🔐 Mem0 is now SOC 2 and HIPAA compliant! We're committed to the highest standards of data security and privacy, enabling secure memory for enterprises, healthcare, and beyond. Learn more

​
How to define configurations?

The config is defined as a Python dictionary with two main keys:
  • llm: Specifies the llm provider and its configuration
    • provider: The name of the llm (e.g., “openai”, “groq”)
    • config: A nested dictionary containing provider-specific settings

​
Config Values Precedence

Config values are applied in the following order of precedence (from highest to lowest):
  1. Values explicitly set in the config object/dictionary
  2. Environment variables (e.g., OPENAI_API_KEY, OPENAI_BASE_URL)
  3. Default values defined in the LLM implementation
This means that values specified in the config will override corresponding environment variables, which in turn override default values.

​
How to Use Config

Here’s a general example of how to use the config with Mem0: 
import os
from mem0 import Memory

os.environ["OPENAI_API_KEY"] = "sk-xx" # for embedder

config = {
    "llm": {
        "provider": "your_chosen_provider",
        "config": {
            # Provider-specific settings go here
        }
    }
}

m = Memory.from_config(config)
m.add("Your text here", user_id="user", metadata={"category": "example"})

​
Why is Config Needed?

Config is essential for:
  1. Specifying which LLM to use.
  2. Providing necessary connection details (e.g., model, api_key, temperature).
  3. Ensuring proper initialization and connection to your chosen LLM.

​
Master List of All Params in Config

Here’s a comprehensive list of all parameters that can be used across different LLMs:
ParameterDescriptionProvider
modelEmbedding model to useAll
temperatureTemperature of the modelAll
api_keyAPI key to useAll
max_tokensTokens to generateAll
top_pProbability threshold for nucleus samplingAll
top_kNumber of highest probability tokens to keepAll
http_client_proxiesAllow proxy server settingsAzureOpenAI
modelsList of modelsOpenrouter
routeRouting strategyOpenrouter
openrouter_base_urlBase URL for Openrouter APIOpenrouter
site_urlSite URLOpenrouter
app_nameApplication nameOpenrouter
ollama_base_urlBase URL for Ollama APIOllama
openai_base_urlBase URL for OpenAI APIOpenAI
azure_kwargsAzure LLM args for initializationAzureOpenAI
deepseek_base_urlBase URL for DeepSeek APIDeepSeek
xai_base_urlBase URL for XAI APIXAI
sarvam_base_urlBase URL for Sarvam APISarvam
reasoning_effortReasoning level (low, medium, high)Sarvam
frequency_penaltyPenalize frequent tokens (-2.0 to 2.0)Sarvam
presence_penaltyPenalize existing tokens (-2.0 to 2.0)Sarvam
seedSeed for deterministic samplingSarvam
stopStop sequences (max 4)Sarvam
lmstudio_base_urlBase URL for LM Studio APILM Studio

​
Supported LLMs

For detailed information on configuring specific LLMs, please visit the LLMs section. There you’ll find information for each supported LLM with provider-specific usage examples and configuration details.