pinecone update

service/vector_store.py

@@ -24,13 +24,14 @@ class VectorStore(Pinecone):
     NAMESPACE = "filecoin"
 
     def __init__(self) -> None:
-        pinecone.init(
-            api_key=os.getenv("PINECONE_API_KEY"),  
-            environment=os.getenv("PINECONE_ENV"),  
-        )
+        # pinecone.init(
+        #     api_key=os.getenv("PINECONE_API_KEY"),  
+        #     environment=os.getenv("PINECONE_ENV"),  
+        # )
+        pc = pinecone.Pinecone(api_key=os.getenv("PINECONE_API_KEY"))
 
         self.dims = 1536
-        index = pinecone.Index(self.INDEX_NAME)
+        index = pc.Index(self.INDEX_NAME)
         super().__init__(index, OpenAIEmbeddings(),"text")  
 
     def add_docs(self,docs):
@@ -56,8 +57,8 @@ class VectorStore(Pinecone):
         Returns:
             List of Documents most similar to the query and score for each
         """
-        docs_and_scores = self.similarity_search_with_score(
-            query, k=k, filter=filter, namespace=namespace, **kwargs
+        docs_and_scores = self.similarity_search_by_vector_with_score(
+            self._embed_query(query), k=k, filter=filter, namespace=namespace
         )
         return [doc for doc, _ in docs_and_scores]
 
@@ -109,7 +110,7 @@ class VectorStore(Pinecone):
             namespace = self._namespace
         docs = []
         results = self._index.query(
-            [embedding],
+            vector=[embedding],
             top_k=k,
             include_metadata=True,
             namespace=namespace,
@@ -159,7 +160,7 @@ class VectorStore(Pinecone):
         if namespace is None:
             namespace = self._namespace
         results = self._index.query(
-            [embedding],
+            vector=[embedding],
             top_k=fetch_k,
             include_values=True,
             include_metadata=True,