chore: add static anaysis

.vscode/extensions.json

@@ -0,0 +1,8 @@
+{
+    "recommendations": [
+        "charliermarsh.ruff",
+        "dbaeumer.vscode-eslint",
+        "ms-python.vscode-pylance",
+        "ms-pyright.pyright"
+    ]
+}

.vscode/settings.json

@@ -6,13 +6,13 @@
     "source.unusedImports": true
   },
   "python.linting.enabled": true,
-  "python.linting.flake8Enabled": true,
   "editor.formatOnSave": true,
   "[python]": {
     "editor.defaultFormatter": "ms-python.black-formatter",
     "editor.formatOnSave": true,
     "editor.codeActionsOnSave": {
-      "source.organizeImports": true
+      "source.fixAll": true,
+      "source.organizeImports.ruff": true
     }
   },
   "[typescriptreact]": {
@@ -30,5 +30,10 @@
     "editor.defaultFormatter": "esbenp.prettier-vscode",
     "editor.formatOnSave": true
   },
-  "editor.formatOnSaveMode": "file"
-}
+  "editor.formatOnSaveMode": "file",
+  "ruff.args": ["--config=/backend/ruff.toml"],
+  "python.linting.pycodestyleCategorySeverity.W": "Error",
+  "python.defaultInterpreterPath": "python3",
+  "python.linting.flake8CategorySeverity.W": "Error",
+  "python.analysis.typeCheckingMode": "strict"
+}

backend/auth/api_key_handler.py

@@ -1,9 +1,10 @@
 from datetime import datetime
 
 from fastapi import HTTPException
-from models.settings import common_dependencies
 from pydantic import DateError
 
+from models.settings import common_dependencies
+
 
 async def verify_api_key(
     api_key: str,

backend/crawl/crawler.py

@@ -4,7 +4,6 @@
 import unicodedata
 
 import requests
-from langchain.document_loaders import GitLoader
 from pydantic import BaseModel
 
 

backend/lint.sh

@@ -0,0 +1,8 @@
+# Check if "python3" command is available
+if command -v python3 &>/dev/null; then
+    # Run with Python 3
+    python3 -m ruff check .
+else
+    # Run with Python 2 (assuming it's available)
+    python -m ruff check .
+fi

backend/llm/brainpicking.py

@@ -10,18 +10,21 @@
 from langchain.chat_models import ChatOpenAI
 from langchain.embeddings.openai import OpenAIEmbeddings
 from langchain.llms.base import LLM
+from pydantic import BaseModel  # For data validation and settings management
+from supabase import (
+    Client,  # For interacting with Supabase database
+    create_client,
+)
+
 from llm.prompt.CONDENSE_PROMPT import CONDENSE_QUESTION_PROMPT
 from logger import get_logger
 from models.settings import BrainSettings  # Importing settings related to the 'brain'
-from pydantic import BaseModel  # For data validation and settings management
 from repository.chat.get_chat_history import get_chat_history
 from repository.chat.update_chat_history import update_chat_history
 from repository.chat.update_message_by_id import update_message_by_id
-from supabase import Client  # For interacting with Supabase database
-from supabase import create_client
 from vectorstore.supabase import (
     CustomSupabaseVectorStore,
-)  # Custom class for handling vector storage with Supabase
+)
 
 logger = get_logger(__name__)
 

backend/models/brains.py

@@ -2,9 +2,10 @@
 from typing import Any, List, Optional
 from uuid import UUID
 
+from pydantic import BaseModel
+
 from models.settings import CommonsDep, common_dependencies
 from models.users import User
-from pydantic import BaseModel
 
 
 class Brain(BaseModel):
@@ -43,7 +44,7 @@ def remaining_brain_size(self):
     @classmethod
     def create(cls, *args, **kwargs):
         commons = common_dependencies()
-        return cls(commons=commons, *args, **kwargs)
+        return cls(commons=commons, *args, **kwargs)  # noqa: B026
 
     def get_user_brains(self, user_id):
         response = (

backend/models/files.py

@@ -5,10 +5,11 @@
 
 from fastapi import UploadFile
 from langchain.text_splitter import RecursiveCharacterTextSplitter
+from pydantic import BaseModel
+
 from logger import get_logger
 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__)
@@ -30,14 +31,16 @@ class File(BaseModel):
 
     def __init__(self, **kwargs):
         super().__init__(**kwargs)
-        
+
         if self.file:
             self.file_name = self.file.filename
-            self.file_size = self.file.file._file.tell() 
+            self.file_size = self.file.file._file.tell()
             self.file_extension = os.path.splitext(self.file.filename)[-1].lower()
-      
+
     async def compute_file_sha1(self):
-        with tempfile.NamedTemporaryFile(delete=False, suffix=self.file.filename) as tmp_file:
+        with tempfile.NamedTemporaryFile(
+            delete=False, suffix=self.file.filename
+        ) as tmp_file:
             await self.file.seek(0)
             self.content = await self.file.read()
             tmp_file.write(self.content)
@@ -48,18 +51,20 @@ async def compute_file_sha1(self):
 
     def compute_documents(self, loader_class):
         logger.info(f"Computing documents from file {self.file_name}")
-        
+
         documents = []
-        with tempfile.NamedTemporaryFile(delete=False, suffix=self.file.filename) as tmp_file:
+        with tempfile.NamedTemporaryFile(
+            delete=False, suffix=self.file.filename
+        ) as tmp_file:
             tmp_file.write(self.content)
             tmp_file.flush()
             loader = loader_class(tmp_file.name)
             documents = loader.load()
-            
+
             print("documents", documents)
 
         os.remove(tmp_file.name)
-    
+
         text_splitter = RecursiveCharacterTextSplitter.from_tiktoken_encoder(
             chunk_size=self.chunk_size, chunk_overlap=self.chunk_overlap
         )
@@ -70,20 +75,21 @@ def compute_documents(self, loader_class):
 
     def set_file_vectors_ids(self):
         """
-        Set the vectors_ids property with the ids of the vectors 
+        Set the vectors_ids property with the ids of the vectors
         that are associated with the file in the vectors table
         """
 
-        commons = common_dependencies() 
+        commons = common_dependencies()
         response = (
-            commons["supabase"].table("vectors")
+            commons["supabase"]
+            .table("vectors")
             .select("id")
             .filter("metadata->>file_sha1", "eq", self.file_sha1)
             .execute()
         )
         self.vectors_ids = response.data
         return
-    
+
     def file_already_exists(self):
         """
         Check if file already exists in vectors table
@@ -97,15 +103,16 @@ def file_already_exists(self):
         # if the file does not exist in vectors then no need to go check in brains_vectors
         if len(self.vectors_ids) == 0:
             return False
-       
+
         return True
-    
+
     def file_already_exists_in_brain(self, brain_id):
-        commons = common_dependencies() 
+        commons = common_dependencies()
         self.set_file_vectors_ids()
         # Check if file exists in that brain
         response = (
-            commons["supabase"].table("brains_vectors")
+            commons["supabase"]
+            .table("brains_vectors")
             .select("brain_id, vector_id")
             .filter("brain_id", "eq", brain_id)
             .filter("file_sha1", "eq", self.file_sha1)
@@ -114,15 +121,15 @@ def file_already_exists_in_brain(self, brain_id):
         print("response.data", response.data)
         if len(response.data) == 0:
             return False
-                
+
         return True
-  
+
     def file_is_empty(self):
-        return self.file.file._file.tell()  < 1
-    
+        return self.file.file._file.tell() < 1
+
     def link_file_to_brain(self, brain: Brain):
         self.set_file_vectors_ids()
 
         for vector_id in self.vectors_ids:
-            brain.create_brain_vector(vector_id['id'], self.file_sha1)
+            brain.create_brain_vector(vector_id["id"], self.file_sha1)
         print(f"Successfully linked file {self.file_sha1} to brain {brain.id}")

backend/models/settings.py

@@ -3,7 +3,7 @@
 from fastapi import Depends
 from langchain.embeddings.openai import OpenAIEmbeddings
 from pydantic import BaseSettings
-from supabase import Client, create_client
+from supabase.client import Client, create_client
 from vectorstore.supabase import SupabaseVectorStore
 
 
@@ -21,9 +21,29 @@ class LLMSettings(BaseSettings):
     model_n_batch: int = 8
 
 
-def common_dependencies() -> dict:
-    settings = BrainSettings()
-    embeddings = OpenAIEmbeddings(openai_api_key=settings.openai_api_key)
+class CommonDependencies:
+    def __init__(
+        self,
+        supabase: Client,
+        embeddings: OpenAIEmbeddings,
+        documents_vector_store: SupabaseVectorStore,
+        summaries_vector_store: SupabaseVectorStore,
+    ):
+        self.supabase = supabase
+        self.embeddings = embeddings
+        self.documents_vector_store = documents_vector_store
+        self.summaries_vector_store = summaries_vector_store
+
+
+def common_dependencies() -> CommonDependencies:
+    settings = BrainSettings(
+        # type: ignore automatically loads .env file
+    )
+
+    embeddings = OpenAIEmbeddings(
+        openai_api_key=settings.openai_api_key,
+        # type: ignore other parameters are optional
+    )
     supabase_client: Client = create_client(
         settings.supabase_url, settings.supabase_service_key
     )
@@ -34,12 +54,12 @@ def common_dependencies() -> dict:
         supabase_client, embeddings, table_name="summaries"
     )
 
-    return {
-        "supabase": supabase_client,
-        "embeddings": embeddings,
-        "documents_vector_store": documents_vector_store,
-        "summaries_vector_store": summaries_vector_store,
-    }
+    return CommonDependencies(
+        supabase_client,
+        embeddings,
+        documents_vector_store,
+        summaries_vector_store,
+    )
 
 
-CommonsDep = Annotated[dict, Depends(common_dependencies)]
+CommonsDep = Annotated[CommonDependencies, Depends(common_dependencies)]

backend/models/users.py

@@ -15,17 +15,31 @@ class User(BaseModel):
 
     # [TODO] Rename the user table and its references to 'user_usage'
     def create_user(self, date):
-
         commons = common_dependencies()
         logger.info(f"New user entry in db document for user {self.email}")
 
-        return (commons['supabase'].table("users").insert(
-            {"user_id": self.id, "email": self.email, "date": date, "requests_count": 1}).execute())
+        return (
+            commons.supabase.table("users")
+            .insert(
+                {
+                    "user_id": self.id,
+                    "email": self.email,
+                    "date": date,
+                    "requests_count": 1,
+                }
+            )
+            .execute()
+        )
 
     def get_user_request_stats(self):
         commons = common_dependencies()
-        requests_stats = commons['supabase'].from_('users').select(
-            '*').filter("user_id", "eq", self.id).execute()
+        requests_stats = (
+            commons["supabase"]
+            .from_("users")
+            .select("*")
+            .filter("user_id", "eq", self.id)
+            .execute()
+        )
         return requests_stats.data
 
     def fetch_user_requests_count(self, date):
@@ -46,7 +60,7 @@ def increment_user_request_count(self, date):
         commons = common_dependencies()
         requests_count = self.fetch_user_requests_count(date) + 1
         logger.info(f"User {self.email} request count updated to {requests_count}")
-        commons['supabase'].table("users").update(
-            {"requests_count": requests_count}).match({"user_id": self.id, "date": date}).execute()
+        commons["supabase"].table("users").update(
+            {"requests_count": requests_count}
+        ).match({"user_id": self.id, "date": date}).execute()
         self.requests_count = requests_count
-