Skip to content

Latest commit

 

History

History
46 lines (32 loc) · 2.72 KB

.env.markdown

File metadata and controls

46 lines (32 loc) · 2.72 KB

Environment file info

If you're running in production, you should set these securely.

However, if you just want to experiment, set the following values

AI Settings

  • INPUT_TOKEN_LIMIT: 15000
    • (REQUIRED IF USING AI MODES) Ensure the input/output token count meets requirements and is supported by the model selected. Will not allow files with more than tokens specified to be processed
  • TEMPERATURE: 0.0
    • The temperature value ranges from 0 to 2, with lower values indicating greater determinism and higher values indicating more randomness in responses.

A small note on selecting a provider

Below are the models you can use. We highly recommend using OpenRouter (OPENROUTER_API_KEY) which gives you access to a wide range of models / providers. There is no benefit in function to using one provider over another (the txt2detection logic is the same for all). We provide the option to use provider supplied API keys (e.g. OPENAI_API_KEY) for those who cannot / do not want to use OpenRouter.

CTIBUTLER

txt2detection requires ctibutler to lookup ATT&CK

  • CTIBUTLER_BASE_URL: 'http://api.ctibutler.com' (recommended)
    • If you are running CTI Butler locally, be sure to set 'http://host.docker.internal:8006/api/' in the .env file otherwise you will run into networking errors.
  • CTIBUTLER_BASE_URL:

VULMATCH

txt2detection requires vulmatch to lookup CVE IDs

  • VULMATCH_BASE_URL: 'http://api.vulmatch.com' (recommended)
    • If you are running CTI Butler locally, be sure to set 'http://host.docker.internal:8005/api/' in the .env file otherwise you will run into networking errors.
  • VULMATCH_BASE_URL: