Added filter argument to pinecone queries, fixes #600 (#601)

Added filter argument to similarity_search() and
similarity_search_with_score()

Co-authored-by: Sam Cartford (MBP) <[email protected]>

Author: babbldev

langchain/vectorstores/pinecone.py

@@ -80,13 +80,15 @@ def similarity_search_with_score(
         self,
         query: str,
         k: int = 5,
+        filter: Optional[dict] = None,
         namespace: Optional[str] = None,
     ) -> List[Tuple[Document, float]]:
         """Return pinecone documents most similar to query, along with scores.
 
         Args:
             query: Text to look up documents similar to.
             k: Number of Documents to return. Defaults to 4.
+            filter: Dictionary of argument(s) to filter on metadata
             namespace: Namespace to search in. Default will search in '' namespace.
 
         Returns:
@@ -95,7 +97,11 @@ def similarity_search_with_score(
         query_obj = self._embedding_function(query)
         docs = []
         results = self._index.query(
-            [query_obj], top_k=k, include_metadata=True, namespace=namespace
+            [query_obj],
+            top_k=k,
+            include_metadata=True,
+            namespace=namespace,
+            filter=filter,
         )
         for res in results["matches"]:
             metadata = res["metadata"]
@@ -107,13 +113,15 @@ def similarity_search(
         self,
         query: str,
         k: int = 5,
+        filter: Optional[dict] = None,
         namespace: Optional[str] = None,
     ) -> List[Document]:
         """Return pinecone documents most similar to query.
 
         Args:
             query: Text to look up documents similar to.
             k: Number of Documents to return. Defaults to 4.
+            filter: Dictionary of argument(s) to filter on metadata
             namespace: Namespace to search in. Default will search in '' namespace.
 
         Returns:
@@ -122,7 +130,11 @@ def similarity_search(
         query_obj = self._embedding_function(query)
         docs = []
         results = self._index.query(
-            [query_obj], top_k=k, include_metadata=True, namespace=namespace
+            [query_obj],
+            top_k=k,
+            include_metadata=True,
+            namespace=namespace,
+            filter=filter,
         )
         for res in results["matches"]:
             metadata = res["metadata"]