[Bug fix] Fix typos, static methods and other sanity improvements in the package (#1129)

embedchain/vectordb/base.py

@@ -49,7 +49,7 @@ class BaseVectorDB(JSONSerializable):
         raise NotImplementedError
 
     def query(self):
-        """Query contents from vector data base based on vector similarity"""
+        """Query contents from vector database based on vector similarity"""
         raise NotImplementedError
 
     def count(self) -> int:

embedchain/vectordb/chroma.py

@@ -75,7 +75,8 @@ class ChromaDB(BaseVectorDB):
         """Called during initialization"""
         return self.client
 
-    def _generate_where_clause(self, where: Dict[str, any]) -> str:
+    @staticmethod
+    def _generate_where_clause(where: Dict[str, any]) -> Dict[str, any]:
         # If only one filter is supplied, return it as is
         # (no need to wrap in $and based on chroma docs)
         if len(where.keys()) <= 1:
@@ -160,7 +161,8 @@ class ChromaDB(BaseVectorDB):
                 ids=ids[i : i + self.BATCH_SIZE],
             )
 
-    def _format_result(self, results: QueryResult) -> list[tuple[Document, float]]:
+    @staticmethod
+    def _format_result(results: QueryResult) -> list[tuple[Document, float]]:
         """
         Format Chroma results
 

embedchain/vectordb/elasticsearch.py

@@ -88,7 +88,7 @@ class ElasticsearchDB(BaseVectorDB):
         """
         Get existing doc ids present in vector database
 
-        :param ids: _list of doc ids to check for existance
+        :param ids: _list of doc ids to check for existence
         :type ids: List[str]
         :param where: to filter data
         :type where: Dict[str, any]
@@ -161,7 +161,7 @@ class ElasticsearchDB(BaseVectorDB):
         **kwargs: Optional[Dict[str, Any]],
     ) -> Union[List[Tuple[str, Dict]], List[str]]:
         """
-        query contents from vector data base based on vector similarity
+        query contents from vector database based on vector similarity
 
         :param input_query: list of query string
         :type input_query: List[str]

embedchain/vectordb/opensearch.py

@@ -163,7 +163,7 @@ class OpenSearchDB(BaseVectorDB):
         **kwargs: Optional[Dict[str, Any]],
     ) -> Union[List[Tuple[str, Dict]], List[str]]:
         """
-        query contents from vector data base based on vector similarity
+        query contents from vector database based on vector similarity
 
         :param input_query: list of query string
         :type input_query: List[str]

embedchain/vectordb/weaviate.py

@@ -305,7 +305,8 @@ class WeaviateDB(BaseVectorDB):
         """
         return f"{self.config.collection_name}_{self.embedder.vector_dimension}".capitalize()
 
-    def _query_with_cursor(self, query, cursor):
+    @staticmethod
+    def _query_with_cursor(query, cursor):
         if cursor is not None:
             query.with_after(cursor)
         results = query.do()

embedchain/vectordb/zilliz.py

@@ -6,8 +6,7 @@ from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.vectordb.base import BaseVectorDB
 
 try:
-    from pymilvus import (Collection, CollectionSchema, DataType, FieldSchema,
-                          MilvusClient, connections, utility)
+    from pymilvus import Collection, CollectionSchema, DataType, FieldSchema, MilvusClient, connections, utility
 except ImportError:
     raise ImportError(
         "Zilliz requires extra dependencies. Install with `pip install --upgrade embedchain[milvus]`"
@@ -97,10 +96,10 @@ class ZillizVectorDB(BaseVectorDB):
         if ids is None or len(ids) == 0 or self.collection.num_entities == 0:
             return {"ids": []}
 
-        if not (self.collection.is_empty):
-            filter = f"id in {ids}"
+        if not self.collection.is_empty:
+            filter_ = f"id in {ids}"
             results = self.client.query(
-                collection_name=self.config.collection_name, filter=filter, output_fields=["id"]
+                collection_name=self.config.collection_name, filter=filter_, output_fields=["id"]
             )
             results = [res["id"] for res in results]
 
@@ -134,7 +133,7 @@ class ZillizVectorDB(BaseVectorDB):
         **kwargs: Optional[Dict[str, Any]],
     ) -> Union[List[Tuple[str, Dict]], List[str]]:
         """
-        Query contents from vector data base based on vector similarity
+        Query contents from vector database based on vector similarity
 
         :param input_query: list of query string
         :type input_query: List[str]