes
+/volumes/

.pre-commit-config.yaml

@@ -0,0 +1,10 @@
+repos:
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    # Ruff version.
+    rev: v0.1.14
+    hooks:
+      # Run the linter.
+      - id: ruff
+        args: [ --fix ]
+      # Run the formatter.
+      - id: ruff-format

Dockerfile

@@ -0,0 +1,41 @@
+FROM python:3.11
+
+# Create app user
+RUN groupadd -r user && useradd -r -g user --create-home app
+RUN chown -R app /home/app
+RUN mkdir -v /app && chown -R app /app
+
+WORKDIR /app
+
+RUN apt-get -y update && \
+    apt-get install -y --no-install-recommends \
+    make \
+    curl \
+    jq && \
+    apt-get clean
+
+# Create virtual environment and activate it
+ENV VIRTUAL_ENV=/opt/venv
+RUN python -m venv $VIRTUAL_ENV
+ENV PATH="$VIRTUAL_ENV/bin:$PATH"
+
+RUN python -m pip install wheel poetry==1.8.2
+
+COPY poetry.lock pyproject.toml ./
+
+# Install required libraries in the virtual environment
+RUN poetry install --no-root
+
+# Python won’t try to write .pyc files on the import of source modules
+ENV PYTHONDONTWRITEBYTECODE 1
+# Ensure that the stdout and stderr streams are sent straight to terminal
+ENV PYTHONUNBUFFERED 1
+
+# Copy python files
+COPY src ./src
+COPY data ./data
+
+# Using non-root user to reduce vulnerabilities
+USER app
+
+CMD ["python", "src/server.py"]

Makefile

@@ -0,0 +1,109 @@
+.PHONY: app-build app-run db-up db-down db-populate clean
+
+PYTHON_VERSION = 3.11
+DRUN = docker run --rm
+DBASH = $(DRUN) -u root -v ${PWD}:/foo -w="/foo" python:$(PYTHON_VERSION) bash -c
+IMAGE_NAME = openai-rag-chatbot-app
+IMAGE_VERSION = 0.0.0
+
+# ============================================================
+# App commands
+# ============================================================
+
+## Buid Docker image of Langserve app
+app-build:
+	docker build -t ${IMAGE_NAME}:${IMAGE_VERSION} .
+
+## Run Docker image
+app-run:
+	docker compose up app
+
+## Return API version (useful for tagging Docker image in CI)
+app-get-version:
+	@echo ${IMAGE_NAME}:${IMAGE_VERSION}
+
+# ============================================================
+# DB commands
+# ============================================================
+
+## Start DB
+db-up:
+	docker-compose up -d milvus-standalone
+
+## Stop DB
+db-down:
+	docker compose down
+
+## Populate DB with the LASIK eye surgery complications dataset
+db-populate:
+	docker compose run db-populate
+
+## Delete all compiled Python files and Milvus volumes
+clean:
+	find . -type f -name "*.py[co]" -delete
+	find . -type f -name ".coverage" -delete
+	find . -type d -name "_pycache_" -delete
+	find . -type d -name "*.egg-info" -exec rm -r "{}" +
+	find . -type d -name ".pytest_cache" -exec rm -r "{}" +
+	rm -rf  volumes
+
+#################################################################################
+# Self Documenting Commands                                                     #
+#################################################################################
+
+.DEFAULT_GOAL := help
+
+# Inspired by <http://marmelab.com/blog/2016/02/29/auto-documented-makefile.html>
+# sed script explained:
+# /^##/:
+# 	* save line in hold space
+# 	* purge line
+# 	* Loop:
+# 		* append newline + line to hold space
+# 		* go to next line
+# 		* if line starts with doc comment, strip comment character off and loop
+# 	* remove target prerequisites
+# 	* append hold space (+ newline) to line
+# 	* replace newline plus comments by ---
+# 	* print line
+# Separate expressions are necessary because labels cannot be delimited by
+# semicolon; see <http://stackoverflow.com/a/11799865/1968>
+.PHONY: help
+help:
+	@echo "$$(tput bold)Available rules:$$(tput sgr0)"
+	@echo
+	@sed -n -e "/^## / { \
+		h; \
+		s/.*//; \
+		:doc" \
+		-e "H; \
+		n; \
+		s/^## //; \
+		t doc" \
+		-e "s/:.*//; \
+		G; \
+		s/\\n## /---/; \
+		s/\\n/ /g; \
+		p; \
+	}" ${MAKEFILE_LIST} \
+	| LC_ALL='C' sort --ignore-case \
+	| awk -F '---' \
+		-v ncol=$$(tput cols) \
+		-v indent=19 \
+		-v col_on="$$(tput setaf 6)" \
+		-v col_off="$$(tput sgr0)" \
+	'{ \
+		printf "%s%*s%s ", col_on, -indent, $$1, col_off; \
+		n = split($$2, words, " "); \
+		line_length = ncol - indent; \
+		for (i = 1; i <= n; i++) { \
+			line_length -= length(words[i]) + 1; \
+			if (line_length <= 0) { \
+				line_length = ncol - indent - length(words[i]) - 1; \
+				printf "\n%*s ", -indent, " "; \
+			} \
+			printf "%s ", words[i]; \
+		} \
+		printf "\n"; \
+	}' \
+	| more $(shell test $(shell uname) = Darwin && echo '--no-init --raw-control-chars')