Split --index-name flag into --pinecone-index-name and --index-namespace.

sage/index.py

@@ -71,10 +71,15 @@ def main():
         help="Maximum chunks per batch. We recommend 2000 for the OpenAI embedder. Marqo enforces a limit of 64.",
     )
     parser.add_argument(
-        "--index-name",
+        "--pinecone-index-name",
         default=None,
-        help="Vector store index name. For Marqo, we default it to the repository name. Required for Pinecone. "
-        "In Pinecone terminology, this is *not* the namespace (which we default to the repo ID).",
+        help="Pinecone index name. Required if using Pinecone as the vector store. If the index doesn't exist already, "
+        "we will create it.",
+    )
+    parser.add_argument(
+        "--index-namespace",
+        default=None,
+        help="Index namespace for this repo. When not specified, we default it to a derivative of the repo name."
     )
     parser.add_argument(
         "--include",
@@ -133,15 +138,10 @@ def main():
     if args.embedder_type == "marqo" and args.vector_store_type != "marqo":
         parser.error("When using the marqo embedder, the vector store type must also be marqo.")
     if args.vector_store_type == "marqo":
-        if not args.index_name:
-            args.index_name = args.repo_id.split("/")[1]
-        if "/" in args.index_name:
-            parser.error("The index name cannot contain slashes when using Marqo as the vector store.")
-    elif args.vector_store_type == "pinecone" and not args.index_name:
-        parser.error(
-            "When using Pinecone as the vector store, you must specify an index name. You can create one on "
-            "the Pinecone website. Make sure to set it the right --embedding-size."
-        )
+        if "/" in args.index_namespace:
+            parser.error("The index namespace cannot contain slashes when using Marqo as the vector store.")
+    elif args.vector_store_type == "pinecone" and not args.pinecone_index_name:
+        parser.error("When using Pinecone as the vector store, you must specify --pinecone-index-name")
 
     # Validate embedder parameters.
     if args.embedder_type == "marqo":

sage/vector_store.py

@@ -149,27 +149,32 @@ class MarqoVectorStore(VectorStore):
 def build_from_args(args: dict) -> VectorStore:
     """Builds a vector store from the given command-line arguments."""
     if args.vector_store_type == "pinecone":
-        if not args.index_name:
-            raise ValueError("Please specify --index-name for Pinecone.")
+        if not args.pinecone_index_name:
+            raise ValueError("Please specify --pinecone-index-name for Pinecone.")
         dimension = args.embedding_size if "embedding_size" in args else None
 
-        namespace = args.repo_id
-        if args.commit_hash:
-            namespace += "/" + args.commit_hash
+        index_namespace = args.index_namespace
+        if not index_namespace:
+            index_namespace = args.repo_id
+            if args.commit_hash:
+                namespace += "/" + args.commit_hash
 
         return PineconeVectorStore(
-            index_name=args.index_name, namespace=namespace, dimension=dimension, hybrid=args.hybrid_retrieval
+            index_name=args.pinecone_index_name,
+            namespace=index_namespace,
+            dimension=dimension,
+            hybrid=args.hybrid_retrieval,
         )
     elif args.vector_store_type == "marqo":
         marqo_url = args.marqo_url or "http://localhost:8882"
 
-        index_name = args.index_name
-        if not index_name:
+        index_namespace = args.index_namespace
+        if not index_namespace:
             # Marqo doesn't allow slashes in the index name.
-            index_name = args.repo_id.split("/")[1]
+            index_namespace = args.repo_id.split("/")[1]
             if args.commit_hash:
-                index_name += "_" + args.commit_hash
+                index_namespace += "_" + args.commit_hash
 
-        return MarqoVectorStore(url=marqo_url, index_name=index_name)
+        return MarqoVectorStore(url=marqo_url, index_name=index_namespace)
     else:
         raise ValueError(f"Unrecognized vector store type {args.vector_store_type}")