orio-search/config.yaml at master · vkfolio/orio-search · 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
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
server:
  host: "0.0.0.0"
  port: 8000

search:
  backend: "searxng"  # "searxng" | "duckduckgo"
  searxng_url: "http://searxng:8080"
  google_api_key: ""
  google_cx: ""

extraction:
  max_concurrent: 5
  timeout: 10
  max_content_length: 50000
  domain_concurrency: 2
  domain_semaphore_max_size: 1000
  user_agents:
    - "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36"
    - "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36"
    - "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:133.0) Gecko/20100101 Firefox/133.0"
    - "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/18.2 Safari/605.1.15"
    - "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36"
    - "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36 Edg/131.0.0.0"
    - "Mozilla/5.0 (X11; Linux x86_64; rv:133.0) Gecko/20100101 Firefox/133.0"
    - "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.15; rv:133.0) Gecko/20100101 Firefox/133.0"
    - "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:133.0) Gecko/20100101 Firefox/133.0"
    - "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/130.0.0.0 Safari/537.36"

cache:
  enabled: true
  redis_url: "redis://redis:6379"
  search_ttl: 3600
  extract_ttl: 86400

proxy:
  enabled: false
  url: ""

auth:
  enabled: false
  api_keys: []
  # api_keys:
  #   - "your-secret-key-here"

rate_limit:
  enabled: false
  default_rate: "60/minute"
  search_rate: "30/minute"
  extract_rate: "30/minute"

rerank:
  enabled: false
  model: "ms-marco-MiniLM-L-12-v2"
  top_k: 5

resilience:
  circuit_breaker_failure_threshold: 5
  circuit_breaker_recovery_timeout: 30
  retry_max_attempts: 3
  retry_backoff_base: 0.5
  retry_on_status_codes: [429, 503, 502, 504]
  request_timeout: 120
  backend_fallback: true

logging:
  format: "json"    # "json" | "console"
  level: "INFO"

cors:
  allow_origins: ["*"]

llm:
  enabled: true
  provider: "ollama"         # label for logs (ollama, openai, groq, etc.)
  base_url: "http://host.docker.internal:11434/v1"   # host Ollama with GPU (must end with /v1)
  api_key: "ollama"          # "ollama" for local, real key for cloud providers
  model: "qwen3.5:9b"
  max_tokens: 1024
  temperature: 0.1
  timeout: 120
  # system_prompt: "Custom system prompt here"
  # max_context_results: 5
  # max_context_chars: 8000
  # answer_ttl: 3600
  #
  # --- Other provider examples ---
  # OpenAI:
  #   base_url: "https://api.openai.com/v1"
  #   api_key: "sk-..."
  #   model: "gpt-4o-mini"
  # Groq:
  #   base_url: "https://api.groq.com/openai/v1"
  #   api_key: "gsk_..."
  #   model: "llama-3.1-70b-versatile"
  # Together AI:
  #   base_url: "https://api.together.xyz/v1"
  #   api_key: "..."
  #   model: "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo"