khoj 2.0.0b13.dev5__py3-none-any.whl → 2.0.0b13.dev23__py3-none-any.whl

khoj/routers/api_chat.py

@@ -10,7 +10,6 @@ from functools import partial
 from typing import Any, Dict, List, Optional
 from urllib.parse import unquote
 
-from asgiref.sync import sync_to_async
 from fastapi import (
     APIRouter,
     Depends,
@@ -32,10 +31,10 @@ from khoj.database.adapters import (
     PublicConversationAdapters,
     aget_user_name,
 )
-from khoj.database.models import Agent, ChatMessageModel, KhojUser
+from khoj.database.models import Agent, KhojUser
 from khoj.processor.conversation import prompts
 from khoj.processor.conversation.openai.utils import is_local_api
-from khoj.processor.conversation.prompts import help_message, no_entries_found
+from khoj.processor.conversation.prompts import no_entries_found
 from khoj.processor.conversation.utils import (
     OperatorRun,
     ResponseWithThought,
@@ -65,11 +64,8 @@ from khoj.routers.helpers import (
     acreate_title_from_history,
     agenerate_chat_response,
     aget_data_sources_and_output_format,
-    construct_automation_created_message,
-    create_automation,
     gather_raw_query_files,
     generate_mermaidjs_diagram,
-    generate_summary_from_files,
     get_conversation_command,
     get_message_from_queue,
     is_query_empty,
@@ -89,13 +85,11 @@ from khoj.utils.helpers import (
     convert_image_to_webp,
     get_country_code_from_timezone,
     get_country_name_from_timezone,
-    get_device,
     is_env_var_true,
     is_none_or_empty,
     is_operator_enabled,
 )
 from khoj.utils.rawconfig import (
-    ChatRequestBody,
     FileAttachment,
     FileFilterRequest,
     FilesFilterRequest,
@@ -689,7 +683,6 @@ async def event_generator(
     region = body.region
     country = body.country or get_country_name_from_timezone(body.timezone)
     country_code = body.country_code or get_country_code_from_timezone(body.timezone)
-    timezone = body.timezone
     raw_images = body.images
     raw_query_files = body.files
 
@@ -853,7 +846,8 @@ async def event_generator(
                 if (
                     len(train_of_thought) > 0
                     and train_of_thought[-1]["type"] == ChatEvent.THOUGHT.value
-                    and type(train_of_thought[-1]["data"]) == type(data) == str
+                    and isinstance(train_of_thought[-1]["data"], str)
+                    and isinstance(data, str)
                 ):
                     train_of_thought[-1]["data"] += data
                 else:
@@ -1075,11 +1069,11 @@ async def event_generator(
 
         # researched_results = await extract_relevant_info(q, researched_results, agent)
         if state.verbose > 1:
-            logger.debug(f'Researched Results: {"".join(r.summarizedResult or "" for r in research_results)}')
+            logger.debug(f"Researched Results: {''.join(r.summarizedResult or '' for r in research_results)}")
 
     # Gather Context
     ## Extract Document References
-    if not ConversationCommand.Research in conversation_commands:
+    if ConversationCommand.Research not in conversation_commands:
         try:
             async for result in search_documents(
                 q,
@@ -1218,7 +1212,7 @@ async def event_generator(
                 else:
                     code_results = result
         except ValueError as e:
-            program_execution_context.append(f"Failed to run code")
+            program_execution_context.append("Failed to run code")
             logger.warning(
                 f"Failed to use code tool: {e}. Attempting to respond without code results",
                 exc_info=True,
@@ -1297,7 +1291,7 @@ async def event_generator(
         inferred_queries.append(improved_image_prompt)
         if generated_image is None or status_code != 200:
             program_execution_context.append(f"Failed to generate image with {improved_image_prompt}")
-            async for result in send_event(ChatEvent.STATUS, f"Failed to generate image"):
+            async for result in send_event(ChatEvent.STATUS, "Failed to generate image"):
                 yield result
         else:
             generated_images.append(generated_image)
@@ -1315,7 +1309,7 @@ async def event_generator(
                 yield result
 
     if ConversationCommand.Diagram in conversation_commands:
-        async for result in send_event(ChatEvent.STATUS, f"Creating diagram"):
+        async for result in send_event(ChatEvent.STATUS, "Creating diagram"):
             yield result
 
         inferred_queries = []
@@ -1372,7 +1366,7 @@ async def event_generator(
         return
 
     ## Generate Text Output
-    async for result in send_event(ChatEvent.STATUS, f"**Generating a well-informed response**"):
+    async for result in send_event(ChatEvent.STATUS, "**Generating a well-informed response**"):
         yield result
 
     llm_response, chat_metadata = await agenerate_chat_response(

khoj/routers/api_model.py

@@ -3,7 +3,6 @@ import logging
 from typing import Dict, Optional, Union
 
 from fastapi import APIRouter, Request
-from fastapi.requests import Request
 from fastapi.responses import Response
 from starlette.authentication import has_required_scope, requires
 

khoj/routers/api_subscription.py

@@ -117,7 +117,7 @@ async def subscribe(request: Request):
         )
         logger.log(logging.INFO, f"🥳 New User Created: {user.user.uuid}")
 
-    logger.info(f'Stripe subscription {event["type"]} for {customer_email}')
+    logger.info(f"Stripe subscription {event['type']} for {customer_email}")
     return {"success": success}
 
 

khoj/routers/email.py

@@ -44,7 +44,7 @@ async def send_magic_link_email(email, unique_id, host):
         {
             "sender": os.environ.get("RESEND_EMAIL", "noreply@khoj.dev"),
             "to": email,
-            "subject": f"Your login code to Khoj",
+            "subject": "Your login code to Khoj",
             "html": html_content,
         }
     )
@@ -98,11 +98,11 @@ async def send_query_feedback(uquery, kquery, sentiment, user_email):
         user_email=user_email if not is_none_or_empty(user_email) else "N/A",
     )
     # send feedback to fixed account
-    r = resend.Emails.send(
+    resend.Emails.send(
         {
             "sender": os.environ.get("RESEND_EMAIL", "noreply@khoj.dev"),
             "to": "team@khoj.dev",
-            "subject": f"User Feedback",
+            "subject": "User Feedback",
             "html": html_content,
         }
     )
@@ -127,7 +127,7 @@ def send_task_email(name, email, query, result, subject, is_image=False):
 
     r = resend.Emails.send(
         {
-            "sender": f'Khoj <{os.environ.get("RESEND_EMAIL", "khoj@khoj.dev")}>',
+            "sender": f"Khoj <{os.environ.get('RESEND_EMAIL', 'khoj@khoj.dev')}>",
             "to": email,
             "subject": f"✨ {subject}",
             "html": html_content,

khoj/routers/helpers.py

@@ -1,6 +1,5 @@
 import asyncio
 import base64
-import concurrent.futures
 import fnmatch
 import hashlib
 import json
@@ -47,14 +46,12 @@ from khoj.database.adapters import (
     EntryAdapters,
     FileObjectAdapters,
     aget_user_by_email,
-    ais_user_subscribed,
     create_khoj_token,
     get_default_search_model,
     get_khoj_tokens,
     get_user_name,
     get_user_notion_config,
     get_user_subscription_state,
-    is_user_subscribed,
     run_with_process_lock,
 )
 from khoj.database.models import (
@@ -160,7 +157,7 @@ def validate_chat_model(user: KhojUser):
 
 async def is_ready_to_chat(user: KhojUser):
     user_chat_model = await ConversationAdapters.aget_user_chat_model(user)
-    if user_chat_model == None:
+    if user_chat_model is None:
         user_chat_model = await ConversationAdapters.aget_default_chat_model(user)
 
     if (
@@ -581,7 +578,7 @@ async def generate_online_subqueries(
             )
             return {q}
         return response
-    except Exception as e:
+    except Exception:
         logger.error(f"Invalid response for constructing online subqueries: {response}. Returning original query: {q}")
         return {q}
 
@@ -1172,8 +1169,8 @@ async def search_documents(
         agent_has_entries = await sync_to_async(EntryAdapters.agent_has_entries)(agent=agent)
 
     if (
-        not ConversationCommand.Notes in conversation_commands
-        and not ConversationCommand.Default in conversation_commands
+        ConversationCommand.Notes not in conversation_commands
+        and ConversationCommand.Default not in conversation_commands
         and not agent_has_entries
     ):
         yield compiled_references, inferred_queries, q
@@ -1267,6 +1264,7 @@ async def extract_questions(
     location_data: LocationData = None,
     query_images: Optional[List[str]] = None,
     query_files: str = None,
+    max_queries: int = 5,
     tracer: dict = {},
 ):
     """
@@ -1296,14 +1294,20 @@ async def extract_questions(
         location=location,
         username=username,
         personality_context=personality_context,
+        max_queries=max_queries,
     )
 
     prompt = prompts.extract_questions_user_message.format(text=query, chat_history=chat_history_str)
 
     class DocumentQueries(BaseModel):
-        """Choose searches to run on user documents."""
+        """Choose semantic search queries to run on user documents."""
 
-        queries: List[str] = Field(..., min_items=1, description="List of search queries to run on user documents.")
+        queries: List[str] = Field(
+            ...,
+            min_length=1,
+            max_length=max_queries,
+            description="List of semantic search queries to run on user documents.",
+        )
 
     raw_response = await send_message_to_model_wrapper(
         system_message=system_prompt,
@@ -1325,8 +1329,8 @@ async def extract_questions(
             logger.error(f"Invalid response for constructing subqueries: {response}")
             return [query]
         return queries
-    except:
-        logger.warning(f"LLM returned invalid JSON. Falling back to using user message as search query.")
+    except Exception:
+        logger.warning("LLM returned invalid JSON. Falling back to using user message as search query.")
         return [query]
 
 
@@ -1351,7 +1355,7 @@ async def execute_search(
         return results
 
     if q is None or q == "":
-        logger.warning(f"No query param (q) passed in API call to initiate search")
+        logger.warning("No query param (q) passed in API call to initiate search")
         return results
 
     # initialize variables
@@ -1364,7 +1368,7 @@ async def execute_search(
     if user:
         query_cache_key = f"{user_query}-{n}-{t}-{r}-{max_distance}-{dedupe}"
         if query_cache_key in state.query_cache[user.uuid]:
-            logger.debug(f"Return response from query cache")
+            logger.debug("Return response from query cache")
             return state.query_cache[user.uuid][query_cache_key]
 
     # Encode query with filter terms removed
@@ -1875,8 +1879,8 @@ class ApiUserRateLimiter:
 
         user: KhojUser = websocket.scope["user"].object
         subscribed = has_required_scope(websocket, ["premium"])
-        current_window = "today" if self.window == 60 * 60 * 24 else f"now"
-        next_window = "tomorrow" if self.window == 60 * 60 * 24 else f"in a bit"
+        current_window = "today" if self.window == 60 * 60 * 24 else "now"
+        next_window = "tomorrow" if self.window == 60 * 60 * 24 else "in a bit"
         common_message_prefix = f"I'm glad you're enjoying interacting with me! You've unfortunately exceeded your usage limit for {current_window}."
 
         # Remove requests outside of the time window
@@ -2219,7 +2223,7 @@ def should_notify(original_query: str, executed_query: str, ai_response: str, us
             should_notify_result = response["decision"] == "Yes"
             reason = response.get("reason", "unknown")
             logger.info(
-                f'Decided to {"not " if not should_notify_result else ""}notify user of automation response because of reason: {reason}.'
+                f"Decided to {'not ' if not should_notify_result else ''}notify user of automation response because of reason: {reason}."
             )
             return should_notify_result
         except Exception as e:
@@ -2313,7 +2317,7 @@ def scheduled_chat(
         response_map = raw_response.json()
         ai_response = response_map.get("response") or response_map.get("image")
         is_image = False
-        if type(ai_response) == dict:
+        if isinstance(ai_response, dict):
             is_image = ai_response.get("image") is not None
     else:
         ai_response = raw_response.text
@@ -2460,12 +2464,12 @@ async def aschedule_automation(
 
 def construct_automation_created_message(automation: Job, crontime: str, query_to_run: str, subject: str):
     # Display next run time in user timezone instead of UTC
-    schedule = f'{cron_descriptor.get_description(crontime)} {automation.next_run_time.strftime("%Z")}'
+    schedule = f"{cron_descriptor.get_description(crontime)} {automation.next_run_time.strftime('%Z')}"
     next_run_time = automation.next_run_time.strftime("%Y-%m-%d %I:%M %p %Z")
     # Remove /automated_task prefix from inferred_query
     unprefixed_query_to_run = re.sub(r"^\/automated_task\s*", "", query_to_run)
     # Create the automation response
-    automation_icon_url = f"/static/assets/icons/automation.svg"
+    automation_icon_url = "/static/assets/icons/automation.svg"
     return f"""
     ### ![]({automation_icon_url}) Created Automation
 - Subject: **{subject}**
@@ -2713,13 +2717,13 @@ def configure_content(
     t: Optional[state.SearchType] = state.SearchType.All,
 ) -> bool:
     success = True
-    if t == None:
+    if t is None:
         t = state.SearchType.All
 
     if t is not None and t in [type.value for type in state.SearchType]:
         t = state.SearchType(t)
 
-    if t is not None and not t.value in [type.value for type in state.SearchType]:
+    if t is not None and t.value not in [type.value for type in state.SearchType]:
         logger.warning(f"🚨 Invalid search type: {t}")
         return False
 
@@ -2988,7 +2992,7 @@ async def grep_files(
             query += f" {' and '.join(context_info)}"
         if line_count > max_results:
             if lines_before or lines_after:
-                query += f" for"
+                query += " for"
             query += f" first {max_results} results"
         return query
 
@@ -2998,7 +3002,7 @@ async def grep_files(
     lines_after = lines_after or 0
 
     try:
-        regex = re.compile(regex_pattern, re.IGNORECASE)
+        regex = re.compile(regex_pattern, re.IGNORECASE | re.MULTILINE)
     except re.error as e:
         yield {
             "query": _generate_query(0, 0, path_prefix, regex_pattern, lines_before, lines_after),
@@ -3008,7 +3012,14 @@ async def grep_files(
         return
 
     try:
-        file_matches = await FileObjectAdapters.aget_file_objects_by_regex(user, regex_pattern, path_prefix)
+        # Make db pushdown filters more permissive by removing line anchors
+        # The precise line-anchored matching will be done in Python stage
+        db_pattern = regex_pattern
+        db_pattern = re.sub(r"\(\?\w*\)", "", db_pattern)  # Remove inline flags like (?i), (?m), (?im)
+        db_pattern = re.sub(r"^\^", "", db_pattern)  # Remove ^ at regex pattern start
+        db_pattern = re.sub(r"\$$", "", db_pattern)  # Remove $ at regex pattern end
+
+        file_matches = await FileObjectAdapters.aget_file_objects_by_regex(user, db_pattern, path_prefix)
 
         line_matches = []
         for file_object in file_matches:

khoj/routers/research.py

@@ -15,7 +15,6 @@ from khoj.processor.conversation.utils import (
     ResearchIteration,
     ToolCall,
     construct_iteration_history,
-    construct_structured_message,
     construct_tool_chat_history,
     load_complex_json,
 )
@@ -24,7 +23,6 @@ from khoj.processor.tools.online_search import read_webpages_content, search_onl
 from khoj.processor.tools.run_code import run_code
 from khoj.routers.helpers import (
     ChatEvent,
-    generate_summary_from_files,
     get_message_from_queue,
     grep_files,
     list_files,
@@ -184,7 +182,7 @@ async def apick_next_tool(
         # TODO: Handle multiple tool calls.
         response_text = response.text
         parsed_response = [ToolCall(**item) for item in load_complex_json(response_text)][0]
-    except Exception as e:
+    except Exception:
         # Otherwise assume the model has decided to end the research run and respond to the user.
         parsed_response = ToolCall(name=ConversationCommand.Text, args={"response": response_text}, id=None)
 
@@ -199,7 +197,7 @@ async def apick_next_tool(
         if i.warning is None and isinstance(i.query, ToolCall)
     }
     if (parsed_response.name, dict_to_tuple(parsed_response.args)) in previous_tool_query_combinations:
-        warning = f"Repeated tool, query combination detected. Skipping iteration. Try something different."
+        warning = "Repeated tool, query combination detected. Skipping iteration. Try something different."
     # Only send client status updates if we'll execute this iteration and model has thoughts to share.
     elif send_status_func and not is_none_or_empty(response.thought):
         async for event in send_status_func(response.thought):

khoj/search_filter/base_filter.py

@@ -4,12 +4,10 @@ from typing import List
 
 class BaseFilter(ABC):
     @abstractmethod
-    def get_filter_terms(self, query: str) -> List[str]:
-        ...
+    def get_filter_terms(self, query: str) -> List[str]: ...
 
     def can_filter(self, raw_query: str) -> bool:
         return len(self.get_filter_terms(raw_query)) > 0
 
     @abstractmethod
-    def defilter(self, query: str) -> str:
-        ...
+    def defilter(self, query: str) -> str: ...

khoj/search_type/text_search.py

@@ -9,9 +9,8 @@ from asgiref.sync import sync_to_async
 from sentence_transformers import util
 
 from khoj.database.adapters import EntryAdapters, get_default_search_model
-from khoj.database.models import Agent
+from khoj.database.models import Agent, KhojUser
 from khoj.database.models import Entry as DbEntry
-from khoj.database.models import KhojUser
 from khoj.processor.content.text_to_entries import TextToEntries
 from khoj.utils import state
 from khoj.utils.helpers import get_absolute_path, timer

khoj/utils/constants.py

@@ -40,6 +40,9 @@ model_to_cost: Dict[str, Dict[str, float]] = {
     "o3": {"input": 2.0, "output": 8.00},
     "o3-pro": {"input": 20.0, "output": 80.00},
     "o4-mini": {"input": 1.10, "output": 4.40},
+    "gpt-5-2025-08-07": {"input": 1.25, "output": 10.00, "cache_read": 0.125},
+    "gpt-5-mini-2025-08-07": {"input": 0.25, "output": 2.00, "cache_read": 0.025},
+    "gpt-5-nano-2025-08-07": {"input": 0.05, "output": 0.40, "cache_read": 0.005},
     # Gemini Pricing: https://ai.google.dev/pricing
     "gemini-1.5-flash": {"input": 0.075, "output": 0.30},
     "gemini-1.5-flash-002": {"input": 0.075, "output": 0.30},

khoj/utils/helpers.py

@@ -77,7 +77,7 @@ class AsyncIteratorWrapper:
 
 
 def is_none_or_empty(item):
-    return item == None or (hasattr(item, "__iter__") and len(item) == 0) or item == ""
+    return item is None or (hasattr(item, "__iter__") and len(item) == 0) or item == ""
 
 
 def to_snake_case_from_dash(item: str):
@@ -97,7 +97,7 @@ def get_from_dict(dictionary, *args):
     Returns: dictionary[args[0]][args[1]]... or None if any keys missing"""
     current = dictionary
     for arg in args:
-        if not hasattr(current, "__iter__") or not arg in current:
+        if not hasattr(current, "__iter__") or arg not in current:
             return None
         current = current[arg]
     return current
@@ -751,7 +751,7 @@ def is_valid_url(url: str) -> bool:
     try:
         result = urlparse(url.strip())
         return all([result.scheme, result.netloc])
-    except:
+    except Exception:
         return False
 
 
@@ -759,7 +759,7 @@ def is_internet_connected():
     try:
         response = requests.head("https://www.google.com")
         return response.status_code == 200
-    except:
+    except Exception:
         return False
 
 

khoj/utils/initialization.py

@@ -60,9 +60,7 @@ def initialization(interactive: bool = True):
                 ]
                 default_chat_models = known_available_models + other_available_models
             except Exception as e:
-                logger.warning(
-                    f"⚠️ Failed to fetch {provider} chat models. Fallback to default models. Error: {str(e)}"
-                )
+                logger.warning(f"⚠️ Failed to fetch {provider} chat models. Fallback to default models. Error: {str(e)}")
 
         # Set up OpenAI's online chat models
         openai_configured, openai_provider = _setup_chat_model_provider(

khoj/utils/models.py

@@ -8,12 +8,10 @@ from tqdm import trange
 
 class BaseEncoder(ABC):
     @abstractmethod
-    def __init__(self, model_name: str, device: torch.device = None, **kwargs):
-        ...
+    def __init__(self, model_name: str, device: torch.device = None, **kwargs): ...
 
     @abstractmethod
-    def encode(self, entries: List[str], device: torch.device = None, **kwargs) -> torch.Tensor:
-        ...
+    def encode(self, entries: List[str], device: torch.device = None, **kwargs) -> torch.Tensor: ...
 
 
 class OpenAI(BaseEncoder):

khoj/utils/rawconfig.py

@@ -1,8 +1,7 @@
 # System Packages
 import json
 import uuid
-from pathlib import Path
-from typing import Dict, List, Optional
+from typing import List, Optional
 
 from pydantic import BaseModel
 

khoj/utils/state.py

@@ -2,7 +2,7 @@ import os
 import threading
 from collections import defaultdict
 from pathlib import Path
-from typing import Any, Dict, List
+from typing import Dict, List
 
 from apscheduler.schedulers.background import BackgroundScheduler
 from openai import OpenAI

{khoj-2.0.0b13.dev5.dist-info → khoj-2.0.0b13.dev23.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: khoj
-Version: 2.0.0b13.dev5
+Version: 2.0.0b13.dev23
 Summary: Your Second Brain
 Project-URL: Homepage, https://khoj.dev
 Project-URL: Documentation, https://docs.khoj.dev
@@ -27,6 +27,7 @@ Requires-Dist: anyio~=4.8.0
 Requires-Dist: apscheduler~=3.10.0
 Requires-Dist: authlib==1.2.1
 Requires-Dist: beautifulsoup4~=4.12.3
+Requires-Dist: click<8.2.2
 Requires-Dist: cron-descriptor==1.4.3
 Requires-Dist: dateparser>=1.1.1
 Requires-Dist: defusedxml==0.7.1
@@ -78,7 +79,6 @@ Requires-Dist: tzdata==2023.3
 Requires-Dist: uvicorn==0.30.6
 Requires-Dist: websockets==13.0
 Provides-Extra: dev
-Requires-Dist: black>=23.1.0; extra == 'dev'
 Requires-Dist: boto3>=1.34.57; extra == 'dev'
 Requires-Dist: datasets; extra == 'dev'
 Requires-Dist: factory-boy>=3.2.1; extra == 'dev'
@@ -93,6 +93,7 @@ Requires-Dist: pytest-asyncio==0.21.1; extra == 'dev'
 Requires-Dist: pytest-django==4.5.2; extra == 'dev'
 Requires-Dist: pytest-xdist[psutil]; extra == 'dev'
 Requires-Dist: pytest>=7.1.2; extra == 'dev'
+Requires-Dist: ruff>=0.12.0; extra == 'dev'
 Requires-Dist: stripe==7.3.0; extra == 'dev'
 Requires-Dist: twilio==8.11; extra == 'dev'
 Provides-Extra: local