refactor: app design concept (#305)

embedchain/config/InitConfig.py

@@ -1,74 +0,0 @@
-import logging
-import os
-
-from chromadb.utils import embedding_functions
-
-from embedchain.config.BaseConfig import BaseConfig
-
-
-class InitConfig(BaseConfig):
-    """
-    Config to initialize an embedchain `App` instance.
-    """
-
-    def __init__(self, log_level=None, ef=None, db=None, host=None, port=None, id=None):
-        """
-        :param log_level: Optional. (String) Debug level
-        ['DEBUG', 'INFO', 'WARNING', 'ERROR', 'CRITICAL'].
-        :param ef: Optional. Embedding function to use.
-        :param db: Optional. (Vector) database to use for embeddings.
-        :param id: Optional. ID of the app. Document metadata will have this id.
-        :param host: Optional. Hostname for the database server.
-        :param port: Optional. Port for the database server.
-        """
-        self._setup_logging(log_level)
-        self.ef = ef
-        self.db = db
-        self.host = host
-        self.port = port
-        self.id = id
-        return
-
-    def _set_embedding_function(self, ef):
-        self.ef = ef
-        return
-
-    def _set_embedding_function_to_default(self):
-        """
-        Sets embedding function to default (`text-embedding-ada-002`).
-
-        :raises ValueError: If the template is not valid as template should contain
-        $context and $query
-        """
-        if os.getenv("OPENAI_API_KEY") is None and os.getenv("OPENAI_ORGANIZATION") is None:
-            raise ValueError("OPENAI_API_KEY or OPENAI_ORGANIZATION environment variables not provided")  # noqa:E501
-        self.ef = embedding_functions.OpenAIEmbeddingFunction(
-            api_key=os.getenv("OPENAI_API_KEY"),
-            organization_id=os.getenv("OPENAI_ORGANIZATION"),
-            model_name="text-embedding-ada-002",
-        )
-        return
-
-    def _set_db(self, db):
-        if db:
-            self.db = db
-        return
-
-    def _set_db_to_default(self):
-        """
-        Sets database to default (`ChromaDb`).
-        """
-        from embedchain.vectordb.chroma_db import ChromaDB
-
-        self.db = ChromaDB(ef=self.ef, host=self.host, port=self.port)
-
-    def _setup_logging(self, debug_level):
-        level = logging.WARNING  # Default level
-        if debug_level is not None:
-            level = getattr(logging, debug_level.upper(), None)
-            if not isinstance(level, int):
-                raise ValueError(f"Invalid log level: {debug_level}")
-
-        logging.basicConfig(format="%(asctime)s [%(name)s] [%(levelname)s] %(message)s", level=level)
-        self.logger = logging.getLogger(__name__)
-        return

embedchain/config/__init__.py

@@ -1,5 +1,7 @@
 from .AddConfig import AddConfig, ChunkerConfig  # noqa: F401
+from .apps.AppConfig import AppConfig  # noqa: F401
+from .apps.CustomAppConfig import CustomAppConfig  # noqa: F401
+from .apps.OpenSourceAppConfig import OpenSourceAppConfig  # noqa: F401
 from .BaseConfig import BaseConfig  # noqa: F401
 from .ChatConfig import ChatConfig  # noqa: F401
-from .InitConfig import InitConfig  # noqa: F401
 from .QueryConfig import QueryConfig  # noqa: F401

embedchain/config/apps/AppConfig.py

@@ -0,0 +1,38 @@
+import os
+
+from chromadb.utils import embedding_functions
+
+from .BaseAppConfig import BaseAppConfig
+
+
+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):
+        """
+        :param log_level: Optional. (String) Debug level
+        ['DEBUG', 'INFO', 'WARNING', 'ERROR', 'CRITICAL'].
+        :param id: Optional. ID of the app. Document metadata will have this id.
+        :param host: Optional. Hostname for the database server.
+        :param port: Optional. Port for the database server.
+        """
+        super().__init__(log_level=log_level, ef=AppConfig.default_embedding_function(), host=host, port=port, id=id)
+
+    @staticmethod
+    def default_embedding_function():
+        """
+        Sets embedding function to default (`text-embedding-ada-002`).
+
+        :raises ValueError: If the template is not valid as template should contain
+        $context and $query
+        :returns: The default embedding function for the app class.
+        """
+        if os.getenv("OPENAI_API_KEY") is None and os.getenv("OPENAI_ORGANIZATION") is None:
+            raise ValueError("OPENAI_API_KEY or OPENAI_ORGANIZATION environment variables not provided")  # noqa:E501
+        return embedding_functions.OpenAIEmbeddingFunction(
+            api_key=os.getenv("OPENAI_API_KEY"),
+            organization_id=os.getenv("OPENAI_ORGANIZATION"),
+            model_name="text-embedding-ada-002",
+        )

embedchain/config/apps/BaseAppConfig.py

@@ -0,0 +1,53 @@
+import logging
+
+from embedchain.config.BaseConfig import BaseConfig
+
+
+class BaseAppConfig(BaseConfig):
+    """
+    Parent config to initialize an instance of `App`, `OpenSourceApp` or `CustomApp`.
+    """
+
+    def __init__(self, log_level=None, ef=None, db=None, host=None, port=None, id=None):
+        """
+        :param log_level: Optional. (String) Debug level
+        ['DEBUG', 'INFO', 'WARNING', 'ERROR', 'CRITICAL'].
+        :param ef: Embedding function to use.
+        :param db: Optional. (Vector) database instance to use for embeddings.
+        :param id: Optional. ID of the app. Document metadata will have this id.
+        :param host: Optional. Hostname for the database server.
+        :param port: Optional. Port for the database server.
+        """
+        self._setup_logging(log_level)
+
+        self.db = db if db else BaseAppConfig.default_db(ef=ef, host=host, port=port)
+        self.id = id
+        return
+
+    @staticmethod
+    def default_db(ef, host, port):
+        """
+        Sets database to default (`ChromaDb`).
+
+        :param ef: Embedding function to use in database.
+        :param host: Optional. Hostname for the database server.
+        :param port: Optional. Port for the database server.
+        :returns: Default database
+        :raises ValueError: BaseAppConfig knows no default embedding function.
+        """
+        if ef is None:
+            raise ValueError("ChromaDb cannot be instantiated without an embedding function")
+        from embedchain.vectordb.chroma_db import ChromaDB
+
+        return ChromaDB(ef=ef, host=host, port=port)
+
+    def _setup_logging(self, debug_level):
+        level = logging.WARNING  # Default level
+        if debug_level is not None:
+            level = getattr(logging, debug_level.upper(), None)
+            if not isinstance(level, int):
+                raise ValueError(f"Invalid log level: {debug_level}")
+
+        logging.basicConfig(format="%(asctime)s [%(name)s] [%(levelname)s] %(message)s", level=level)
+        self.logger = logging.getLogger(__name__)
+        return

embedchain/config/apps/CustomAppConfig.py

@@ -0,0 +1,19 @@
+from .BaseAppConfig import BaseAppConfig
+
+
+class CustomAppConfig(BaseAppConfig):
+    """
+    Config to initialize an embedchain custom `App` instance, with extra config options.
+    """
+
+    def __init__(self, log_level=None, ef=None, db=None, host=None, port=None, id=None):
+        """
+        :param log_level: Optional. (String) Debug level
+        ['DEBUG', 'INFO', 'WARNING', 'ERROR', 'CRITICAL'].
+        :param ef: Optional. Embedding function to use.
+        :param db: Optional. (Vector) database to use for embeddings.
+        :param id: Optional. ID of the app. Document metadata will have this id.
+        :param host: Optional. Hostname for the database server.
+        :param port: Optional. Port for the database server.
+        """
+        super().__init__(log_level=log_level, db=db, host=host, port=port, id=id)

embedchain/config/apps/OpenSourceAppConfig.py

@@ -0,0 +1,30 @@
+from chromadb.utils import embedding_functions
+
+from .BaseAppConfig import BaseAppConfig
+
+
+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):
+        """
+        :param log_level: Optional. (String) Debug level
+        ['DEBUG', 'INFO', 'WARNING', 'ERROR', 'CRITICAL'].
+        :param id: Optional. ID of the app. Document metadata will have this id.
+        :param host: Optional. Hostname for the database server.
+        :param port: Optional. Port for the database server.
+        """
+        super().__init__(
+            log_level=log_level, ef=OpenSourceAppConfig.default_embedding_function(), host=host, port=port, id=id
+        )
+
+    @staticmethod
+    def default_embedding_function():
+        """
+        Sets embedding function to default (`all-MiniLM-L6-v2`).
+
+        :returns: The default embedding function
+        """
+        return embedding_functions.SentenceTransformerEmbeddingFunction(model_name="all-MiniLM-L6-v2")