refactor: Cleans en vars and setup instructions (#36)

* docs: Updates README

* chore: Updates gitignore

* chore: Updates docker compose

* refactor: Updates test docker compose

* ci: Updates CI jobs

* refactor: Remove GitHub route config var

* refactor: Cleans up env vars

* refactor: Refactors model mapping

* feat: Adds description to guideline example

* docs: Updates README & CONTRIBUTING

* refactor: Removes traefik

* ci: Reflects changes

* docs: Updates CONTRIBUTING

* fix: Fixes typo

* ci: Fixes env var

.env.example

@@ -0,0 +1,8 @@
+SUPERADMIN_GH_PAT=your-github-pat
+GH_OAUTH_ID=your-github-oauth-app-id
+GH_OAUTH_SECRET=your-github-oauth-app-secret
+OPENAI_API_KEY=your-openai-api-key
+SUPERADMIN_PWD='Dumm1PassW0rdz!'
+POSTGRES_DB=postgres
+POSTGRES_USER=postgres
+POSTGRES_PASSWORD='An0th3rDumm1PassW0rdz!'

.github/workflows/builds.yml

@@ -24,19 +24,18 @@ jobs:
         run: poetry export -f requirements.txt --without-hashes --output requirements.txt
       - name: Build & run docker
         env:
-          POSTGRES_DB: ${{ secrets.POSTGRES_DB }}
-          POSTGRES_USER: ${{ secrets.POSTGRES_USER }}
-          POSTGRES_PASSWORD: ${{ secrets.POSTGRES_PASSWORD }}
-          SUPERUSER_LOGIN: ${{ secrets.SUPERUSER_LOGIN }}
-          SUPERUSER_ID: ${{ secrets.SUPERUSER_ID }}
-          SUPERUSER_PWD: ${{ secrets.SUPERUSER_PWD }}
+          SUPERADMIN_GH_PAT: ${{ secrets.SUPERADMIN_GH_PAT }}
+          SUPERADMIN_PWD: dummy_pwd
           GH_OAUTH_ID: ${{ secrets.GH_OAUTH_ID }}
           GH_OAUTH_SECRET: ${{ secrets.GH_OAUTH_SECRET }}
+          POSTGRES_DB: postgres
+          POSTGRES_USER: postgres
+          POSTGRES_PASSWORD: pg_pwd
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
         run: docker-compose up -d --build
       - name: Docker sanity check
-        run: sleep 20 && nc -vz api.localhost 8050
+        run: sleep 20 && nc -vz localhost 8050
       - name: Debug
         run: docker-compose logs
       - name: Ping server
-        run: curl http://api.localhost:8050/docs
+        run: curl http://localhost:8050/docs

.github/workflows/scripts.yml

@@ -24,12 +24,7 @@ jobs:
         run: poetry export -f requirements.txt --without-hashes --output requirements.txt
       - name: Build & run docker
         env:
-          POSTGRES_DB: ${{ secrets.POSTGRES_DB }}
-          POSTGRES_LOGIN: ${{ secrets.POSTGRES_LOGIN }}
-          POSTGRES_PASSWORD: ${{ secrets.POSTGRES_PASSWORD }}
-          SUPERUSER_LOGIN: ${{ secrets.SUPERUSER_LOGIN }}
-          SUPERUSER_ID: ${{ secrets.SUPERUSER_ID }}
-          SUPERUSER_PWD: ${{ secrets.SUPERUSER_PWD }}
+          SUPERADMIN_GH_PAT: ${{ secrets.SUPERADMIN_GH_PAT }}
           GH_OAUTH_ID: ${{ secrets.GH_OAUTH_ID }}
           GH_OAUTH_SECRET: ${{ secrets.GH_OAUTH_SECRET }}
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
@@ -43,5 +38,5 @@ jobs:
       - name: Run integration test
         env:
           SUPERUSER_LOGIN: ${{ secrets.SUPERUSER_LOGIN }}
-          SUPERUSER_PWD: ${{ secrets.SUPERUSER_PWD }}
+          SUPERUSER_PWD: superadmin_pwd
         run: python scripts/test_e2e.py

.github/workflows/tests.yml

@@ -21,18 +21,14 @@ jobs:
         run: poetry export -f requirements.txt --without-hashes --with dev --output requirements.txt
       - name: Build & run docker
         env:
-          SUPERUSER_LOGIN: ${{ secrets.SUPERUSER_LOGIN }}
-          SUPERUSER_ID: ${{ secrets.SUPERUSER_ID }}
-          SUPERUSER_PWD: ${{ secrets.SUPERUSER_PWD }}
+          SUPERADMIN_GH_PAT: ${{ secrets.SUPERADMIN_GH_PAT }}
           GH_OAUTH_ID: ${{ secrets.GH_OAUTH_ID }}
           GH_OAUTH_SECRET: ${{ secrets.GH_OAUTH_SECRET }}
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
         run: docker compose -f docker-compose.test.yml up -d --build
       - name: Run docker test
         env:
-          SUPERUSER_LOGIN: ${{ secrets.SUPERUSER_LOGIN }}
-          SUPERUSER_ID: ${{ secrets.SUPERUSER_ID }}
-          SUPERUSER_PWD: ${{ secrets.SUPERUSER_PWD }}
+          SUPERADMIN_GH_PAT: ${{ secrets.SUPERADMIN_GH_PAT }}
           GH_OAUTH_ID: ${{ secrets.GH_OAUTH_ID }}
           GH_OAUTH_SECRET: ${{ secrets.GH_OAUTH_SECRET }}
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}

.gitignore

@@ -166,3 +166,7 @@ cython_debug/
 src/app/requirements.txt
 src/requirements-dev.txt
 requirements.txt
+# Ollama
+.ollama
+# SQL dump
+*.sql

CONTRIBUTING.md

@@ -10,7 +10,9 @@ Whatever the way you wish to contribute to the project, please respect the [code
 
 - [`src/app`](https://github.com/quack-ai/contribution-api/blob/main/src/app) - The actual API codebase
 - [`src/tests`](https://github.com/quack-ai/contribution-api/blob/main/src/tests) - The API unit tests
-- [`./traefik`](https://github.com/quack-ai/contribution-api/blob/main/traefik) - Configuration files for the reverse proxy
+- [`.github`](https://github.com/quack-ai/contribution-api/blob/main/.github) - Configuration for CI (GitHub Workflows)
+- [`docs`](https://github.com/quack-ai/contribution-api/blob/main/docs) - Everything related to documentation
+- [`scripts`](https://github.com/quack-ai/contribution-api/blob/main/scripts) - Custom scripts
 
 
 ## Continuous Integration
@@ -21,8 +23,9 @@ This project uses the following integrations to ensure proper codebase maintenan
 - [Codacy](https://www.codacy.com/) - analyzes commits for code quality
 - [Codecov](https://codecov.io/) - reports back coverage results
 - [Sentry](https://docs.sentry.io/platforms/python/) - automatically reports errors back to us
-- [LogTail](https://betterstack.com/logtail) - manage logs
 - [PostgreSQL](https://www.postgresql.org/) - storing and interacting with the metadata database
+- [PostHog](https://posthog.com/) - product analytics
+- [Slack](https://slack.com/) - event notifications
 - [Traefik](https://traefik.io/) - the reverse proxy and load balancer
 
 As a contributor, you will only have to ensure coverage of your code by adding appropriate unit testing of your code.

README.md

@@ -40,7 +40,7 @@ You can run the API containers using this command:
 make run
 ```
 
-You can now navigate to [`http://api.localhost:8050/docs`](http://api.localhost:8050/docs) to interact with the API (or do it through HTTP requests) and explore the documentation.
+You can now navigate to [`http://localhost:8050/docs`](http://localhost:8050/docs) to interact with the API (or do it through HTTP requests) and explore the documentation.
 
 In order to stop the service, run:
 ```shell
@@ -77,42 +77,34 @@ The project was designed so that everything runs with Docker orchestration (stan
 
 In order to run the project, you will need to specific some information, which can be done using a `.env` file.
 This file will have to hold the following information:
-- `POSTGRES_DB`: the name of the [PostgreSQL](https://www.postgresql.org/) database that will be created
-- `POSTGRES_USER`: the login to the PostgreSQL database
-- `POSTGRES_PASSWORD`: the password to the PostgreSQL database
-- `SUPERUSER_LOGIN`: the login of the initial admin access
-- `SUPERUSER_ID`: the GitHub ID of the initial admin access
-- `SUPERUSER_PWD`: the password of the initial admin access
-- `GH_OAUTH_ID`: the ID of the GitHub Oauth app
-- `GH_OAUTH_SECRET`: the secret of the GitHub Oauth app
-- `OPENAI_API_KEY`: your API key for Open AI
+- `SUPERADMIN_GH_PAT`: the GitHub token of the initial admin access (Generate a new token on [GitHub](https://github.com/settings/tokens?type=beta), with no extra permissions = read-only)
+- `SUPERADMIN_PWD`*: the password of the initial admin access
+- `GH_OAUTH_ID`: the Client ID of the GitHub Oauth app (Create an OAuth app on [GitHub](https://github.com/settings/applications/new), pointing to your Quack dashboard w/ callback URL)
+- `GH_OAUTH_SECRET`: the secret of the GitHub Oauth app (Generate a new client secret on the created OAuth app)
+- `POSTGRES_DB`*: a name for the [PostgreSQL](https://www.postgresql.org/) database that will be created
+- `POSTGRES_USER`*: a login for the PostgreSQL database
+- `POSTGRES_PASSWORD`*: a password for the PostgreSQL database
+- `OPENAI_API_KEY`: your API key for Open AI (Create new secret key on [OpenAI](https://platform.openai.com/api-keys))
 
-Optionally, the following information can be added:
-- `SENTRY_DSN`: the URL of the [Sentry](https://sentry.io/) project, which monitors back-end errors and report them back.
-- `SERVER_NAME`: the server tag to apply to events.
+_* marks the values where you can pick what you want._
 
-So your `.env` file should look like something similar to:
-```
-POSTGRES_DB=review_db
-POSTGRES_USER=admin
-POSTGRES_PASSWORD=my_password
-SUPERUSER_LOGIN=superadmin
-SUPERUSER_PWD=super_password
-SUPERUSER_ID=1
-SENTRY_DSN='https://replace.with.you.sentry.dsn/'
-SENTRY_SERVER_NAME=my_storage_bucket_name
-GH_OAUTH_ID=your_github_oauth_app_id
-GH_OAUTH_SECRET=your_github_oauth_app_secret
-OPENAI_API_KEY='you-openai-key'
-```
+Optionally, the following information can be added:
+- `SECRET_KEY`*: if set, tokens can be reused between sessions. All instances sharing the same secret key can use the same token.
+- `SENTRY_DSN`: the DSN for your [Sentry](https://sentry.io/) project, which monitors back-end errors and report them back.
+- `SERVER_NAME`*: the server tag that will be used to report events to Sentry.
+- `POSTHOG_KEY`: the project API key for PostHog [PostHog](https://eu.posthog.com/settings/project-details).
+- `SLACK_API_TOKEN`: the App key for your Slack bot (Create New App on [Slack](https://api.slack.com/apps), go to OAuth & Permissions and generate a bot User OAuth Token).
+- `SLACK_CHANNEL`: the Slack channel where your bot will post events (defaults to `#general`, you have to invite the App to your channel).
+- `DEBUG`: if set to false, silence debug logs.
 
-The file should be placed at the root folder of your local copy of the project.
+So your `.env` file should look like something similar to [`.env.example`](.env.example)
+The file should be placed in the folder of your `./docker-compose.yml`.
 
 ## More goodies
 
 ### Documentation
 
-The full package documentation is available [here](https://quack-ai.github.io/contribution-api) for detailed specifications.
+Your API documentation gets a swagger automatically available on [here](http://localhost:8050/docs) for detailed specifications.
 
 
 ## Contributing

docker-compose.test.yml

@@ -9,14 +9,12 @@ services:
     ports:
       - "8050:8050"
     environment:
-      - POSTGRES_URL=postgresql+asyncpg://dummy_login:dummy_pwd@test_db/dummy_db
-      - SUPERUSER_LOGIN=${SUPERUSER_LOGIN}
-      - SUPERUSER_ID=${SUPERUSER_ID}
-      - SUPERUSER_PWD=${SUPERUSER_PWD}
+      - SUPERADMIN_GH_PAT=${SUPERADMIN_GH_PAT}
+      - SUPERADMIN_PWD=superadmin_pwd
       - GH_OAUTH_ID=${GH_OAUTH_ID}
       - GH_OAUTH_SECRET=${GH_OAUTH_SECRET}
+      - POSTGRES_URL=postgresql+asyncpg://dummy_login:dummy_pwd@test_db/dummy_db
       - OPENAI_API_KEY=${OPENAI_API_KEY}
-      - SERVER_NAME=dummy_server
       - DEBUG=true
     depends_on:
       test_db:

docker-compose.yml

@@ -9,27 +9,22 @@ services:
     ports:
       - "8050:8050"
     environment:
-      - POSTGRES_URL=postgresql+asyncpg://${POSTGRES_USER}:${POSTGRES_PASSWORD}@db/${POSTGRES_DB}
-      - SUPERUSER_LOGIN=${SUPERUSER_LOGIN}
-      - SUPERUSER_ID=${SUPERUSER_ID}
-      - SUPERUSER_PWD=${SUPERUSER_PWD}
+      - SUPERADMIN_GH_PAT=${SUPERADMIN_GH_PAT}
+      - SUPERADMIN_PWD=${SUPERADMIN_PWD}
       - GH_OAUTH_ID=${GH_OAUTH_ID}
       - GH_OAUTH_SECRET=${GH_OAUTH_SECRET}
+      - POSTGRES_URL=postgresql+asyncpg://${POSTGRES_USER}:${POSTGRES_PASSWORD}@db/${POSTGRES_DB}
       - OPENAI_API_KEY=${OPENAI_API_KEY}
-      - SERVER_NAME=${SERVER_NAME}
       - SECRET_KEY=${SECRET_KEY}
+      - SENTRY_DSN=${SENTRY_DSN}
+      - SERVER_NAME=${SERVER_NAME}
+      - POSTHOG_KEY=${POSTHOG_KEY}
       - SLACK_API_TOKEN=${SLACK_API_TOKEN}
       - SLACK_CHANNEL=${SLACK_CHANNEL}
       - DEBUG=true
     depends_on:
       db:
         condition: service_healthy
-    labels:
-      - "traefik.enable=true"
-      - "traefik.http.routers.api.rule=Host(`api.localhost`) && PathPrefix(`/`)"
-      - "traefik.http.routers.api.service=backend@docker"
-      - "traefik.http.routers.api.tls={}"
-      - "traefik.http.services.backend.loadbalancer.server.port=8050"
 
   db:
     image: postgres:15-alpine
@@ -47,17 +42,5 @@ services:
       timeout: 3s
       retries: 3
 
-  traefik:
-    image: traefik:v2.9.6
-    volumes:
-      - "./traefik:/etc/traefik"
-      - "/var/run/docker.sock:/var/run/docker.sock:ro"
-    ports:
-      # http(s) traffic
-      - "80:80"
-      - "443:443"
-      # traefik dashboard
-      - "8080:8080"
-
 volumes:
   postgres_data:

src/app/api/api_v1/endpoints/login.py

@@ -31,7 +31,7 @@ async def authorize_github(
     redirect_uri: HttpUrl,
 ) -> RedirectResponse:
     return RedirectResponse(
-        f"{settings.GH_AUTHORIZE_ENDPOINT}?scope={scope}&client_id={settings.GH_OAUTH_ID}&redirect_uri={redirect_uri}"
+        f"https://github.com/login/oauth/authorize?scope={scope}&client_id={settings.GH_OAUTH_ID}&redirect_uri={redirect_uri}"
     )
 
 

src/app/core/config.py

@@ -5,6 +5,7 @@
 
 import os
 import secrets
+import socket
 from typing import Union
 
 from pydantic import BaseSettings, validator
@@ -21,24 +22,14 @@ class Settings(BaseSettings):
     VERSION: str = "0.1.0.dev0"
     API_V1_STR: str = "/api/v1"
     CORS_ORIGIN: str = "*"
-    # Ext API endpoints
-    GH_AUTHORIZE_ENDPOINT: str = "https://github.com/login/oauth/authorize"
+    # Authentication
+    SUPERADMIN_GH_PAT: str = os.environ["SUPERADMIN_GH_PAT"]
+    SUPERADMIN_PWD: str = os.environ["SUPERADMIN_PWD"]
     GH_OAUTH_ID: str = os.environ["GH_OAUTH_ID"]
     GH_OAUTH_SECRET: str = os.environ["GH_OAUTH_SECRET"]
     GH_TOKEN: Union[str, None] = os.environ.get("GH_TOKEN")
-    # Security
-    SECRET_KEY: str = os.environ.get("SECRET_KEY", secrets.token_urlsafe(32))
-    ACCESS_TOKEN_EXPIRE_MINUTES: int = 60
-    ACCESS_TOKEN_UNLIMITED_MINUTES: int = 60 * 24 * 365
-    JWT_ENCODING_ALGORITHM: str = "HS256"
     # DB
     POSTGRES_URL: str = os.environ["POSTGRES_URL"]
-    SUPERUSER_LOGIN: str = os.environ["SUPERUSER_LOGIN"]
-    SUPERUSER_ID: int = int(os.environ["SUPERUSER_ID"])
-    SUPERUSER_PWD: str = os.environ["SUPERUSER_PWD"]
-    # Compute
-    OPENAI_API_KEY: str = os.environ["OPENAI_API_KEY"]
-    OPENAI_MODEL: OpenAIModel = OpenAIModel.GPT3_5
 
     @validator("POSTGRES_URL", pre=True)
     @classmethod
@@ -48,8 +39,18 @@ def sqlachmey_uri(cls, v: str) -> str:
             return v.replace("postgres://", "postgresql+asyncpg://", 1)
         return v
 
+    # Security
+    SECRET_KEY: str = os.environ.get("SECRET_KEY", secrets.token_urlsafe(32))
+    ACCESS_TOKEN_EXPIRE_MINUTES: int = 60
+    ACCESS_TOKEN_UNLIMITED_MINUTES: int = 60 * 24 * 365
+    JWT_ENCODING_ALGORITHM: str = "HS256"
+    # Compute
+    OPENAI_API_KEY: str = os.environ["OPENAI_API_KEY"]
+    OPENAI_MODEL: OpenAIModel = OpenAIModel.GPT4_TURBO
+
+    # Error monitoring
     SENTRY_DSN: Union[str, None] = os.environ.get("SENTRY_DSN")
-    SERVER_NAME: str = os.environ["SERVER_NAME"]
+    SERVER_NAME: str = os.environ.get("SERVER_NAME", socket.gethostname())
 
     @validator("SENTRY_DSN", pre=True)
     @classmethod
@@ -58,6 +59,7 @@ def sentry_dsn_can_be_blank(cls, v: str) -> Union[str, None]:
             return None
         return v
 
+    # Product analytics
     POSTHOG_KEY: Union[str, None] = os.environ.get("POSTHOG_KEY")
 
     @validator("POSTHOG_KEY", pre=True)
@@ -67,6 +69,7 @@ def posthog_key_can_be_blank(cls, v: str) -> Union[str, None]:
             return None
         return v
 
+    # Event notifications
     SLACK_API_TOKEN: Union[str, None] = os.environ.get("SLACK_API_TOKEN")
     SLACK_CHANNEL: str = os.environ.get("SLACK_CHANNEL", "#general")
 

src/app/db.py

@@ -11,6 +11,7 @@
 from app.core.config import settings
 from app.core.security import hash_password
 from app.models import User, UserScope
+from app.services.github import gh_client
 
 __all__ = ["get_session", "init_db"]
 
@@ -29,14 +30,12 @@ async def init_db():
         await conn.run_sync(SQLModel.metadata.create_all)
 
     async with AsyncSession(engine) as session:
-        statement = select(User).where(User.login == settings.SUPERUSER_LOGIN)
+        # Fetch authenticated GitHub User
+        gh_user = gh_client.get_my_user(settings.SUPERADMIN_GH_PAT)
+        statement = select(User).where(User.login == gh_user["login"])
         results = await session.execute(statement=statement)
         current_user = results.scalar_one_or_none()
         if not current_user:
-            pwd = await hash_password(settings.SUPERUSER_PWD)
-            session.add(
-                User(
-                    id=settings.SUPERUSER_ID, login=settings.SUPERUSER_LOGIN, hashed_password=pwd, scope=UserScope.ADMIN
-                )
-            )
+            pwd = await hash_password(settings.SUPERADMIN_PWD)
+            session.add(User(id=gh_user["id"], login=gh_user["login"], hashed_password=pwd, scope=UserScope.ADMIN))
         await session.commit()

src/app/schemas/guidelines.py

@@ -21,8 +21,12 @@ class ExampleRequest(TextContent):
 
 
 class GuidelineExample(BaseModel):
-    positive: str = Field(..., min_length=3)
-    negative: str = Field(..., min_length=3)
+    positive: str = Field(
+        ..., min_length=3, description="a minimal code snippet where the instruction was correctly followed."
+    )
+    negative: str = Field(
+        ..., min_length=3, description="the same snippet with minimal modifications that invalidates the instruction."
+    )
 
 
 class GuidelineContent(BaseModel):

src/app/schemas/services.py

@@ -13,10 +13,10 @@
 
 class OpenAIModel(str, Enum):
     # https://platform.openai.com/docs/models/overview
-    GPT3_5: str = "gpt-3.5-turbo-1106"
-    GPT3_5_LEGACY: str = "gpt-3.5-turbo-0613"
-    GPT4: str = "gpt-4-1106-preview"
-    GPT4_LEGACY: str = "gpt-4-0613"
+    GPT3_5_TURBO: str = "gpt-3.5-turbo-1106"
+    GPT3_5_TURBO_LEGACY: str = "gpt-3.5-turbo-0613"
+    GPT4_TURBO: str = "gpt-4-1106-preview"
+    GPT4: str = "gpt-4-0613"
 
 
 class OpenAIChatRole(str, Enum):
@@ -71,7 +71,7 @@ class _ResponseFormat(BaseModel):
 
 
 class ChatCompletion(BaseModel):
-    model: OpenAIModel = OpenAIModel.GPT3_5
+    model: OpenAIModel = OpenAIModel.GPT3_5_TURBO
     messages: List[OpenAIMessage]
     functions: List[OpenAIFunction]
     function_call: Dict[str, str]