Skip to content

Configuration

Jump to bottom
Silas Marvin edited this page Aug 6, 2024 · 47 revisions

Overview

LSP-AI is configured by passing initializationOptions to the language server at startup. There are three configurable keys:

  • memory
  • models
  • chat
  • completion

Memory

LSP-AI keeps track of the text in all opened files during the editor session and builds prompts using this text. The memory key configures the method LSP-AI uses to track text and build prompts. Currently an empty file_store object is only one valid option for memory:

{
  "memory": {
    "file_store": {}
  }
}

There will soon be more options that allow for the usage of vector storage backends such as PostgresML. This will enable more powerful context building for prompts, and even future features like semantic search over the codebase.

Models

At server initialization, LSP-AI configures models per the models key specification. These models are then used during textDocument/completion, textDocument/generation and textDocument/codeAction requests.

There are currently four different types of configurable models:

  • llama.cpp models
  • Ollama models
  • OpenAI API compatible models
  • Anthropic API compatible models
  • Mistral AI API compatible models

The type of model is specified by setting the type parameter.

llama.cpp

LSP-AI binds directly to the llama.cpp library and runs LLMs locally.

{
  "models": {
    "model1": {
      "type": "llama_cpp",
      "repository": "stabilityai/stable-code-3b",
      "name": "stable-code-3b-Q5_K_M.gguf",
      "n_ctx": 2048,
      "n_gpu_layers": 1000
    }
  }
}

Parameters:

  • repository the HuggingFace repository the model is located in
  • name the name of the model file
  • file_path the path to a gguf file to use (either provide file_path or repository and name)
  • n_ctx the maximum number of tokens the model can process at once
  • n_gpu_layers the number of layers to offload onto the GPU
  • max_requests_per_second rate limits requests (some editors like to send a lot of completion requests)

Ollama Models

LSP-AI uses the Ollama API.

{
  "models": {
    "model1": {
      "type": "ollama",
      "model": "deepseek-coder"
    }
  }
}

Parameters:

  • model the model to use
  • chat_endpoint the chat endpoint to use. Defaults to http://localhost:11434/api/chat
  • generate_endpoint the generate endpoint to use. Defaults to http://localhost:11434/api/generate
  • max_requests_per_second rate limits requests (some editors like to send a lot of completion requests)

OpenAI Compatible APIs

LSP-AI works with any OpenAI compatible API. This means LSP-AI will work with OpenAI and any model hosted behind a compatible API. We recommend considering Groq, OpenRouter, or Fireworks AI for hosted model inference though we are sure there are other good providers out there.

Using an API provider means parts of your code may be sent to the provider in the form of a prompt. If you do not want to potentially expose your code to 3rd parties we recommend using the llama.cpp backend

{
  "models": {
    "model1": {
      "type": "open_ai",
      "chat_endpoint": "https://api.groq.com/openai/v1/chat/completions",
      "model": "llama3-70b-8192",
      "auth_token_env_var_name": "GROQ_API_KEY"
    }
  }
}

Parameters:

  • completions_endpoint is the endpoint for text completion
  • chat_endpoint is the chat endpoint to use
  • model specifies which model to use
  • auth_token_env_var_name is the environment variable name to get the authentication token from. See auth_token for more authentication options
  • auth_token is the authentication token to use. This can be used in place of auth_token_env_var_name
  • max_requests_per_second rate limits requests (some editors like to send a lot of completion requests)

Anthropic Compatible APIs

LSP-AI works with any Anthropic compatible API. This means LSP-AI will work with Anthropic and any model hosted behind a compatible API.

Using an API provider means parts of your code may be sent to the provider in the form of a LLM prompt. If you do not want to potentially expose your code to 3rd parties we recommend using the llama.cpp backend.

{
  "models": {
    "model1": {
      "type": "anthropic",
      "chat_endpoint": "https://api.anthropic.com/v1/messages",
      "model": "claude-3-haiku-20240307",
      "auth_token_env_var_name": "ANTHROPIC_API_KEY"
    }
  }
}

Parameters:

  • chat_endpoint is the chat endpoint to use
  • model specifies which model to use
  • auth_token_env_var_name is the environment variable name to get the authentication token from. See auth_token for more authentication options
  • auth_token is the authentication token to use. This can be used in place of auth_token_env_var_name
  • max_requests_per_second rate limits requests (some editors like to send a lot of completion requests)

Mistral FIM Compatible APIs

LSP-AI works with any Mistral AI FIM compatible API. This means LSP-AI will work with Mistral FIM API models and any other models that use the same FIM API.

Using an API provider means parts of your code may be sent to the provider in the form of a LLM prompt. If you do not want to potentially expose your code to 3rd parties we recommend using the llama.cpp backend.

{
  "models": {
    "model1": {
      "type": "mistral_fim",
      "fim_endpoint": "https://api.mistral.ai/v1/fim/completion",
      "model": "codestral-latest",
      "auth_token_env_var_name": "MISTRAL_API_KEY"
    }
  }
}

Parameters:

  • fim_endpoint is the endpoint for FIM
  • model specifies which model to use
  • auth_token_env_var_name is the environment variable name to get the authentication token from. See auth_token for more authentication options
  • auth_token is the authentication token to use. This can be used in place of auth_token_env_var_name
  • max_requests_per_second rate limits requests (some editors like to send a lot of completion requests)

In-Editor Chatting

LSP-AI brings support for chatting directly with models in your editor utilizing code actions.

To enable this provide the chat key in the initializationOptions. Ensure that the model(s) you specify are instruction tuned.

{
  "chat": [
    {
      "trigger": "!C",
      "action_display_name": "Chat",
      "model": "model1",
      "parameters": {
        "max_context": 4096,
        "max_tokens": 1024,
        "system": "You are a code assistant chatbot. The user will ask you for assistance coding and you will do you best to answer succinctly and accurately"
      }
    },
    {
      "trigger": "!CC",
      "action_display_name": "Chat with context",
      "model": "model1",
      "parameters": {
        "max_context": 4096,
        "max_tokens": 1024,
        "system": "You are a code assistant chatbot. The user will ask you for assistance coding and you will do you best to answer succinctly and accurately given the code context:\n\n{CONTEXT}"
      }
    }
  ]
}

In this example we are initializing two new code actions that perform chat. One called "Chat" has a simple prompt that does not include any context from our code base. The second called "Chat with context" has a slightly more complex prompt that will include context from the code base.

Note that to actually have context in the "Chat with context" action you need to use a Memory Backend that provides context (not the FileStore backend).

See the In-Editor Chatting wiki page for more information on how in-editor chatting works.

Parameters:

  • trigger is a string required to be present to enable the chat code action. It can be left blank and the code action can be used anywhere
  • action_display_name is the text displayed in the menu by your editor
  • model is the model to use for chatting. Ensure this model is instruction tuned
  • parameters are the model a parameters. Refer to the specific model backend you are using for a detailed list of available parameters

Code Completion

LSP-AI is a language server that provides support for completions. To use this feature, provide a completion key in the initializationOptions. You can disable completions by leaving out the completion key.

{
  "completion": {
    "model": "model1",
    "parameters": {}
  }
}

The model key specifies which model to use during a completion request. The value of model must be a key specified in the models key. Notice we specify the model as model1 which is the key we used in all examples above. The choice of model1 was arbitrary and can be any valid string.

The available keys in the parameters object depend on the type of model specified and which features you want enabled for the model.

Instruction

Instruction is enabled by supplying the messages key in the parameters object.

{
  "completion": {
    "model": "model1",
    "parameters": {
      "messages": [
        {
          "role": "system",
          "content": "Test"
        },
        {
          "role": "user",
          "content": "Test {CONTEXT} - {CODE}"
        }
      ],
      "max_context": 1024
    }
  }
}

Note that {CONTEXT} and {CODE} are replaced by LSP-AI with the context and code. These values are supplied by the memory backend. The file_store backend leaves the {CONTEXT} blank, and provides {CODE} around the cursor controlled by the max_context. To see the prompts being generated by LSP-AI enable debugging.

If the messages key is provided and you are using an OpenAI compatible API, be sure to provide the chat_endpoint and that the model is instruction tuned.

FIM

FIM is enabled by supplying the fim key in the parameters object.

{
  "completion": {
    "model": "model1",
    "parameters": {
      "fim": {
        "start": "<fim_prefix>",
        "middle": "<fim_suffix>",
        "end": "<fim_middle>"
      },
      "max_context": 1024
    }
  }
}

With the file_store backend, this will prepend start, insert middle at the cursor, and append end to the code around the cursor.

Note that Mistral AI FIM API compatible models don't require the fim parameters. Instead, when using mistral_fim models, FIM is enabled automatically and we do not do augment the code with special FIM tokens as the API itself presumably handles this.

Text Completion

If both messages and fim are omitted, the model performs text completion. Be sure to provide the completions_endpoint if using an OpenAI compatible API. In this case, the file_store backend will take max_context tokens before the cursor as the prompt.

Post Processing

LSP-AI can do some post processing to the responses generated by LLMs. By default LSP-AI will remove duplicate characters from the start and end of the generated text. In other words, it will try to remove characters that you have already typed and the LLM echos back to you.

This can be disabled by setting remove_duplicate_start and remove_duplicate_end to false. By default these are set to true.

{
  "completion": {
    "model": "model1",
    "parameters": {
      "max_context": 1024
    },
    "post_process": {
      "remove_duplicate_start": false,
      "remove_duplicate_end": false
    }
  }
}

Other Parameters

The other parameters available are dependent on the backend being used.

llama.cpp:

  • max_tokens restricts the number of tokens the model generates
  • chat_template the jinja template to use. Currently we use MiniJinja as the backend.
  • chat_format the chat template format to use. This is directly forwarded to llama.cpp's apply_chat_template function.

Ollama:

OpenAI:

Anthropic:

Mistral FIM:

Example Configurations

llama.cpp

In-Editor Chatting

{
  "memory": {
    "file_store": {}
  },
  "models": {
    "model1": {
      "type": "llama_cpp",
      "repository": "QuantFactory/Meta-Llama-3-70B-Instruct-GGUF-v2",
      "name": "Meta-Llama-3-70B-Instruct-v2.Q5_K_M.gguf",
      "n_ctx": 6000
    }
  },
  "chat": [
    {
      "trigger": "!C",
      "action_display_name": "Chat",
      "model": "model1",
      "parameters": {
        "max_context": 4096,
        "max_tokens": 1024,
        "messages": [
          {
            "role": "system",
            "content": "You are a code assistant chatbot. The user will ask you for assistance coding and you will do you best to answer succinctly and accurately"
          }
        ]
      }
    }
  ]
}

FIM Code Completion

{
  "memory": {
    "file_store": {}
  },
  "models": {
    "model1": {
      "type": "llama_cpp",
      "repository": "stabilityai/stable-code-3b",
      "name": "stable-code-3b-Q5_K_M.gguf",
      "n_ctx": 2048
    }
  },
  "completion": {
    "model": "model1",
    "parameters": {
      "fim": {
        "start": "<fim_prefix>",
        "middle": "<fim_suffix>",
        "end": "<fim_middle>"
      },
      "max_context": 2000,
      "max_tokens": 32
    }
  }
}

Instruction Code Completion

{
  "memory": {
    "file_store": {}
  },
  "models": {
    "model1": {
      "type": "llama_cpp",
      "repository": "QuantFactory/Meta-Llama-3-70B-Instruct-GGUF-v2",
      "name": "Meta-Llama-3-70B-Instruct-v2.Q5_K_M.gguf",
      "n_ctx": 2048
    }
  },
  "completion": {
    "model": "model1",
    "parameters": {
      "max_context": 1800,
      "max_tokens": 32,
      "messages": [
        {
          "role": "system",
          "content": "Instructions:\n- You are an AI programming assistant.\n- Given a piece of code with the cursor location marked by \"<CURSOR>\", replace \"<CURSOR>\" with the correct code or comment.\n- First, think step-by-step.\n- Describe your plan for what to build in pseudocode, written out in great detail.\n- Then output the code replacing the \"<CURSOR>\"\n- Ensure that your completion fits within the language context of the provided code snippet (e.g., Python, JavaScript, Rust).\n\nRules:\n- Only respond with code or comments.\n- Only replace \"<CURSOR>\"; do not include any previously written code.\n- Never include \"<CURSOR>\" in your response\n- If the cursor is within a comment, complete the comment meaningfully.\n- Handle ambiguous cases by providing the most contextually appropriate completion.\n- Be consistent with your responses."
        },
        {
          "role": "user",
          "content": "def greet(name):\n    print(f\"Hello, {<CURSOR>}\")"
        },
        {
          "role": "assistant",
          "content": "name"
        },
        {
          "role": "user",
          "content": "function sum(a, b) {\n    return a + <CURSOR>;\n}"
        },
        {
          "role": "assistant",
          "content": "b"
        },
        {
          "role": "user",
          "content": "fn multiply(a: i32, b: i32) -> i32 {\n    a * <CURSOR>\n}"
        },
        {
          "role": "assistant",
          "content": "b"
        },
        {
          "role": "user",
          "content": "# <CURSOR>\ndef add(a, b):\n    return a + b"
        },
        {
          "role": "assistant",
          "content": "Adds two numbers"
        },
        {
          "role": "user",
          "content": "# This function checks if a number is even\n<CURSOR>"
        },
        {
          "role": "assistant",
          "content": "def is_even(n):\n    return n % 2 == 0"
        },
        {
          "role": "user",
          "content": "{CODE}"
        }
      ]
    }
  }
}

Code Completion

{
  "memory": {
    "file_store": {}
  },
  "models": {
    "model1": {
      "type": "llama_cpp",
      "repository": "TheBloke/deepseek-coder-6.7B-instruct-GGUF",
      "name": "deepseek-coder-6.7b-instruct.Q5_K_S.gguf",
      "n_ctx": 2048
    }
  },
  "completion": {
    "model": "model1",
    "parameters": {
      "max_context": 2000,
      "max_tokens": 32
    }
  }
}

Ollama

In-Editor Chatting

{
  "memory": {
    "file_store": {}
  },
  "models": {
    "model1": {
      "type": "ollama",
      "model": "llama3"
    }
  },
  "chat": [
    {
      "trigger": "!C",
      "action_display_name": "Chat",
      "model": "model1",
      "parameters": {
        "max_context": 4096,
        "max_tokens": 1024,
        "messages": [
          {
            "role": "system",
            "content": "You are a code assistant chatbot. The user will ask you for assistance coding and you will do you best to answer succinctly and accurately"
          }
        ]
      }
    }
  ]
}

FIM Code Completion

{
  "memory": {
    "file_store": {}
  },
  "models": {
    "model1": {
      "type": "ollama",
      "model": "deepseek-coder"
    }
  },
  "completion": {
    "model": "model1",
    "parameters": {
      "fim": {
        "start": "<｜fim▁begin｜>",
        "middle": "<｜fim▁hole｜>",
        "end": "<｜fim▁end｜>"
      },
      "max_context": 2000,
      "options": {
        "num_predict": 32
      }
    }
  }
}

Instruction Code Completion

{
  "memory": {
    "file_store": {}
  },
  "models": {
    "model1": {
      "type": "ollama",
      "model": "llama3"
    }
  },
  "completion": {
    "model": "model1",
    "parameters": {
      "max_context": 1800,
      "options": {
        "num_predict": 32
      },
      "system": "Instructions:\n- You are an AI programming assistant.\n- Given a piece of code with the cursor location marked by \"<CURSOR>\", replace \"<CURSOR>\" with the correct code or comment.\n- First, think step-by-step.\n- Describe your plan for what to build in pseudocode, written out in great detail.\n- Then output the code replacing the \"<CURSOR>\"\n- Ensure that your completion fits within the language context of the provided code snippet (e.g., Python, JavaScript, Rust).\n\nRules:\n- Only respond with code or comments.\n- Only replace \"<CURSOR>\"; do not include any previously written code.\n- Never include \"<CURSOR>\" in your response\n- If the cursor is within a comment, complete the comment meaningfully.\n- Handle ambiguous cases by providing the most contextually appropriate completion.\n- Be consistent with your responses.",
      "messages": [
        {
          "role": "user",
          "content": "def greet(name):\n    print(f\"Hello, {<CURSOR>}\")"
        },
        {
          "role": "assistant",
          "content": "name"
        },
        {
          "role": "user",
          "content": "function sum(a, b) {\n    return a + <CURSOR>;\n}"
        },
        {
          "role": "assistant",
          "content": "b"
        },
        {
          "role": "user",
          "content": "fn multiply(a: i32, b: i32) -> i32 {\n    a * <CURSOR>\n}"
        },
        {
          "role": "assistant",
          "content": "b"
        },
        {
          "role": "user",
          "content": "# <CURSOR>\ndef add(a, b):\n    return a + b"
        },
        {
          "role": "assistant",
          "content": "Adds two numbers"
        },
        {
          "role": "user",
          "content": "# This function checks if a number is even\n<CURSOR>"
        },
        {
          "role": "assistant",
          "content": "def is_even(n):\n    return n % 2 == 0"
        },
        {
          "role": "user",
          "content": "{CODE}"
        }
      ]
    }
  }
}

Code Completion

{
  "memory": {
    "file_store": {}
  },
  "models": {
    "model1": {
      "type": "ollama",
      "model": "deepseek-coder"
    }
  },
  "completion": {
    "model": "model1",
    "parameters": {
      "max_context": 2000,
      "options": {
        "num_predict": 32
      }
    }
  }
}

OpenAI Compatible APIs

In-Editor Chatting

{
  "memory": {
    "file_store": {}
  },
  "models": {
    "model1": {
      "type": "open_ai",
      "chat_endpoint": "https://api.openai.com/v1/chat/completions",
      "model": "gpt-4o",
      "auth_token_env_var_name": "OPENAI_API_KEY"
    }
  },
  "chat": [
    {
      "trigger": "!C",
      "action_display_name": "Chat",
      "model": "model1",
      "parameters": {
        "max_context": 4096,
        "max_tokens": 1024,
        "messages": [
          {
            "role": "system",
            "content": "You are a code assistant chatbot. The user will ask you for assistance coding and you will do you best to answer succinctly and accurately"
          }
        ]
      }
    }
  ]
}

Instruction Code Completion

{
  "memory": {
    "file_store": {}
  },
  "models": {
    "model1": {
      "type": "open_ai",
      "chat_endpoint": "https://api.openai.com/v1/chat/completions",
      "model": "gpt-4o",
      "auth_token_env_var_name": "OPENAI_API_KEY"
    }
  },
  "completion": {
    "model": "model1",
    "parameters": {
      "max_context": 2048,
      "max_tokens": 128,
      "messages": [
        {
          "role": "system",
          "content": "Instructions:\n- You are an AI programming assistant.\n- Given a piece of code with the cursor location marked by \"<CURSOR>\", replace \"<CURSOR>\" with the correct code or comment.\n- First, think step-by-step.\n- Describe your plan for what to build in pseudocode, written out in great detail.\n- Then output the code replacing the \"<CURSOR>\"\n- Ensure that your completion fits within the language context of the provided code snippet (e.g., Python, JavaScript, Rust).\n\nRules:\n- Only respond with code or comments.\n- Only replace \"<CURSOR>\"; do not include any previously written code.\n- Never include \"<CURSOR>\" in your response\n- If the cursor is within a comment, complete the comment meaningfully.\n- Handle ambiguous cases by providing the most contextually appropriate completion.\n- Be consistent with your responses."
        },
        {
          "role": "user",
          "content": "def greet(name):\n    print(f\"Hello, {<CURSOR>}\")"
        },
        {
          "role": "assistant",
          "content": "name"
        },
        {
          "role": "user",
          "content": "function sum(a, b) {\n    return a + <CURSOR>;\n}"
        },
        {
          "role": "assistant",
          "content": "b"
        },
        {
          "role": "user",
          "content": "fn multiply(a: i32, b: i32) -> i32 {\n    a * <CURSOR>\n}"
        },
        {
          "role": "assistant",
          "content": "b"
        },
        {
          "role": "user",
          "content": "# <CURSOR>\ndef add(a, b):\n    return a + b"
        },
        {
          "role": "assistant",
          "content": "Adds two numbers"
        },
        {
          "role": "user",
          "content": "# This function checks if a number is even\n<CURSOR>"
        },
        {
          "role": "assistant",
          "content": "def is_even(n):\n    return n % 2 == 0"
        },
        {
          "role": "user",
          "content": "{CODE}"
        }
      ]
    }
  }
}

FIM Code Completion

{
  "memory": {
    "file_store": {}
  },
  "models": {
    "model1": {
      "type": "open_ai",
      "completions_endpoint": "https://api.fireworks.ai/inference/v1/completions",
      "model": "accounts/fireworks/models/starcoder-16b",
      "auth_token_env_var_name": "FIREWORKS_API_KEY"
    }
  },
  "completion": {
    "model": "model1",
    "parameters": {
      "max_context": 2048,
      "max_tokens": 128,
      "fim": {
        "start": "<fim_prefix>",
        "middle": "<fim_middle>",
        "end": "<fim_suffix>"
      }
    }
  }
}

Code Completion

{
  "memory": {
    "file_store": {}
  },
  "models": {
    "model1": {
      "type": "open_ai",
      "completions_endpoint": "https://api.fireworks.ai/inference/v1/completions",
      "model": "accounts/fireworks/models/starcoder-16b",
      "auth_token_env_var_name": "FIREWORKS_API_KEY"
    }
  },
  "completion": {
    "model": "model1",
    "parameters": {
      "max_context": 2048,
      "max_tokens": 128
    }
  }
}

Anthropic Compatible APIs

In-Editor Chatting

{
  "memory": {
    "file_store": {}
  },
  "models": {
    "model1": {
      "type": "anthropic",
      "chat_endpoint": "https://api.anthropic.com/v1/messages",
      "model": "claude-3-haiku-20240307",
      "auth_token_env_var_name": "ANTHROPIC_API_KEY"
    }
  },
  "chat": [
    {
      "trigger": "!C",
      "action_display_name": "Chat",
      "model": "model1",
      "parameters": {
        "max_context": 4096,
        "max_tokens": 1024,
        "system": "You are a code assistant chatbot. The user will ask you for assistance coding and you will do you best to answer succinctly and accurately"
      }
    }
  ]
}

Instruction Code Completion

{
  "memory": {
    "file_store": {}
  },
  "models": {
    "model1": {
      "type": "anthropic",
      "chat_endpoint": "https://api.anthropic.com/v1/messages",
      "model": "claude-3-haiku-20240307",
      "auth_token_env_var_name": "ANTHROPIC_API_KEY"
    }
  },
  "completion": {
    "model": "model1",
    "parameters": {
      "max_context": 2048,
      "max_tokens": 128,
      "system": "Instructions:\n- You are an AI programming assistant.\n- Given a piece of code with the cursor location marked by \"<CURSOR>\", replace \"<CURSOR>\" with the correct code or comment.\n- First, think step-by-step.\n- Describe your plan for what to build in pseudocode, written out in great detail.\n- Then output the code replacing the \"<CURSOR>\"\n- Ensure that your completion fits within the language context of the provided code snippet (e.g., Python, JavaScript, Rust).\n\nRules:\n- Only respond with code or comments.\n- Only replace \"<CURSOR>\"; do not include any previously written code.\n- Never include \"<CURSOR>\" in your response\n- If the cursor is within a comment, complete the comment meaningfully.\n- Handle ambiguous cases by providing the most contextually appropriate completion.\n- Be consistent with your responses.",
      "messages": [
        {
          "role": "user",
          "content": "def greet(name):\n    print(f\"Hello, {<CURSOR>}\")"
        },
        {
          "role": "assistant",
          "content": "name"
        },
        {
          "role": "user",
          "content": "function sum(a, b) {\n    return a + <CURSOR>;\n}"
        },
        {
          "role": "assistant",
          "content": "b"
        },
        {
          "role": "user",
          "content": "fn multiply(a: i32, b: i32) -> i32 {\n    a * <CURSOR>\n}"
        },
        {
          "role": "assistant",
          "content": "b"
        },
        {
          "role": "user",
          "content": "# <CURSOR>\ndef add(a, b):\n    return a + b"
        },
        {
          "role": "assistant",
          "content": "Adds two numbers"
        },
        {
          "role": "user",
          "content": "# This function checks if a number is even\n<CURSOR>"
        },
        {
          "role": "assistant",
          "content": "def is_even(n):\n    return n % 2 == 0"
        },
        {
          "role": "user",
          "content": "{CODE}"
        }
      ]
    }
  }
}

Mistral FIM Compatible APIs

FIM Code Completion

{
  "memory": {
    "file_store": {}
  },
  "models": {
    "model1": {
      "type": "mistral_fim",
      "fim_endpoint": "https://api.mistral.ai/v1/fim/completion",
      "model": "codestral-latest",
      "auth_token_env_var_name": "MISTRAL_API_KEY"
    }
  },
  "completion": {
    "model": "model1",
    "parameters": {
      "max_tokens": 64
    }
  }
}
Clone this wiki locally