JDSS/mem0
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Fix: prevent double embedding in mem0.add (fixes #3723) (#3996)

Browse Source 
Co-authored-by: utkarsh240799 <utkarsh240799@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Varun Chawla
2026-03-25 18:14:48 +05:30
committed by GitHub
co-authored by utkarsh240799 Claude Opus 4.6
parent 13c7f84eec
commit 7e3b727528
2 changed files with 173 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files
mem0/memory/main.py
+39 -11
View File
@@ -9,7 +9,7 @@ import uuid
import warnings
from copy import deepcopy
from datetime import datetime, timezone
from typing import Any, Dict, Optional
from typing import Any, Dict, List, Optional, Union
from pydantic import ValidationError
@@ -479,7 +479,8 @@ class Memory(MemoryBase):
msg_content = message_dict["content"]
msg_embeddings = self.embedding_model.embed(msg_content, "add")
mem_id = self._create_memory(msg_content, msg_embeddings, per_msg_meta)
# Pass embeddings as a dict so _create_memory can reuse the cached embedding
mem_id = self._create_memory(msg_content, {msg_content: msg_embeddings}, per_msg_meta)
returned_memories.append(
{
@@ -608,6 +609,9 @@ class Memory(MemoryBase):
event_type = resp.get("event")
if event_type == "ADD":
# Ensure action_text has an embedding cached to avoid redundant API calls
if action_text not in new_message_embeddings:
new_message_embeddings[action_text] = self.embedding_model.embed(action_text, "add")
memory_id = self._create_memory(
data=action_text,
existing_embeddings=new_message_embeddings,
@@ -615,6 +619,9 @@ class Memory(MemoryBase):
)
returned_memories.append({"id": memory_id, "memory": action_text, "event": event_type})
elif event_type == "UPDATE":
# Ensure action_text has an embedding cached to avoid redundant API calls
if action_text not in new_message_embeddings:
new_message_embeddings[action_text] = self.embedding_model.embed(action_text, "update")
self._update_memory(
memory_id=temp_uuid_mapping[resp.get("id")],
data=action_text,
@@ -1173,10 +1180,13 @@ class Memory(MemoryBase):
capture_event("mem0.history", self, {"memory_id": memory_id, "sync_type": "sync"})
return self.db.get_history(memory_id)
def _create_memory(self, data, existing_embeddings, metadata=None):
def _create_memory(self, data: str, existing_embeddings: Union[Dict[str, List[float]], List[float]], metadata=None):
logger.debug(f"Creating memory with {data=}")
if data in existing_embeddings:
# existing_embeddings may be a dict (preferred) or a precomputed vector
if isinstance(existing_embeddings, dict) and data in existing_embeddings:
embeddings = existing_embeddings[data]
elif not isinstance(existing_embeddings, dict):
embeddings = existing_embeddings
else:
embeddings = self.embedding_model.embed(data, memory_action="add")
memory_id = str(uuid.uuid4())
@@ -1241,7 +1251,7 @@ class Memory(MemoryBase):
return result
def _update_memory(self, memory_id, data, existing_embeddings, metadata=None):
def _update_memory(self, memory_id, data: str, existing_embeddings: Union[Dict[str, List[float]], List[float]], metadata=None):
logger.info(f"Updating memory with {data=}")
try:
@@ -1274,8 +1284,10 @@ class Memory(MemoryBase):
if "role" not in new_metadata and "role" in existing_memory.payload:
new_metadata["role"] = existing_memory.payload["role"]
if data in existing_embeddings:
if isinstance(existing_embeddings, dict) and data in existing_embeddings:
embeddings = existing_embeddings[data]
elif not isinstance(existing_embeddings, dict):
embeddings = existing_embeddings
else:
embeddings = self.embedding_model.embed(data, "update")
@@ -1545,7 +1557,8 @@ class AsyncMemory(MemoryBase):
msg_content = message_dict["content"]
msg_embeddings = await asyncio.to_thread(self.embedding_model.embed, msg_content, "add")
mem_id = await self._create_memory(msg_content, msg_embeddings, per_msg_meta)
# Pass embeddings as a dict so _create_memory can reuse the cached embedding
mem_id = await self._create_memory(msg_content, {msg_content: msg_embeddings}, per_msg_meta)
returned_memories.append(
{
@@ -1673,6 +1686,11 @@ class AsyncMemory(MemoryBase):
event_type = resp.get("event")
if event_type == "ADD":
# Ensure action_text has an embedding cached to avoid redundant API calls
if action_text not in new_message_embeddings:
new_message_embeddings[action_text] = await asyncio.to_thread(
self.embedding_model.embed, action_text, "add"
)
task = asyncio.create_task(
self._create_memory(
data=action_text,
@@ -1682,6 +1700,11 @@ class AsyncMemory(MemoryBase):
)
memory_tasks.append((task, resp, "ADD", None))
elif event_type == "UPDATE":
# Ensure action_text has an embedding cached to avoid redundant API calls
if action_text not in new_message_embeddings:
new_message_embeddings[action_text] = await asyncio.to_thread(
self.embedding_model.embed, action_text, "update"
)
task = asyncio.create_task(
self._update_memory(
memory_id=temp_uuid_mapping[resp["id"]],
@@ -2271,10 +2294,13 @@ class AsyncMemory(MemoryBase):
capture_event("mem0.history", self, {"memory_id": memory_id, "sync_type": "async"})
return await asyncio.to_thread(self.db.get_history, memory_id)
async def _create_memory(self, data, existing_embeddings, metadata=None):
async def _create_memory(self, data: str, existing_embeddings: Union[Dict[str, List[float]], List[float]], metadata=None):
logger.debug(f"Creating memory with {data=}")
if data in existing_embeddings:
# existing_embeddings may be a dict (preferred) or a precomputed vector
if isinstance(existing_embeddings, dict) and data in existing_embeddings:
embeddings = existing_embeddings[data]
elif not isinstance(existing_embeddings, dict):
embeddings = existing_embeddings
else:
embeddings = await asyncio.to_thread(self.embedding_model.embed, data, memory_action="add")
@@ -2358,7 +2384,7 @@ class AsyncMemory(MemoryBase):
return result
async def _update_memory(self, memory_id, data, existing_embeddings, metadata=None):
async def _update_memory(self, memory_id, data: str, existing_embeddings: Union[Dict[str, List[float]], List[float]], metadata=None):
logger.info(f"Updating memory with {data=}")
try:
@@ -2392,8 +2418,10 @@ class AsyncMemory(MemoryBase):
if "role" not in new_metadata and "role" in existing_memory.payload:
new_metadata["role"] = existing_memory.payload["role"]
if data in existing_embeddings:
if isinstance(existing_embeddings, dict) and data in existing_embeddings:
embeddings = existing_embeddings[data]
elif not isinstance(existing_embeddings, dict):
embeddings = existing_embeddings
else:
embeddings = await asyncio.to_thread(self.embedding_model.embed, data, "update")