docs(backend): add docstrings (QuivrHQ#590)

backend/models/files.py

@@ -6,11 +6,10 @@
 from fastapi import UploadFile
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from logger import get_logger
-from pydantic import BaseModel
-from utils.file import compute_sha1_from_file
-
 from models.brains import Brain
 from models.settings import CommonsDep, common_dependencies
+from pydantic import BaseModel
+from utils.file import compute_sha1_from_file
 
 logger = get_logger(__name__)
 
@@ -19,9 +18,9 @@ class File(BaseModel):
     id: Optional[UUID] = None
     file: Optional[UploadFile]
     file_name: Optional[str] = ""
-    file_size: Optional[int] = ""  # pyright: ignore reportPrivateUsage=none
+    file_size: Optional[int] = None
     file_sha1: Optional[str] = ""
-    vectors_ids: Optional[int] = []  # pyright: ignore reportPrivateUsage=none
+    vectors_ids: Optional[list] = []
     file_extension: Optional[str] = ""
     content: Optional[Any] = None
     chunk_size: int = 500
@@ -42,6 +41,9 @@ def __init__(self, **kwargs):
             )[-1].lower()
 
     async def compute_file_sha1(self):
+        """
+        Compute the sha1 of the file using a temporary file
+        """
         with tempfile.NamedTemporaryFile(
             delete=False,
             suffix=self.file.filename,  # pyright: ignore reportPrivateUsage=none
@@ -57,6 +59,12 @@ async def compute_file_sha1(self):
         os.remove(tmp_file.name)
 
     def compute_documents(self, loader_class):
+        """
+        Compute the documents from the file
+
+        Args:
+            loader_class (class): The class of the loader to use to load the file
+        """
         logger.info(f"Computing documents from file {self.file_name}")
 
         documents = []
@@ -118,6 +126,12 @@ def file_already_exists(self):
         return True
 
     def file_already_exists_in_brain(self, brain_id):
+        """
+        Check if file already exists in a brain
+
+        Args:
+            brain_id (str): Brain id
+        """
         commons = common_dependencies()
         self.set_file_vectors_ids()
         # Check if file exists in that brain
@@ -136,13 +150,19 @@ def file_already_exists_in_brain(self, brain_id):
         return True
 
     def file_is_empty(self):
+        """
+        Check if file is empty by checking if the file pointer is at the beginning of the file
+        """
         return (
             self.file.file._file.tell() < 1  # pyright: ignore reportPrivateUsage=none
         )
 
     def link_file_to_brain(self, brain: Brain):
         self.set_file_vectors_ids()
 
+        if self.vectors_ids is None:
+            return
+
         for vector_id in self.vectors_ids:  # pyright: ignore reportPrivateUsage=none
             brain.create_brain_vector(vector_id["id"], self.file_sha1)
         print(f"Successfully linked file {self.file_sha1} to brain {brain.id}")

backend/models/users.py

@@ -16,6 +16,12 @@ class User(BaseModel):
 
     # [TODO] Rename the user table and its references to 'user_usage'
     def create_user(self, date):
+        """
+        Create a new user entry in the database
+
+        Args:
+            date (str): Date of the request
+        """
         commons = common_dependencies()
         logger.info(f"New user entry in db document for user {self.email}")
 
@@ -34,6 +40,9 @@ def create_user(self, date):
         )
 
     def get_user_request_stats(self):
+        """
+        Fetch the user request stats from the database
+        """
         commons = common_dependencies()
         requests_stats = (
             commons["supabase"]
@@ -45,6 +54,9 @@ def get_user_request_stats(self):
         return requests_stats.data
 
     def fetch_user_requests_count(self, date):
+        """
+        Fetch the user request count from the database
+        """
         commons = common_dependencies()
         response = (
             commons["supabase"]
@@ -59,6 +71,9 @@ def fetch_user_requests_count(self, date):
         return userItem["requests_count"]
 
     def increment_user_request_count(self, date):
+        """
+        Increment the user request count in the database
+        """
         commons = common_dependencies()
         requests_count = self.fetch_user_requests_count(date) + 1
         logger.info(f"User {self.email} request count updated to {requests_count}")