Ruff and black

Author: pamelafox

.github/workflows/python-code-quality.yaml

@@ -20,6 +20,6 @@ jobs:
             python -m pip install --upgrade pip
             pip install -r requirements-dev.txt
         - name: Lint with ruff
-          run: ruff .
+          run: ruff check .
         - name: Check formatting with black
           run: black . --check --verbose

pyproject.toml

@@ -1,9 +1,10 @@
 [tool.ruff]
 line-length = 120
 target-version = "py311"
+
+[tool.ruff.lint]
 select = ["E", "F", "I", "UP"]
 ignore = ["D203"]
-show-source = true
 
 [tool.ruff.lint.isort]
 known-first-party = ["fastapi_app"]

src/fastapi_app/query_rewriter.py

@@ -26,7 +26,7 @@ def build_search_function() -> list[ChatCompletionToolParam]:
                             "properties": {
                                 "comparison_operator": {
                                     "type": "string",
-                                    "description": "Operator to compare the column value, either '>', '<', '>=', '<=', '=='",
+                                    "description": "Operator to compare the column value, either '>', '<', '>=', '<=', '=='",  # noqa
                                 },
                                 "value": {
                                     "type": "number",

src/fastapi_app/rag_advanced.py

@@ -17,7 +17,6 @@
 
 
 class AdvancedRAGChat:
-
     def __init__(
         self,
         *,
@@ -26,7 +25,8 @@ def __init__(
         chat_model: str,
         chat_deployment: str | None,  # Not needed for non-Azure OpenAI
         openai_embed_client: AsyncOpenAI,
-        embed_deployment: str | None,  # Not needed for non-Azure OpenAI or for retrieval_mode="text"
+        embed_deployment: str
+        | None,  # Not needed for non-Azure OpenAI or for retrieval_mode="text"
         embed_model: str,
         embed_dimensions: int,
     ):
@@ -46,7 +46,6 @@ def __init__(
     async def run(
         self, messages: list[dict], overrides: dict[str, Any] = {}
     ) -> dict[str, Any] | AsyncGenerator[dict[str, Any], None]:
-
         text_search = overrides.get("retrieval_mode") in ["text", "hybrid", None]
         vector_search = overrides.get("retrieval_mode") in ["vectors", "hybrid", None]
         top = overrides.get("top", 3)
@@ -61,7 +60,8 @@ async def run(
             system_prompt=self.query_prompt_template,
             new_user_content=original_user_query,
             past_messages=past_messages,
-            max_tokens=self.chat_token_limit - query_response_token_limit,  # TODO: count functions
+            max_tokens=self.chat_token_limit
+            - query_response_token_limit,  # TODO: count functions
             fallback_to_default=True,
         )
 
@@ -70,7 +70,7 @@ async def run(
             # Azure OpenAI takes the deployment name as the model name
             model=self.chat_deployment if self.chat_deployment else self.chat_model,
             temperature=0.0,  # Minimize creativity for search query generation
-            max_tokens=query_response_token_limit,  # Setting too low risks malformed JSON, setting too high may affect performance
+            max_tokens=query_response_token_limit,  # Setting too low risks malformed JSON, too high risks performance
             n=1,
             tools=build_search_function(),
             tool_choice="auto",
@@ -93,14 +93,17 @@ async def run(
 
         results = await self.searcher.search(query_text, vector, top, filters)
 
-        sources_content = [f"[{(item.id)}]:{item.to_str_for_rag()}\n\n" for item in results]
+        sources_content = [
+            f"[{(item.id)}]:{item.to_str_for_rag()}\n\n" for item in results
+        ]
         content = "\n".join(sources_content)
 
         # Generate a contextual and content specific answer using the search results and chat history
         response_token_limit = 1024
         messages = build_messages(
             model=self.chat_model,
-            system_prompt=overrides.get("prompt_template") or self.answer_prompt_template,
+            system_prompt=overrides.get("prompt_template")
+            or self.answer_prompt_template,
             new_user_content=original_user_query + "\n\nSources:\n" + content,
             past_messages=past_messages,
             max_tokens=self.chat_token_limit - response_token_limit,

src/fastapi_app/setup_postgres_seeddata.py

@@ -9,33 +9,38 @@
 from sqlalchemy import select, text
 from sqlalchemy.ext.asyncio import async_sessionmaker
 
-from fastapi_app.postgres_engine import create_postgres_engine_from_args, create_postgres_engine_from_env
+from fastapi_app.postgres_engine import (
+    create_postgres_engine_from_args,
+    create_postgres_engine_from_env,
+)
 from fastapi_app.postgres_models import Item
 
 logger = logging.getLogger("ragapp")
 
 
 async def seed_data(engine):
-
     # Check if Item table exists
     async with engine.begin() as conn:
         result = await conn.execute(
             text(
-                "SELECT EXISTS (SELECT 1 FROM information_schema.tables WHERE table_schema = 'public' AND table_name = 'items')"
+                "SELECT EXISTS (SELECT 1 FROM information_schema.tables WHERE table_schema = 'public' AND table_name = 'items')"  # noqa
             )
         )
         if not result.scalar():
-            logger.error("Items table does not exist. Please run the database setup script first.")
+            logger.error(
+                "Items table does not exist. Please run the database setup script first."
+            )
             return
 
     async with async_sessionmaker(engine, expire_on_commit=False)() as session:
-
         # Insert the items from the JSON file into the database
         current_dir = os.path.dirname(os.path.realpath(__file__))
         with open(os.path.join(current_dir, "seed_data.json")) as f:
             catalog_items = json.load(f)
             for catalog_item in catalog_items:
-                item = await session.execute(select(Item).filter(Item.id == catalog_item["Id"]))
+                item = await session.execute(
+                    select(Item).filter(Item.id == catalog_item["Id"])
+                )
                 if item.scalars().first():
                     continue
                 item = Item(
@@ -57,7 +62,6 @@ async def seed_data(engine):
 
 
 async def main():
-
     parser = argparse.ArgumentParser(description="Create database schema")
     parser.add_argument("--host", type=str, help="Postgres host")
     parser.add_argument("--username", type=str, help="Postgres username")
@@ -78,7 +82,6 @@ async def main():
 
 
 if __name__ == "__main__":
-
     logging.basicConfig(level=logging.WARNING)
     logger.setLevel(logging.INFO)
     load_dotenv(override=True)

src/gunicorn.conf.py

@@ -8,4 +8,4 @@
 
 worker_class = "uvicorn.workers.UvicornWorker"
 
-timeout = 600
+timeout = 600