FlashTriage / .env.example
Chris4K's picture
Upload 19 files
39a5a79 verified
Raw
History Blame Contribute Delete
1.06 kB
# --- Cerebras (the star of the show) ---
CEREBRAS_API_KEY=
CEREBRAS_BASE_URL=https://api.cerebras.ai/v1
CEREBRAS_MODEL=gemma-4-31b
# --- Optional real baseline provider for an honest side-by-side ---
# Any OpenAI-compatible endpoint. The strongest demo is your OWN GPU:
# Ollama on the RTX 5090 -> the local-GPU-vs-Cerebras race.
#
# ollama serve # then: ollama pull gemma2 (or a gemma you have)
# BASELINE_BASE_URL=http://localhost:11434/api
# BASELINE_API_KEY=ollama
# BASELINE_MODEL=gemma2
# BASELINE_LABEL=RTX 5090 · Ollama
#
# If left blank, the "baseline" lane runs the SAME Cerebras model SEQUENTIALLY
# (a fair contrast that isolates Cerebras throughput + parallel fan-out).
BASELINE_BASE_URL=
BASELINE_API_KEY=
BASELINE_MODEL=
BASELINE_LABEL=
# --- Tuning ---
MAX_CONCURRENCY=10 # parallel analyst calls (stay under your RPM/TPM)
REMEDIATE_MIN_CVSS=7.0 # only auto-draft fixes for High/Critical (realistic prioritization)
# Force mock mode (no network) to rehearse the UI without burning quota:
USE_MOCK=0