Change dependency to mem0ai (#1476)

embedchain/docs/api-reference/advanced/configuration.mdx

@@ -250,7 +250,6 @@ Alright, let's dive into what each key means in the yaml config above:
       - `similarity_threshold` (Float): The threshold for similarity evaluation. Defaults to `0.8`.
       - `auto_flush` (Integer): The number of queries after which the cache is flushed. Defaults to `20`.
 7. `memory` Section: (Optional)
-    - `api_key` (String): The API key of mem0.
     - `top_k` (Integer): The number of top-k results to return. Defaults to `10`.
     <Note>
     If you provide a cache section, the app will automatically configure and use a cache to store the results of the language model. This is useful if you want to speed up the response time and save inference cost of your app.

embedchain/docs/api-reference/app/chat.mdx

@@ -149,17 +149,15 @@ app.chat("What is the net worth of Elon Musk?", config=query_config)
 
 Mem0 is a cutting-edge long-term memory for LLMs to enable personalization for the GenAI stack. It enables LLMs to remember past interactions and provide more personalized responses.
 
-Follow these steps to use Mem0  to enable memory for personalization in your apps:
-- Install the [`mem0`](https://docs.mem0.ai/) package using `pip install memzero`. 
-- Get the api_key from [Mem0 Platform](https://app.mem0.ai/).
-- Provide api_key in config under `memory`, refer [Configurations](docs/api-reference/advanced/configuration.mdx).
+In order to use Mem0 to enable memory for personalization in your apps:
+- Install the [`mem0`](https://docs.mem0.ai/) package using `pip install mem0ai`. 
+- Prepare config for `memory`, refer [Configurations](docs/api-reference/advanced/configuration.mdx).
 
 ```python with mem0
 from embedchain import App
 
 config = {
   "memory": {
-    "api_key": "m0-xxx",
     "top_k": 5
   }
 }

embedchain/embedchain/app.py

@@ -9,7 +9,7 @@
 import yaml
 from tqdm import tqdm
 
-from mem0 import Mem0
+from mem0 import Memory
 from embedchain.cache import (
     Config,
     ExactMatchEvaluation,
@@ -131,9 +131,9 @@ def __init__(
             self._init_cache()
 
         # If memory_config is provided, initializing the memory ...
-        self.mem0_client = None
+        self.mem0_memory = None
         if self.memory_config is not None:
-            self.mem0_client = Mem0(api_key=self.memory_config.api_key)
+            self.mem0_memory = Memory()
 
         # Send anonymous telemetry
         self._telemetry_props = {"class": self.__class__.__name__}

embedchain/embedchain/embedchain.py

@@ -53,7 +53,7 @@ def __init__(
         self.config = config
         self.cache_config = None
         self.memory_config = None
-        self.mem0_client = None
+        self.mem0_memory = None
         # Llm
         self.llm = llm
         # Database has support for config assignment for backwards compatibility
@@ -598,8 +598,8 @@ def chat(
             contexts_data_for_llm_query = contexts
 
         memories = None
-        if self.mem0_client:
-            memories = self.mem0_client.search(
+        if self.mem0_memory:
+            memories = self.mem0_memory.search(
                 query=input_query, agent_id=self.config.id, session_id=session_id, limit=self.memory_config.top_k
             )
 
@@ -641,8 +641,8 @@ def chat(
         # Add to Mem0 memory if enabled
         # TODO: Might need to prepend with some text like: 
         # "Remember user preferences from following user query: {input_query}"
-        if self.mem0_client:
-            self.mem0_client.add(data=input_query, agent_id=self.config.id, session_id=session_id)
+        if self.mem0_memory:
+            self.mem0_memory.add(data=input_query, agent_id=self.config.id, session_id=session_id)
 
         # add conversation in memory
         self.llm.add_history(self.config.id, input_query, answer, session_id=session_id)