memorisdk 2.0.0__tar.gz → 2.0.1__tar.gz

{memorisdk-2.0.0 → memorisdk-2.0.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: memorisdk
-Version: 2.0.0
+Version: 2.0.1
 Summary: The Open-Source Memory Layer for AI Agents & Multi-Agent Systems
 Author-email: GibsonAI Team <noc@gibsonai.com>
 License: Apache-2.0
@@ -458,19 +458,25 @@ memori/
 - **[Memory Retrieval](./memory_retrival_example.py)** - Function calling with memory tools
 - **[Advanced Config](./examples/advanced_config.py)** - Production configuration
 - **[Interactive Demo](./memori_example.py)** - Live conscious ingestion showcase
+- **[Simple Multi-User](./examples/multiple-users/simple_multiuser.py)** - Basic demonstration of user memory isolation with namespaces
+- **[FastAPI Multi-User App](./examples/multiple-users/fastapi_multiuser_app.py)** - Full-featured REST API with Swagger UI for testing multi-user functionality
 
 ## Framework Integrations
 
 Memori works seamlessly with popular AI frameworks:
 
-| Framework | Description | Example | Features |
-|-----------|-------------|---------|----------|
-| 🤖 [Agno](./examples/integrations/agno_example.py) | Memory-enhanced agent framework integration with persistent conversations | Simple chat agent with memory search | Memory tools, conversation persistence, contextual responses |
-| 👥 [CrewAI](./examples/integrations/crewai_example.py) | Multi-agent system with shared memory across agent interactions | Collaborative agents with memory | Agent coordination, shared memory, task-based workflows |
-| 🌊 [Digital Ocean AI](./examples/integrations/digital_ocean_example.py) | Memory-enhanced customer support using Digital Ocean's AI platform | Customer support assistant with conversation history | Context injection, session continuity, support analytics |
-| 🔗 [LangChain](./examples/integrations/langchain_example.py) | Enterprise-grade agent framework with advanced memory integration | AI assistant with LangChain tools and memory | Custom tools, agent executors, memory persistence, error handling |
-| � [OpenAI Agent](./examples/integrations/openai_agent_example.py) | Memory-enhanced OpenAI Agent with function calling and user preference tracking | Interactive assistant with memory search and user info storage | Function calling tools, memory search, preference tracking, async conversations |
-| �🚀 [Swarms](./examples/integrations/swarms_example.py) | Multi-agent system framework with persistent memory capabilities | Memory-enhanced Swarms agents with auto/conscious ingestion | Agent memory persistence, multi-agent coordination, contextual awareness |
+| Framework | Description | Example |
+|-----------|-------------|---------|
+| [AgentOps](./examples/integrations/agentops_example.py) | Track and monitor Memori memory operations with comprehensive observability | Memory operation tracking with AgentOps analytics |
+| [Agno](./examples/integrations/agno_example.py) | Memory-enhanced agent framework integration with persistent conversations | Simple chat agent with memory search |
+| [AWS Strands](./examples/integrations/aws_strands_example.py) | Professional development coach with Strands SDK and persistent memory | Career coaching agent with goal tracking |
+| [Azure AI Foundry](./examples/integrations/azure_ai_foundry_example.py) | Azure AI Foundry agents with persistent memory across conversations | Enterprise AI agents with Azure integration |
+| [CamelAI](./examples/integrations/camelai_example.py) | Multi-agent communication framework with automatic memory recording and retrieval | Memory-enhanced chat agents with conversation continuity |
+| [CrewAI](./examples/integrations/crewai_example.py) | Multi-agent system with shared memory across agent interactions | Collaborative agents with memory |
+| [Digital Ocean AI](./examples/integrations/digital_ocean_example.py) | Memory-enhanced customer support using Digital Ocean's AI platform | Customer support assistant with conversation history |
+| [LangChain](./examples/integrations/langchain_example.py) | Enterprise-grade agent framework with advanced memory integration | AI assistant with LangChain tools and memory |
+| [OpenAI Agent](./examples/integrations/openai_agent_example.py) | Memory-enhanced OpenAI Agent with function calling and user preference tracking | Interactive assistant with memory search and user info storage |
+| [Swarms](./examples/integrations/swarms_example.py) | Multi-agent system framework with persistent memory capabilities | Memory-enhanced Swarms agents with auto/conscious ingestion |
 
 ## Interactive Demos
 

{memorisdk-2.0.0 → memorisdk-2.0.1}/README.md

@@ -363,19 +363,25 @@ memori/
 - **[Memory Retrieval](./memory_retrival_example.py)** - Function calling with memory tools
 - **[Advanced Config](./examples/advanced_config.py)** - Production configuration
 - **[Interactive Demo](./memori_example.py)** - Live conscious ingestion showcase
+- **[Simple Multi-User](./examples/multiple-users/simple_multiuser.py)** - Basic demonstration of user memory isolation with namespaces
+- **[FastAPI Multi-User App](./examples/multiple-users/fastapi_multiuser_app.py)** - Full-featured REST API with Swagger UI for testing multi-user functionality
 
 ## Framework Integrations
 
 Memori works seamlessly with popular AI frameworks:
 
-| Framework | Description | Example | Features |
-|-----------|-------------|---------|----------|
-| 🤖 [Agno](./examples/integrations/agno_example.py) | Memory-enhanced agent framework integration with persistent conversations | Simple chat agent with memory search | Memory tools, conversation persistence, contextual responses |
-| 👥 [CrewAI](./examples/integrations/crewai_example.py) | Multi-agent system with shared memory across agent interactions | Collaborative agents with memory | Agent coordination, shared memory, task-based workflows |
-| 🌊 [Digital Ocean AI](./examples/integrations/digital_ocean_example.py) | Memory-enhanced customer support using Digital Ocean's AI platform | Customer support assistant with conversation history | Context injection, session continuity, support analytics |
-| 🔗 [LangChain](./examples/integrations/langchain_example.py) | Enterprise-grade agent framework with advanced memory integration | AI assistant with LangChain tools and memory | Custom tools, agent executors, memory persistence, error handling |
-| � [OpenAI Agent](./examples/integrations/openai_agent_example.py) | Memory-enhanced OpenAI Agent with function calling and user preference tracking | Interactive assistant with memory search and user info storage | Function calling tools, memory search, preference tracking, async conversations |
-| �🚀 [Swarms](./examples/integrations/swarms_example.py) | Multi-agent system framework with persistent memory capabilities | Memory-enhanced Swarms agents with auto/conscious ingestion | Agent memory persistence, multi-agent coordination, contextual awareness |
+| Framework | Description | Example |
+|-----------|-------------|---------|
+| [AgentOps](./examples/integrations/agentops_example.py) | Track and monitor Memori memory operations with comprehensive observability | Memory operation tracking with AgentOps analytics |
+| [Agno](./examples/integrations/agno_example.py) | Memory-enhanced agent framework integration with persistent conversations | Simple chat agent with memory search |
+| [AWS Strands](./examples/integrations/aws_strands_example.py) | Professional development coach with Strands SDK and persistent memory | Career coaching agent with goal tracking |
+| [Azure AI Foundry](./examples/integrations/azure_ai_foundry_example.py) | Azure AI Foundry agents with persistent memory across conversations | Enterprise AI agents with Azure integration |
+| [CamelAI](./examples/integrations/camelai_example.py) | Multi-agent communication framework with automatic memory recording and retrieval | Memory-enhanced chat agents with conversation continuity |
+| [CrewAI](./examples/integrations/crewai_example.py) | Multi-agent system with shared memory across agent interactions | Collaborative agents with memory |
+| [Digital Ocean AI](./examples/integrations/digital_ocean_example.py) | Memory-enhanced customer support using Digital Ocean's AI platform | Customer support assistant with conversation history |
+| [LangChain](./examples/integrations/langchain_example.py) | Enterprise-grade agent framework with advanced memory integration | AI assistant with LangChain tools and memory |
+| [OpenAI Agent](./examples/integrations/openai_agent_example.py) | Memory-enhanced OpenAI Agent with function calling and user preference tracking | Interactive assistant with memory search and user info storage |
+| [Swarms](./examples/integrations/swarms_example.py) | Multi-agent system framework with persistent memory capabilities | Memory-enhanced Swarms agents with auto/conscious ingestion |
 
 ## Interactive Demos
 

{memorisdk-2.0.0 → memorisdk-2.0.1}/memori/__init__.py

@@ -5,7 +5,7 @@ Professional-grade memory layer with comprehensive error handling, configuration
 management, and modular architecture for production AI systems.
 """
 
-__version__ = "2.0.0"
+__version__ = "2.0.1"
 __author__ = "Harshal More"
 __email__ = "harshalmore2468@gmail.com"
 

{memorisdk-2.0.0 → memorisdk-2.0.1}/memori/agents/retrieval_agent.py

@@ -411,32 +411,96 @@ Be strategic and comprehensive in your search planning."""
 
         # This would need to be implemented in the database manager
         # For now, get all memories and filter by category
+        logger.debug(
+            f"Searching memories by categories: {categories} in namespace: {namespace}"
+        )
         all_results = db_manager.search_memories(
             query="", namespace=namespace, limit=limit * 3
         )
 
+        logger.debug(
+            f"Retrieved {len(all_results)} total results for category filtering"
+        )
+
         filtered_results = []
-        for result in all_results:
+        for i, result in enumerate(all_results):
+            logger.debug(f"Processing result {i+1}/{len(all_results)}: {type(result)}")
+
             # Extract category from processed_data if it's stored as JSON
             try:
-                if "processed_data" in result:
+                memory_category = None
+
+                # Check processed_data field first
+                if "processed_data" in result and result["processed_data"]:
                     processed_data = result["processed_data"]
+                    logger.debug(
+                        f"Found processed_data: {type(processed_data)} - {str(processed_data)[:100]}..."
+                    )
+
                     # Handle both dict and JSON string formats
                     if isinstance(processed_data, str):
-                        processed_data = json.loads(processed_data)
-                    elif not isinstance(processed_data, dict):
-                        continue  # Skip if neither dict nor string
+                        try:
+                            processed_data = json.loads(processed_data)
+                        except json.JSONDecodeError as je:
+                            logger.debug(f"JSON decode error for processed_data: {je}")
+                            continue
+
+                    if isinstance(processed_data, dict):
+                        # Try multiple possible category locations
+                        category_paths = [
+                            ["category", "primary_category"],
+                            ["category"],
+                            ["primary_category"],
+                            ["metadata", "category"],
+                            ["classification", "category"],
+                        ]
+
+                        for path in category_paths:
+                            temp_data = processed_data
+                            try:
+                                for key in path:
+                                    temp_data = temp_data.get(key, {})
+                                if isinstance(temp_data, str) and temp_data:
+                                    memory_category = temp_data
+                                    logger.debug(
+                                        f"Found category via path {path}: {memory_category}"
+                                    )
+                                    break
+                            except (AttributeError, TypeError):
+                                continue
+                    else:
+                        logger.debug(
+                            f"processed_data is not a dict after parsing: {type(processed_data)}"
+                        )
+                        continue
 
-                    memory_category = processed_data.get("category", {}).get(
-                        "primary_category", ""
+                # Fallback: check direct category field
+                if not memory_category and "category" in result and result["category"]:
+                    memory_category = result["category"]
+                    logger.debug(f"Found category via direct field: {memory_category}")
+
+                # Check if the found category matches any of our target categories
+                if memory_category:
+                    logger.debug(
+                        f"Comparing memory category '{memory_category}' against target categories {categories}"
                     )
                     if memory_category in categories:
                         filtered_results.append(result)
-                elif result.get("category") in categories:
-                    filtered_results.append(result)
-            except (json.JSONDecodeError, KeyError, AttributeError):
+                        logger.debug(f"✓ Category match found: {memory_category}")
+                    else:
+                        logger.debug(
+                            f"✗ Category mismatch: {memory_category} not in {categories}"
+                        )
+                else:
+                    logger.debug("No category found in result")
+
+            except Exception as e:
+                logger.debug(f"Error processing result {i+1}: {e}")
                 continue
 
+        logger.debug(
+            f"Category filtering complete: {len(filtered_results)} results match categories {categories}"
+        )
         return filtered_results[:limit]
 
     def _detect_structured_output_support(self) -> bool:
@@ -821,8 +885,11 @@ Be strategic and comprehensive in your search planning."""
         """
         # This is a compatibility method that uses the database manager directly
         # We'll need the database manager to be injected or passed
-        # For now, return empty list and log the issue
-        logger.warning(f"search_memories called without database manager: {query}")
+        # For now, return empty list and log the issue with parameters
+        logger.warning(
+            f"search_memories called without database manager: query='{query}', "
+            f"max_results={max_results}, namespace='{namespace}'"
+        )
         return []
 
 

{memorisdk-2.0.0 → memorisdk-2.0.1}/memori/core/memory.py

@@ -1036,15 +1036,38 @@ class Memori:
             self._in_context_retrieval = True
 
             logger.debug(
-                f"Auto-ingest: Starting context retrieval for query: '{user_input[:50]}...'"
+                f"Auto-ingest: Starting context retrieval for query: '{user_input[:50]}...' in namespace: '{self.namespace}'"
             )
 
             # Always try direct database search first as it's more reliable
             logger.debug("Auto-ingest: Using direct database search (primary method)")
-            results = self.db_manager.search_memories(
-                query=user_input, namespace=self.namespace, limit=5
+            logger.debug(
+                f"Auto-ingest: Database manager type: {type(self.db_manager).__name__}"
             )
 
+            try:
+                results = self.db_manager.search_memories(
+                    query=user_input, namespace=self.namespace, limit=5
+                )
+                logger.debug(
+                    f"Auto-ingest: Database search returned {len(results) if results else 0} results"
+                )
+
+                if results:
+                    for i, result in enumerate(
+                        results[:3]
+                    ):  # Log first 3 results for debugging
+                        logger.debug(
+                            f"Auto-ingest: Result {i+1}: {type(result)} with keys: {list(result.keys()) if isinstance(result, dict) else 'N/A'}"
+                        )
+            except Exception as db_search_e:
+                logger.error(f"Auto-ingest: Database search failed: {db_search_e}")
+                logger.debug(
+                    f"Auto-ingest: Database search error details: {type(db_search_e).__name__}: {str(db_search_e)}",
+                    exc_info=True,
+                )
+                results = []
+
             if results:
                 logger.debug(
                     f"Auto-ingest: Direct database search returned {len(results)} results"
@@ -1085,8 +1108,12 @@ class Memori:
                         )
 
                 except Exception as search_error:
-                    logger.warning(
-                        f"Auto-ingest: Search engine failed ({search_error})"
+                    logger.error(
+                        f"Auto-ingest: Search engine failed for query '{user_input[:50]}...': {search_error}"
+                    )
+                    logger.debug(
+                        f"Auto-ingest: Search engine error details: {type(search_error).__name__}: {str(search_error)}",
+                        exc_info=True,
                     )
             else:
                 logger.debug("Auto-ingest: No search engine available")
@@ -1095,22 +1122,39 @@ class Memori:
             logger.debug(
                 "Auto-ingest: All search methods returned 0 results, using recent memories fallback"
             )
-            fallback_results = self.db_manager.search_memories(
-                query="",  # Empty query to get recent memories
-                namespace=self.namespace,
-                limit=3,
+            logger.debug(
+                f"Auto-ingest: Attempting fallback search in namespace '{self.namespace}'"
             )
 
-            if fallback_results:
+            try:
+                fallback_results = self.db_manager.search_memories(
+                    query="",  # Empty query to get recent memories
+                    namespace=self.namespace,
+                    limit=3,
+                )
                 logger.debug(
-                    f"Auto-ingest: Fallback returned {len(fallback_results)} recent memories"
+                    f"Auto-ingest: Fallback search returned {len(fallback_results) if fallback_results else 0} results"
+                )
+
+                if fallback_results:
+                    logger.debug(
+                        f"Auto-ingest: Fallback returned {len(fallback_results)} recent memories"
+                    )
+                    # Add search metadata to fallback results
+                    for result in fallback_results:
+                        if isinstance(result, dict):
+                            result["retrieval_method"] = "recent_memories_fallback"
+                            result["retrieval_query"] = user_input
+                    return fallback_results
+                else:
+                    logger.debug("Auto-ingest: Fallback search returned no results")
+
+            except Exception as fallback_e:
+                logger.error(f"Auto-ingest: Fallback search failed: {fallback_e}")
+                logger.debug(
+                    f"Auto-ingest: Fallback error details: {type(fallback_e).__name__}: {str(fallback_e)}",
+                    exc_info=True,
                 )
-                # Add search metadata to fallback results
-                for result in fallback_results:
-                    if isinstance(result, dict):
-                        result["retrieval_method"] = "recent_memories_fallback"
-                        result["retrieval_query"] = user_input
-                return fallback_results
 
             logger.debug(
                 "Auto-ingest: All retrieval methods failed, returning empty context"