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.

feat(LM Studio): Add response_format param for LM Studio to config (#2502)

i-sun62c330e5b31b
diff --git a/docs/components/llms/models/lmstudio.mdx b/docs/components/llms/models/lmstudio.mdx
index 9c5195611..fa3b23474 100644
--- a/docs/components/llms/models/lmstudio.mdx
+++ b/docs/components/llms/models/lmstudio.mdx
@@ -23,6 +23,7 @@ config = {
"temperature": 0.2,
"max_tokens": 2000,
"lmstudio_base_url": "http://localhost:1234/v1", # default LM Studio API URL
+ "lmstudio_response_format": {"type": "json_schema", "json_schema": {"type": "object", "schema": {}}},
}
}
}
diff --git a/mem0/configs/llms/base.py b/mem0/configs/llms/base.py
index 271de2ef4..900556832 100644
--- a/mem0/configs/llms/base.py
+++ b/mem0/configs/llms/base.py
@@ -43,6 +43,7 @@ class BaseLlmConfig(ABC):
sarvam_base_url: Optional[str] = "https://api.sarvam.ai/v1",
# LM Studio specific
lmstudio_base_url: Optional[str] = "http://localhost:1234/v1",
+ lmstudio_response_format: dict = None,
# AWS Bedrock specific
aws_access_key_id: Optional[str] = None,
aws_secret_access_key: Optional[str] = None,
@@ -95,6 +96,8 @@ class BaseLlmConfig(ABC):
:type sarvam_base_url: Optional[str], optional
:param lmstudio_base_url: LM Studio base URL to be use, defaults to "http://localhost:1234/v1"
:type lmstudio_base_url: Optional[str], optional
+ :param lmstudio_response_format: LM Studio response format to be use, defaults to None
+ :type lmstudio_response_format: Optional[Dict], optional
"""
self.model = model
@@ -134,6 +137,7 @@ class BaseLlmConfig(ABC):
# LM Studio specific
self.lmstudio_base_url = lmstudio_base_url
+ self.lmstudio_response_format = lmstudio_response_format
# AWS Bedrock specific
self.aws_access_key_id = aws_access_key_id
diff --git a/mem0/llms/lmstudio.py b/mem0/llms/lmstudio.py
index 7e003eaf6..cdcafe555 100644
--- a/mem0/llms/lmstudio.py
+++ b/mem0/llms/lmstudio.py
@@ -46,6 +46,8 @@ class LMStudioLLM(LLMBase):
}
if response_format:
params["response_format"] = response_format
+ if self.config.lmstudio_response_format is not None:
+ params["response_format"] = self.config.lmstudio_response_format
response = self.client.chat.completions.create(**params)
return response.choices[0].message.content
diff --git a/tests/llms/test_lm_studio.py b/tests/llms/test_lm_studio.py
index bed1b98b6..37033e024 100644
--- a/tests/llms/test_lm_studio.py
+++ b/tests/llms/test_lm_studio.py
@@ -42,3 +42,30 @@ def test_generate_response_without_tools(mock_lm_studio_client):
)
assert response == "I'm doing well, thank you for asking!"
+
+def test_generate_response_specifying_response_format(mock_lm_studio_client):
+ config = BaseLlmConfig(
+ model="lmstudio-community/Meta-Llama-3.1-8B-Instruct-GGUF/Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf",
+ temperature=0.7,
+ max_tokens=100,
+ top_p=1.0,
+ lmstudio_response_format={"type": "json_schema"}, # Specifying the response format in config
+ )
+ llm = LMStudioLLM(config)
+ messages = [
+ {"role": "system", "content": "You are a helpful assistant."},
+ {"role": "user", "content": "Hello, how are you?"},
+ ]
+
+ response = llm.generate_response(messages)
+
+ mock_lm_studio_client.chat.completions.create.assert_called_once_with(
+ model="lmstudio-community/Meta-Llama-3.1-8B-Instruct-GGUF/Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf",
+ messages=messages,
+ temperature=0.7,
+ max_tokens=100,
+ top_p=1.0,
+ response_format={"type": "json_schema"},
+ )
+
+ assert response == "I'm doing well, thank you for asking!"
\ No newline at end of file