Allow disabling Khoj telemetry via KHOJ_TELEMETRY_DISABLE env var

docker-compose.yml

@@ -61,6 +61,10 @@ services:
       # - KHOJ_NO_HTTPS=True
       # - KHOJ_DOMAIN=192.168.0.104
       # - KHOJ_DOMAIN=khoj.example.com
+      # Uncomment the line below to disable telemetry.
+      # Telemetry helps us prioritize feature development and understand how people are using Khoj
+      # Read more at https://docs.khoj.dev/miscellaneous/telemetry
+      # - KHOJ_TELEMETRY_DISABLE=True
     command: --host="0.0.0.0" --port=42110 -vv --anonymous-mode --non-interactive
 
 

documentation/docs/miscellaneous/telemetry.md

@@ -14,13 +14,6 @@ We don't send any personal information or any information from/about your conten
 
 ## Disable Telemetry
 
-If you're self-hosting Khoj, you can opt out of telemetry at any time. To do so,
+If you're self-hosting Khoj, you can opt out of telemetry at any time by setting the `KHOJ_TELEMETRY_DISABLE` environment variable to `True` via shell or `docker-compose.yml`
-1. Open `~/.khoj/khoj.yml`
-2. Add the following configuration:
-```
-app:
-  should-log-telemetry: false
-```
-3. Save the file and restart Khoj
 
 If you have any questions or concerns, please reach out to us on [Discord](https://discord.gg/BDgyabRM6e).

src/khoj/configure.py

@@ -249,7 +249,11 @@ def configure_server(
         state.search_models = configure_search(state.search_models, state.config.search_type)
         setup_default_agent(user)
 
-        message = "📡 Telemetry disabled" if telemetry_disabled(state.config.app) else "📡 Telemetry enabled"
+        message = (
+            "📡 Telemetry disabled"
+            if telemetry_disabled(state.config.app, state.telemetry_disabled)
+            else "📡 Telemetry enabled"
+        )
         logger.info(message)
 
         if not init:
@@ -361,7 +365,7 @@ def configure_search_types():
 
 @schedule.repeat(schedule.every(2).minutes)
 def upload_telemetry():
-    if telemetry_disabled(state.config.app) or not state.telemetry:
+    if telemetry_disabled(state.config.app, state.telemetry_disabled) or not state.telemetry:
         return
 
     try:

src/khoj/routers/helpers.py

@@ -204,7 +204,12 @@ def update_telemetry_state(
 
     state.telemetry += [
         log_telemetry(
-            telemetry_type=telemetry_type, api=api, client=client, app_config=state.config.app, properties=user_state
+            telemetry_type=telemetry_type,
+            api=api,
+            client=client,
+            app_config=state.config.app,
+            disable_telemetry_env=state.telemetry_disabled,
+            properties=user_state,
         )
     ]
 

src/khoj/utils/cli.py

@@ -16,7 +16,7 @@ from khoj.migrations.migrate_processor_config_openai import (
 )
 from khoj.migrations.migrate_server_pg import migrate_server_pg
 from khoj.migrations.migrate_version import migrate_config_to_version
-from khoj.utils.helpers import in_debug_mode, resolve_absolute_path
+from khoj.utils.helpers import in_debug_mode, is_env_var_true, resolve_absolute_path
 from khoj.utils.yaml import parse_config_from_file
 
 
@@ -79,7 +79,7 @@ def cli(args=None):
     else:
         args = run_migrations(args)
         args.config = parse_config_from_file(args.config_file)
-        if in_debug_mode():
+        if is_env_var_true("KHOJ_TELEMETRY_DISABLE") or in_debug_mode():
             args.config.app.should_log_telemetry = False
 
     return args

src/khoj/utils/helpers.py

@@ -254,8 +254,10 @@ def get_server_id():
     return server_id
 
 
-def telemetry_disabled(app_config: AppConfig):
+def telemetry_disabled(app_config: AppConfig, telemetry_disable_env) -> bool:
-    return not app_config or not app_config.should_log_telemetry
+    return (
+        not app_config.should_log_telemetry if app_config and app_config.should_log_telemetry else telemetry_disable_env
+    )
 
 
 def log_telemetry(
@@ -263,11 +265,12 @@ def log_telemetry(
     api: str = None,
     client: Optional[str] = None,
     app_config: Optional[AppConfig] = None,
+    disable_telemetry_env: bool = False,
     properties: dict = None,
 ):
     """Log basic app usage telemetry like client, os, api called"""
     # Do not log usage telemetry, if telemetry is disabled via app config
-    if telemetry_disabled(app_config):
+    if telemetry_disabled(app_config, disable_telemetry_env):
         return []
 
     if properties.get("server_id") is None:

src/khoj/utils/state.py

@@ -12,7 +12,7 @@ from khoj.database.models import ProcessLock
 from khoj.processor.embeddings import CrossEncoderModel, EmbeddingsModel
 from khoj.utils import config as utils_config
 from khoj.utils.config import OfflineChatProcessorModel, SearchModels
-from khoj.utils.helpers import LRU, get_device
+from khoj.utils.helpers import LRU, get_device, is_env_var_true
 from khoj.utils.rawconfig import FullConfig
 
 # Application Global State
@@ -34,6 +34,7 @@ SearchType = utils_config.SearchType
 scheduler: BackgroundScheduler = None
 schedule_leader_process_lock: ProcessLock = None
 telemetry: List[Dict[str, str]] = []
+telemetry_disabled: bool = is_env_var_true("KHOJ_TELEMETRY_DISABLE")
 khoj_version: str = None
 device = get_device()
 chat_on_gpu: bool = True