Guide · Reference

Configuration

Keep the local pipeline useful on its own, then make the remote handoff explicit with a small set of environment variables.

Minimum connection settings

Mneme uses an OpenAI-compatible endpoint for LLM-backed work. Set these values in .env, or let the onboarding wizard save them for you.

API_KEY=sk-your-api-key-here\nBASE_URL=https://api.deepseek.com/v1\nLLM_MODEL=deepseek-chat
Endpoint boundary

Remote endpoints must use HTTPS by default. Plain HTTP is permitted for loopback addresses. A non-local HTTP endpoint requires MNEME_ALLOW_INSECURE_HTTP=1.

Retrieval and generation

VariableDefaultPurpose
LLM_TEMPERATURE0.2Generation temperature.
LLM_TOP_K_MIN12Minimum chunks for standard retrieval.
LLM_TOP_K_MAX70Maximum chunks for standard retrieval.
ALPHA0.7Graph RAG fusion weight.
EMBEDDING_MODEL_NAMEall-MiniLM-L6-v2Model identifier for local loading.

Resource limits

VariableDefaultPurpose
MNEME_MAX_DOCUMENT_BYTES52428800Maximum document size: 50 MiB.
MNEME_MAX_PDF_PAGES2000Maximum PDF pages.
MNEME_MAX_REMOTE_CONTEXT_CHARS60000Maximum retrieved context sent to an endpoint.
MNEME_DOCUMENT_ROOTunsetOptional root allowed for indexed files.

What can leave the machine

File discovery, parsing, indexing, cache management, and vector/BM25 retrieval run locally. When an LLM-backed feature is used, retrieved snippets are sent to your configured endpoint for answer generation, query decomposition, or Graph RAG entity extraction.

Search Mneme documentation