hebbrix 2.0.1__tar.gz → 2.0.2__tar.gz

{hebbrix-2.0.1 → hebbrix-2.0.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: hebbrix
-Version: 2.0.1
+Version: 2.0.2
 Summary: Advanced Memory API for AI Agents with Reinforcement Learning - 3-line integration
 Home-page: https://github.com/hebbrix/hebbrix-python
 Author: Hebbrix Team

{hebbrix-2.0.1 → hebbrix-2.0.2}/hebbrix/__init__.py

@@ -41,7 +41,7 @@ Features:
 - ✅ Type hints throughout
 """
 
-__version__ = "2.0.0"
+__version__ = "2.0.2"
 __author__ = "Hebbrix Team"
 __license__ = "MIT"
 

{hebbrix-2.0.1 → hebbrix-2.0.2}/hebbrix/chat.py

@@ -286,6 +286,8 @@ class MemoryChat:
         response.raise_for_status()
 
     # Convenience methods for memory operations
+    # These use synchronous requests.post() (same as send/send_with_context)
+    # instead of the async MemoryClient to avoid coroutine issues.
     def add_memory(self, content: str, collection_id: str, importance: float = 0.5) -> Dict[str, Any]:
         """
         Add a memory manually.
@@ -298,11 +300,20 @@ class MemoryChat:
         Returns:
             Created memory dict
         """
-        return self.client.memories.create(
-            content=content,
-            collection_id=collection_id,
-            importance=importance,
-        )
+        url = f"{self.base_url}/v1/memories"
+        headers = {
+            "Authorization": f"Bearer {self.api_key}",
+            "Content-Type": "application/json",
+        }
+        payload = {
+            "content": content,
+            "collection_id": collection_id,
+            "importance": importance,
+        }
+
+        response = requests.post(url, json=payload, headers=headers)
+        response.raise_for_status()
+        return response.json()
 
     def search_memories(self, query: str, collection_id: Optional[str] = None, limit: int = 10) -> List[Dict[str, Any]]:
         """
@@ -316,11 +327,21 @@ class MemoryChat:
         Returns:
             List of memory dicts
         """
-        return self.client.memories.search(
-            query=query,
-            collection_id=collection_id,
-            limit=limit,
-        )["results"]
+        url = f"{self.base_url}/v1/search"
+        headers = {
+            "Authorization": f"Bearer {self.api_key}",
+            "Content-Type": "application/json",
+        }
+        payload: Dict[str, Any] = {
+            "query": query,
+            "limit": limit,
+        }
+        if collection_id:
+            payload["collection_id"] = collection_id
+
+        response = requests.post(url, json=payload, headers=headers)
+        response.raise_for_status()
+        return response.json().get("results", [])
 
 
 # Convenience function for even simpler usage

{hebbrix-2.0.1 → hebbrix-2.0.2}/hebbrix.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: hebbrix
-Version: 2.0.1
+Version: 2.0.2
 Summary: Advanced Memory API for AI Agents with Reinforcement Learning - 3-line integration
 Home-page: https://github.com/hebbrix/hebbrix-python
 Author: Hebbrix Team

{hebbrix-2.0.1 → hebbrix-2.0.2}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "hebbrix"
-version = "2.0.1"
+version = "2.0.2"
 description = "Advanced Memory API for AI Agents with Reinforcement Learning - 3-line integration"
 readme = "README.md"
 requires-python = ">=3.8"