migrate the ai service to the new repo

.github/workflows/ai-service-ci.yaml

@@ -0,0 +1,41 @@
+# This workflow will install Python dependencies, run tests and lint with a single version of Python
+# For more information see: https://docs.github.com/en/actions/automating-builds-and-tests/building-and-testing-python
+
+name: AI Service CI
+
+on:
+  push:
+    branches: [ "main" ]
+  pull_request:
+    branches: [ "main" ]
+
+permissions:
+  contents: read
+
+jobs:
+  ci:
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: [ "3.12" ]
+        poetry-version: [ "1.7.1" ]
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up Python 3.12
+        uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Run image
+        uses: abatilo/actions-poetry@v2
+        with:
+          poetry-version: ${{ matrix.poetry-version }}
+      - name: Install the project dependencies
+        run: poetry install
+      - name: Run Qdrant
+        run: docker run -p 6333:6333 -p 6334:6334 -d --name qdrant qdrant/qdrant:v1.7.4
+      - name: Test with pytest
+        run: poetry run pytest -s
+        env:
+          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+          ENV: dev

.gitignore

@@ -0,0 +1,32 @@
+# vectorstore
+vectorstore
+retrieve_db/
+wren-ai-service/qdrant_storage/
+
+# app
+.env
+.env.*
+!.env.*.example
+!src/eval/vulcansql-core-server/.env
+src/eval/vulcansql-core-server/config.properties
+outputs/
+spider/
+data/
+!tests/data
+!src/eval/data
+poetry.lock
+assertion.log
+
+# cache
+__pycache__
+local_cache
+.ruff_cache
+.pytest_cache
+
+# ide
+.idea
+.vscode/
+
+# os
+.DS_Store
+__MACOSX/

wren-ai-service/.dockerignore

@@ -0,0 +1,4 @@
+*
+src/eval
+!src
+!pyproject.toml

wren-ai-service/.env.dev.example

@@ -0,0 +1,12 @@
+# fastapi related
+UVICORN_HOST=127.0.0.1
+UVICORN_PORT=8080
+
+# app related
+OPENAI_API_KEY=
+LANGFUSE_PUBLIC_KEY=
+LANGFUSE_SECRET_KEY=
+ENABLE_TRACE=
+
+# evaluation related
+DATASET_NAME=book_2

wren-ai-service/.env.prod.example

@@ -0,0 +1,12 @@
+# docker related
+# This will determine the prefix of container name.
+# If the service name in docker-compose.yaml is copilot, 
+# then the container name will be vulcansql-copilot-1.
+# If COMPOSE_PROJECT_NAME is not set, the default prefix name is docker.
+COMPOSE_PROJECT_NAME=vulcansql
+
+# fastapi related
+UVICORN_PORT=8080
+
+# app related
+OPENAI_API_KEY=

wren-ai-service/.pre-commit-config.yaml

@@ -0,0 +1,10 @@
+repos:
+- repo: https://github.com/astral-sh/ruff-pre-commit
+  # Ruff version.
+  rev: v0.2.2
+  hooks:
+    # Run the linter.
+    - id: ruff
+      args: [ --fix ]
+    # Run the formatter.
+    - id: ruff-format

wren-ai-service/Makefile

@@ -0,0 +1,45 @@
+args ?=
+
+start:
+	poetry run python -m src.__main__
+
+build:
+	docker compose -f docker/docker-compose.yml build
+
+up:
+	docker compose -f docker/docker-compose.yml --env-file .env.prod up -d
+
+down:
+	docker compose -f docker/docker-compose.yml --env-file .env.prod down
+
+run-qdrant:
+	docker run \
+	-p 6333:6333 \
+	-p 6334:6334 \
+	-d \
+	--name qdrant \
+	qdrant/qdrant:v1.7.4
+
+stop-qdrant:
+	docker stop qdrant && docker rm qdrant
+
+# evaluation related
+eval:
+	poetry run python -m src.eval.ask $(args)
+
+run-vulcansql-core-server:
+	docker compose -f ./src/eval/vulcansql-core-server/docker-compose.yml --env-file .env.dev --env-file ./src/eval/vulcansql-core-server/.env up -d
+
+stop-vulcansql-core-server:
+	docker compose -f ./src/eval/vulcansql-core-server/docker-compose.yml --env-file .env.dev --env-file ./src/eval/vulcansql-core-server/.env down
+
+psql:
+	docker exec -it vulcansql-engine-1 bash launch-cli.sh
+
+run-all:
+	make run-qdrant && \
+	make run-vulcansql-core-server
+
+stop-all:
+	make stop-qdrant && \
+	make stop-vulcansql-core-server

wren-ai-service/README.md

@@ -0,0 +1,30 @@
+## Introduction
+
+## Environment Setup
+
+- Python 3.12 or later 
+- follow the instructions at https://pipx.pypa.io/stable/ install `pipx`
+- execute `pipx install poetry` to install `poetry`
+- execute `poetry install` to install the dependencies
+- copy `.env.example` file to `.env`, and `.env.dev.example` file to `.env.dev` and fill in the environment variables
+- [for development] execute `poetry run pre-commit install` to install the pre-commit hooks and `poetry run pre-commit run --all-files` to run the pre-commit checks at the first time to check if everything is set up correctly
+
+## Start the service for development
+
+- execute `make start` to start the service
+  - go to `http://UVICORN_HOST:UVICORN_PORT/docs` to see the API documentation and try the API
+
+## Production Environment Setup
+
+- copy `.env.prod.example` file to `.env.prod` and fill in the environment variables
+- `make build` to build the docker image
+- `make up` to run the docker container
+- `make down` to stop the docker container
+
+## Pipeline Evaluation(for development)
+
+- fill in environment variables: `.env.dev` in the src folder and `config.properties` in the src/eval/vulcansql-core-server folder
+- start docker
+- run qdrant and vulcansql-core-server docker containers: `make run-all`
+- evaluation: `make eval` and check out the outputs folder
+- to run individual pipeline: `poetry run python -m src.pipelines.ask.[pipeline_name]` (e.g. `poetry run python -m src.pipelines.ask.retrieval_pipeline`)

wren-ai-service/docker/Dockerfile

@@ -0,0 +1,13 @@
+FROM python:3.12.2-bookworm
+
+RUN pip install poetry==1.7.1
+
+WORKDIR /app
+
+COPY pyproject.toml poetry.lock ./
+
+RUN poetry install --without dev
+
+COPY src/ src/
+
+ENTRYPOINT [ "poetry", "run", "uvicorn", "src.__main__:app", "--host", "0.0.0.0", "--port", "80" ]

wren-ai-service/docker/docker-compose.yml

@@ -0,0 +1,24 @@
+version: '3.8'
+
+services:
+  copilot:
+    image: vulcansql-copilot:latest
+    build:
+      context: ..
+      dockerfile: docker/Dockerfile
+    environment:
+      UVICORN_PORT: ${UVICORN_PORT}
+      OPENAI_API_KEY: ${OPENAI_API_KEY}
+      # sometimes the console won't show print messages,
+      # using PYTHONUNBUFFERED: 1 can fix this
+      PYTHONUNBUFFERED: 1
+    ports:
+      - ${UVICORN_PORT}:80
+    depends_on:
+      - qdrant
+
+  qdrant:
+    image: qdrant/qdrant:v1.7.4
+    ports:
+      - 6333:6333
+      - 6334:6334

wren-ai-service/pyproject.toml

@@ -0,0 +1,33 @@
+[tool.poetry]
+name = "wren-ai-service"
+version = "0.1.0"
+description = ""
+authors = ["Jimmy Yeh <[email protected]>", "Pao Sheng Wang <[email protected]>"]
+readme = "README.md"
+
+[tool.poetry.dependencies]
+python = "^3.12"
+fastapi = "^0.109.2"
+uvicorn = "^0.27.1"
+python-dotenv = "^1.0.1"
+setuptools = "^69.1.0"
+haystack-ai = "^2.0.0"
+openai = "^1.12.0"
+langfuse = "^2.19.1"
+ragas = "^0.1.1"
+qdrant-haystack = "^3.0.0"
+backoff = "^2.2.1"
+ragas-haystack = "^0.1.1"
+tqdm = "^4.66.2"
+
+[tool.poetry.group.dev.dependencies]
+pytest = "^8.0.0"
+pre-commit = "^3.6.1"
+pytest-cov = "^4.1.0"
+gdown = "^5.1.0"
+sqlglot = "^22.1.0"
+httpx = "^0.27.0"
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"

wren-ai-service/ruff.toml

@@ -0,0 +1,77 @@
+# Exclude a variety of commonly ignored directories.
+exclude = [
+    ".bzr",
+    ".direnv",
+    ".eggs",
+    ".git",
+    ".git-rewrite",
+    ".hg",
+    ".ipynb_checkpoints",
+    ".mypy_cache",
+    ".nox",
+    ".pants.d",
+    ".pyenv",
+    ".pytest_cache",
+    ".pytype",
+    ".ruff_cache",
+    ".svn",
+    ".tox",
+    ".venv",
+    ".vscode",
+    "__pypackages__",
+    "_build",
+    "buck-out",
+    "build",
+    "dist",
+    "node_modules",
+    "site-packages",
+    "venv",
+]
+
+# Same as Black.
+line-length = 88
+indent-width = 4
+
+# Assume Python 3.8
+target-version = "py38"
+
+[lint]
+# Enable Pyflakes (`F`) and a subset of the pycodestyle (`E`)  codes by default.
+# Unlike Flake8, Ruff doesn't enable pycodestyle warnings (`W`) or
+# McCabe complexity (`C901`) by default.
+select = ["E4", "E7", "E9", "F", "I001"]
+ignore = []
+
+# Allow fix for all enabled rules (when `--fix`) is provided.
+fixable = ["ALL"]
+unfixable = []
+
+# Allow unused variables when underscore-prefixed.
+dummy-variable-rgx = "^(_+|(_+[a-zA-Z0-9_]*[a-zA-Z0-9]+?))$"
+
+[format]
+# Like Black, use double quotes for strings.
+quote-style = "double"
+
+# Like Black, indent with spaces, rather than tabs.
+indent-style = "space"
+
+# Like Black, respect magic trailing commas.
+skip-magic-trailing-comma = false
+
+# Like Black, automatically detect the appropriate line ending.
+line-ending = "auto"
+
+# Enable auto-formatting of code examples in docstrings. Markdown,
+# reStructuredText code/literal blocks and doctests are all supported.
+#
+# This is currently disabled by default, but it is planned for this
+# to be opt-out in the future.
+docstring-code-format = false
+
+# Set the line length limit used when formatting code snippets in
+# docstrings.
+#
+# This only has an effect when the `docstring-code-format` setting is
+# enabled.
+docstring-code-line-length = "dynamic"