Feat: chat name edit (QuivrHQ#343)

* feat(chat): add name update

* chore(linting): add flake8

* feat: add chat name edit

.flake8

@@ -0,0 +1,4 @@
+[flake8]
+; Minimal configuration for Flake8 to work with Black.
+max-line-length = 100
+ignore = E101,E111,E112,E221,E222,E501,E711,E712,W503,W504,F401

.vscode/settings.json

@@ -1,10 +1,15 @@
 {
-  "[python]": {
-    "editor.defaultFormatter": "ms-python.autopep8"
-  },
   "python.formatting.provider": "black",
   "editor.codeActionsOnSave": {
-    "source.organizeImports": true
+    "source.organizeImports": true,
+    "source.fixAll":true
+  },
+  "python.linting.enabled": true,
+  "python.linting.flake8Enabled": true,
+  "editor.formatOnSave": true,
+  "[typescript]": {
+    "editor.defaultFormatter": "esbenp.prettier-vscode",
+    "editor.formatOnSave": true
   },
-  "python.linting.enabled": true
+  "editor.formatOnSaveMode": "modifications"
 }

backend/auth/api_key_handler.py

@@ -1,36 +1,61 @@
-
 from datetime import datetime
 
 from fastapi import HTTPException
 from models.settings import CommonsDep
 from pydantic import DateError
 
 
-async def verify_api_key(api_key: str, commons: CommonsDep):     
+async def verify_api_key(api_key: str, commons: CommonsDep):
     try:
         # Use UTC time to avoid timezone issues
         current_date = datetime.utcnow().date()
-        result = commons['supabase'].table('api_keys').select('api_key', 'creation_time').filter('api_key', 'eq', api_key).filter('is_active', 'eq', True).execute()
+        result = (
+            commons["supabase"]
+            .table("api_keys")
+            .select("api_key", "creation_time")
+            .filter("api_key", "eq", api_key)
+            .filter("is_active", "eq", True)
+            .execute()
+        )
         if result.data is not None and len(result.data) > 0:
-            api_key_creation_date = datetime.strptime(result.data[0]['creation_time'], "%Y-%m-%dT%H:%M:%S").date()
+            api_key_creation_date = datetime.strptime(
+                result.data[0]["creation_time"], "%Y-%m-%dT%H:%M:%S"
+            ).date()
 
             # Check if the API key was created today: Todo remove this check and use deleted_time instead.
             if api_key_creation_date == current_date:
                 return True
         return False
     except DateError:
         return False
-
+
+
 async def get_user_from_api_key(api_key: str, commons: CommonsDep):
     # Lookup the user_id from the api_keys table
-        user_id_data = commons['supabase'].table('api_keys').select('user_id').filter('api_key', 'eq', api_key).execute()
-
-        if not user_id_data.data:
-            raise HTTPException(status_code=400, detail="Invalid API key.")
-
-        user_id = user_id_data.data[0]['user_id']
+    user_id_data = (
+        commons["supabase"]
+        .table("api_keys")
+        .select("user_id")
+        .filter("api_key", "eq", api_key)
+        .execute()
+    )
+
+    if not user_id_data.data:
+        raise HTTPException(status_code=400, detail="Invalid API key.")
+
+    user_id = user_id_data.data[0]["user_id"]
 
-        # Lookup the email from the users table. Todo: remove and use user_id for credentials
-        user_email_data = commons['supabase'].table('users').select('email').filter('user_id', 'eq', user_id).execute()
+    # Lookup the email from the users table. Todo: remove and use user_id for credentials
+    user_email_data = (
+        commons["supabase"]
+        .table("users")
+        .select("email")
+        .filter("user_id", "eq", user_id)
+        .execute()
+    )
 
-        return {'email': user_email_data.data[0]['email']} if user_email_data.data else {'email': None}
+    return (
+        {"email": user_email_data.data[0]["email"]}
+        if user_email_data.data
+        else {"email": None}
+    )

backend/auth/auth_bearer.py

@@ -14,7 +14,9 @@ def __init__(self, auto_error: bool = True):
         super().__init__(auto_error=auto_error)
 
     async def __call__(self, request: Request, commons: CommonsDep):
-        credentials: Optional[HTTPAuthorizationCredentials] = await super().__call__(request)
+        credentials: Optional[HTTPAuthorizationCredentials] = await super().__call__(
+            request
+        )
         self.check_scheme(credentials)
         token = credentials.credentials
         return await self.authenticate(token, commons)
@@ -33,10 +35,13 @@ async def authenticate(self, token: str, commons: CommonsDep):
         elif await verify_api_key(token, commons):
             return await get_user_from_api_key(token, commons)
         else:
-            raise HTTPException(status_code=402, detail="Invalid token or expired token.")
+            raise HTTPException(
+                status_code=402, detail="Invalid token or expired token."
+            )
 
     def get_test_user(self):
-        return {'email': '[email protected]'}  # replace with test user information
+        return {"email": "[email protected]"}  # replace with test user information
+
 
 def get_current_user(credentials: dict = Depends(AuthBearer())) -> User:
-    return User(email=credentials.get('email', 'none'))
+    return User(email=credentials.get("email", "none"))

backend/auth/jwt_token_handler.py

@@ -8,6 +8,7 @@
 SECRET_KEY = os.environ.get("JWT_SECRET_KEY")
 ALGORITHM = "HS256"
 
+
 def create_access_token(data: dict, expires_delta: Optional[timedelta] = None):
     to_encode = data.copy()
     if expires_delta:
@@ -18,19 +19,24 @@ def create_access_token(data: dict, expires_delta: Optional[timedelta] = None):
     encoded_jwt = jwt.encode(to_encode, SECRET_KEY, algorithm=ALGORITHM)
     return encoded_jwt
 
+
 def decode_access_token(token: str):
     try:
-        payload = jwt.decode(token, SECRET_KEY, algorithms=[ALGORITHM], options={"verify_aud": False})
+        payload = jwt.decode(
+            token, SECRET_KEY, algorithms=[ALGORITHM], options={"verify_aud": False}
+        )
         return payload
-    except JWTError as e:
+    except JWTError:
         return None
-
+
+
 def verify_token(token: str):
     payload = decode_access_token(token)
     return payload is not None
 
+
 def get_user_email_from_token(token: str):
     payload = decode_access_token(token)
     if payload:
         return payload.get("email")
-    return "none"
+    return "none"

backend/crawl/crawler.py

@@ -9,11 +9,11 @@
 
 
 class CrawlWebsite(BaseModel):
-    url : str
-    js : bool = False
-    depth : int = 1
-    max_pages : int = 100
-    max_time : int = 60
+    url: str
+    js: bool = False
+    depth: int = 1
+    max_pages: int = 100
+    max_time: int = 60
 
     def _crawl(self, url):
         response = requests.get(url)
@@ -24,28 +24,28 @@ def _crawl(self, url):
 
     def process(self):
         content = self._crawl(self.url)
-            
-        ## Create a file
+
+        # Create a file
         file_name = slugify(self.url) + ".html"
         temp_file_path = os.path.join(tempfile.gettempdir(), file_name)
-        with open(temp_file_path, 'w') as temp_file:
+        with open(temp_file_path, "w") as temp_file:
             temp_file.write(content)
-            ## Process the file
-        
+            # Process the file
+
         if content:
             return temp_file_path, file_name
         else:
             return None
+
     def checkGithub(self):
         if "github.com" in self.url:
             return True
         else:
             return False
 
 
-
 def slugify(text):
-    text = unicodedata.normalize('NFKD', text).encode('ascii', 'ignore').decode('utf-8')
-    text = re.sub(r'[^\w\s-]', '', text).strip().lower()
-    text = re.sub(r'[-\s]+', '-', text)
-    return text
+    text = unicodedata.normalize("NFKD", text).encode("ascii", "ignore").decode("utf-8")
+    text = re.sub(r"[^\w\s-]", "", text).strip().lower()
+    text = re.sub(r"[-\s]+", "-", text)
+    return text

backend/llm/summarization.py

@@ -8,11 +8,12 @@
 
 openai_api_key = os.environ.get("OPENAI_API_KEY")
 openai.api_key = openai_api_key
-summary_llm = guidance.llms.OpenAI('gpt-3.5-turbo-0613', caching=False)
+summary_llm = guidance.llms.OpenAI("gpt-3.5-turbo-0613", caching=False)
 
 
 def llm_summerize(document):
-    summary = guidance("""
+    summary = guidance(
+        """
 {{#system~}}
 You are a world best summarizer. \n
 Condense the text, capturing essential points and core ideas. Include relevant \
@@ -28,21 +29,23 @@ def llm_summerize(document):
 {{#assistant~}}
 {{gen 'summarization' temperature=0.2 max_tokens=100}}
 {{/assistant~}}
-""", llm=summary_llm)
+""",
+        llm=summary_llm,
+    )
 
     summary = summary(document=document)
-    logger.info('Summarization: %s', summary)
-    return summary['summarization']
+    logger.info("Summarization: %s", summary)
+    return summary["summarization"]
 
 
 def llm_evaluate_summaries(question, summaries, model):
-    if not model.startswith('gpt'):
-        logger.info(
-            f'Model {model} not supported. Using gpt-3.5-turbo instead.')
-        model = 'gpt-3.5-turbo-0613'
-    logger.info(f'Evaluating summaries with {model}')
+    if not model.startswith("gpt"):
+        logger.info(f"Model {model} not supported. Using gpt-3.5-turbo instead.")
+        model = "gpt-3.5-turbo-0613"
+    logger.info(f"Evaluating summaries with {model}")
     evaluation_llm = guidance.llms.OpenAI(model, caching=False)
-    evaluation = guidance("""
+    evaluation = guidance(
+        """
 {{#system~}}
 You are a world best evaluator. You evaluate the relevance of summaries based \
 on user input question. Return evaluation in following csv format, csv headers \
@@ -73,23 +76,30 @@ def llm_evaluate_summaries(question, summaries, model):
 {{#assistant~}}
 {{gen 'evaluation' temperature=0.2 stop='<|im_end|>'}}
 {{/assistant~}}
-""", llm=evaluation_llm)
+""",
+        llm=evaluation_llm,
+    )
     result = evaluation(question=question, summaries=summaries)
     evaluations = {}
-    for evaluation in result['evaluation'].split('\n'):
-        if evaluation == '' or not evaluation[0].isdigit():
+    for evaluation in result["evaluation"].split("\n"):
+        if evaluation == "" or not evaluation[0].isdigit():
             continue
-        logger.info('Evaluation Row: %s', evaluation)
-        summary_id, document_id, score, *reason = evaluation.split(',')
+        logger.info("Evaluation Row: %s", evaluation)
+        summary_id, document_id, score, *reason = evaluation.split(",")
         if not score.isdigit():
             continue
         score = int(score)
         if score < 3 or score > 5:
             continue
         evaluations[summary_id] = {
-            'evaluation': score,
-            'reason': ','.join(reason),
-            'summary_id': summary_id,
-            'document_id': document_id,
+            "evaluation": score,
+            "reason": ",".join(reason),
+            "summary_id": summary_id,
+            "document_id": document_id,
         }
-    return [e for e in sorted(evaluations.values(), key=lambda x: x['evaluation'], reverse=True)]
+    return [
+        e
+        for e in sorted(
+            evaluations.values(), key=lambda x: x["evaluation"], reverse=True
+        )
+    ]

backend/models/brains.py

@@ -11,12 +11,13 @@ class Brain(BaseModel):
     model: str = "gpt-3.5-turbo-0613"
     temperature: float = 0.0
     max_tokens: int = 256
-
-class BrainToUpdate(BaseModel): 
+
+
+class BrainToUpdate(BaseModel):
     brain_id: UUID
     brain_name: Optional[str] = "New Brain"
     status: Optional[str] = "public"
     model: Optional[str] = "gpt-3.5-turbo-0613"
     temperature: Optional[float] = 0.0
     max_tokens: Optional[int] = 256
-    file_sha1: Optional[str] = ''
+    file_sha1: Optional[str] = ""

backend/models/chats.py

@@ -12,4 +12,9 @@ class ChatMessage(BaseModel):
     temperature: float = 0.0
     max_tokens: int = 256
     use_summarization: bool = False
-    chat_id: Optional[UUID] = None,
+    chat_id: Optional[UUID] = None
+    chat_name: Optional[str] = None
+
+
+class ChatAttributes(BaseModel):
+    chat_name: Optional[str] = None

backend/models/users.py

@@ -1,5 +1,5 @@
 from pydantic import BaseModel
 
 
-class User (BaseModel):
+class User(BaseModel):
     email: str