Store user_id in vectordb (#2466)

mem0/memory/main.py

@@ -3,6 +3,7 @@ import concurrent
 import hashlib
 import json
 import logging
+import os
 import uuid
 import warnings
 from datetime import datetime
@@ -18,7 +19,7 @@ from mem0.configs.prompts import (
     get_update_memory_messages,
 )
 from mem0.memory.base import MemoryBase
-from mem0.memory.setup import setup_config
+from mem0.memory.setup import mem0_dir, setup_config
 from mem0.memory.storage import SQLiteManager
 from mem0.memory.telemetry import capture_event
 from mem0.memory.utils import (
@@ -62,6 +63,15 @@ class Memory(MemoryBase):
             self.graph = MemoryGraph(self.config)
             self.enable_graph = True
 
+        self.config.vector_store.config.collection_name = "mem0_migrations"
+        if self.config.vector_store.provider in ["faiss", "qdrant"]:
+            provider_path = f"migrations_{self.config.vector_store.provider}"
+            self.config.vector_store.config.path = os.path.join(mem0_dir, provider_path)
+            os.makedirs(self.config.vector_store.config.path, exist_ok=True)
+
+        self._telemetry_vector_store = VectorStoreFactory.create(
+            self.config.vector_store.provider, self.config.vector_store.config
+        )
         capture_event("mem0.init", self)
 
     @classmethod

mem0/memory/setup.py

@@ -3,6 +3,7 @@ import os
 import uuid
 
 # Set up the directory path
+VECTOR_ID = str(uuid.uuid4())
 home_dir = os.path.expanduser("~")
 mem0_dir = os.environ.get("MEM0_DIR") or os.path.join(home_dir, ".mem0")
 os.makedirs(mem0_dir, exist_ok=True)
@@ -29,3 +30,29 @@ def get_user_id():
             return user_id
     except Exception:
         return "anonymous_user"
+
+
+def get_or_create_user_id(vector_store):
+    """Store user_id in vector store and return it."""
+    user_id = get_user_id()
+
+    # Try to get existing user_id from vector store
+    try:
+        existing = vector_store.get(vector_id=VECTOR_ID)
+        if existing and hasattr(existing, "payload") and existing.payload and "user_id" in existing.payload:
+            return existing.payload["user_id"]
+    except:
+        pass
+
+    # If we get here, we need to insert the user_id
+    try:
+        dims = getattr(vector_store, "embedding_model_dims", 1)
+        vector_store.insert(
+            vectors=[[0.0] * dims],
+            payloads=[{"user_id": user_id, "type": "user_identity"}],
+            ids=[VECTOR_ID]
+        )
+    except:
+        pass
+
+    return user_id

mem0/memory/telemetry.py

@@ -6,7 +6,7 @@ import sys
 from posthog import Posthog
 
 import mem0
-from mem0.memory.setup import get_user_id, setup_config
+from mem0.memory.setup import get_or_create_user_id
 
 MEM0_TELEMETRY = os.environ.get("MEM0_TELEMETRY", "True")
 
@@ -21,11 +21,11 @@ logging.getLogger("urllib3").setLevel(logging.CRITICAL + 1)
 
 
 class AnonymousTelemetry:
-    def __init__(self, project_api_key, host):
+    def __init__(self, project_api_key, host, vector_store=None):
         self.posthog = Posthog(project_api_key=project_api_key, host=host)
-        # Call setup config to ensure that the user_id is generated
-        setup_config()
-        self.user_id = get_user_id()
+
+        self.user_id = get_or_create_user_id(vector_store)
+
         if not MEM0_TELEMETRY:
             self.posthog.disabled = True
 
@@ -50,14 +50,12 @@ class AnonymousTelemetry:
         self.posthog.shutdown()
 
 
-# Initialize AnonymousTelemetry
-telemetry = AnonymousTelemetry(
-    project_api_key="phc_hgJkUVJFYtmaJqrvf6CYN67TIQ8yhXAkWzUn9AMU4yX",
-    host="https://us.i.posthog.com",
-)
-
-
 def capture_event(event_name, memory_instance, additional_data=None):
+    global telemetry
+
+    # For OSS, we use the telemetry vector store to store the user_id
+    telemetry = AnonymousTelemetry(project_api_key="phc_hgJkUVJFYtmaJqrvf6CYN67TIQ8yhXAkWzUn9AMU4yX", host="https://us.i.posthog.com", vector_store=memory_instance._telemetry_vector_store if hasattr(memory_instance, "_telemetry_vector_store") else None)
+
     event_data = {
         "collection": memory_instance.collection_name,
         "vector_size": memory_instance.embedding_model.config.embedding_dims,