[Refactor] Improve logging package wide (#1315)

embedchain/alembic.ini

@@ -91,7 +91,6 @@ keys = console
 keys = generic
 
 [logger_root]
-level = WARN
 handlers = console
 qualname =
 

embedchain/app.py

@@ -32,6 +32,8 @@
 from embedchain.vectordb.base import BaseVectorDB
 from embedchain.vectordb.chroma import ChromaDB
 
+logger = logging.getLogger(__name__)
+
 
 @register_deserializable
 class App(EmbedChain):
@@ -50,10 +52,10 @@ def __init__(
         embedding_model: BaseEmbedder = None,
         llm: BaseLlm = None,
         config_data: dict = None,
-        log_level=logging.WARN,
         auto_deploy: bool = False,
         chunker: ChunkerConfig = None,
         cache_config: CacheConfig = None,
+        log_level: int = logging.WARN,
     ):
         """
         Initialize a new `App` instance.
@@ -68,8 +70,6 @@ def __init__(
         :type llm: BaseLlm, optional
         :param config_data: Config dictionary, defaults to None
         :type config_data: dict, optional
-        :param log_level: Log level to use, defaults to logging.WARN
-        :type log_level: int, optional
         :param auto_deploy: Whether to deploy the pipeline automatically, defaults to False
         :type auto_deploy: bool, optional
         :raises Exception: If an error occurs while creating the pipeline
@@ -83,13 +83,12 @@ def __init__(
         if name and config:
             raise Exception("Cannot provide both name and config. Please provide only one of them.")
 
-        # logging.basicConfig(level=log_level, format="%(asctime)s - %(name)s - %(levelname)s - %(message)s")
-        self.logger = logging.getLogger(__name__)
-
+        logger.debug("4.0")
         # Initialize the metadata db for the app
         setup_engine(database_uri=os.environ.get("EMBEDCHAIN_DB_URI"))
         init_db()
 
+        logger.debug("4.0")
         self.auto_deploy = auto_deploy
         # Store the dict config as an attribute to be able to send it
         self.config_data = config_data if (config_data and validate_config(config_data)) else None
@@ -119,13 +118,15 @@ def __init__(
         self.llm = llm or OpenAILlm()
         self._init_db()
 
+        logger.debug("4.1")
         # Session for the metadata db
         self.db_session = get_session()
 
         # If cache_config is provided, initializing the cache ...
         if self.cache_config is not None:
             self._init_cache()
 
+        logger.debug("4.2")
         # Send anonymous telemetry
         self._telemetry_props = {"class": self.__class__.__name__}
         self.telemetry = AnonymousTelemetry(enabled=self.config.collect_metrics)
@@ -238,7 +239,7 @@ def _upload_file_to_presigned_url(self, presigned_url, file_path):
                 response.raise_for_status()
                 return response.status_code == 200
         except Exception as e:
-            self.logger.exception(f"Error occurred during file upload: {str(e)}")
+            logger.exception(f"Error occurred during file upload: {str(e)}")
             print("❌ Error occurred during file upload!")
             return False
 
@@ -272,7 +273,7 @@ def _process_and_upload_data(self, data_hash, data_type, data_value):
                 metadata = {"file_path": data_value, "s3_key": s3_key}
                 data_value = presigned_url
             else:
-                self.logger.error(f"File upload failed for hash: {data_hash}")
+                logger.error(f"File upload failed for hash: {data_hash}")
                 return False
         else:
             if data_type == "qna_pair":
@@ -336,6 +337,7 @@ def from_config(
         :return: An instance of the App class.
         :rtype: App
         """
+        logger.debug("6")
         # Backward compatibility for yaml_path
         if yaml_path and not config_path:
             config_path = yaml_path
@@ -357,15 +359,13 @@ def from_config(
         elif config and isinstance(config, dict):
             config_data = config
         else:
-            logging.error(
+            logger.error(
                 "Please provide either a config file path (YAML or JSON) or a config dictionary. Falling back to defaults because no config is provided.",  # noqa: E501
             )
             config_data = {}
 
-        try:
-            validate_config(config_data)
-        except Exception as e:
-            raise Exception(f"Error occurred while validating the config. Error: {str(e)}")
+        # Validate the config
+        validate_config(config_data)
 
         app_config_data = config_data.get("app", {}).get("config", {})
         vector_db_config_data = config_data.get("vectordb", {})
@@ -477,12 +477,12 @@ def evaluate(
             EvalMetric.GROUNDEDNESS.value,
         ]
 
-        logging.info(f"Collecting data from {len(queries)} questions for evaluation...")
+        logger.info(f"Collecting data from {len(queries)} questions for evaluation...")
         dataset = []
         for q, a, c in zip(queries, answers, contexts):
             dataset.append(EvalData(question=q, answer=a, contexts=c))
 
-        logging.info(f"Evaluating {len(dataset)} data points...")
+        logger.info(f"Evaluating {len(dataset)} data points...")
         result = {}
         with concurrent.futures.ThreadPoolExecutor(max_workers=num_workers) as executor:
             future_to_metric = {executor.submit(self._eval, dataset, metric): metric for metric in metrics}

embedchain/bots/discord.py

@@ -17,6 +17,8 @@
     ) from None
 
 
+logger = logging.getLogger(__name__)
+
 intents = discord.Intents.default()
 intents.message_content = True
 client = discord.Client(intents=intents)
@@ -37,15 +39,15 @@ def add_data(self, message):
             self.add(data)
             response = f"Added data from: {data}"
         except Exception:
-            logging.exception(f"Failed to add data {data}.")
+            logger.exception(f"Failed to add data {data}.")
             response = "Some error occurred while adding data."
         return response
 
     def ask_bot(self, message):
         try:
             response = self.query(message)
         except Exception:
-            logging.exception(f"Failed to query {message}.")
+            logger.exception(f"Failed to query {message}.")
             response = "An error occurred. Please try again!"
         return response
 
@@ -60,7 +62,7 @@ def start(self):
 async def query_command(interaction: discord.Interaction, question: str):
     await interaction.response.defer()
     member = client.guilds[0].get_member(client.user.id)
-    logging.info(f"User: {member}, Query: {question}")
+    logger.info(f"User: {member}, Query: {question}")
     try:
         answer = discord_bot.ask_bot(question)
         if args.include_question:
@@ -70,20 +72,20 @@ async def query_command(interaction: discord.Interaction, question: str):
         await interaction.followup.send(response)
     except Exception as e:
         await interaction.followup.send("An error occurred. Please try again!")
-        logging.error("Error occurred during 'query' command:", e)
+        logger.error("Error occurred during 'query' command:", e)
 
 
 @tree.command(name="add", description="add new content to the embedchain database")
 async def add_command(interaction: discord.Interaction, url_or_text: str):
     await interaction.response.defer()
     member = client.guilds[0].get_member(client.user.id)
-    logging.info(f"User: {member}, Add: {url_or_text}")
+    logger.info(f"User: {member}, Add: {url_or_text}")
     try:
         response = discord_bot.add_data(url_or_text)
         await interaction.followup.send(response)
     except Exception as e:
         await interaction.followup.send("An error occurred. Please try again!")
-        logging.error("Error occurred during 'add' command:", e)
+        logger.error("Error occurred during 'add' command:", e)
 
 
 @tree.command(name="ping", description="Simple ping pong command")
@@ -96,16 +98,16 @@ async def on_app_command_error(interaction: discord.Interaction, error: discord.
     if isinstance(error, commands.CommandNotFound):
         await interaction.followup.send("Invalid command. Please refer to the documentation for correct syntax.")
     else:
-        logging.error("Error occurred during command execution:", error)
+        logger.error("Error occurred during command execution:", error)
 
 
 @client.event
 async def on_ready():
     # TODO: Sync in admin command, to not hit rate limits.
     # This might be overkill for most users, and it would require to set a guild or user id, where sync is allowed.
     await tree.sync()
-    logging.debug("Command tree synced")
-    logging.info(f"Logged in as {client.user.name}")
+    logger.debug("Command tree synced")
+    logger.info(f"Logged in as {client.user.name}")
 
 
 def start_command():

embedchain/bots/slack.py

@@ -19,6 +19,8 @@
     ) from None
 
 
+logger = logging.getLogger(__name__)
+
 SLACK_BOT_TOKEN = os.environ.get("SLACK_BOT_TOKEN")
 
 
@@ -42,10 +44,10 @@ def handle_message(self, event_data):
                     try:
                         response = self.chat_bot.chat(question)
                         self.send_slack_message(message["channel"], response)
-                        logging.info("Query answered successfully!")
+                        logger.info("Query answered successfully!")
                     except Exception as e:
                         self.send_slack_message(message["channel"], "An error occurred. Please try again!")
-                        logging.error("Error occurred during 'query' command:", e)
+                        logger.error("Error occurred during 'query' command:", e)
                 elif text.startswith("add"):
                     _, data_type, url_or_text = text.split(" ", 2)
                     if url_or_text.startswith("<") and url_or_text.endswith(">"):
@@ -55,10 +57,10 @@ def handle_message(self, event_data):
                         self.send_slack_message(message["channel"], f"Added {data_type} : {url_or_text}")
                     except ValueError as e:
                         self.send_slack_message(message["channel"], f"Error: {str(e)}")
-                        logging.error("Error occurred during 'add' command:", e)
+                        logger.error("Error occurred during 'add' command:", e)
                     except Exception as e:
                         self.send_slack_message(message["channel"], f"Failed to add {data_type} : {url_or_text}")
-                        logging.error("Error occurred during 'add' command:", e)
+                        logger.error("Error occurred during 'add' command:", e)
 
     def send_slack_message(self, channel, message):
         response = self.client.chat_postMessage(channel=channel, text=message)
@@ -68,7 +70,7 @@ def start(self, host="0.0.0.0", port=5000, debug=True):
         app = Flask(__name__)
 
         def signal_handler(sig, frame):
-            logging.info("\nGracefully shutting down the SlackBot...")
+            logger.info("\nGracefully shutting down the SlackBot...")
             sys.exit(0)
 
         signal.signal(signal.SIGINT, signal_handler)

embedchain/bots/whatsapp.py

@@ -8,6 +8,8 @@
 
 from .base import BaseBot
 
+logger = logging.getLogger(__name__)
+
 
 @register_deserializable
 class WhatsAppBot(BaseBot):
@@ -35,23 +37,23 @@ def add_data(self, message):
             self.add(data)
             response = f"Added data from: {data}"
         except Exception:
-            logging.exception(f"Failed to add data {data}.")
+            logger.exception(f"Failed to add data {data}.")
             response = "Some error occurred while adding data."
         return response
 
     def ask_bot(self, message):
         try:
             response = self.query(message)
         except Exception:
-            logging.exception(f"Failed to query {message}.")
+            logger.exception(f"Failed to query {message}.")
             response = "An error occurred. Please try again!"
         return response
 
     def start(self, host="0.0.0.0", port=5000, debug=True):
         app = self.flask.Flask(__name__)
 
         def signal_handler(sig, frame):
-            logging.info("\nGracefully shutting down the WhatsAppBot...")
+            logger.info("\nGracefully shutting down the WhatsAppBot...")
             sys.exit(0)
 
         signal.signal(signal.SIGINT, signal_handler)

embedchain/cache.py

@@ -14,6 +14,8 @@
 from gptcache.similarity_evaluation.exact_match import \
     ExactMatchEvaluation  # noqa: F401
 
+logger = logging.getLogger(__name__)
+
 
 def gptcache_pre_function(data: dict[str, Any], **params: dict[str, Any]):
     return data["input_query"]
@@ -24,12 +26,12 @@ def gptcache_data_manager(vector_dimension):
 
 
 def gptcache_data_convert(cache_data):
-    logging.info("[Cache] Cache hit, returning cache data...")
+    logger.info("[Cache] Cache hit, returning cache data...")
     return cache_data
 
 
 def gptcache_update_cache_callback(llm_data, update_cache_func, *args, **kwargs):
-    logging.info("[Cache] Cache missed, updating cache...")
+    logger.info("[Cache] Cache missed, updating cache...")
     update_cache_func(Answer(llm_data, CacheDataType.STR))
     return llm_data
 

embedchain/chunkers/base_chunker.py

@@ -6,6 +6,8 @@
 from embedchain.helpers.json_serializable import JSONSerializable
 from embedchain.models.data_type import DataType
 
+logger = logging.getLogger(__name__)
+
 
 class BaseChunker(JSONSerializable):
     def __init__(self, text_splitter):
@@ -27,7 +29,7 @@ def create_chunks(self, loader, src, app_id=None, config: Optional[ChunkerConfig
         chunk_ids = []
         id_map = {}
         min_chunk_size = config.min_chunk_size if config is not None else 1
-        logging.info(f"Skipping chunks smaller than {min_chunk_size} characters")
+        logger.info(f"Skipping chunks smaller than {min_chunk_size} characters")
         data_result = loader.load_data(src)
         data_records = data_result["data"]
         doc_id = data_result["doc_id"]

embedchain/client.py

@@ -7,6 +7,8 @@
 
 from embedchain.constants import CONFIG_DIR, CONFIG_FILE
 
+logger = logging.getLogger(__name__)
+
 
 class Client:
     def __init__(self, api_key=None, host="https://apiv2.embedchain.ai"):
@@ -24,7 +26,7 @@ def __init__(self, api_key=None, host="https://apiv2.embedchain.ai"):
         else:
             if "api_key" in self.config_data:
                 self.api_key = self.config_data["api_key"]
-                logging.info("API key loaded successfully!")
+                logger.info("API key loaded successfully!")
             else:
                 raise ValueError(
                     "You are not logged in. Please obtain an API key from https://app.embedchain.ai/settings/keys/"
@@ -64,34 +66,34 @@ def save(self):
         with open(CONFIG_FILE, "w") as config_file:
             json.dump(self.config_data, config_file, indent=4)
 
-        logging.info("API key saved successfully!")
+        logger.info("API key saved successfully!")
 
     def clear(self):
         if "api_key" in self.config_data:
             del self.config_data["api_key"]
             with open(CONFIG_FILE, "w") as config_file:
                 json.dump(self.config_data, config_file, indent=4)
             self.api_key = None
-            logging.info("API key deleted successfully!")
+            logger.info("API key deleted successfully!")
         else:
-            logging.warning("API key not found in the configuration file.")
+            logger.warning("API key not found in the configuration file.")
 
     def update(self, api_key):
         if self.check(api_key):
             self.api_key = api_key
             self.save()
-            logging.info("API key updated successfully!")
+            logger.info("API key updated successfully!")
         else:
-            logging.warning("Invalid API key provided. API key not updated.")
+            logger.warning("Invalid API key provided. API key not updated.")
 
     def check(self, api_key):
         validation_url = f"{self.host}/api/v1/accounts/api_keys/validate/"
         response = requests.post(validation_url, headers={"Authorization": f"Token {api_key}"})
         if response.status_code == 200:
             return True
         else:
-            logging.warning(f"Response from API: {response.text}")
-            logging.warning("Invalid API key. Unable to validate.")
+            logger.warning(f"Response from API: {response.text}")
+            logger.warning("Invalid API key. Unable to validate.")
             return False
 
     def get(self):