mirror of
https://github.com/SilasMarvin/lsp-ai.git
synced 2024-07-14 15:40:26 +03:00
Cleanup vscode plugin
This commit is contained in:
Silas Marvin
parent
ffbafe39c8
commit
22092632ff
1
.gitignore
vendored
1
.gitignore
vendored
@ -4,3 +4,4 @@ node_modules
|
||||
out
|
||||
dist
|
||||
lsp-ai.log
|
||||
.vsix
|
||||
|
||||
13
README.md
13
README.md
@ -1,6 +1,6 @@
|
||||
# LSP-AI
|
||||
|
||||
LSP-AI is an open source language server that performs completion with large language models. Because it is a language server, it works with any editor that has LSP support.
|
||||
LSP-AI is an open source language server that serves as a backend for performing completion with large language models and soon other AI powered functionality. Because it is a language server, it works with any editor that has LSP support.
|
||||
|
||||
A short list of a few of the editors it works with:
|
||||
- VS Code
|
||||
@ -10,3 +10,14 @@ A short list of a few of the editors it works with:
|
||||
- Sublime
|
||||
|
||||
It works with many many many more editors.
|
||||
|
||||
See the wiki for instructions on:
|
||||
- [Installation](https://github.com/SilasMarvin/lsp-ai/wiki/Installation)
|
||||
- [Configuration](https://github.com/SilasMarvin/lsp-ai/wiki/Configuration)
|
||||
- [Plugins](https://github.com/SilasMarvin/lsp-ai/wiki/Plugins)
|
||||
- [Server Capabilities](https://github.com/SilasMarvin/lsp-ai/wiki/Server-Capabilities-and-Functions)
|
||||
- [and more](https://github.com/SilasMarvin/lsp-ai/wiki)
|
||||
|
||||
# The Case for LSP-AI
|
||||
|
||||
|
||||
|
||||
@ -31,112 +31,12 @@
|
||||
"properties": {
|
||||
"lsp-ai.serverConfiguration": {
|
||||
"type": "object",
|
||||
"default": {
|
||||
"memory": {
|
||||
"file_store": {}
|
||||
},
|
||||
"models": {
|
||||
"model1": {
|
||||
"type": "openai",
|
||||
"chat_endpoint": "https://api.openai.com/v1/chat/completions",
|
||||
"model": "gpt-4o",
|
||||
"auth_token_env_var_name": "OPENAI_API_KEY"
|
||||
}
|
||||
}
|
||||
},
|
||||
"default": {},
|
||||
"description": "JSON configuration for LSP-AI language server"
|
||||
},
|
||||
"lsp-ai.generationConfiguration": {
|
||||
"type": "object",
|
||||
"default": {
|
||||
"model": "model1",
|
||||
"parameters": {
|
||||
"max_tokens": 128,
|
||||
"max_context": 1024,
|
||||
"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.\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": "public class HelloWorld {\n public static void main(String[] args) {\n System.out.println(\"Hello, <CURSOR>\");\n }\n}"
|
||||
},
|
||||
{
|
||||
"role": "assistant",
|
||||
"content": "world"
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"content": "try:\n # Trying to open a file\n file = open(\"example.txt\", \"r\")\n # <CURSOR>\nfinally:\n file.close()"
|
||||
},
|
||||
{
|
||||
"role": "assistant",
|
||||
"content": "content = file.read()"
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"content": "#include <iostream>\nusing namespace std;\n\nint main() {\n int a = 5, b = 10;\n cout << \"Sum: \" << (a + <CURSOR>) << endl;\n return 0;\n}"
|
||||
},
|
||||
{
|
||||
"role": "assistant",
|
||||
"content": "b"
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"content": "<!DOCTYPE html>\n<html>\n<head>\n <title>My Page</title>\n</head>\n<body>\n <h1>Welcome to My Page</h1>\n <p>This is a sample page with a list of items:</p>\n <ul>\n <li>Item 1</li>\n <li>Item 2</li>\n <li><CURSOR></li>\n </ul>\n</body>\n</html>"
|
||||
},
|
||||
{
|
||||
"role": "assistant",
|
||||
"content": "Item 3"
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"content": "{CODE}"
|
||||
}
|
||||
]
|
||||
}
|
||||
},
|
||||
"default": {},
|
||||
"description": "JSON configuration for LSP-AI generation"
|
||||
}
|
||||
}
|
||||
|
||||
@ -9,6 +9,113 @@ import {
|
||||
|
||||
let client: LanguageClient;
|
||||
|
||||
// We set the default configurations here becauase VS Code tries to combine keys from defaults and user provided values which is annoying to deal with
|
||||
const defaultServerConfiguration =
|
||||
{
|
||||
"memory": {
|
||||
"file_store": {}
|
||||
},
|
||||
"models": {
|
||||
"model1": {
|
||||
"type": "openai",
|
||||
"chat_endpoint": "https://api.openai.com/v1/chat/completions",
|
||||
"model": "gpt-4o",
|
||||
"auth_token_env_var_name": "OPENAI_API_KEY"
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
const defaultGenerationConfiguration = {
|
||||
"model": "model1",
|
||||
"parameters": {
|
||||
"max_tokens": 128,
|
||||
"max_context": 1024,
|
||||
"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.\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": "public class HelloWorld {\n public static void main(String[] args) {\n System.out.println(\"Hello, <CURSOR>\");\n }\n}"
|
||||
},
|
||||
{
|
||||
"role": "assistant",
|
||||
"content": "world"
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"content": "try:\n # Trying to open a file\n file = open(\"example.txt\", \"r\")\n # <CURSOR>\nfinally:\n file.close()"
|
||||
},
|
||||
{
|
||||
"role": "assistant",
|
||||
"content": "content = file.read()"
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"content": "#include <iostream>\nusing namespace std;\n\nint main() {\n int a = 5, b = 10;\n cout << \"Sum: \" << (a + <CURSOR>) << endl;\n return 0;\n}"
|
||||
},
|
||||
{
|
||||
"role": "assistant",
|
||||
"content": "b"
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"content": "<!DOCTYPE html>\n<html>\n<head>\n <title>My Page</title>\n</head>\n<body>\n <h1>Welcome to My Page</h1>\n <p>This is a sample page with a list of items:</p>\n <ul>\n <li>Item 1</li>\n <li>Item 2</li>\n <li><CURSOR></li>\n </ul>\n</body>\n</html>"
|
||||
},
|
||||
{
|
||||
"role": "assistant",
|
||||
"content": "Item 3"
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"content": "{CODE}"
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
|
||||
export function activate(context: vscode.ExtensionContext) {
|
||||
// Configure the server options
|
||||
const serverOptions: ServerOptions = {
|
||||
@ -16,11 +123,25 @@ export function activate(context: vscode.ExtensionContext) {
|
||||
transport: TransportKind.stdio,
|
||||
};
|
||||
|
||||
// Options to control the language client
|
||||
const config = vscode.workspace.getConfiguration("lsp-ai");
|
||||
// Set the serverConfiguration
|
||||
let serverConfiguration;
|
||||
if (Object.keys(vscode.workspace.getConfiguration("lsp-ai").serverConfiguration).length != 0) {
|
||||
serverConfiguration = vscode.workspace.getConfiguration("lsp-ai").serverConfiguration;
|
||||
} else {
|
||||
serverConfiguration = defaultServerConfiguration;
|
||||
}
|
||||
|
||||
// Set the generationConfiguration
|
||||
let generationConfiguration;
|
||||
if (Object.keys(vscode.workspace.getConfiguration("lsp-ai").generationConfiguration).length != 0) {
|
||||
generationConfiguration = vscode.workspace.getConfiguration("lsp-ai").generationConfiguration;
|
||||
} else {
|
||||
generationConfiguration = defaultGenerationConfiguration;
|
||||
}
|
||||
|
||||
const clientOptions: LanguageClientOptions = {
|
||||
documentSelector: [{ scheme: "file" }],
|
||||
initializationOptions: config.serverConfiguration
|
||||
initializationOptions: serverConfiguration
|
||||
};
|
||||
|
||||
// Create the language client and start the client
|
||||
@ -37,15 +158,13 @@ export function activate(context: vscode.ExtensionContext) {
|
||||
// Register generate function
|
||||
const generateCommand = 'lsp-ai.generation';
|
||||
const generateCommandHandler = (editor: vscode.TextEditor) => {
|
||||
console.log("THE GENERATION CONFIGURATION");
|
||||
console.log(config.generationConfiguration);
|
||||
let params = {
|
||||
textDocument: {
|
||||
uri: editor.document.uri.toString(),
|
||||
},
|
||||
position: editor.selection.active,
|
||||
model: config.generationConfiguration.model,
|
||||
parameters: config.generationConfiguration.parameters
|
||||
model: generationConfiguration.model,
|
||||
parameters: generationConfiguration.parameters
|
||||
};
|
||||
client.sendRequest("textDocument/generation", params).then(result => {
|
||||
editor.edit((edit) => {
|
||||
@ -66,8 +185,8 @@ export function activate(context: vscode.ExtensionContext) {
|
||||
uri: document.uri.toString(),
|
||||
},
|
||||
position: position,
|
||||
model: config.generationConfiguration.model,
|
||||
parameters: config.generationConfiguration.parameters
|
||||
model: generationConfiguration.model,
|
||||
parameters: generationConfiguration.parameters
|
||||
};
|
||||
const result = await client.sendRequest("textDocument/generation", params);
|
||||
return [new vscode.InlineCompletionItem(result["generatedText"])];
|
||||
|
||||
Loading…
Reference in New Issue
Block a user