ERROR:mem0.memory.graph_memory:Error in search tool: 'entity_type'

🐛 Describe the bug

When replacing llm with locally deployed mixtral: 8x22b and executing m.add ("I like pizza", user_id="alice123"), an error is reported: ERROR: mm0. memory. graph. memory: Error in search tool: 'entity type' TypeError Traceback (most recent call last) Cell In[22], line 1 ----> 1 m.add("I like pizza", user_id="alice123")

File ~/opt/anaconda3/envs/mem0/lib/python3.10/site-packages/mem0/memory/main.py:120, in Memory.add(self, messages, user_id, agent_id, run_id, metadata, filters, prompt) 117 concurrent.futures.wait([future1, future2]) 119 vector_store_result = future1.result() --> 120 graph_result = future2.result() 122 if self.api_version == "v1.1": 123 return { 124 "results": vector_store_result, 125 "relations": graph_result, 126 }

File ~/opt/anaconda3/envs/mem0/lib/python3.10/concurrent/futures/_base.py:451, in Future.result(self, timeout) 449 raise CancelledError() 450 elif self._state == FINISHED: --> 451 return self.__get_result() 453 self._condition.wait(timeout) 455 if self._state in [CANCELLED, CANCELLED_AND_NOTIFIED]:

File ~/opt/anaconda3/envs/mem0/lib/python3.10/concurrent/futures/_base.py:403, in Future.__get_result(self) 401 if self._exception: 402 try: --> 403 raise self._exception 404 finally: 405 # Break a reference cycle with the exception in self._exception 406 self = None

File ~/opt/anaconda3/envs/mem0/lib/python3.10/concurrent/futures/thread.py:58, in _WorkItem.run(self) 55 return 57 try: ---> 58 result = self.fn(*self.args, **self.kwargs) 59 except BaseException as exc: 60 self.future.set_exception(exc)

File ~/opt/anaconda3/envs/mem0/lib/python3.10/site-packages/mem0/memory/main.py:252, in Memory._add_to_graph(self, messages, filters) 250 self.graph.user_id = "USER" 251 data = "\n".join([msg["content"] for msg in messages if "content" in msg and msg["role"] != "system"]) --> 252 added_entities = self.graph.add(data, filters) 254 return added_entities

File ~/opt/anaconda3/envs/mem0/lib/python3.10/site-packages/mem0/memory/graph_memory.py:69, in MemoryGraph.add(self, data, filters) 66 extracted_relations = self._extract_relations(data, filters, entity_type_map) 68 search_output_string = format_entities(search_output) ---> 69 extracted_relations_string = format_entities(extracted_relations) 70 update_memory_prompt = get_update_memory_messages(search_output_string, extracted_relations_string) 72 _tools = [UPDATE_MEMORY_TOOL_GRAPH, ADD_MEMORY_TOOL_GRAPH, NOOP_TOOL]

File ~/opt/anaconda3/envs/mem0/lib/python3.10/site-packages/mem0/memory/utils.py:27, in format_entities(entities) 25 formatted_lines = [] 26 for entity in entities: ---> 27 simplified = f"{entity['source']} -- {entity['relation'].upper()} -- {entity['destination']}" 28 formatted_lines.append(simplified) 30 return "\n".join(formatted_lines) TypeError: string indices must be integers

I can see that you're encountering an issue when trying to use Mixtral 8x22B with mem0's graph memory component. The error occurs because the graph memory component expects a specific structured output from the LLM that Mixtral isn't providing correctly.

From the codebase, I can see that the format_entities() function expects each entity to be a dictionary with 'source', 'relation', and 'destination' keys, but it seems Mixtral is returning strings instead.

Here's what's happening:

The graph memory component uses LLMs to extract entities and relationships from text
It expects the LLM to return structured data in a specific format
The Mixtral model appears to be returning unstructured string output instead of the required JSON format

To fix this, you have two options:

Use a supported structured model:

config = {
"llm": {
    "provider": "openai_structured",  # or "azure_openai_structured"
    "config": {
        "model": "gpt-4o-mini",  # or another supported structured model
        "temperature": 0.1,
        "max_tokens": 2000
    }
},
"graph_store": {
    "provider": "neo4j",
    "config": {
        "url": "your_neo4j_url",
        "username": "neo4j",
        "password": "your_password"
    }
},
"version": "v1.1"
}

If you must use Mixtral, you'll need to create a custom wrapper that formats its output to match the expected structure:

class MixtralWrapper:
def generate_response(self, messages, tools):
    # Add formatting logic here to convert Mixtral's output
    # to the expected structure with source/relation/destination
    pass

References:

From the codebase (mem0/memory/graph_memory.py): The graph memory component expects structured output with specific tools and formats
From issue #1822: There was a similar issue with non-structured models, confirming this is a known limitation

Important notes:

The graph memory feature requires structured output from the LLM
Not all models support the required structured output format
Using unsupported models may lead to format compatibility issues

Let me know if you'd like to try either of these solutions or if you need help implementing a custom wrapper for Mixtral.

I can see that you're encountering an issue when trying to use Mixtral 8x22B with mem0's graph memory component. The error occurs because the graph memory component expects a specific structured output from the LLM that Mixtral isn't providing correctly.

From the codebase, I can see that the format_entities() function expects each entity to be a dictionary with 'source', 'relation', and 'destination' keys, but it seems Mixtral is returning strings instead.

Here's what's happening:

The graph memory component uses LLMs to extract entities and relationships from text

It expects the LLM to return structured data in a specific format

The Mixtral model appears to be returning unstructured string output instead of the required JSON format

To fix this, you have two options:

Use a supported structured model:
config = {
    "llm": {
        "provider": "openai_structured",  # or "azure_openai_structured"
        "config": {
            "model": "gpt-4o-mini",  # or another supported structured model
            "temperature": 0.1,
            "max_tokens": 2000
        }
    },
    "graph_store": {
        "provider": "neo4j",
        "config": {
            "url": "your_neo4j_url",
            "username": "neo4j",
            "password": "your_password"
        }
    },
    "version": "v1.1"
}
If you must use Mixtral, you'll need to create a custom wrapper that formats its output to match the expected structure:
class MixtralWrapper:
    def generate_response(self, messages, tools):
        # Add formatting logic here to convert Mixtral's output
        # to the expected structure with source/relation/destination
        pass
References:

From the codebase (mem0/memory/graph_memory.py): The graph memory component expects structured output with specific tools and formats

From issue [graph_memory]: The current tools does not support non-structured models. #1822: There was a similar issue with non-structured models, confirming this is a known limitation

Important notes:

The graph memory feature requires structured output from the LLM

Not all models support the required structured output format

Using unsupported models may lead to format compatibility issues

Let me know if you'd like to try either of these solutions or if you need help implementing a custom wrapper for Mixtral.

Thank you for your response. If possible, we hope to provide support for mixtral: 8x22b and qwen2.5:72b.

mem0ai / mem0

ERROR:mem0.memory.graph_memory:Error in search tool: 'entity_type' #2054

🐛 Describe the bug