feat: anonymous telemetry (#423)

embedchain/config/apps/AppConfig.py

@@ -1,4 +1,5 @@
 import os
+from typing import Optional
 
 try:
     from chromadb.utils import embedding_functions
@@ -16,7 +17,15 @@ class AppConfig(BaseAppConfig):
     Config to initialize an embedchain custom `App` instance, with extra config options.
     """
 
-    def __init__(self, log_level=None, host=None, port=None, id=None, collection_name=None):
+    def __init__(
+        self,
+        log_level=None,
+        host=None,
+        port=None,
+        id=None,
+        collection_name=None,
+        collect_metrics: Optional[bool] = None,
+    ):
         """
         :param log_level: Optional. (String) Debug level
         ['DEBUG', 'INFO', 'WARNING', 'ERROR', 'CRITICAL'].
@@ -24,6 +33,7 @@ class AppConfig(BaseAppConfig):
         :param port: Optional. Port for the database server.
         :param id: Optional. ID of the app. Document metadata will have this id.
         :param collection_name: Optional. Collection name for the database.
+        :param collect_metrics: Defaults to True. Send anonymous telemetry to improve embedchain.
         """
         super().__init__(
             log_level=log_level,
@@ -32,6 +42,7 @@ class AppConfig(BaseAppConfig):
             port=port,
             id=id,
             collection_name=collection_name,
+            collect_metrics=collect_metrics,
         )
 
     @staticmethod

embedchain/config/apps/BaseAppConfig.py

@@ -19,6 +19,7 @@ class BaseAppConfig(BaseConfig):
         port=None,
         id=None,
         collection_name=None,
+        collect_metrics: bool = True,
         db_type: VectorDatabases = None,
         vector_dim: VectorDimensions = None,
         es_config: ElasticsearchDBConfig = None,
@@ -32,6 +33,7 @@ class BaseAppConfig(BaseConfig):
         :param port: Optional. Port for the database server.
         :param id: Optional. ID of the app. Document metadata will have this id.
         :param collection_name: Optional. Collection name for the database.
+        :param collect_metrics: Defaults to True. Send anonymous telemetry to improve embedchain.
         :param db_type: Optional. type of Vector database to use
         :param vector_dim: Vector dimension generated by embedding fn
         :param es_config: Optional. elasticsearch database config to be used for connection
@@ -49,6 +51,7 @@ class BaseAppConfig(BaseConfig):
             es_config=es_config,
         )
         self.id = id
+        self.collect_metrics = True if (collect_metrics is True or collect_metrics is None) else False
         return
 
     @staticmethod

embedchain/config/apps/CustomAppConfig.py

@@ -1,4 +1,4 @@
-from typing import Any
+from typing import Any, Optional
 
 from chromadb.api.types import Documents, Embeddings
 from dotenv import load_dotenv
@@ -30,6 +30,7 @@ class CustomAppConfig(BaseAppConfig):
         provider: Providers = None,
         open_source_app_config=None,
         deployment_name=None,
+        collect_metrics: Optional[bool] = None,
         db_type: VectorDatabases = None,
         es_config: ElasticsearchDBConfig = None,
     ):
@@ -45,6 +46,7 @@ class CustomAppConfig(BaseAppConfig):
         :param collection_name: Optional. Collection name for the database.
         :param provider: Optional. (Providers): LLM Provider to use.
         :param open_source_app_config: Optional. Config instance needed for open source apps.
+        :param collect_metrics: Defaults to True. Send anonymous telemetry to improve embedchain.
         :param db_type: Optional. type of Vector database to use.
         :param es_config: Optional. elasticsearch database config to be used for connection
         """
@@ -65,6 +67,7 @@ class CustomAppConfig(BaseAppConfig):
             port=port,
             id=id,
             collection_name=collection_name,
+            collect_metrics=collect_metrics,
             db_type=db_type,
             vector_dim=CustomAppConfig.get_vector_dimension(embedding_function=embedding_fn),
             es_config=es_config,

embedchain/config/apps/OpenSourceAppConfig.py

@@ -1,3 +1,5 @@
+from typing import Optional
+
 from chromadb.utils import embedding_functions
 
 from .BaseAppConfig import BaseAppConfig
@@ -8,7 +10,16 @@ class OpenSourceAppConfig(BaseAppConfig):
     Config to initialize an embedchain custom `OpenSourceApp` instance, with extra config options.
     """
 
-    def __init__(self, log_level=None, host=None, port=None, id=None, collection_name=None, model=None):
+    def __init__(
+        self,
+        log_level=None,
+        host=None,
+        port=None,
+        id=None,
+        collection_name=None,
+        collect_metrics: Optional[bool] = None,
+        model=None,
+    ):
         """
         :param log_level: Optional. (String) Debug level
         ['DEBUG', 'INFO', 'WARNING', 'ERROR', 'CRITICAL'].
@@ -16,6 +27,7 @@ class OpenSourceAppConfig(BaseAppConfig):
         :param collection_name: Optional. Collection name for the database.
         :param host: Optional. Hostname for the database server.
         :param port: Optional. Port for the database server.
+        :param collect_metrics: Defaults to True. Send anonymous telemetry to improve embedchain.
         :param model: Optional. GPT4ALL uses the model to instantiate the class.
         So unlike `App`, it has to be provided before querying.
         """
@@ -28,6 +40,7 @@ class OpenSourceAppConfig(BaseAppConfig):
             port=port,
             id=id,
             collection_name=collection_name,
+            collect_metrics=collect_metrics,
         )
 
     @staticmethod