​
Full Explanation of config.yaml

We use a single config.yaml file as the source to configure Memobase Backend. An example is like this:

max_chat_blob_buffer_token_size: 1024
buffer_flush_interval: 3600

llm_api_key: YOUR-KEY
llm_base_url: https://api.openai.com/v1/

best_llm_model: gpt-4o

additional_user_profiles:
  - topic: "gaming"
    sub_topics:
      - "Soul-Like"
...

​
Storage Config

  • max_chat_blob_buffer_token_size: int, default to 1024. This is the parameter to control the buffer size of Memobase. Large the number, lower your LLM cost will be, but more lagging of profile update.
  • max_pre_profile_token_size: int, default to 512. The maximum token size of one profile slot can be. When a profile slot is larger than this, it will be trigger a re-summary.
  • max_profile_subtopics: int, default to 15. The maximum subtopics of one topic can be. When a topic has more than this, it will be trigger a re-organization.
  • persistent_chat_blobs: bool, default to false. If set to true, the chat blobs will be persisted in the database.

​
Profile Config

Check what is profile in Memobase in here

  • additional_user_profiles: list, default to []. This is the parameter to add additional user profiles. Each profile should have a topic and a list of sub_topics.
    • For topic, it must have a topic field and maybe a description field:
    additional_user_profiles:
  - topic: "gaming"
    # description: "User's gaming interests"
    sub_topics:
      ...
    • For each sub_topic, it must have a name field(or just a string) and maybe a description field:
    sub_topics:
  - "SP1"
  - name: "SP2"
    description: "Sub-Profile 2"
  • overwrite_user_profiles: list, default to null. The format is the same as additional_user_profiles. Memobase will have some built-in profile slots like work_title, name etc. If you want full control of the slots, you can use this parameter. The final profiles slots will be those you defined in here.

​
LLM Config

  • language: string, default to en, available options {'en', 'zh'}. The prompt language of Memobase you like to use.
  • llm_base_url: string, default to https://api.openai.com/v1/. The base URL of any OpenAI-Compatible API.
  • llm_api_key: string, default to null. Your LLM API key.
  • best_llm_model: string, default to gpt-4o-mini. The AI model to use.

​
Environment Variable Overrides

All configuration values can be overridden using environment variables. The naming convention is to prefix the configuration field name with MEMOBASE_ and convert it to uppercase.

For example, to override the llm_api_key configuration:

export MEMOBASE_LLM_API_KEY="your-api-key-here"

This is particularly useful for:

  • Keeping sensitive information like API keys out of configuration files
  • Deploying to different environments (development, staging, production)
  • Containerized deployments where environment variables are the preferred configuration method

For complex data types (lists, dictionaries, etc.), you can use JSON-formatted strings:

# Override additional_user_profiles with a JSON array
export MEMOBASE_ADDITIONAL_USER_PROFILES='[{"topic": "gaming", "sub_topics": ["RPG", "Strategy"]}]'

The server will automatically parse JSON-formatted environment variables when appropriate.