ollama-chat-interface/config.yaml at master · shrimpy8/ollama-chat-interface · 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
# Ollama Chat Interface - Configuration File
# ==========================================
# This file contains all customizable settings for the chat interface.
# You can modify these settings without changing the code.

# Ollama Server Configuration
ollama:
  base_url: "http://localhost:11434"
  api_endpoint: "/api/generate"
  model_name: "deepseek-r1:8b"

  # Model Parameters
  parameters:
    temperature: 0.7        # Creativity level (0.0 = deterministic, 1.0 = creative)
    top_p: 0.9             # Nucleus sampling
    top_k: 40              # Top-k sampling
    num_predict: 2048      # Maximum tokens to generate

# Request Configuration
request:
  timeout: 120             # Timeout in seconds for API requests
  retry:
    max_attempts: 3        # Maximum retry attempts for failed requests
    min_wait: 2            # Minimum wait time between retries (seconds)
    max_wait: 10           # Maximum wait time between retries (seconds)
    multiplier: 2          # Exponential backoff multiplier

# Logging Configuration
logging:
  level: "INFO"            # Logging level: DEBUG, INFO, WARNING, ERROR, CRITICAL
  format: "%(asctime)s - %(name)s - %(levelname)s - %(message)s"
  file: "ollama_chat.log"  # Log file name
  console: true            # Enable console logging
  file_logging: true       # Enable file logging

# Gradio UI Configuration
ui:
  title: "DeepSeek-R1 AI Chat Interface"
  description: "Chat with DeepSeek-R1 model via local Ollama server"
  theme: "default"         # Gradio theme: default, soft, monochrome
  share: false             # Enable public sharing via gradio.live link
  server:
    port: 7860             # Port to run the server on
    host: "127.0.0.1"      # Host address (127.0.0.1 for local only)

  # Interface Components
  components:
    input:
      placeholder: "Type your message here..."
      lines: 3
      max_lines: 10
    output:
      placeholder: "Response will appear here..."
      lines: 10

  # Chat History
  history:
    max_messages: 20       # Maximum number of messages to keep in history
    show_timestamps: true  # Show timestamps in chat history

# Conversation Settings
conversation:
  system_prompt: "You are a helpful AI assistant powered by DeepSeek-R1."
  memory_enabled: true     # Enable conversation memory
  context_window: 4096     # Maximum context window in tokens