Merge branch 'develop'

Default.sublime-commands

@@ -1,20 +1,41 @@
 [
 	{
-		"caption": "OpenAI Complete",
+		"caption": "OpenAI: Complete",
 		"command": "openai",
 		"args": {
 			"mode": "completion"
 		}
 	},
 	{
-		"caption": "OpenAI Insert",
+		"caption": "OpenAI: New Message",
+		"command": "openai",
+		"args": {
+			"mode": "chat_completion"
+		}
+	},
+	{
+		"caption": "OpenAI: Reset Chat History",
+		"command": "openai",
+		"args": {
+			"mode": "reset_chat_history"
+		}
+	},
+	{
+		"caption": "OpenAI: Refresh Chat",
+		"command": "openai",
+		"args": {
+			"mode": "refresh_output_panel"
+		}
+	},
+	{
+		"caption": "OpenAI: Insert",
 		"command": "openai",
 		"args": {
 			"mode": "insertion"
 		}
 	},
 	{
-		"caption": "OpenAI Edit",
+		"caption": "OpenAI: Edit",
 		"command": "openai",
 		"args": {
 			"mode": "edition"

README.md

@@ -7,19 +7,40 @@ OpenAI Completion is a Sublime Text 4 plugin that uses the OpenAI natural langua
 - Append suggested text to selected code
 - Insert suggested text instead of placeholder in selected code
 - Edit selected code according to a given command
+- **ChatGPT mode support**.
+- [Multi]Markdown syntax with syntax highlight support (ChatGPT mode only).
+- Proxy support.
+- **GPT-4 support**.
+
+### ChatGPT completion demo
 
-### Demo
 <details><summary>Click to see screens</summary>
-![](static/image1.png)
+
+![](static/chatgpt_completion/image1.png)
 
 ---
-![](static/image2.png)
+![](static/chatgpt_completion/image2.png)
 
 ---
-![](static/image3.png)
+![](static/chatgpt_completion/image3.png)
+
+</details>
+
+### Simple completion demo
+
+<details><summary>Click to see screens</summary>
+
+![](static/simple_completion/image1.png)
 
 ---
-![](static/image4.png)
+![](static/simple_completion/image2.png)
+
+---
+![](static/simple_completion/image3.png)
+
+---
+![](static/simple_completion/image4.png)
+
 </details>
 
 ## Requirements
@@ -29,24 +50,73 @@ OpenAI Completion is a Sublime Text 4 plugin that uses the OpenAI natural langua
 - Internet connection
 
 ## Usage
+
+### ChatGPT usage
+
+ChatGPT mode works the following way:
+1. Run the `OpenAI: New Message` command
+2. Wait until OpenAI performs a response (be VERY patient in the case of the GPT-4 model it's way slower than you could imagine).
+3. On the Response plugin opens the `OpenAI completion` output panel with the whole log of your chat at [any] active Window.
+4. If you would like to fetch chat history to another window manually, you can do that by running the `OpenAI: Refresh Chat` command.
+5. When you're done or want to start all over you should run the `OpenAI: Reset Chat History` command, which deletes the chat cache.
+
+> **Note**
+>  You can bind both of the most usable commands `OpenAI: New Message` and `OpenAI: Show output panel`, to do that please follow `Settings` -> `Package Control` -> `OpenAI completion` -> `Key Bindings`.
+
+> **Note**
+> As for now there's just a single history instance. I guess this limitation would disappear sometime.
+
+### Single shot completion usage
+
 1. Open the Sublime Text 4 editor and select some code.
-2. Open the command palette and run the `OpenAI Append`, `OpenAI Insert`, or `OpenAI Edit` command.
-    - To use the `OpenAI Insert` command, the selected code should include a placeholder `[insert]`. This can be modified in the settings.
+2. Open the command palette and run the `OpenAI: Complete`, `OpenAI: Insert`, or `OpenAI: Edit` commands.
+    - To use the `OpenAI: Insert` command, the selected code should include a placeholder `[insert]`. This can be modified in the settings.
 3. **The plugin will send the selected code to the OpenAI servers**, using your API key, to generate a suggestion for editing the code.
 4. The suggestion will modify the selected code in the editor, according to the command you ran (append, insert, or edit).
 
+### Other features
+
+### [Multi]Markdown syntax with syntax highlight support
+
+ChatGPT output panel supports markdown syntax highlight. It should just work (if it's not please report an issue).
+
+Although it's highly recommended to install the [`MultimarkdownEditing`](https://sublimetext-markdown.github.io/MarkdownEditing/) to apply syntax highlighting for code snippets provided by ChatGPT. `OpenAI completion` should just pick it up implicitly for the output panel content.
+
+### Proxy support
+
+That's it. Now you can set up a proxy for this plugin.
+You can setup it up by overriding the proxy property in the `OpenAI completion` settings like follow:
+
+```json
+"proxy": {
+    "address": "127.0.0.1",
+    "port": 9898
+}
+```
+
+### GPT-4 support
+
+> **Note**
+> You have to have access to the `GPT-4` model within your account, to use that feature.
+
+It should just work, just set the `chat_model` setting to `GPT-4`. Please be patient while working with it. (1) It's **very** slow and (2) an answer would appear only after it finishes its prompt. It could take up to 10 seconds easily.
+
+
 ## Settings
 The OpenAI Completion plugin has a settings file where you can set your OpenAI API key. This is required for the plugin to work. To set your API key, open the settings within `Preferences` -> `Package Settings` -> `OpenAI` -> `Settings` and paste your API key in the token property, as follows:
+
 ```JSON
 {
     "token": "sk-your-token",
 }
 ```
 
-## Note
-Please note that OpenAI is a paid service, and you will need to have an API key and sufficient credit to use the plugin.
+## Disclaimers
+
+> **Note**
+> Please note that OpenAI is a paid service, and you will need to have an API key and sufficient credit to use this plugin.
 
-Additionally, **all selected code will be sent to the OpenAI servers for processing, so make sure you have the necessary permissions to do so**.
+> **Warning**
+> **All selected code will be sent to the OpenAI servers for processing, so make sure you have all necessary permissions to do so**.
 
-## Disclamer
-This one was at 80% written by that thing itself including this readme. I was here mostly for debugging purposes, rather then designing and researching. This is pure magic, i swear.
+> This one was at 80% written by that thing itself including this readme. I was here mostly for debugging purposes, rather than designing and researching. This is pure magic, I swear.

cacher.py

@@ -0,0 +1,46 @@
+import sublime
+import os
+from . import jl_utility as jl
+
+
+class Cacher():
+    def __init__(self) -> None:
+        cache_dir = sublime.cache_path()
+        plugin_cache_dir = os.path.join(cache_dir, "OpenAI completion")
+        if not os.path.exists(plugin_cache_dir):
+            os.makedirs(plugin_cache_dir)
+
+        # Create the file path to store the data
+        self.history_file = os.path.join(plugin_cache_dir, "chat_history.jl")
+
+    def read_all(self):
+        json_objects = []
+        reader = jl.reader(self.history_file)
+        for json_object in reader:
+            json_objects.append(json_object)
+
+        return json_objects
+
+    def append_to_cache(self, cache_lines):
+        # Create a new JSON Lines writer for output.jl
+        writer = jl.writer(self.history_file)
+        next(writer)
+        writer.send(cache_lines[0])
+        # for line in cache_lines:
+        #     writer.send(line)
+
+    def drop_first(self, number = 4):
+        # Read all lines from the JSON Lines file
+        with open(self.history_file, "r") as file:
+            lines = file.readlines()
+
+        # Remove the specified number of lines from the beginning
+        lines = lines[number:]
+
+        # Write the remaining lines back to the cache file
+        with open(self.history_file, "w") as file:
+            file.writelines(lines)
+
+    def drop_all(self):
+        with open(self.history_file, "w") as _:
+            pass # Truncate the file by opening it in 'w' mode and doing nothing

jl_utility.py

@@ -0,0 +1,38 @@
+import json
+from typing import Iterator, Generator
+
+
+def reader(fname: str) -> Iterator[dict]:
+    with open(fname) as file:
+        for line in file:
+            obj = json.loads(line.strip())
+            yield obj
+
+
+def writer(fname: str, mode: str = 'a') -> Generator[None, dict, None]:
+    with open(fname, mode) as file:
+        while True:
+            obj = yield
+            line = json.dumps(obj, ensure_ascii=False)
+            file.write(f"{line}\n")
+
+
+# if __name__ == "__main__":
+#     # Read employees from employees.jl
+#     reader = jl_reader("employees.jl")
+
+#     # Create a new JSON Lines writer for output.jl
+#     writer = jl_writer("output.jl")
+#     next(writer)
+
+#     for employee in reader:
+#         id = employee["id"]
+#         name = employee["name"]
+#         dept = employee["department"]
+#         print(f"#{id} - {name} ({dept})")
+
+#         # Write the employee data to output.jl
+#         writer.send(employee)
+
+#     # Close the writer
+#     writer.close()

messages.json

@@ -0,0 +1,3 @@
+{
+    "2.0.0": "messages/2.0.0.txt"
+}

messages/2.0.0.txt

@@ -0,0 +1,50 @@
+=> 2.0.0
+
+# Features summary
+- ChatGPT mode support.
+- [Multi]Markdown syntax with syntax highlight support (ChatGPT mode only).
+- Proxy support.
+- GPT-4 support.
+
+## ChatGPT mode
+
+ChatGPT mode works the following way:
+1. Run the `OpenAI: New Message` command
+2. Wait until OpenAI performs a response (be VERY patient in the case of the GPT-4 model it's way slower than you could imagine).
+3. On the Response plugin opens the `OpenAI completion` output panel with the whole log of your chat at [any] active Window.
+4. If you would like to fetch chat history to another window manually, you can do that by running the `OpenAI: Refresh Chat` command.
+5. When you're done or want to start all over you should run the `OpenAI: Reset Chat History` command, which deletes the chat cache.
+
+> You can bind both of the most usable commands `OpenAI: New Message` and `OpenAI: Show output panel`, to do that please follow `Settings`->`Package Control`->`OpenAI completion`->`Key Bindings`.
+
+> As for now there's just a single history instance. I guess this limitation would disappear sometime, but highly likely it wouldn't be soon.
+
+## [Multi]Markdown syntax with syntax highlight support (ChatGPT mode only).
+
+ChatGPT output panel supports markdown syntax highlight. It should just work (if it's not please report an issue).
+
+Although it's highly recommended to install the [`MultimarkdownEditing`](https://sublimetext-markdown.github.io/MarkdownEditing/) to apply syntax highlighting for code snippets provided by ChatGPT. `OpenAI completion` should just pick it up implicitly for the output panel content.
+
+## Proxy support
+
+That's it. Now you can set up a proxy for this plugin.
+You can setup it up by overriding the proxy property in the `OpenAI completion` settings like follow:
+
+```json
+// Proxy setting
+"proxy": {
+    // Proxy address
+    "address": "127.0.0.1",
+
+    // Proxy port
+    "port": 9898
+}
+```
+
+## GPT-4 support
+
+It should just work, just set the `chat_model` setting to `GPT-4`. Please be patient while working with it. (1) It's **very** slow and an answer would appear only after it finishes its prompt. It could take up to 10 seconds easily.
+
+## Disclaimer
+
+Unfortunately, this version hasn't got covered with comprehensive testing, so there could be bugs. Please report them, so I'd be happy to release a patch.

messages/install.txt

@@ -0,0 +1,48 @@
+# Features summary
+- ChatGPT mode support.
+- [Multi]Markdown syntax with syntax highlight support (ChatGPT mode only).
+- Proxy support.
+- GPT-4 support.
+
+## ChatGPT mode
+
+ChatGPT mode works the following way:
+1. Run the `OpenAI: New Message` command
+2. Wait until OpenAI performs a response (be VERY patient in the case of the GPT-4 model it's way slower than you could imagine).
+3. On the Response plugin opens the `OpenAI completion` output panel with the whole log of your chat at [any] active Window.
+4. If you would like to fetch chat history to another window manually, you can do that by running the `OpenAI: Refresh Chat` command.
+5. When you're done or want to start all over you should run the `OpenAI: Reset Chat History` command, which deletes the chat cache.
+
+> You can bind both of the most usable commands `OpenAI: New Message` and `OpenAI: Show output panel`, to do that please follow `Settings`->`Package Control`->`OpenAI completion`->`Key Bindings`.
+
+> As for now there's just a single history instance. I guess this limitation would disappear sometime, but highly likely it wouldn't be soon.
+
+## [Multi]Markdown syntax with syntax highlight support (ChatGPT mode only).
+
+ChatGPT output panel supports markdown syntax highlight. It should just work (if it's not please report an issue).
+
+Although it's highly recommended to install the [`MultimarkdownEditing`](https://sublimetext-markdown.github.io/MarkdownEditing/) to apply syntax highlighting for code snippets provided by ChatGPT. `OpenAI completion` should just pick it up implicitly for the output panel content.
+
+## Proxy support
+
+That's it. Now you can set up a proxy for this plugin.
+You can setup it up by overriding the proxy property in the `OpenAI completion` settings like follow:
+
+```json
+// Proxy setting
+"proxy": {
+    // Proxy address
+    "address": "127.0.0.1",
+
+    // Proxy port
+    "port": 9898
+}
+```
+
+## GPT-4 support
+
+It should just work, just set the `chat_model` setting to `GPT-4`. Please be patient while working with it. (1) It's **very** slow and an answer would appear only after it finishes its prompt. It could take up to 10 seconds easily.
+
+## Disclaimer
+
+Unfortunately, this version hasn't got covered with comprehensive testing, so there could be bugs. Please report them, so I'd be happy to release a patch.