refactor: classes and configs (#528)

embedchain/config/apps/BaseAppConfig.py

@@ -1,9 +1,9 @@
 import logging
+from typing import Optional
 
 from embedchain.config.BaseConfig import BaseConfig
-from embedchain.config.vectordbs import ElasticsearchDBConfig
 from embedchain.helper_classes.json_serializable import JSONSerializable
-from embedchain.models import VectorDatabases, VectorDimensions
+from embedchain.vectordb.base_vector_db import BaseVectorDB
 
 
 class BaseAppConfig(BaseConfig, JSONSerializable):
@@ -14,81 +14,38 @@ class BaseAppConfig(BaseConfig, JSONSerializable):
     def __init__(
         self,
         log_level=None,
-        embedding_fn=None,
-        db=None,
-        host=None,
-        port=None,
+        db: Optional[BaseVectorDB] = None,
         id=None,
-        collection_name=None,
         collect_metrics: bool = True,
-        db_type: VectorDatabases = None,
-        vector_dim: VectorDimensions = None,
-        es_config: ElasticsearchDBConfig = None,
-        chroma_settings: dict = {},
+        collection_name: Optional[str] = None,
     ):
         """
         :param log_level: Optional. (String) Debug level
         ['DEBUG', 'INFO', 'WARNING', 'ERROR', 'CRITICAL'].
-        :param embedding_fn: Embedding function to use.
-        :param db: Optional. (Vector) database instance to use for embeddings.
-        :param host: Optional. Hostname for the database server.
-        :param port: Optional. Port for the database server.
+        :param db: Optional. (Vector) database instance to use for embeddings. Deprecated in favor of app(..., db).
         :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 db_type: Optional. Initializes a default vector database of the given type.
+        Using the `db` argument is preferred.
         :param es_config: Optional. elasticsearch database config to be used for connection
-        :param chroma_settings: Optional. Chroma settings for connection.
+        :param collection_name: Optional. Default collection name.
+        It's recommended to use app.set_collection_name() instead.
         """
         self._setup_logging(log_level)
-        self.collection_name = collection_name if collection_name else "embedchain_store"
-        self.db = BaseAppConfig.get_db(
-            db=db,
-            embedding_fn=embedding_fn,
-            host=host,
-            port=port,
-            db_type=db_type,
-            vector_dim=vector_dim,
-            collection_name=self.collection_name,
-            es_config=es_config,
-            chroma_settings=chroma_settings,
-        )
         self.id = id
         self.collect_metrics = True if (collect_metrics is True or collect_metrics is None) else False
-        return
+        self.collection_name = collection_name
 
-    @staticmethod
-    def get_db(db, embedding_fn, host, port, db_type, vector_dim, collection_name, es_config, chroma_settings):
-        """
-        Get db based on db_type, db with default database (`ChromaDb`)
-        :param Optional. (Vector) database to use for embeddings.
-        :param embedding_fn: Embedding function to use in database.
-        :param host: Optional. Hostname for the database server.
-        :param port: Optional. Port for the database server.
-        :param db_type: Optional. db type to use. Supported values (`es`, `chroma`)
-        :param vector_dim: Vector dimension generated by embedding fn
-        :param collection_name: Optional. Collection name for the database.
-        :param es_config: Optional. elasticsearch database config to be used for connection
-        :raises ValueError: BaseAppConfig knows no default embedding function.
-        :returns: database instance
-        """
         if db:
-            return db
-
-        if embedding_fn is None:
-            raise ValueError("ChromaDb cannot be instantiated without an embedding function")
-
-        if db_type == VectorDatabases.ELASTICSEARCH:
-            from embedchain.vectordb.elasticsearch_db import ElasticsearchDB
-
-            return ElasticsearchDB(
-                embedding_fn=embedding_fn, vector_dim=vector_dim, collection_name=collection_name, es_config=es_config
+            self._db = db
+            logging.warning(
+                "DEPRECATION WARNING: Please supply the database as the second parameter during app init. "
+                "Such as `app(config=config, db=db)`."
             )
 
-        from embedchain.vectordb.chroma_db import ChromaDB
-
-        return ChromaDB(embedding_fn=embedding_fn, host=host, port=port, chroma_settings=chroma_settings)
+        if collection_name:
+            logging.warning("DEPRECATION WARNING: Please supply the collection name to the database config.")
+        return
 
     def _setup_logging(self, debug_level):
         level = logging.WARNING  # Default level