Minor fixes in procedural memory (#2469)

mem0/configs/prompts.py

@@ -220,14 +220,14 @@ You are a memory summarization system that records and preserves the complete in
   Each numbered step must be a self-contained entry that includes all of the following elements:
 
   1. **Agent Action**:
-     - Precisely describe what the agent did (e.g., "Clicked on the 'Blog' link", "Called API to fetch content", "Scraped page data").  
+     - Precisely describe what the agent did (e.g., "Clicked on the 'Blog' link", "Called API to fetch content", "Scraped page data").
      - Include all parameters, target elements, or methods involved.
-     
-  2. **Action Result (Mandatory, Unmodified)**:  
-     - Immediately follow the agent action with its exact, unaltered output.  
+
+  2. **Action Result (Mandatory, Unmodified)**:
+     - Immediately follow the agent action with its exact, unaltered output.
      - Record all returned data, responses, HTML snippets, JSON content, or error messages exactly as received. This is critical for constructing the final output later.
-     
-  3. **Embedded Metadata**:  
+
+  3. **Embedded Metadata**:
      For the same numbered step, include additional context such as:
      - **Key Findings**: Any important information discovered (e.g., URLs, data points, search results).
      - **Navigation History**: For browser agents, detail which pages were visited, including their URLs and relevance.
@@ -246,6 +246,8 @@ You are a memory summarization system that records and preserves the complete in
 ### Example Template:
 
 ```
+## Summary of the agent's execution history
+
 **Task Objective**: Scrape blog post titles and full content from the OpenAI blog.
 **Progress Status**: 10% complete — 5 out of 50 blog posts processed.
 

mem0/memory/main.py

@@ -89,6 +89,7 @@ class Memory(MemoryBase):
         infer=True,
         memory_type=None,
         prompt=None,
+        llm=None,
     ):
         """
         Create a new memory.
@@ -103,6 +104,7 @@ class Memory(MemoryBase):
             infer (bool, optional): Whether to infer the memories. Defaults to True.
             memory_type (str, optional): Type of memory to create. Defaults to None. By default, it creates the short term memories and long term (semantic and episodic) memories. Pass "procedural_memory" to create procedural memories.
             prompt (str, optional): Prompt to use for the memory creation. Defaults to None.
+            llm (BaseChatModel, optional): LLM class to use for generating procedural memories. Defaults to None. Useful when user is using LangChain ChatModel.
         Returns:
             dict: A dictionary containing the result of the memory addition operation.
             result: dict of affected events with each dict has the following key:
@@ -139,7 +141,7 @@ class Memory(MemoryBase):
             messages = [{"role": "user", "content": messages}]
 
         if agent_id is not None and memory_type == MemoryType.PROCEDURAL.value:
-            results = self._create_procedural_memory(messages, metadata, prompt)
+            results = self._create_procedural_memory(messages, metadata=metadata, llm=llm, prompt=prompt)
             return results
 
         if self.config.llm.config.get("enable_vision"):
@@ -623,9 +625,15 @@ class Memory(MemoryBase):
         capture_event("mem0._create_memory", self, {"memory_id": memory_id})
         return memory_id
 
-    def _create_procedural_memory(self, messages, metadata, llm=None, prompt=None):
+    def _create_procedural_memory(self, messages, metadata=None, llm=None, prompt=None):
         """
         Create a procedural memory
+
+        Args:
+            messages (list): List of messages to create a procedural memory from.
+            metadata (dict): Metadata to create a procedural memory from.
+            llm (BaseChatModel, optional): LLM class to use for generating procedural memories. Defaults to None. Useful when user is using LangChain ChatModel.
+            prompt (str, optional): Prompt to use for the procedural memory creation. Defaults to None.
         """
         try:
             from langchain_core.messages.utils import convert_to_messages  # type: ignore
@@ -644,7 +652,7 @@ class Memory(MemoryBase):
         try:
             if llm is not None:
                 parsed_messages = convert_to_messages(parsed_messages)
-                response = llm.invoke(messages=parsed_messages)
+                response = llm.invoke(input=parsed_messages)
                 procedural_memory = response.content
             else:
                 procedural_memory = self.llm.generate_response(messages=parsed_messages)

mem0/vector_stores/faiss.py

@@ -101,7 +101,6 @@ class FAISS(VectorStoreBase):
             faiss.write_index(self.index, index_path)
             with open(docstore_path, "wb") as f:
                 pickle.dump((self.docstore, self.index_to_id), f)
-            logger.info(f"Saved FAISS index to {index_path} with {self.index.ntotal} vectors")
         except Exception as e:
             logger.warning(f"Failed to save FAISS index: {e}")
 

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "mem0ai"
-version = "0.1.80"
+version = "0.1.81"
 description = "Long-term memory for AI Agents"
 authors = ["Mem0 <founders@mem0.ai>"]
 exclude = [