ngpt 4.0.2__tar.gz → 4.1.0__tar.gz

{ngpt-4.0.2 → ngpt-4.1.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ngpt
-Version: 4.0.2
+Version: 4.1.0
 Summary: A Swiss army knife for LLMs: A fast, lightweight CLI and interactive chat tool that brings the power of any OpenAI-compatible LLM (OpenAI, Ollama, Groq, Claude, Gemini, etc.) straight to your terminal. rewrite texts or refine code, craft git commit messages, generate and run OS-aware shell commands.
 Project-URL: Homepage, https://github.com/nazdridoy/ngpt
 Project-URL: Repository, https://github.com/nazdridoy/ngpt
@@ -81,6 +81,7 @@ Description-Content-Type: text/markdown
 - 🎭 **System Prompts**: Customize model behavior with custom system prompts
 - 🤖 **Custom Roles**: Create and use reusable AI roles for specialized tasks
 - 📃 **Conversation Logging**: Save your conversations to text files for later reference
+- 💾 **Session Management**: Save, load, and list interactive chat sessions.
 - 🔌 **Modular Architecture**: Well-structured codebase with clean separation of concerns
 - 🔄 **Provider Switching**: Easily switch between different LLM providers with a single parameter
 - 🚀 **Performance Optimized**: Fast response times and minimal resource usage
@@ -138,6 +139,13 @@ python -m ngpt "Tell me about quantum computing"
 
 # Start an interactive chat session with conversation memory
 ngpt -i
+# Inside interactive mode, you can use commands like:
+# help     - Show help menu
+# save     - Save the current session
+# load     - Load a previous session
+# sessions - List saved sessions
+# clear    - Clear the conversation
+# exit     - Exit the session
 
 # Return response without streaming
 ngpt --no-stream "Tell me about quantum computing"

{ngpt-4.0.2 → ngpt-4.1.0}/README.md

@@ -44,6 +44,7 @@
 - 🎭 **System Prompts**: Customize model behavior with custom system prompts
 - 🤖 **Custom Roles**: Create and use reusable AI roles for specialized tasks
 - 📃 **Conversation Logging**: Save your conversations to text files for later reference
+- 💾 **Session Management**: Save, load, and list interactive chat sessions.
 - 🔌 **Modular Architecture**: Well-structured codebase with clean separation of concerns
 - 🔄 **Provider Switching**: Easily switch between different LLM providers with a single parameter
 - 🚀 **Performance Optimized**: Fast response times and minimal resource usage
@@ -101,6 +102,13 @@ python -m ngpt "Tell me about quantum computing"
 
 # Start an interactive chat session with conversation memory
 ngpt -i
+# Inside interactive mode, you can use commands like:
+# help     - Show help menu
+# save     - Save the current session
+# load     - Load a previous session
+# sessions - List saved sessions
+# clear    - Clear the conversation
+# exit     - Exit the session
 
 # Return response without streaming
 ngpt --no-stream "Tell me about quantum computing"

ngpt-4.1.0/docs/index.md

@@ -0,0 +1,74 @@
+---
+layout: default
+title: nGPT Documentation
+nav_order: 1
+permalink: /
+---
+
+# nGPT Documentation
+
+Welcome to the nGPT documentation. This guide will help you get started with nGPT, a Swiss army knife for LLMs that combines a powerful CLI and interactive chatbot in one package.
+
+
+![ngpt-i](https://raw.githubusercontent.com/nazdridoy/ngpt/main/previews/ngpt-i.png)
+
+## What is nGPT?
+
+nGPT is a versatile command-line tool designed to interact with AI language models through various APIs. It provides a seamless interface for generating text, code, shell commands, and more, all from your terminal.
+
+## Getting Started
+
+For a quick start, refer to the [Installation](installation.md) and [CLI Usage](usage/cli_usage.md) guides.
+
+## Key Features
+
+- ✅ **Versatile**: Powerful and easy-to-use CLI tool for various AI tasks
+- 🪶 **Lightweight**: Minimal dependencies with everything you need included
+- 🔄 **API Flexibility**: Works with OpenAI, Ollama, Groq, Claude, Gemini, and any OpenAI-compatible endpoint
+- 💬 **Interactive Chat**: Continuous conversation with memory in modern UI
+- 📊 **Streaming Responses**: Real-time output for better user experience
+- 🔍 **Web Search**: Enhance any model with contextual information from the web, using advanced content extraction to identify the most relevant information from web pages
+- 📥 **Stdin Processing**: Process piped content by using `{}` placeholder in prompts
+- 🎨 **Markdown Rendering**: Beautiful formatting of markdown and code with syntax highlighting
+- ⚡ **Real-time Markdown**: Stream responses with live updating syntax highlighting and formatting
+- ⚙️ **Multiple Configurations**: Cross-platform config system supporting different profiles
+- 💻 **Shell Command Generation**: OS-aware command execution
+- 🧠 **Text Rewriting**: Improve text quality while maintaining original tone and meaning
+- 🧩 **Clean Code Generation**: Output code without markdown or explanations
+- 📝 **Rich Multiline Editor**: Interactive multiline text input with syntax highlighting and intuitive controls
+- 📑 **Git Commit Messages**: AI-powered generation of conventional, detailed commit messages from git diffs
+- 🎭 **System Prompts**: Customize model behavior with custom system prompts
+- 🤖 **Custom Roles**: Create and use reusable AI roles for specialized tasks
+- 📃 **Conversation Logging**: Save your conversations to text files for later reference
+- 💾 **Session Management**: Save, load, and list interactive chat sessions.
+- 🔌 **Modular Architecture**: Well-structured codebase with clean separation of concerns
+- 🔄 **Provider Switching**: Easily switch between different LLM providers with a single parameter
+- 🚀 **Performance Optimized**: Fast response times and minimal resource usage
+
+## Quick Examples
+
+```bash
+# Basic chat
+ngpt "Tell me about quantum computing"
+
+# Interactive chat session
+ngpt -i
+# Inside interactive mode, you can use commands like:
+# help     - Show help menu
+# save     - Save the current session
+# load     - Load a previous session
+# sessions - List saved sessions
+# clear    - Clear the conversation
+# exit     - Exit the session
+
+# Generate code
+ngpt --code "function to calculate Fibonacci numbers"
+
+# Generate and execute shell commands
+ngpt --shell "find large files in current directory"
+
+# Generate git commit messages
+ngpt --gitcommsg
+```
+
+For more examples and detailed instructions, please refer to the side panel for navigation through the documentation sections.

{ngpt-4.0.2 → ngpt-4.1.0}/docs/overview.md

@@ -15,25 +15,28 @@ nGPT is a Swiss army knife for LLMs: powerful CLI and interactive chatbot in one
 
 ## Key Features
 
-- **Versatile**: Powerful and easy-to-use CLI tool for various AI tasks
-- **Lightweight**: Minimal dependencies with everything you need included
-- **API Flexibility**: Works with OpenAI, Ollama, Groq, Claude, Gemini, and any OpenAI-compatible endpoint
-- **Interactive Chat**: Continuous conversation with memory in modern UI
-- **Streaming Responses**: Real-time output for better user experience
-- **Web Search**: Enhance any model with contextual information from the web, using advanced content extraction to identify the most relevant information from web pages
-- **Stdin Processing**: Process piped content by using `{}` placeholder in prompts
-- **Markdown Rendering**: Beautiful formatting of markdown and code with syntax highlighting
-- **Real-time Markdown**: Stream responses with live updating syntax highlighting and formatting
-- **Multiple Configurations**: Cross-platform config system supporting different profiles
-- **Shell Command Generation**: OS-aware command execution
-- **Text Rewriting**: Improve text quality while maintaining original tone and meaning
-- **Clean Code Generation**: Output code without markdown or explanations
-- **Rich Multiline Editor**: Interactive multiline text input with syntax highlighting and intuitive controls
-- **Git Commit Messages**: AI-powered generation of conventional, detailed commit messages from git diffs
-- **System Prompts**: Customize model behavior with custom system prompts
-- **Conversation Logging**: Save your conversations to text files for later reference
-- **Provider Switching**: Easily switch between different LLM providers with a single parameter
-- **Performance Optimized**: Fast response times and minimal resource usage
+- ✅ **Versatile**: Powerful and easy-to-use CLI tool for various AI tasks
+- 🪶 **Lightweight**: Minimal dependencies with everything you need included
+- 🔄 **API Flexibility**: Works with OpenAI, Ollama, Groq, Claude, Gemini, and any OpenAI-compatible endpoint
+- 💬 **Interactive Chat**: Continuous conversation with memory in modern UI
+- 📊 **Streaming Responses**: Real-time output for better user experience
+- 🔍 **Web Search**: Enhance any model with contextual information from the web, using advanced content extraction to identify the most relevant information from web pages
+- 📥 **Stdin Processing**: Process piped content by using `{}` placeholder in prompts
+- 🎨 **Markdown Rendering**: Beautiful formatting of markdown and code with syntax highlighting
+- ⚡ **Real-time Markdown**: Stream responses with live updating syntax highlighting and formatting
+- ⚙️ **Multiple Configurations**: Cross-platform config system supporting different profiles
+- 💻 **Shell Command Generation**: OS-aware command execution
+- 🧠 **Text Rewriting**: Improve text quality while maintaining original tone and meaning
+- 🧩 **Clean Code Generation**: Output code without markdown or explanations
+- 📝 **Rich Multiline Editor**: Interactive multiline text input with syntax highlighting and intuitive controls
+- 📑 **Git Commit Messages**: AI-powered generation of conventional, detailed commit messages from git diffs
+- 🎭 **System Prompts**: Customize model behavior with custom system prompts
+- 🤖 **Custom Roles**: Create and use reusable AI roles for specialized tasks
+- 📃 **Conversation Logging**: Save your conversations to text files for later reference
+- 💾 **Session Management**: Save, load, and list interactive chat sessions.
+- 🔌 **Modular Architecture**: Well-structured codebase with clean separation of concerns
+- 🔄 **Provider Switching**: Easily switch between different LLM providers with a single parameter
+- 🚀 **Performance Optimized**: Fast response times and minimal resource usage
 
 ## Core Modes
 
@@ -50,6 +53,13 @@ Start an ongoing conversation with memory:
 ```bash
 ngpt -i
 ngpt --interactive
+# Inside interactive mode, you can use commands like:
+# help     - Show help menu
+# save     - Save the current session
+# load     - Load a previous session
+# sessions - List saved sessions
+# clear    - Clear the conversation
+# exit     - Exit the session
 ```
 
 ### Code Generation Mode

{ngpt-4.0.2 → ngpt-4.1.0}/docs/usage/cli_usage.md

@@ -151,6 +151,32 @@ This opens a continuous chat session where the AI remembers previous exchanges.
 - Type your messages and press Enter to send
 - Use arrow keys to navigate message history
 - Press Ctrl+C to exit the session
+- Use `help` to see a list of available commands.
+
+#### Session Management
+
+In interactive mode, you can manage your chat sessions with the following commands:
+
+- **`save`**: Saves the current conversation to a timestamped JSON file in the `history` subdirectory of your configuration folder.
+- **`load`**: Lists recent sessions and prompts you to select one to load, restoring the conversation history.
+- **`sessions`**: Displays a list of all saved sessions.
+- **`clear`**: Clears the current conversation history.
+- **`history`**: Shows the full history of the current conversation.
+- **`exit`**: Exits the interactive session.
+- **`help`**: Shows the help menu with all available commands.
+
+Example:
+```
+> save
+Session saved to /home/user/.config/ngpt/history/session_2024-10-26_12-30-00.json
+
+> load
+Saved Sessions:
+  [0] session_2024-10-26_12-30-00.json
+  [1] session_2024-10-25_18-00-00.json
+Enter the number of the session to load: 0
+Session loaded from ...
+```
 
 #### Conversation Logging
 

{ngpt-4.0.2 → ngpt-4.1.0}/ngpt/cli/modes/interactive.py

@@ -4,6 +4,9 @@ import traceback
 import threading
 import sys
 import time
+import json
+from datetime import datetime
+from ...utils.config import get_config_dir
 from ..formatters import COLORS
 from ..renderers import prettify_markdown, prettify_streaming_markdown, TERMINAL_RENDER_LOCK
 from ..ui import spinner, get_multiline_input
@@ -50,21 +53,29 @@ def interactive_chat_session(client, web_search=False, no_stream=False, temperat
     # Create a separator line - use a consistent separator length for all lines
     separator_length = min(40, term_width - 10)
     separator = f"{COLORS['gray']}{'─' * separator_length}{COLORS['reset']}"
-    print(separator)
-    
-    # Group commands into categories with better formatting
-    print(f"\n{COLORS['cyan']}Navigation:{COLORS['reset']}")
-    print(f"  {COLORS['yellow']}↑/↓{COLORS['reset']} : Browse input history")
-    
-    print(f"\n{COLORS['cyan']}Session Commands:{COLORS['reset']}")
-    print(f"  {COLORS['yellow']}history{COLORS['reset']} : Show conversation history")
-    print(f"  {COLORS['yellow']}clear{COLORS['reset']}   : Reset conversation")
-    print(f"  {COLORS['yellow']}exit{COLORS['reset']}    : End session")
-    
-    if multiline_enabled:
-        print(f"  {COLORS['yellow']}ml{COLORS['reset']}      : Open multiline editor")
-    
-    print(f"\n{separator}\n")
+
+    def show_help():
+        """Displays the help menu."""
+        print(separator)
+        # Group commands into categories with better formatting
+        print(f"\n{COLORS['cyan']}Navigation:{COLORS['reset']}")
+        print(f"  {COLORS['yellow']}↑/↓{COLORS['reset']} : Browse input history")
+        
+        print(f"\n{COLORS['cyan']}Session Commands:{COLORS['reset']}")
+        print(f"  {COLORS['yellow']}history{COLORS['reset']} : Show conversation history")
+        print(f"  {COLORS['yellow']}clear{COLORS['reset']}   : Reset conversation")
+        print(f"  {COLORS['yellow']}exit{COLORS['reset']}    : End session")
+        print(f"  {COLORS['yellow']}save{COLORS['reset']}    : Save current session")
+        print(f"  {COLORS['yellow']}load{COLORS['reset']}    : Load a previous session")
+        print(f"  {COLORS['yellow']}sessions{COLORS['reset']}: List saved sessions")
+        print(f"  {COLORS['yellow']}help{COLORS['reset']}    : Show this help message")
+        
+        if multiline_enabled:
+            print(f"  {COLORS['yellow']}ml{COLORS['reset']}      : Open multiline editor")
+        
+        print(f"\n{separator}\n")
+
+    show_help()
     
     # Show logging info if logger is available
     if logger:
@@ -148,6 +159,71 @@ def interactive_chat_session(client, web_search=False, no_stream=False, temperat
             print(f"\n{COLORS['yellow']}Conversation history cleared.{COLORS['reset']}")
             print(separator)  # Add separator for consistency
     
+    # --- Session Management Functions ---
+
+    def get_history_dir():
+        """Get the history directory, creating it if it doesn't exist."""
+        history_dir = get_config_dir() / "history"
+        history_dir.mkdir(parents=True, exist_ok=True)
+        return history_dir
+
+    def save_session():
+        """Save the current conversation to a JSON file."""
+        history_dir = get_history_dir()
+        timestamp = datetime.now().strftime("%Y-%m-%d_%H-%M-%S")
+        filename = history_dir / f"session_{timestamp}.json"
+        
+        with open(filename, "w") as f:
+            json.dump(conversation, f, indent=2)
+        
+        print(f"\n{COLORS['green']}Session saved to {filename}{COLORS['reset']}")
+
+    def list_sessions():
+        """List all saved sessions."""
+        history_dir = get_history_dir()
+        sessions = sorted(history_dir.glob("session_*.json"), reverse=True)
+        
+        if not sessions:
+            print(f"\n{COLORS['yellow']}No saved sessions found.{COLORS['reset']}")
+            return
+            
+        print(f"\n{COLORS['cyan']}{COLORS['bold']}Saved Sessions:{COLORS['reset']}")
+        for i, session_file in enumerate(sessions):
+            print(f"  [{i}] {session_file.name}")
+
+    def load_session():
+        """Load a conversation from a saved session file."""
+        nonlocal conversation
+        history_dir = get_history_dir()
+        sessions = sorted(history_dir.glob("session_*.json"), reverse=True)
+
+        if not sessions:
+            print(f"\n{COLORS['yellow']}No saved sessions to load.{COLORS['reset']}")
+            return
+
+        list_sessions()
+        
+        try:
+            choice = input("Enter the number of the session to load: ")
+            choice_index = int(choice)
+            
+            if 0 <= choice_index < len(sessions):
+                session_file = sessions[choice_index]
+                with open(session_file, "r") as f:
+                    loaded_conversation = json.load(f)
+                
+                # Basic validation
+                if isinstance(loaded_conversation, list) and all(isinstance(item, dict) for item in loaded_conversation):
+                    conversation = loaded_conversation
+                    print(f"\n{COLORS['green']}Session loaded from {session_file.name}{COLORS['reset']}")
+                    display_history()
+                else:
+                    print(f"\n{COLORS['red']}Error: Invalid session file format.{COLORS['reset']}")
+            else:
+                print(f"\n{COLORS['red']}Error: Invalid selection.{COLORS['reset']}")
+        except (ValueError, IndexError):
+            print(f"\n{COLORS['red']}Error: Invalid input. Please enter a number from the list.{COLORS['reset']}")
+
     try:
         while True:
             # Get user input
@@ -188,6 +264,22 @@ def interactive_chat_session(client, web_search=False, no_stream=False, temperat
             if user_input.lower() == 'clear':
                 clear_history()
                 continue
+            
+            if user_input.lower() == 'save':
+                save_session()
+                continue
+
+            if user_input.lower() == 'sessions':
+                list_sessions()
+                continue
+
+            if user_input.lower() == 'load':
+                load_session()
+                continue
+
+            if user_input.lower() == 'help':
+                show_help()
+                continue
                 
             if multiline_enabled and user_input.lower() == 'ml':
                 print(f"{COLORS['cyan']}Opening multiline editor. Press Ctrl+D to submit.{COLORS['reset']}")

{ngpt-4.0.2 → ngpt-4.1.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "ngpt"
-version = "4.0.2"
+version = "4.1.0"
 description = "A Swiss army knife for LLMs: A fast, lightweight CLI and interactive chat tool that brings the power of any OpenAI-compatible LLM (OpenAI, Ollama, Groq, Claude, Gemini, etc.) straight to your terminal. rewrite texts or refine code, craft git commit messages, generate and run OS-aware shell commands."
 authors = [
     {name = "nazDridoy", email = "nazdridoy399@gmail.com"},

ngpt-4.0.2/docs/index.md

@@ -1,64 +0,0 @@
----
-layout: default
-title: nGPT Documentation
-nav_order: 1
-permalink: /
----
-
-# nGPT Documentation
-
-Welcome to the nGPT documentation. This guide will help you get started with nGPT, a Swiss army knife for LLMs that combines a powerful CLI and interactive chatbot in one package.
-
-
-![ngpt-i](https://raw.githubusercontent.com/nazdridoy/ngpt/main/previews/ngpt-i.png)
-
-## What is nGPT?
-
-nGPT is a versatile command-line tool designed to interact with AI language models through various APIs. It provides a seamless interface for generating text, code, shell commands, and more, all from your terminal.
-
-## Getting Started
-
-For a quick start, refer to the [Installation](installation.md) and [CLI Usage](usage/cli_usage.md) guides.
-
-## Key Features
-
-- **Versatile**: Powerful and easy-to-use CLI tool for various AI tasks
-- **Lightweight**: Minimal dependencies with everything you need included
-- **API Flexibility**: Works with OpenAI, Ollama, Groq, Claude, Gemini, and any OpenAI-compatible endpoint
-- **Interactive Chat**: Continuous conversation with memory in modern UI
-- **Streaming Responses**: Real-time output for better user experience
-- **Web Search**: Enhance any model with contextual information from the web
-- **Stdin Processing**: Process piped content by using `{}` placeholder in prompts
-- **Markdown Rendering**: Beautiful formatting of markdown and code with syntax highlighting
-- **Real-time Markdown**: Stream responses with live updating syntax highlighting and formatting
-- **Multiple Configurations**: Cross-platform config system supporting different profiles
-- **Shell Command Generation**: OS-aware command execution
-- **Text Rewriting**: Improve text quality while maintaining original tone and meaning
-- **Clean Code Generation**: Output code without markdown or explanations
-- **Rich Multiline Editor**: Interactive multiline text input with syntax highlighting and intuitive controls
-- **Git Commit Messages**: AI-powered generation of conventional, detailed commit messages from git diffs
-- **System Prompts**: Customize model behavior with custom system prompts
-- **Conversation Logging**: Save your conversations to text files for later reference
-- **Provider Switching**: Easily switch between different LLM providers with a single parameter
-- **Performance Optimized**: Fast response times and minimal resource usage
-
-## Quick Examples
-
-```bash
-# Basic chat
-ngpt "Tell me about quantum computing"
-
-# Interactive chat session
-ngpt -i
-
-# Generate code
-ngpt --code "function to calculate Fibonacci numbers"
-
-# Generate and execute shell commands
-ngpt --shell "find large files in current directory"
-
-# Generate git commit messages
-ngpt --gitcommsg
-```
-
-For more examples and detailed instructions, please refer to the side panel for navigation through the documentation sections.