diff --git a/configs/memgpt_hosted.json b/configs/memgpt_hosted.json
index 2e8bcf7b..e7958cfa 100644
--- a/configs/memgpt_hosted.json
+++ b/configs/memgpt_hosted.json
@@ -2,10 +2,10 @@
     "context_window": 32768,
     "model": "ehartford/dolphin-2.5-mixtral-8x7b",
     "model_endpoint_type": "vllm",
-    "model_endpoint": "http://api.memgpt.ai",
+    "model_endpoint": "https://api.memgpt.ai",
     "model_wrapper": "chatml",
     "embedding_endpoint_type": "hugging-face",
-    "embedding_endpoint": "http://embeddings.memgpt.ai",
+    "embedding_endpoint": "https://embeddings.memgpt.ai",
     "embedding_model": "BAAI/bge-large-en-v1.5",
     "embedding_dim": 1536,
     "embedding_chunk_size": 300
diff --git a/memgpt/configs/memgpt_hosted.json b/memgpt/configs/memgpt_hosted.json
index 2e8bcf7b..e7958cfa 100644
--- a/memgpt/configs/memgpt_hosted.json
+++ b/memgpt/configs/memgpt_hosted.json
@@ -2,10 +2,10 @@
     "context_window": 32768,
     "model": "ehartford/dolphin-2.5-mixtral-8x7b",
     "model_endpoint_type": "vllm",
-    "model_endpoint": "http://api.memgpt.ai",
+    "model_endpoint": "https://api.memgpt.ai",
     "model_wrapper": "chatml",
     "embedding_endpoint_type": "hugging-face",
-    "embedding_endpoint": "http://embeddings.memgpt.ai",
+    "embedding_endpoint": "https://embeddings.memgpt.ai",
     "embedding_model": "BAAI/bge-large-en-v1.5",
     "embedding_dim": 1536,
     "embedding_chunk_size": 300
diff --git a/memgpt/memory.py b/memgpt/memory.py
index 2aa4842c..5c0f7d79 100644
--- a/memgpt/memory.py
+++ b/memgpt/memory.py
@@ -338,6 +338,16 @@ class EmbeddingArchivalMemory(ArchivalMemory):
             # breakup string into passages
             for node in parser.get_nodes_from_documents([Document(text=memory_string)]):
                 embedding = self.embed_model.get_text_embedding(node.text)
+                # fixing weird bug where type returned isn't a list, but instead is an object
+                # eg: embedding={'object': 'list', 'data': [{'object': 'embedding', 'embedding': [-0.0071973633, -0.07893023,
+                if isinstance(embedding, dict):
+                    try:
+                        embedding = embedding["data"][0]["embedding"]
+                    except (KeyError, IndexError):
+                        # TODO as a fallback, see if we can find any lists in the payload
+                        raise TypeError(
+                            f"Got back an unexpected payload from text embedding function, type={type(embedding)}, value={embedding}"
+                        )
                 passages.append(Passage(text=node.text, embedding=embedding, doc_id=f"agent_{self.agent_config.name}_memory"))
 
             # insert passages