[{"result":{"data":[{"id":"f85baaab-da6d-4221-b146-76623558fe5c","title":"feat!: range commands - same command across modes (MR: #7, Issue: #5)","text":"feat!: range commands - same command across modes (MR: #7, Issue: #5)\n\n* feat: range commands - same command across modes\r\n\r\n* docs: update README.md\r\n\r\nBREAKING CHANGE:\r\n`GpVisual*` commands no longer exist, please update your shortcuts according to README","type":"breaking-change","createdAt":"2023-07-25T17:17:47.631Z","breakingChange":{"id":15,"postId":"f85baaab-da6d-4221-b146-76623558fe5c","pluginId":129200,"externalUrl":"https://github.com/Robitx/gp.nvim/commit/05d685a8894f54e9f4061230f0781b438cfc4a76","sha":"05d685a8894f54e9f4061230f0781b438cfc4a76","plugin":{"id":129200,"owner":"Robitx","name":"gp.nvim","type":"github","source":"awesome-neovim","category":"ai","link":"https://github.com/Robitx/gp.nvim","shortDescription":"Gp.nvim (GPT prompt) Neovim AI plugin: ChatGPT sessions & Instructable text/code operations & Speech to text [OpenAI]","createdAt":"2023-07-25T11:38:44.449Z","readme":"# Gp (GPT prompt) plugin for Neovim\n\n $\"GitHub\"$ \n $\"GitHub$ \n $\"GitHub$ \n $\"GitHub$ \n $\"GitHub$ \n $\"Static$ \n\nGp.nvim provides you ChatGPT like sessions and instructable text/code operations in your favorite editor.\n\n

\n\n\n

\n\n### [Here is an older 5 minute example of using the plugin (needs update)](https://www.youtube.com/watch?v=wPDcBnQgNCc)\n\n## Goals and Features\n\nThe goal is to extend Neovim with the **power of GPT models in a simple unobtrusive extensible way.** \nTrying to keep things as native as possible - reusing and integrating well with the natural features of (Neo)vim.\n\n- **Streaming responses**\n - no spinner wheel and waiting for the full answer\n - response generation can be canceled half way through\n - properly working undo (response can be undone with a single `u`)\n- **Infinitely extensible** via hook functions specified as part of the config\n - hooks have access to everything in the plugin and are automatically registered as commands\n - see [Configuration](#4-configuration) and [Extend functionality](#extend-functionality) sections for details\n- **Minimum dependencies** (`neovim`, `curl`, `grep` and optionally `sox`)\n - zero dependencies on other lua plugins to minimize chance of breakage\n- **ChatGPT like sessions**\n - just good old neovim buffers formated as markdown with autosave and few buffer bound shortcuts\n - last chat also quickly accessible via toggable popup window\n - chat finder - management popup for searching, previewing, deleting and opening chat sessions\n- **Instructable text/code operations**\n - templating mechanism to combine user instructions, selections etc into the gpt query\n - multimodal - same command works for normal/insert mode, with selection or a range\n - many possible output targets - rewrite, prepend, append, new buffer, popup\n - non interactive command mode available for common repetitive tasks implementable as simple hooks \n (explain something in a popup window, write unit tests for selected code into a new buffer, \n finish selected code based on comments in it, etc.)\n - custom instructions per repository with `.gp.md` file \n (instruct gpt to generate code using certain libs, packages, conventions and so on)\n- **Speech to text support**\n - a mouth is 2-4x faster than fingers when it comes to outputting words - use it where it makes sense \n (dicating comments and notes, asking gpt questions, giving instructions for code operations, ..)\n\n## Install\n\n### 1. Install the plugin with your preferred package manager:\n\n```lua\n-- lazy.nvim\n{\n\t\"robitx/gp.nvim\",\n\tconfig = function()\n\t\trequire(\"gp\").setup()\n\n\t\t-- or setup with your own config (see Install > Configuration in Readme)\n\t\t-- require(\"gp\").setup(config)\n\n \t-- shortcuts might be setup here (see Usage > Shortcuts in Readme)\n\tend,\n}\n```\n\n```lua\n-- packer.nvim\nuse({\n \"robitx/gp.nvim\",\n config = function()\n require(\"gp\").setup()\n\n\t-- or setup with your own config (see Install > Configuration in Readme)\n\t-- require(\"gp\").setup(config)\n\n -- shortcuts might be setup here (see Usage > Shortcuts in Readme)\n end,\n})\n```\n\n### 2. OpenAI API key\n\nMake sure you have OpenAI API key. [Get one here](https://platform.openai.com/account/api-keys)\nand use it in the [config](#4-configuration) (or **setup env `OPENAI_API_KEY`**).\n\nAlso consider setting up [usage limits](https://platform.openai.com/account/billing/limits) so you won't get suprised at the end of the month.\n\n### 3. Dependencies\n\nThe core plugin only needs `curl` installed to make calls to OpenAI API and `grep` for ChatFinder. So Linux, BSD and Mac OS should be covered.\n\nVoice commands (`:GpWhisper*`) depend on `SoX` (Sound eXchange) to handle audio recording and processing:\n\n- Mac OS: `brew install sox`\n- Ubuntu/Debian: `apt-get install sox`\n- Arch Linux: `pacman -S sox`\n- Redhat/CentOS: `yum install sox`\n- NixOS: `nix-env -i sox`\n\n### 4. Configuration\n\nBellow are the default values, but I suggest starting with minimal config possible (just `openai_api_key` if you don't have `OPENAI_API_KEY` env set up). Defaults change over time to improve things, options might get deprecated and so on - it's better to change only things where the default doesn't fit your needs.\n\nhttps://github.com/Robitx/gp.nvim/blob/84a39ce557ac771b42c38e9b9d211ec3f3bd32cc/lua/gp/config.lua#L8-L246\n\n## Usage\n\n### Commands\n\n- Have ChatGPT experience directly in neovim:\n\n - `:GpChatNew` - open fresh chat in the current window \n (either empty or with the visual selection or specified range as a context)\n - `:GpChatPaste` - paste the selection or specified range to the latest chat\n (simplifies adding code from multiple files into a single chat buffer)\n - `:GpChatToggle` - open chat in toggleable popup window \n (the last active chat or a fresh one with selection or a range as a context)\n - `:GpChatFinder` - open a dialog to search through chats\n - `:GpChatRespond` - request new gpt response for the current chat\n - `:GpChatRespond N` - request new gpt response with only last N messages as a context \n (using everything from the end up to Nth instance of `🗨:..` => `N=1` is like asking a question in a new chat)\n - `:GpChatDelete` - delete the current chat\n\n when calling `:GpChatNew` or `:GpChatPaste` and `GpChatToggle` you can also specify where to display chat using subcommands:\n ![image](https://github.com/Robitx/gp.nvim/assets/8431097/350b38ce-52fb-4df7-b2a5-d6e51581f0c3)\n\n- Ask GPT and get response to the specified output:\n\n - `:GpRewrite` - answer replaces the current line, visual selection or range\n - `:GpAppend` - answers after the current line, visual selection or range\n - `:GpPrepend` - answers before the current line, selection or range\n - `:GpEnew` - answers into new buffer\n - `:GpPopup` - answers into pop up window\n - `:GpImplement` - default example hook command for finishing the code \n based on comments provided in visual selection or specified range\n\n all these command work either:\n\n - as pure user commands without any other context in normal/insert mode\n - with current selection (using whole lines) as a context in visual/Visual mode\n - with specified range (such as `%` for the entire current buffer => `:%GpRewrite`)\n\n- Provide custom context per repository with`:GpContext`:\n\n - opens `.gp.md` file for given repository in toggable window\n - if used with selection/range it appends it to the context file\n - supports display targeting subcommands just like `GpChatNew`\n - see [Custom instructions](#custom-instructions-per-repository) section\n\n- Switch between configured agents (model + persona):\n\n - `:GpNextAgent` - cycle between available agents\n - `:GpAgent` - display currently used agents for chat and command instructions\n - `:GpAgent XY` - choose new agent based on its name\n\n commands are context aware (they switch chat or command agent based on the current buffer)\n\n- Voice commands transcribed by Whisper API:\n - `:GpWhisper` - transcription replaces the current line, visual selection or range\n - `:GpWhisperRewrite` - answer replaces the current line, visual selection or range\n - `:GpWhisperAppend` - answers after the current line, visual selection or range\n - `:GpWhisperPrepend` - answers before the current line, selection or range\n - `:GpWhisperEnew` - answers into new buffer\n - `:GpWhisperPopup` - answers into pop up window\n- To stop the stream of currently running gpt response you can use `:GpStop`\n- Run your own custom hook commands:\n - `:GpInspectPlugin` - inspect GPT prompt plugin object\n\n### GpDone autocommand to run consequent actions\n\nCommands like `GpRewrite`, `GpAppend` etc. run asynchronously and generate event `GpDone`, so you can define autocmd (like auto formating) to run when gp finishes:\n\n```lua\n vim.api.nvim_create_autocmd({ \"User\" }, {\n pattern = {\"GpDone\"},\n callback = function(event)\n print(\"event fired:\\n\", vim.inspect(event))\n -- local b = event.buf\n -- DO something\n end,\n })\n```\n\n### Custom instructions per repository\n\nBy calling `:GpContext` you can make `.gp.md` markdown file in a root of a repository. Commands such as `:GpRewrite`, `:GpAppend` etc. will respect instructions provided in this file (works better with gpt4, gpt 3.5 doesn't always listen to system commands). For example:\n\n```md\nUse ‎C++17.\nUse Testify library when writing Go tests.\nUse Early return/Guard Clauses pattern to avoid excessive nesting.\n...\n```\n\nHere is [another example](https://github.com/Robitx/gp.nvim/blob/main/.gp.md).\n\n### Scripting and multifile edits\n\n`GpDone` event + `.gp.md` custom instructions provide a possibility to run gp.nvim using headless (neo)vim from terminal or shell script. So you can let gp run edits accross many files if you put it in a loop.\n\n`test` file:\n\n```\n1\n2\n3\n4\n5\n```\n\n`.gp.md` file:\n\n````\nIf user says hello, please respond with:\n\n```\nAhoy there!\n```\n````\n\ncalling gp.nvim from terminal/script:\n\n- register autocommand to save and quit nvim when Gp is done\n- second jumps to occurrence of something I want to rewrite/append/prepend to (in this case number `3`)\n- selecting the line\n- calling gp.nvim acction\n\n```\n$ nvim --headless -c \"autocmd User GpDone wq\" -c \"/3\" -c \"normal V\" -c \"GpAppend hello there\" test\n```\n\nresulting `test` file:\n\n```\n1\n2\n3\nAhoy there!\n4\n5\n```\n\n### Shortcuts\n\nThere are no default global shortcuts to mess with your own config. Bellow are examples for you to adjust or just use directly.\n\n#### Native\n\nYou can use the good old `vim.keymap.set` and paste the following after `require(\"gp\").setup(conf)` call\n(or anywhere you keep shortcuts if you want them at one place).\n\n```lua\nlocal function keymapOptions(desc)\n return {\n noremap = true,\n silent = true,\n nowait = true,\n desc = \"GPT prompt \" .. desc,\n }\nend\n\n-- Chat commands\nvim.keymap.set({\"n\", \"i\"}, \"c\", \"GpChatNew\", keymapOptions(\"New Chat\"))\nvim.keymap.set({\"n\", \"i\"}, \"t\", \"GpChatToggle\", keymapOptions(\"Toggle Chat\"))\nvim.keymap.set({\"n\", \"i\"}, \"f\", \"GpChatFinder\", keymapOptions(\"Chat Finder\"))\n\nvim.keymap.set(\"v\", \"c\", \":'<,'>GpChatNew\", keymapOptions(\"Visual Chat New\"))\nvim.keymap.set(\"v\", \"v\", \":'<,'>GpChatPaste\", keymapOptions(\"Visual Chat Paste\"))\nvim.keymap.set(\"v\", \"t\", \":'<,'>GpChatToggle\", keymapOptions(\"Visual Toggle Chat\"))\n\nvim.keymap.set({ \"n\", \"i\" }, \"

\", \"GpChatNew split\", keymapOptions(\"New Chat split\"))\nvim.keymap.set({ \"n\", \"i\" }, \"

\", \"GpChatNew vsplit\", keymapOptions(\"New Chat vsplit\"))\nvim.keymap.set({ \"n\", \"i\" }, \"

\", \"GpChatNew tabnew\", keymapOptions(\"New Chat tabnew\"))\n\nvim.keymap.set(\"v\", \"

\", \":'<,'>GpChatNew split\", keymapOptions(\"Visual Chat New split\"))\nvim.keymap.set(\"v\", \"

\", \":'<,'>GpChatNew vsplit\", keymapOptions(\"Visual Chat New vsplit\"))\nvim.keymap.set(\"v\", \"

\", \":'<,'>GpChatNew tabnew\", keymapOptions(\"Visual Chat New tabnew\"))\n\n-- Prompt commands\nvim.keymap.set({\"n\", \"i\"}, \"r\", \"GpRewrite\", keymapOptions(\"Inline Rewrite\"))\nvim.keymap.set({\"n\", \"i\"}, \"a\", \"GpAppend\", keymapOptions(\"Append\"))\nvim.keymap.set({\"n\", \"i\"}, \"b\", \"GpPrepend\", keymapOptions(\"Prepend\"))\nvim.keymap.set({\"n\", \"i\"}, \"e\", \"GpEnew\", keymapOptions(\"Enew\"))\nvim.keymap.set({\"n\", \"i\"}, \"p\", \"GpPopup\", keymapOptions(\"Popup\"))\n\nvim.keymap.set(\"v\", \"r\", \":'<,'>GpRewrite\", keymapOptions(\"Visual Rewrite\"))\nvim.keymap.set(\"v\", \"a\", \":'<,'>GpAppend\", keymapOptions(\"Visual Append\"))\nvim.keymap.set(\"v\", \"b\", \":'<,'>GpPrepend\", keymapOptions(\"Visual Prepend\"))\nvim.keymap.set(\"v\", \"e\", \":'<,'>GpEnew\", keymapOptions(\"Visual Enew\"))\nvim.keymap.set(\"v\", \"p\", \":'<,'>GpPopup\", keymapOptions(\"Visual Popup\"))\n\nvim.keymap.set({\"n\", \"i\"}, \"x\", \"GpContext\", keymapOptions(\"Toggle Context\"))\nvim.keymap.set(\"v\", \"x\", \":'<,'>GpContext\", keymapOptions(\"Visual Toggle Context\"))\n\nvim.keymap.set({\"n\", \"i\", \"v\", \"x\"}, \"s\", \"GpStop\", keymapOptions(\"Stop\"))\nvim.keymap.set({\"n\", \"i\", \"v\", \"x\"}, \"n\", \"GpNextAgent\", keymapOptions(\"Next Agent\"))\n\n-- optional Whisper commands\nvim.keymap.set({\"n\", \"i\"}, \"w\", \"GpWhisper\", keymapOptions(\"Whisper\"))\nvim.keymap.set({\"n\", \"i\"}, \"R\", \"GpWhisperRewrite\", keymapOptions(\"Inline Rewrite\"))\nvim.keymap.set({\"n\", \"i\"}, \"A\", \"GpWhisperAppend\", keymapOptions(\"Append\"))\nvim.keymap.set({\"n\", \"i\"}, \"B\", \"GpWhisperPrepend\", keymapOptions(\"Prepend\"))\nvim.keymap.set({\"n\", \"i\"}, \"E\", \"GpWhisperEnew\", keymapOptions(\"Enew\"))\nvim.keymap.set({\"n\", \"i\"}, \"P\", \"GpWhisperPopup\", keymapOptions(\"Popup\"))\n\nvim.keymap.set(\"v\", \"w\", \":'<,'>GpWhisper\", keymapOptions(\"Whisper\"))\nvim.keymap.set(\"v\", \"R\", \":'<,'>GpWhisperRewrite\", keymapOptions(\"Visual Rewrite\"))\nvim.keymap.set(\"v\", \"A\", \":'<,'>GpWhisperAppend\", keymapOptions(\"Visual Append\"))\nvim.keymap.set(\"v\", \"B\", \":'<,'>GpWhisperPrepend\", keymapOptions(\"Visual Prepend\"))\nvim.keymap.set(\"v\", \"E\", \":'<,'>GpWhisperEnew\", keymapOptions(\"Visual Enew\"))\nvim.keymap.set(\"v\", \"P\", \":'<,'>GpWhisperPopup\", keymapOptions(\"Visual Popup\"))\n```\n\n#### Whichkey\n\nOr go more fancy by using [which-key.nvim](https://github.com/folke/which-key.nvim) plugin:\n\n```lua\n-- VISUAL mode mappings\n-- s, x, v modes are handled the same way by which_key\nrequire(\"which-key\").register({\n -- ...\n\t[\"\"] = {\n\t\tc = { \":'<,'>GpChatNew\", \"Visual Chat New\" },\n\t\tv = { \":'<,'>GpChatPaste\", \"Visual Chat Paste\" },\n\t\tt = { \":'<,'>GpChatToggle\", \"Visual Toggle Chat\" },\n\n\t\t[\"\"] = { \":'<,'>GpChatNew split\", \"Visual Chat New split\" },\n\t\t[\"\"] = { \":'<,'>GpChatNew vsplit\", \"Visual Chat New vsplit\" },\n\t\t[\"\"] = { \":'<,'>GpChatNew tabnew\", \"Visual Chat New tabnew\" },\n\n\t\tr = { \":'<,'>GpRewrite\", \"Visual Rewrite\" },\n\t\ta = { \":'<,'>GpAppend\", \"Visual Append\" },\n\t\tb = { \":'<,'>GpPrepend\", \"Visual Prepend\" },\n\t\te = { \":'<,'>GpEnew\", \"Visual Enew\" },\n\t\tp = { \":'<,'>GpPopup\", \"Visual Popup\" },\n\n\t\tx = { \":'<,'>GpContext\", \"Visual Toggle Context\" },\n\n\t\tn = { \"GpNextAgent\", \"Next Agent\" },\n\t\ts = { \"GpStop\", \"Stop\" },\n\n\n -- optional Whisper commands\n\t\tw = { \":'<,'>GpWhisper\", \"Whisper\" },\n\t\tR = { \":'<,'>GpWhisperRewrite\", \"Whisper Visual Rewrite\" },\n\t\tA = { \":'<,'>GpWhisperAppend\", \"Whisper Visual Append\" },\n\t\tB = { \":'<,'>GpWhisperPrepend\", \"Whisper Visual Prepend\" },\n\t\tE = { \":'<,'>GpWhisperEnew\", \"Whisper Visual Enew\" },\n\t\tP = { \":'<,'>GpWhisperPopup\", \"Whisper Visual Popup\" },\n\t},\n -- ...\n}, {\n\tmode = \"v\", -- VISUAL mode\n\tprefix = \"\",\n\tbuffer = nil,\n\tsilent = true,\n\tnoremap = true,\n\tnowait = true,\n})\n\n-- NORMAL mode mappings\nrequire(\"which-key\").register({\n -- ...\n\t[\"\"] = {\n\t\tc = { \"GpChatNew\", \"New Chat\" },\n\t\tt = { \"GpChatToggle\", \"Toggle Chat\" },\n\t\tf = { \"GpChatFinder\", \"Chat Finder\" },\n\n\t\t[\"\"] = { \"GpChatNew split\", \"New Chat split\" },\n\t\t[\"\"] = { \"GpChatNew vsplit\", \"New Chat vsplit\" },\n\t\t[\"\"] = { \"GpChatNew tabnew\", \"New Chat tabnew\" },\n\n\t\tr = { \"GpRewrite\", \"Inline Rewrite\" },\n\t\ta = { \"GpAppend\", \"Append\" },\n\t\tb = { \"GpPrepend\", \"Prepend\" },\n\t\te = { \"GpEnew\", \"Enew\" },\n\t\tp = { \"GpPopup\", \"Popup\" },\n\n\t\tx = { \"GpContext\", \"Toggle Context\" },\n\t\tn = { \"GpNextAgent\", \"Next Agent\" },\n\t\ts = { \"GpStop\", \"Stop\" },\n\n -- optional Whisper commands\n\t\tw = { \"GpWhisper\", \"Whisper\" },\n\t\tR = { \"GpWhisperRewrite\", \"Whisper Inline Rewrite\" },\n\t\tA = { \"GpWhisperAppend\", \"Whisper Append\" },\n\t\tB = { \"GpWhisperPrepend\", \"Whisper Prepend\" },\n\t\tE = { \"GpWhisperEnew\", \"Whisper Enew\" },\n\t\tP = { \"GpWhisperPopup\", \"Whisper Popup\" },\n\t},\n -- ...\n}, {\n\tmode = \"n\", -- NORMAL mode\n\tprefix = \"\",\n\tbuffer = nil,\n\tsilent = true,\n\tnoremap = true,\n\tnowait = true,\n})\n\n-- INSERT mode mappings\nrequire(\"which-key\").register({\n -- ...\n\t[\"\"] = {\n\t\tc = { \"GpChatNew\", \"New Chat\" },\n\t\tt = { \"GpChatToggle\", \"Toggle Popup Chat\" },\n\t\tf = { \"GpChatFinder\", \"Chat Finder\" },\n\n\t\t[\"\"] = { \"GpChatNew split\", \"New Chat split\" },\n\t\t[\"\"] = { \"GpChatNew vsplit\", \"New Chat vsplit\" },\n\t\t[\"\"] = { \"GpChatNew tabnew\", \"New Chat tabnew\" },\n\n\t\tr = { \"GpRewrite\", \"Inline Rewrite\" },\n\t\ta = { \"GpAppend\", \"Append\" },\n\t\tb = { \"GpPrepend\", \"Prepend\" },\n\t\te = { \"GpEnew\", \"Enew\" },\n\t\tp = { \"GpPopup\", \"Popup\" },\n\n\t\tx = { \"GpContext\", \"Toggle Context\" },\n\t\tn = { \"GpNextAgent\", \"Next Agent\" },\n\t\ts = { \"GpStop\", \"Stop\" },\n\n -- optional Whisper commands\n\t\tw = { \"GpWhisper\", \"Whisper\" },\n\t\tR = { \"GpWhisperRewrite\", \"Whisper Inline Rewrite\" },\n\t\tA = { \"GpWhisperAppend\", \"Whisper Append\" },\n\t\tB = { \"GpWhisperPrepend\", \"Whisper Prepend\" },\n\t\tE = { \"GpWhisperEnew\", \"Whisper Enew\" },\n\t\tP = { \"GpWhisperPopup\", \"Whisper Popup\" },\n\t},\n -- ...\n}, {\n\tmode = \"i\", -- INSERT mode\n\tprefix = \"\",\n\tbuffer = nil,\n\tsilent = true,\n\tnoremap = true,\n\tnowait = true,\n})\n```\n\n## Extend functionality\n\nYou can extend/override the plugin functionality with your own, by putting functions into `config.hooks`.\nHooks have access to everything (see `InspectPlugin` example in defaults) and are\nautomatically registered as commands (`GpInspectPlugin`).\n\nHere are some more examples:\n\n- `:GpUnitTests`\n\n ````lua\n -- example of adding command which writes unit tests for the selected code\n UnitTests = function(gp, params)\n local template = \"I have the following code from {{filename}}:\\n\\n\"\n .. \"```{{filetype}}\\n{{selection}}\\n```\\n\\n\"\n .. \"Please respond by writing table driven unit tests for the code above.\"\n local agent = gp.get_command_agent()\n gp.Prompt(params, gp.Target.enew, nil, agent.model, template, agent.system_prompt)\n end,\n ````\n\n- `:GpExplain`\n\n ````lua\n -- example of adding command which explains the selected code\n Explain = function(gp, params)\n local template = \"I have the following code from {{filename}}:\\n\\n\"\n .. \"```{{filetype}}\\n{{selection}}\\n```\\n\\n\"\n .. \"Please respond by explaining the code above.\"\n local agent = gp.get_chat_agent()\n gp.Prompt(params, gp.Target.popup, nil, agent.model, template, agent.system_prompt)\n end,\n ````\n\n- `:GpCodeReview`\n\n ````lua\n -- example of usig enew as a function specifying type for the new buffer\n CodeReview = function(gp, params)\n local template = \"I have the following code from {{filename}}:\\n\\n\"\n .. \"```{{filetype}}\\n{{selection}}\\n```\\n\\n\"\n .. \"Please analyze for code smells and suggest improvements.\"\n local agent = gp.get_chat_agent()\n gp.Prompt(params, gp.Target.enew(\"markdown\"), nil, agent.model, template, agent.system_prompt)\n end,\n ````\n\n- `:GpTranslator`\n\n ```lua\n -- example of adding command which opens new chat dedicated for translation\n Translator = function(gp, params)\n local agent = gp.get_command_agent()\n local chat_system_prompt = \"You are a Translator, please translate between English and Chinese.\"\n gp.cmd.ChatNew(params, agent.model, chat_system_prompt)\n end,\n ```\n\n- `:GpBufferChatNew`\n\n ```lua\n -- example of making :%GpChatNew a dedicated command which\n -- opens new chat with the entire current buffer as a context\n BufferChatNew = function(gp, _)\n -- call GpChatNew command in range mode on whole buffer\n vim.api.nvim_command(\"%\" .. gp.config.cmd_prefix .. \"ChatNew\")\n end,\n ```\n\nThe raw plugin text editing method `Prompt` has seven aprameters:\n\n- `params` is a [table passed to neovim user commands](https://neovim.io/doc/user/lua-guide.html#lua-guide-commands-create), `Prompt` currently uses:\n\n - `range, line1, line2` to work with [ranges](https://neovim.io/doc/user/usr_10.html#10.3)\n - `args` so instructions can be passed directly after command (`:GpRewrite something something`)\n\n ```lua\n params = {\n args = \"\",\n bang = false,\n count = -1,\n fargs = {},\n line1 = 1352,\n line2 = 1352,\n mods = \"\",\n name = \"GpChatNew\",\n range = 0,\n reg = \"\",\n smods = {\n browse = false,\n confirm = false,\n emsg_silent = false,\n hide = false,\n horizontal = false,\n keepalt = false,\n keepjumps = false,\n keepmarks = false,\n keeppatterns = false,\n lockmarks = false,\n noautocmd = false,\n noswapfile = false,\n sandbox = false,\n silent = false,\n split = \"\",\n tab = -1,\n unsilent = false,\n verbose = -1,\n vertical = false\n }\n }\n ```\n\n- `target` specifying where to direct GPT response\n\n - enew can be used as a function so you can pass in a filetype\n for the new buffer (`enew/enew()/enew(\"markdown\")/..`)\n\n ```lua\n M.Target = {\n rewrite = 0, -- for replacing the selection, range or the current line\n append = 1, -- for appending after the selection, range or the current line\n prepend = 2, -- for prepending before the selection, range or the current line\n popup = 3, -- for writing into the popup window\n\n -- for writing into a new buffer\n ---@param filetype nil | string # nil = same as the original buffer\n ---@return table # a table with type=4 and filetype=filetype\n enew = function(filetype)\n return { type = 4, filetype = filetype }\n end,\n }\n ```\n\n- `prompt`\n - string used similarly as bash/zsh prompt in terminal, when plugin asks for user command to gpt.\n - if `nil`, user is not asked to provide input (for specific predefined commands - document this, explain that, write tests ..)\n - simple `🤖 ~ ` might be used or you could use different msg to convey info about the method which is called \n (`🤖 rewrite ~`, `🤖 popup ~`, `🤖 enew ~`, `🤖 inline ~`, etc.)\n- `model`\n - see [gpt model overview](https://platform.openai.com/docs/models/overview)\n- `template`\n\n - template of the user message send to gpt\n - string can include variables bellow:\n\n | name | Description |\n | --------------- | --------------------------------- |\n | `{{filetype}}` | filetype of the current buffer |\n | `{{selection}}` | last or currently selected text |\n | `{{command}}` | instructions provided by the user |\n\n- `system_template`\n - See [gpt api intro](https://platform.openai.com/docs/guides/chat/introduction)\n- `whisper`\n - optional string serving as a default for input prompt (for example generated from speech by Whisper)\n","dotfyleShieldAddedAt":null,"stars":159,"lastSyncedAt":"2023-11-30T02:19:44.792Z","addedLastWeek":0}}}]}}]