config_template.yml

# {{ index .Help "model" }}
default-model: gpt-4o
# {{ index .Help "format-text" }}
format-text:
  markdown: '{{ index .Config.FormatText "markdown" }}'
  json: '{{ index .Config.FormatText "json" }}'
# {{ index .Help "roles" }}
roles:
  "default": []
  # Example, a role called `shell`:
  # shell:
  #   - you are a shell expert
  #   - you do not explain anything
  #   - you simply output one liners to solve the problems you're asked
  #   - you do not provide any explanation whatsoever, ONLY the command
# {{ index .Help "format" }}
format: false
# {{ index .Help "role" }}
role: "default"
# {{ index .Help "raw" }}
raw: false
# {{ index .Help "quiet" }}
quiet: false
# {{ index .Help "temp" }}
temp: 1.0
# {{ index .Help "topp" }}
topp: 1.0
# {{ index .Help "topk" }}
topk: 50
# {{ index .Help "no-limit" }}
no-limit: false
# {{ index .Help "word-wrap" }}
word-wrap: 80
# {{ index .Help "prompt-args" }}
include-prompt-args: false
# {{ index .Help "prompt" }}
include-prompt: 0
# {{ index .Help "max-retries" }}
max-retries: 5
# {{ index .Help "fanciness" }}
fanciness: 10
# {{ index .Help "status-text" }}
status-text: Generating
# {{ index .Help "theme" }}
theme: charm
# {{ index .Help "max-input-chars" }}
max-input-chars: 12250
# {{ index .Help "max-tokens" }}
# max-tokens: 100
# {{ index .Help "apis" }}
apis:
  openai:
    base-url: https://api.openai.com/v1
    api-key:
    api-key-env: OPENAI_API_KEY
    models: # https://platform.openai.com/docs/models
      gpt-4o-mini:
        aliases: ["4o-mini"]
        max-input-chars: 392000
        fallback: gpt-4o
      gpt-4o:
        aliases: ["4o"]
        max-input-chars: 392000
        fallback: gpt-4
      gpt-4:
        aliases: ["4"]
        max-input-chars: 24500
        fallback: gpt-3.5-turbo
      gpt-4-1106-preview:
        aliases: ["128k"]
        max-input-chars: 392000
        fallback: gpt-4
      gpt-4-32k:
        aliases: ["32k"]
        max-input-chars: 98000
        fallback: gpt-4
      gpt-3.5-turbo:
        aliases: ["35t"]
        max-input-chars: 12250
        fallback: gpt-3.5
      gpt-3.5-turbo-1106:
        aliases: ["35t-1106"]
        max-input-chars: 12250
        fallback: gpt-3.5-turbo
      gpt-3.5-turbo-16k:
        aliases: ["35t16k"]
        max-input-chars: 44500
        fallback: gpt-3.5
      gpt-3.5:
        aliases: ["35"]
        max-input-chars: 12250
        fallback:
  copilot:
    base-url: https://api.githubcopilot.com
  anthropic:
    base-url: https://api.anthropic.com/v1
    api-key:
    api-key-env: ANTHROPIC_API_KEY
    models: # https://docs.anthropic.com/en/docs/about-claude/models
      claude-3-5-sonnet-20240620:
        aliases: ["claude3.5-sonnet", "claude-3-5-sonnet", "sonnet-3.5"]
        max-input-chars: 680000
      claude-3-opus-20240229:
        aliases: ["claude3-opus", "opus"]
        max-input-chars: 680000
  cohere:
    base-url: https://api.cohere.com/v1
    models:
      command-r-plus:
        max-input-chars: 128000
      command-r:
        max-input-chars: 128000
  google:
    models:
      gemini-1.5-pro-latest:
        aliases: ["gemini"]
        max-input-chars: 392000
      gemini-1.5-flash-latest:
        aliases: ["flash"]
        max-input-chars: 392000
  ollama:
    base-url: http://localhost:11434/api
    models: # https://ollama.com/library
      "llama3:70b":
        aliases: ["llama3"]
        max-input-chars: 650000
  perplexity:
    base-url: https://api.perplexity.ai
    api-key:
    api-key-env: PERPLEXITY_API_KEY
    models: # https://docs.perplexity.ai/docs/model-cards
      llama-3-sonar-small-32k-chat:
        aliases: ["llama3-ss"]
        max-input-chars: 32768
      llama-3-sonar-small-32k-online:
        aliases: ["llam3-sso"]
        max-input-chars: 28000
      llama-3-sonar-large-32k-chat:
        aliases: ["llam3-sl"]
        max-input-chars: 32768
      llama-3-sonar-large-32k-online:
        aliases: ["llam3-slo"]
        max-input-chars: 28000
      llama-3-8b-instruct:
        aliases: ["llam3-8bi"]
        max-input-chars: 8192
      llama-3-70b-instruct:
        aliases: ["llam3-70bi"]
        max-input-chars: 8192
  groq:
    base-url: https://api.groq.com/openai/v1
    api-key:
    api-key-env: GROQ_API_KEY
    models: # https://console.groq.com/docs/models
      gemma-7b-it:
        aliases: ["gemma"]
        max-input-chars: 24500
      gemma2-9b-it:
        aliases: ["gemma2"]
        max-input-chars: 24500
      llama3-70b-8192:
        aliases: ["llama3", "llama3-70b"]
        max-input-chars: 24500
        fallback: llama3-8b-8192
      llama3-8b-8192:
        aliases: ["llama3-8b"]
        max-input-chars: 24500
      mixtral-8x7b-32768:
        aliases: ["mixtral"]
        max-input-chars: 98000
  localai:
    # LocalAI setup instructions: https://github.com/go-skynet/LocalAI#example-use-gpt4all-j-model
    base-url: http://localhost:8080
    models:
      ggml-gpt4all-j:
        aliases: ["local", "4all"]
        max-input-chars: 12250
        fallback:
  azure:
    # Set to 'azure-ad' to use Active Directory
    # Azure OpenAI setup: https://learn.microsoft.com/en-us/azure/cognitive-services/openai/how-to/create-resource
    base-url: https://YOUR_RESOURCE_NAME.openai.azure.com
    api-key:
    api-key-env: AZURE_OPENAI_KEY
    models:
      gpt-4:
        aliases: ["az4"]
        max-input-chars: 24500
        fallback: gpt-35-turbo
      gpt-35-turbo:
        aliases: ["az35t"]
        max-input-chars: 12250
        fallback: gpt-35
      gpt-35:
        aliases: ["az35"]
        max-input-chars: 12250
        fallback:
  runpod:
    # https://docs.runpod.io/serverless/workers/vllm/openai-compatibility
    base-url: https://api.runpod.ai/v2/${YOUR_ENDPOINT}/openai/v1
    api-key:
    api-key-env: RUNPOD_API_KEY
    models:
      openchat/openchat-3.5-1210:
        aliases: ["openchat"]
        max-input-chars: 8192
  mistral:
    base-url: https://api.mistral.ai/v1
    api-key:
    api-key-env: MISTRAL_API_KEY
    models: # https://docs.mistral.ai/getting-started/models/
      mistral-large-latest:
        aliases: ["mistral-large"]
        max-input-chars: 384000
      open-mistral-nemo:
        aliases: ["mistral-nemo"]
        max-input-chars: 384000
  deepseek:
    base-url: https://api.deepseek.com/
    api-key:
    api-key-env: DEEPSEEK_API_KEY
    models: # https://platform.deepseek.com/api-docs/api/list-models/
      deepseek-chat:
        aliases: ["ds-chat"]
        max-input-chars: 384000
      deepseek-code:
        aliases: ["ds-code"]
        max-input-chars: 384000