Skip to content

armgit / mem0

Public Imported from GitHub
0

The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.

fix(llms): skip JSON response_format for Groq compound models (#5513)

David Shraderd3d2e89fd548
diff --git a/mem0/llms/groq.py b/mem0/llms/groq.py
index 4fba88f4b..033577711 100644
--- a/mem0/llms/groq.py
+++ b/mem0/llms/groq.py
@@ -1,6 +1,7 @@
import json
+import logging
import os
-from typing import Dict, List, Optional
+from typing import Dict, List, Optional, Union
try:
from groq import Groq
@@ -11,6 +12,8 @@ from mem0.configs.llms.base import BaseLlmConfig
from mem0.llms.base import LLMBase
from mem0.memory.utils import extract_json
+logger = logging.getLogger(__name__)
+
class GroqLLM(LLMBase):
def __init__(self, config: Optional[BaseLlmConfig] = None):
@@ -22,6 +25,24 @@ class GroqLLM(LLMBase):
api_key = self.config.api_key or os.getenv("GROQ_API_KEY")
self.client = Groq(api_key=api_key)
+ @staticmethod
+ def _supports_json_mode(model: Optional[Union[str, Dict]]) -> bool:
+ """
+ Groq's compound agentic systems (e.g. ``groq/compound``, ``groq/compound-mini``)
+ do not support the JSON ``response_format`` and return empty or non-JSON content
+ when it is requested. See https://console.groq.com/docs/structured-outputs.
+
+ Non-string models (the config allows a dict) are assumed to support JSON mode,
+ preserving prior behavior.
+ """
+ if not isinstance(model, str):
+ return True
+ # Strip provider prefixes (e.g. "groq/compound-mini" -> "compound-mini"),
+ # mirroring the _is_reasoning_model heuristic in LLMBase, so the match
+ # targets the compound family rather than any name containing the substring.
+ base_model = model.lower().rsplit("/", 1)[-1]
+ return not base_model.startswith("compound")
+
def _parse_response(self, response, tools):
"""
Process the response based on whether tools are used or not.
@@ -79,7 +100,17 @@ class GroqLLM(LLMBase):
"top_p": self.config.top_p,
}
if response_format:
- params["response_format"] = response_format
+ requests_json = isinstance(response_format, dict) and response_format.get("type") in (
+ "json_object",
+ "json_schema",
+ )
+ if requests_json and not self._supports_json_mode(self.config.model):
+ logger.debug(
+ f"Model '{self.config.model}' does not support JSON response_format; "
+ "sending the request without it."
+ )
+ else:
+ params["response_format"] = response_format
if tools:
params["tools"] = tools
params["tool_choice"] = tool_choice
diff --git a/tests/llms/test_groq.py b/tests/llms/test_groq.py
index 288b37f80..ddf403263 100644
--- a/tests/llms/test_groq.py
+++ b/tests/llms/test_groq.py
@@ -84,3 +84,101 @@ def test_generate_response_with_tools(mock_groq_client):
assert len(response["tool_calls"]) == 1
assert response["tool_calls"][0]["name"] == "add_memory"
assert response["tool_calls"][0]["arguments"] == {"data": "Today is a sunny day."}
+
+
[email protected]("model", ["groq/compound", "groq/compound-mini"])
+def test_generate_response_skips_json_mode_for_compound_models(mock_groq_client, model):
+ config = BaseLlmConfig(model=model, temperature=0.7, max_tokens=100, top_p=1.0)
+ llm = GroqLLM(config)
+ messages = [{"role": "user", "content": "Hi, I'm Alice and I love hiking."}]
+
+ # Compound models answer JSON-mode requests with empty or non-JSON content;
+ # the mock mirrors that plain-text reply. These tests pin request
+ # construction (response_format omitted), not end-to-end extraction.
+ mock_response = Mock()
+ mock_response.choices = [Mock(message=Mock(content="Alice introduced herself and mentioned she loves hiking."))]
+ mock_groq_client.chat.completions.create.return_value = mock_response
+
+ llm.generate_response(messages, response_format={"type": "json_object"})
+
+ _, kwargs = mock_groq_client.chat.completions.create.call_args
+ assert "response_format" not in kwargs
+
+
+def test_generate_response_keeps_json_mode_for_standard_model(mock_groq_client):
+ config = BaseLlmConfig(model="llama-3.3-70b-versatile", temperature=0.7, max_tokens=100, top_p=1.0)
+ llm = GroqLLM(config)
+ messages = [{"role": "user", "content": "Hi, I'm Alice and I love hiking."}]
+
+ mock_response = Mock()
+ mock_response.choices = [Mock(message=Mock(content='{"memory": ["Name is Alice", "Loves hiking"]}'))]
+ mock_groq_client.chat.completions.create.return_value = mock_response
+
+ llm.generate_response(messages, response_format={"type": "json_object"})
+
+ _, kwargs = mock_groq_client.chat.completions.create.call_args
+ assert kwargs["response_format"] == {"type": "json_object"}
+
+
+def test_generate_response_keeps_non_json_response_format_for_compound_model(mock_groq_client):
+ config = BaseLlmConfig(model="groq/compound", temperature=0.7, max_tokens=100, top_p=1.0)
+ llm = GroqLLM(config)
+ messages = [{"role": "user", "content": "Hi, I'm Alice and I love hiking."}]
+
+ mock_response = Mock()
+ mock_response.choices = [Mock(message=Mock(content="Alice loves hiking."))]
+ mock_groq_client.chat.completions.create.return_value = mock_response
+
+ llm.generate_response(messages, response_format={"type": "text"})
+
+ _, kwargs = mock_groq_client.chat.completions.create.call_args
+ assert kwargs["response_format"] == {"type": "text"}
+
+
+def test_generate_response_keeps_tools_when_skipping_json_mode(mock_groq_client):
+ config = BaseLlmConfig(model="groq/compound", temperature=0.7, max_tokens=100, top_p=1.0)
+ llm = GroqLLM(config)
+ messages = [{"role": "user", "content": "Add a new memory: Today is a sunny day."}]
+ tools = [
+ {
+ "type": "function",
+ "function": {
+ "name": "add_memory",
+ "description": "Add a memory",
+ "parameters": {
+ "type": "object",
+ "properties": {"data": {"type": "string", "description": "Data to add to memory"}},
+ "required": ["data"],
+ },
+ },
+ }
+ ]
+
+ mock_response = Mock()
+ mock_message = Mock()
+ mock_message.content = "Done."
+ mock_message.tool_calls = None
+ mock_response.choices = [Mock(message=mock_message)]
+ mock_groq_client.chat.completions.create.return_value = mock_response
+
+ llm.generate_response(messages, response_format={"type": "json_object"}, tools=tools)
+
+ _, kwargs = mock_groq_client.chat.completions.create.call_args
+ assert "response_format" not in kwargs
+ assert kwargs["tools"] == tools
+ assert kwargs["tool_choice"] == "auto"
+
+
+def test_generate_response_handles_non_string_model(mock_groq_client):
+ config = BaseLlmConfig(model={"name": "custom-model"}, temperature=0.7, max_tokens=100, top_p=1.0)
+ llm = GroqLLM(config)
+ messages = [{"role": "user", "content": "Hi, I'm Alice and I love hiking."}]
+
+ mock_response = Mock()
+ mock_response.choices = [Mock(message=Mock(content='{"memory": []}'))]
+ mock_groq_client.chat.completions.create.return_value = mock_response
+
+ llm.generate_response(messages, response_format={"type": "json_object"})
+
+ _, kwargs = mock_groq_client.chat.completions.create.call_args
+ assert kwargs["response_format"] == {"type": "json_object"}