Merge pull request #3 from parea-ai/use-github-workflows

Use GitHub workflows

.env.example

@@ -1,5 +1,2 @@
 OPENAI_API_KEY=<insert OpenAI API key here>
-LANGCHAIN_TRACING_V2=true
-LANGCHAIN_API_KEY=<insert Langsmith API key here>
-LANGCHAIN_ENDPOINT="https://api.smith.langchain.com"
-LANGCHAIN_PROJECT="rag-demo"
+PAREA_API_KEY=<insert Parea API key here>

.github/workflows/build.yml

@@ -0,0 +1,38 @@
+name: build
+
+on: [ push, pull_request ]
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: [ "3.11" ]
+
+    steps:
+      - uses: actions/[email protected]
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/[email protected]
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Install poetry
+        run: make poetry-download
+
+      - name: Set up cache
+        uses: actions/[email protected]
+        with:
+          path: .venv
+          key: venv-${{ matrix.python-version }}-${{ hashFiles('pyproject.toml') }}-${{ hashFiles('poetry.lock') }}
+      - name: Install dependencies
+        run: |
+          poetry config virtualenvs.in-project true
+          poetry install
+
+      - name: Run style checks
+        run: |
+          make check-codestyle
+
+#      - name: Run tests
+#        run: |
+#          make test

.gitignore

@@ -166,4 +166,4 @@ cython_debug/
 *.swp
 
 .dccache
-.DS_Store
+.DS_Store

.pre-commit-config.yaml

@@ -0,0 +1,36 @@
+default_language_version:
+  python: python3.11
+
+default_stages: [ commit, push ]
+
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.5.0
+    hooks:
+      - id: check-yaml
+      - id: end-of-file-fixer
+        exclude: LICENSE
+
+  - repo: local
+    hooks:
+      - id: pyupgrade
+        name: pyupgrade
+        entry: poetry run pyupgrade --py39-plus
+        types: [ python ]
+        language: system
+
+  - repo: local
+    hooks:
+      - id: isort
+        name: isort
+        entry: poetry run isort --settings-path pyproject.toml
+        types: [ python ]
+        language: system
+
+  - repo: local
+    hooks:
+      - id: black
+        name: black
+        entry: poetry run black --config pyproject.toml
+        types: [ python ]
+        language: system

.pylintrc

@@ -1,2 +1,2 @@
 [MESSAGES CONTROL]
-disable=line-too-long,no-member,too-few-public-methods,missing-function-docstring,missing-module-docstring
+disable=line-too-long,no-member,too-few-public-methods,missing-function-docstring,missing-module-docstring

Makefile

@@ -0,0 +1,89 @@
+#* Variables
+SHELL := /usr/bin/env bash
+PYTHON := python3
+PYTHONPATH := `pwd`
+
+#* Docker variables
+VERSION := latest
+
+#* Poetry
+.PHONY: poetry-download
+poetry-download:
+	curl -sSL https://install.python-poetry.org | $(PYTHON) -
+
+.PHONY: poetry-remove
+poetry-remove:
+	curl -sSL https://raw.githubusercontent.com/python-poetry/poetry/master/install-poetry.py | $(PYTHON) - --uninstall
+
+#* Installation
+.PHONY: install
+install:
+	poetry lock -n && poetry export --without-hashes > requirements.txt
+	poetry install -n
+	poetry run mypy --install-types --non-interactive ./
+
+.PHONY: pre-commit-install
+pre-commit-install:
+	poetry run pre-commit install
+
+#* Formatters
+.PHONY: codestyle
+codestyle:
+	poetry run pyupgrade --exit-zero-even-if-changed --py39-plus **/*.py
+	poetry run isort --settings-path pyproject.toml ./
+	poetry run black --config pyproject.toml ./
+
+.PHONY: formatting
+formatting: codestyle
+
+#* Linting
+.PHONY: test
+test:
+	PYTHONPATH=$(PYTHONPATH) poetry run pytest tests/test_chains.py
+
+.PHONY: check-codestyle
+check-codestyle:
+	poetry run isort --diff --check-only --settings-path pyproject.toml ./
+	poetry run black --diff --check --config pyproject.toml ./
+	poetry run darglint --verbosity 2 parea tests
+
+.PHONY: mypy
+mypy:
+	poetry run mypy --config-file pyproject.toml ./
+
+.PHONY: lint
+lint: test check-codestyle mypy
+
+.PHONY: update-dev-deps
+update-dev-deps:
+	poetry add -D bandit@latest darglint@latest "isort[colors]@latest" mypy@latest pre-commit@latest pydocstyle@latest pylint@latest pytest@latest pyupgrade@latest safety@latest coverage@latest coverage-badge@latest pytest-html@latest pytest-cov@latest
+	poetry add -D --allow-prereleases black@latest
+
+
+#* Cleaning
+.PHONY: pycache-remove
+pycache-remove:
+	find . | grep -E "(__pycache__|\.pyc|\.pyo$$)" | xargs rm -rf
+
+.PHONY: dsstore-remove
+dsstore-remove:
+	find . | grep -E ".DS_Store" | xargs rm -rf
+
+.PHONY: mypycache-remove
+mypycache-remove:
+	find . | grep -E ".mypy_cache" | xargs rm -rf
+
+.PHONY: ipynbcheckpoints-remove
+ipynbcheckpoints-remove:
+	find . | grep -E ".ipynb_checkpoints" | xargs rm -rf
+
+.PHONY: pytestcache-remove
+pytestcache-remove:
+	find . | grep -E ".pytest_cache" | xargs rm -rf
+
+.PHONY: build-remove
+build-remove:
+	rm -rf build/
+
+.PHONY: cleanup
+cleanup: pycache-remove dsstore-remove mypycache-remove ipynbcheckpoints-remove pytestcache-remove

README.md

@@ -2,17 +2,14 @@
 
 To build your LLM and set up automated testing, you’ll need the following frameworks and tools:
 
-- [CircleCI](https://circleci.com/signup/) – A configuration-as-code CI/CD platform that allows users to run and
-  orchestrate cloud-based pipelines across machines.
+- [PareaAI](https://www.parea.ai/) – A tool created to more efficiently debug language model applications
+  by showing the trace of LLM calls, as well as inputs and outputs for certain prompts. This allows you to view the test
+  results and metadata for all LLM calls in a single dashboard.
 
 - [LangChain](https://docs.langchain.com/docs/) – An open-source framework for developing language model-powered
   applications. It provides prompt templates, models, document loaders, text splitters,
   and [many other tools for interacting with models](https://docs.langchain.com/docs/category/components).
 
-- [PareaAI](https://www.parea.ai/) – A tool created to more efficiently debug language model applications
-  by showing the trace of LLM calls, as well as inputs and outputs for certain prompts. This allows you to view the test
-  results and metadata for all LLM calls in a single dashboard.
-
 - [ChromaDB](https://docs.trychroma.com/) – An open-source embedding database/vector store, which tokenizes inputs (in
   our case, text) and stores them in an n-dimensional vector space. Chunks of text similar to new inputs can be returned
   using a modified K-nearest-neighbor algorithm in the vector space.
@@ -23,14 +20,10 @@ To build your LLM and set up automated testing, you’ll need the following fram
   scripts.
     - These scripts rely on a .env file with API keys to OpenAI and Langchain, as well as other environment variables.
       An example is provided, but you need to populate it with your own variables.
-- .circleci/ directory contains the CircleCI config.yml that defines the CircleCI pipelines that call the
-  ML scripts.
 
 # Set up environment
 
-- Fork the example repository and clone your forked version locally.
-
-- Install and activate your virtual environment
+- Install and activate your virtual environment (we use Poetry)
 
 - Create a .env file by running `cp .env.example .env`, then set the necessary environment variables in it. This will
   include:
@@ -43,19 +36,16 @@ To build your LLM and set up automated testing, you’ll need the following fram
       account, and create an API key by clicking on the API Keys button on the bottom left of the page and following the
       instructions. This key should be stored in the `PAREA_API_KEY` environment variable in your .env file.
 
-# Run the application
-
-## Start the server
-
-    flask --app rag/app run &  # spin up the Flask server
-
-## Interact with the server
+# Run tests
 
-    curl -X POST -H "Content-Type: application/json" -d '{"message": "What is LangSmith?"}' http://127.0.0.1:5000
+## Pytest
 
-Ask the application different questions by changing the `message` field in the curl command.
+```bash
+poetry run pytest -s
+``` 
 
-## Stop the server
+or
 
-    fg [job no. of server]
-    Ctrl-C
+```bash
+make test
+```