asklit/fly.toml at main · SuffolkLITLab/asklit · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
app = "asklit-scaffold-lab"
primary_region = "iad"

[build]
  dockerfile = "Dockerfile"

[env]
  APP_ENABLE_SCAFFOLDER = "true"
  APP_ACCESS_MODE = "public"
  MODEL_PROVIDER = "azure_apim"
  MODEL_NAME = "gpt-5.4-mini"
  MODEL_ALLOW_USER_SELECTION = "true"
  MODEL_ALLOWED_MODELS = "gpt-5.4-nano,gpt-5.4-mini,gpt-5.6-sol,deepseek-v4-pro,grok-4.1-fast-reasoning,llama-4-maverick,kimi-k2.6,mistral-large-3,phi-4-mini,gpt-4.1-nano,gpt-4.1-mini"
  MODEL_USE_LOCAL_EMBEDDINGS = "true"
  MODEL_LOCAL_EMBEDDING_MODEL = "all-MiniLM-L6-v2"
  LIMITS_MAX_OUTPUT_TOKENS_HARD = "4000"
  LIMITS_MAX_CONVERSATION_TURNS = "30"
  LIMITS_MAX_PROMPT_LENGTH = "2000"

[http_service]
  internal_port = 8501
  force_https = true
  auto_stop_machines = "stop"
  auto_start_machines = true
  min_machines_running = 0
  processes = ["app"]

  [http_service.concurrency]
    type = "connections"
    soft_limit = 40
    hard_limit = 60

  [[http_service.checks]]
    grace_period = "60s"
    interval = "30s"
    method = "GET"
    timeout = "5s"
    path = "/_stcore/health"

[[vm]]
  size = "shared-cpu-4x"
  memory = "4gb"

[[mounts]]
  source = "asklit_data"
  destination = "/app/data"