ngpt 1.1.1__tar.gz → 1.1.3__tar.gz

{ngpt-1.1.1 → ngpt-1.1.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ngpt
-Version: 1.1.1
+Version: 1.1.3
 Summary: A lightweight Python CLI and library for interacting with OpenAI-compatible APIs, supporting both official and self-hosted LLM endpoints.
 Project-URL: Homepage, https://github.com/nazdridoy/ngpt
 Project-URL: Repository, https://github.com/nazdridoy/ngpt
@@ -33,19 +33,51 @@ Description-Content-Type: text/markdown
 
 # nGPT
 
+[![PyPI version](https://img.shields.io/pypi/v/ngpt.svg)](https://pypi.org/project/ngpt/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+[![Python Versions](https://img.shields.io/pypi/pyversions/ngpt.svg)](https://pypi.org/project/ngpt/)
+
 A lightweight Python CLI and library for interacting with OpenAI-compatible APIs, supporting both official and self-hosted LLM endpoints.
 
+## Table of Contents
+- [Quick Start](#quick-start)
+- [Features](#features)
+- [Installation](#installation)
+- [Usage](#usage)
+  - [CLI Tool](#as-a-cli-tool)
+  - [Python Library](#as-a-library)
+- [Configuration](#configuration)
+  - [Command Line Options](#command-line-options)
+  - [Configuration File](#configuration-file)
+  - [Configuration Priority](#configuration-priority)
+- [License](#license)
+
+## Quick Start
+
+```bash
+# Install
+pip install ngpt
+
+# Chat with default settings
+ngpt "Tell me about quantum computing"
+
+# Generate code
+ngpt --code "function to calculate the Fibonacci sequence"
+
+# Generate and execute shell commands
+ngpt --shell "list all files in the current directory"
+```
+
 ## Features
 
-- Dual mode: Use as a CLI tool or import as a library
-- Minimal dependencies
-- Customizable API endpoints and providers
-- Streaming responses
-- Web search capability (supported by compatible API endpoints)
-- Cross-platform configuration system
-- Experimental features:
-  - Shell command generation and execution (OS-aware)
-  - Code generation with clean output
+- ✅ **Dual Mode**: Use as a CLI tool or import as a Python library
+- 🪶 **Lightweight**: Minimal dependencies (just `requests`)
+- 🔄 **API Flexibility**: Works with OpenAI, Ollama, Groq, and any compatible endpoint
+- 📊 **Streaming Responses**: Real-time output for better user experience
+- 🔍 **Web Search**: Integrated with compatible API endpoints
+- ⚙️ **Multiple Configurations**: Cross-platform config system supporting different profiles
+- 💻 **Shell Command Generation**: OS-aware command execution
+- 🧩 **Clean Code Generation**: Output code without markdown or explanations
 
 ## Installation
 
@@ -53,6 +85,8 @@ A lightweight Python CLI and library for interacting with OpenAI-compatible APIs
 pip install ngpt
 ```
 
+Requires Python 3.8 or newer.
+
 ## Usage
 
 ### As a CLI Tool
@@ -71,15 +105,19 @@ ngpt --show-config
 ngpt --show-config --all
 
 # With custom options
-ngpt --api-key your-key --base-url http://your-endpoint "Hello"
+ngpt --api-key your-key --base-url http://your-endpoint --model your-model "Hello"
 
 # Enable web search (if your API endpoint supports it)
 ngpt --web-search "What's the latest news about AI?"
 
 # Generate and execute shell commands (using -s or --shell flag)
+# OS-aware: generates appropriate commands for Windows, macOS, or Linux
 ngpt -s "list all files in current directory"
+# On Windows generates: dir
+# On Linux/macOS generates: ls -la
 
-# Generate code (using -c or --code flag)
+# Generate clean code (using -c or --code flag)
+# Returns only code without markdown formatting or explanations
 ngpt -c "create a python function that calculates fibonacci numbers"
 ```
 
@@ -115,20 +153,51 @@ command = client.generate_shell_command("list all files")
 code = client.generate_code("create a python function that calculates fibonacci numbers")
 ```
 
+#### Advanced Library Usage
+
+```python
+# Stream responses
+for chunk in client.chat("Write a poem about Python", stream=True):
+    print(chunk, end="", flush=True)
+
+# Customize system prompt
+response = client.chat(
+    "Explain quantum computing",
+    system_prompt="You are a quantum physics professor. Explain complex concepts simply."
+)
+
+# OS-aware shell commands
+# Automatically generates appropriate commands for the current OS
+command = client.generate_shell_command("find large files")
+import subprocess
+result = subprocess.run(command, shell=True, capture_output=True, text=True)
+print(result.stdout)
+
+# Clean code generation
+# Returns only code without markdown or explanations
+code = client.generate_code("function that converts Celsius to Fahrenheit")
+print(code)
+```
+
 ## Configuration
 
 ### Command Line Options
 
 You can configure the client using the following options:
 
-- `--api-key`: API key for the service
-- `--base-url`: Base URL for the API
-- `--model`: Model to use
-- `--web-search`: Enable web search capability (Note: Your API endpoint must support this feature)
-- `--config`: Path to a custom configuration file
-- `--config-index`: Index of the configuration to use from the config file (default: 0)
-- `--show-config`: Show configuration details and exit.
-- `--all`: Used with `--show-config` to display details for all configurations.
+| Option | Description |
+|--------|-------------|
+| `--api-key` | API key for the service |
+| `--base-url` | Base URL for the API |
+| `--model` | Model to use |
+| `--web-search` | Enable web search capability |
+| `--config` | Path to a custom configuration file |
+| `--config-index` | Index of the configuration to use (default: 0) |
+| `--show-config` | Show configuration details and exit |
+| `--all` | Used with `--show-config` to display all configurations |
+| `-s, --shell` | Generate and execute shell commands |
+| `-c, --code` | Generate clean code output |
+| `-v, --version` | Show version information |
 
 ### Configuration File
 
@@ -173,20 +242,6 @@ nGPT determines configuration values in the following order (highest priority fi
 3. Configuration file (selected by `--config-index`, defaults to index 0)
 4. Default values
 
-## Special Features
-
-### OS-Aware Shell Commands
-
-Shell command generation is OS-aware, providing appropriate commands for your operating system (Windows, macOS, or Linux) and shell type (bash, powershell, etc.).
-
-### Clean Code Generation
-
-Code generation uses an improved prompt that ensures only clean code is returned, without markdown formatting or unnecessary explanations.
-
-## Implementation Notes
-
-This library uses direct HTTP requests instead of the OpenAI client library, allowing it to work with custom API endpoints that support additional parameters like `provider` and `web_search`. All parameters are sent directly in the request body, similar to the format shown in the curl example.
-
 ## License
 
 This project is licensed under the MIT License. See the [LICENSE](LICENSE) file for details.

ngpt-1.1.3/README.md

@@ -0,0 +1,214 @@
+# nGPT
+
+[![PyPI version](https://img.shields.io/pypi/v/ngpt.svg)](https://pypi.org/project/ngpt/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+[![Python Versions](https://img.shields.io/pypi/pyversions/ngpt.svg)](https://pypi.org/project/ngpt/)
+
+A lightweight Python CLI and library for interacting with OpenAI-compatible APIs, supporting both official and self-hosted LLM endpoints.
+
+## Table of Contents
+- [Quick Start](#quick-start)
+- [Features](#features)
+- [Installation](#installation)
+- [Usage](#usage)
+  - [CLI Tool](#as-a-cli-tool)
+  - [Python Library](#as-a-library)
+- [Configuration](#configuration)
+  - [Command Line Options](#command-line-options)
+  - [Configuration File](#configuration-file)
+  - [Configuration Priority](#configuration-priority)
+- [License](#license)
+
+## Quick Start
+
+```bash
+# Install
+pip install ngpt
+
+# Chat with default settings
+ngpt "Tell me about quantum computing"
+
+# Generate code
+ngpt --code "function to calculate the Fibonacci sequence"
+
+# Generate and execute shell commands
+ngpt --shell "list all files in the current directory"
+```
+
+## Features
+
+- ✅ **Dual Mode**: Use as a CLI tool or import as a Python library
+- 🪶 **Lightweight**: Minimal dependencies (just `requests`)
+- 🔄 **API Flexibility**: Works with OpenAI, Ollama, Groq, and any compatible endpoint
+- 📊 **Streaming Responses**: Real-time output for better user experience
+- 🔍 **Web Search**: Integrated with compatible API endpoints
+- ⚙️ **Multiple Configurations**: Cross-platform config system supporting different profiles
+- 💻 **Shell Command Generation**: OS-aware command execution
+- 🧩 **Clean Code Generation**: Output code without markdown or explanations
+
+## Installation
+
+```bash
+pip install ngpt
+```
+
+Requires Python 3.8 or newer.
+
+## Usage
+
+### As a CLI Tool
+
+```bash
+# Basic chat (default mode)
+ngpt "Hello, how are you?"
+
+# Show version information
+ngpt -v
+
+# Show active configuration
+ngpt --show-config
+
+# Show all configurations
+ngpt --show-config --all
+
+# With custom options
+ngpt --api-key your-key --base-url http://your-endpoint --model your-model "Hello"
+
+# Enable web search (if your API endpoint supports it)
+ngpt --web-search "What's the latest news about AI?"
+
+# Generate and execute shell commands (using -s or --shell flag)
+# OS-aware: generates appropriate commands for Windows, macOS, or Linux
+ngpt -s "list all files in current directory"
+# On Windows generates: dir
+# On Linux/macOS generates: ls -la
+
+# Generate clean code (using -c or --code flag)
+# Returns only code without markdown formatting or explanations
+ngpt -c "create a python function that calculates fibonacci numbers"
+```
+
+### As a Library
+
+```python
+from ngpt import NGPTClient, load_config
+
+# Load the first configuration (index 0) from config file
+config = load_config(config_index=0)
+
+# Initialize the client with config
+client = NGPTClient(**config)
+
+# Or initialize with custom parameters
+client = NGPTClient(
+    api_key="your-key",
+    base_url="http://your-endpoint",
+    provider="openai",
+    model="o3-mini"
+)
+
+# Chat
+response = client.chat("Hello, how are you?")
+
+# Chat with web search (if your API endpoint supports it)
+response = client.chat("What's the latest news about AI?", web_search=True)
+
+# Generate shell command
+command = client.generate_shell_command("list all files")
+
+# Generate code
+code = client.generate_code("create a python function that calculates fibonacci numbers")
+```
+
+#### Advanced Library Usage
+
+```python
+# Stream responses
+for chunk in client.chat("Write a poem about Python", stream=True):
+    print(chunk, end="", flush=True)
+
+# Customize system prompt
+response = client.chat(
+    "Explain quantum computing",
+    system_prompt="You are a quantum physics professor. Explain complex concepts simply."
+)
+
+# OS-aware shell commands
+# Automatically generates appropriate commands for the current OS
+command = client.generate_shell_command("find large files")
+import subprocess
+result = subprocess.run(command, shell=True, capture_output=True, text=True)
+print(result.stdout)
+
+# Clean code generation
+# Returns only code without markdown or explanations
+code = client.generate_code("function that converts Celsius to Fahrenheit")
+print(code)
+```
+
+## Configuration
+
+### Command Line Options
+
+You can configure the client using the following options:
+
+| Option | Description |
+|--------|-------------|
+| `--api-key` | API key for the service |
+| `--base-url` | Base URL for the API |
+| `--model` | Model to use |
+| `--web-search` | Enable web search capability |
+| `--config` | Path to a custom configuration file |
+| `--config-index` | Index of the configuration to use (default: 0) |
+| `--show-config` | Show configuration details and exit |
+| `--all` | Used with `--show-config` to display all configurations |
+| `-s, --shell` | Generate and execute shell commands |
+| `-c, --code` | Generate clean code output |
+| `-v, --version` | Show version information |
+
+### Configuration File
+
+nGPT uses a configuration file stored in the standard user config directory for your operating system:
+
+- **Linux**: `~/.config/ngpt/ngpt.conf` or `$XDG_CONFIG_HOME/ngpt/ngpt.conf`
+- **macOS**: `~/Library/Application Support/ngpt/ngpt.conf`
+- **Windows**: `%APPDATA%\ngpt\ngpt.conf`
+
+The configuration file uses a JSON list format, allowing you to store multiple configurations. You can select which configuration to use with the `--config-index` argument (or by default, index 0 is used).
+
+#### Multiple Configurations Example (`ngpt.conf`)
+```json
+[
+  {
+    "api_key": "your-openai-api-key-here",
+    "base_url": "https://api.openai.com/v1/",
+    "provider": "OpenAI",
+    "model": "gpt-4o"
+  },
+  {
+    "api_key": "your-groq-api-key-here",
+    "base_url": "https://api.groq.com/openai/v1/",
+    "provider": "Groq",
+    "model": "llama3-70b-8192"
+  },
+  {
+    "api_key": "your-ollama-key-if-needed",
+    "base_url": "http://localhost:11434/v1/",
+    "provider": "Ollama-Local",
+    "model": "llama3"
+  }
+]
+```
+
+### Configuration Priority
+
+nGPT determines configuration values in the following order (highest priority first):
+
+1. Command line arguments (`--api-key`, `--base-url`, `--model`)
+2. Environment variables (`OPENAI_API_KEY`, `OPENAI_BASE_URL`, `OPENAI_MODEL`)
+3. Configuration file (selected by `--config-index`, defaults to index 0)
+4. Default values
+
+## License
+
+This project is licensed under the MIT License. See the [LICENSE](LICENSE) file for details.

{ngpt-1.1.1 → ngpt-1.1.3}/ngpt/cli.py

@@ -35,11 +35,10 @@ def show_config_help():
     print("  3. Or set environment variables:")
     print("     - OPENAI_API_KEY")
     print("     - OPENAI_BASE_URL")
-    print("     - OPENAI_PROVIDER")
     print("     - OPENAI_MODEL")
     
     print("  4. Or provide command line arguments:")
-    print("     ngpt --api-key your-key --base-url https://api.example.com \"Your prompt\"")
+    print("     ngpt --api-key your-key --base-url https://api.example.com --model your-model \"Your prompt\"")
     
     print("  5. Use --config-index to specify which configuration to use:")
     print("     ngpt --config-index 1 \"Your prompt\"")
@@ -171,8 +170,12 @@ def main():
         # Handle modes
         if args.shell:
             if args.prompt is None:
-                print("Enter shell command description: ", end='')
-                prompt = input()
+                try:
+                    print("Enter shell command description: ", end='')
+                    prompt = input()
+                except KeyboardInterrupt:
+                    print("\nInput cancelled by user. Exiting gracefully.")
+                    sys.exit(130)
             else:
                 prompt = args.prompt
                 
@@ -182,20 +185,33 @@ def main():
                 
             print(f"\nGenerated command: {command}")
             
-            print("Do you want to execute this command? [y/N] ", end='')
-            response = input().lower()
+            try:
+                print("Do you want to execute this command? [y/N] ", end='')
+                response = input().lower()
+            except KeyboardInterrupt:
+                print("\nCommand execution cancelled by user.")
+                return
+                
             if response == 'y' or response == 'yes':
                 import subprocess
                 try:
-                    result = subprocess.run(command, shell=True, check=True, capture_output=True, text=True)
-                    print(f"\nOutput:\n{result.stdout}")
+                    try:
+                        print("\nExecuting command... (Press Ctrl+C to cancel)")
+                        result = subprocess.run(command, shell=True, check=True, capture_output=True, text=True)
+                        print(f"\nOutput:\n{result.stdout}")
+                    except KeyboardInterrupt:
+                        print("\nCommand execution cancelled by user.")
                 except subprocess.CalledProcessError as e:
                     print(f"\nError:\n{e.stderr}")
                     
         elif args.code:
             if args.prompt is None:
-                print("Enter code description: ", end='')
-                prompt = input()
+                try:
+                    print("Enter code description: ", end='')
+                    prompt = input()
+                except KeyboardInterrupt:
+                    print("\nInput cancelled by user. Exiting gracefully.")
+                    sys.exit(130)
             else:
                 prompt = args.prompt
                 
@@ -206,16 +222,23 @@ def main():
         else:
             # Default to chat mode
             if args.prompt is None:
-                print("Enter your prompt: ", end='')
-                prompt = input()
+                try:
+                    print("Enter your prompt: ", end='')
+                    prompt = input()
+                except KeyboardInterrupt:
+                    print("\nInput cancelled by user. Exiting gracefully.")
+                    sys.exit(130)
             else:
                 prompt = args.prompt
             client.chat(prompt, web_search=args.web_search)
     
     except KeyboardInterrupt:
-        print("\nOperation cancelled by user.")
+        print("\nOperation cancelled by user. Exiting gracefully.")
+        # Make sure we exit with a non-zero status code to indicate the operation was cancelled
+        sys.exit(130)  # 130 is the standard exit code for SIGINT (Ctrl+C)
     except Exception as e:
         print(f"Error: {e}")
+        sys.exit(1)  # Exit with error code
 
 if __name__ == "__main__":
     main() 

{ngpt-1.1.1 → ngpt-1.1.3}/ngpt/client.py

@@ -82,43 +82,51 @@ class NGPTClient:
         try:
             if not stream:
                 # Regular request
-                response = requests.post(url, headers=self.headers, json=payload)
-                response.raise_for_status()  # Raise exception for HTTP errors
-                result = response.json()
-                
-                # Extract content from response
-                if "choices" in result and len(result["choices"]) > 0:
-                    return result["choices"][0]["message"]["content"]
-                return ""
+                try:
+                    response = requests.post(url, headers=self.headers, json=payload)
+                    response.raise_for_status()  # Raise exception for HTTP errors
+                    result = response.json()
+                    
+                    # Extract content from response
+                    if "choices" in result and len(result["choices"]) > 0:
+                        return result["choices"][0]["message"]["content"]
+                    return ""
+                except KeyboardInterrupt:
+                    print("\nRequest cancelled by user.")
+                    return ""
             else:
                 # Streaming request
                 collected_content = ""
                 with requests.post(url, headers=self.headers, json=payload, stream=True) as response:
                     response.raise_for_status()  # Raise exception for HTTP errors
                     
-                    for line in response.iter_lines():
-                        if not line:
-                            continue
-                            
-                        # Handle SSE format
-                        line = line.decode('utf-8')
-                        if line.startswith('data: '):
-                            line = line[6:]  # Remove 'data: ' prefix
-                            
-                            # Skip keep-alive lines
-                            if line == "[DONE]":
-                                break
+                    try:
+                        for line in response.iter_lines():
+                            if not line:
+                                continue
+                                
+                            # Handle SSE format
+                            line = line.decode('utf-8')
+                            if line.startswith('data: '):
+                                line = line[6:]  # Remove 'data: ' prefix
                                 
-                            try:
-                                chunk = json.loads(line)
-                                if "choices" in chunk and len(chunk["choices"]) > 0:
-                                    delta = chunk["choices"][0].get("delta", {})
-                                    content = delta.get("content", "")
-                                    if content:
-                                        print(content, end="", flush=True)
-                                        collected_content += content
-                            except json.JSONDecodeError:
-                                pass  # Skip invalid JSON
+                                # Skip keep-alive lines
+                                if line == "[DONE]":
+                                    break
+                                    
+                                try:
+                                    chunk = json.loads(line)
+                                    if "choices" in chunk and len(chunk["choices"]) > 0:
+                                        delta = chunk["choices"][0].get("delta", {})
+                                        content = delta.get("content", "")
+                                        if content:
+                                            print(content, end="", flush=True)
+                                            collected_content += content
+                                except json.JSONDecodeError:
+                                    pass  # Skip invalid JSON
+                    except KeyboardInterrupt:
+                        print("\nGeneration cancelled by user.")
+                        return collected_content
                 
                 print()  # Add a final newline
                 return collected_content

{ngpt-1.1.1 → ngpt-1.1.3}/ngpt/config.py

@@ -56,22 +56,26 @@ def add_config_entry(config_path: Path, config_index: Optional[int] = None) -> N
     
     # Interactive configuration
     print("Enter configuration details (press Enter to use default values):")
-    new_entry["api_key"] = input(f"API Key: ") or new_entry["api_key"]
-    new_entry["base_url"] = input(f"Base URL [{new_entry['base_url']}]: ") or new_entry["base_url"]
-    new_entry["provider"] = input(f"Provider [{new_entry['provider']}]: ") or new_entry["provider"]
-    new_entry["model"] = input(f"Model [{new_entry['model']}]: ") or new_entry["model"]
-    
-    # Add or update the entry
-    if config_index is not None and config_index < len(configs):
-        configs[config_index] = new_entry
-        print(f"Updated configuration at index {config_index}")
-    else:
-        configs.append(new_entry)
-        print(f"Added new configuration at index {len(configs)-1}")
-    
-    # Save the updated configs
-    with open(config_path, "w") as f:
-        json.dump(configs, f, indent=2)
+    try:
+        new_entry["api_key"] = input(f"API Key: ") or new_entry["api_key"]
+        new_entry["base_url"] = input(f"Base URL [{new_entry['base_url']}]: ") or new_entry["base_url"]
+        new_entry["provider"] = input(f"Provider [{new_entry['provider']}]: ") or new_entry["provider"]
+        new_entry["model"] = input(f"Model [{new_entry['model']}]: ") or new_entry["model"]
+        
+        # Add or update the entry
+        if config_index is not None and config_index < len(configs):
+            configs[config_index] = new_entry
+            print(f"Updated configuration at index {config_index}")
+        else:
+            configs.append(new_entry)
+            print(f"Added new configuration at index {len(configs)-1}")
+        
+        # Save the updated configs
+        with open(config_path, "w") as f:
+            json.dump(configs, f, indent=2)
+    except KeyboardInterrupt:
+        print("\nConfiguration cancelled by user. Exiting.")
+        sys.exit(130)  # Exit with standard keyboard interrupt code
 
 def load_configs(custom_path: Optional[str] = None) -> List[Dict[str, Any]]:
     """

{ngpt-1.1.1 → ngpt-1.1.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "ngpt"
-version = "1.1.1"
+version = "1.1.3"
 description = "A lightweight Python CLI and library for interacting with OpenAI-compatible APIs, supporting both official and self-hosted LLM endpoints."
 authors = [
     {name = "nazDridoy", email = "nazdridoy399@gmail.com"},

{ngpt-1.1.1 → ngpt-1.1.3}/uv.lock

@@ -113,7 +113,7 @@ wheels = [
 
 [[package]]
 name = "ngpt"
-version = "1.1.0"
+version = "1.1.3"
 source = { editable = "." }
 dependencies = [
     { name = "requests" },

ngpt-1.1.1/README.md

@@ -1,159 +0,0 @@
-# nGPT
-
-A lightweight Python CLI and library for interacting with OpenAI-compatible APIs, supporting both official and self-hosted LLM endpoints.
-
-## Features
-
-- Dual mode: Use as a CLI tool or import as a library
-- Minimal dependencies
-- Customizable API endpoints and providers
-- Streaming responses
-- Web search capability (supported by compatible API endpoints)
-- Cross-platform configuration system
-- Experimental features:
-  - Shell command generation and execution (OS-aware)
-  - Code generation with clean output
-
-## Installation
-
-```bash
-pip install ngpt
-```
-
-## Usage
-
-### As a CLI Tool
-
-```bash
-# Basic chat (default mode)
-ngpt "Hello, how are you?"
-
-# Show version information
-ngpt -v
-
-# Show active configuration
-ngpt --show-config
-
-# Show all configurations
-ngpt --show-config --all
-
-# With custom options
-ngpt --api-key your-key --base-url http://your-endpoint "Hello"
-
-# Enable web search (if your API endpoint supports it)
-ngpt --web-search "What's the latest news about AI?"
-
-# Generate and execute shell commands (using -s or --shell flag)
-ngpt -s "list all files in current directory"
-
-# Generate code (using -c or --code flag)
-ngpt -c "create a python function that calculates fibonacci numbers"
-```
-
-### As a Library
-
-```python
-from ngpt import NGPTClient, load_config
-
-# Load the first configuration (index 0) from config file
-config = load_config(config_index=0)
-
-# Initialize the client with config
-client = NGPTClient(**config)
-
-# Or initialize with custom parameters
-client = NGPTClient(
-    api_key="your-key",
-    base_url="http://your-endpoint",
-    provider="openai",
-    model="o3-mini"
-)
-
-# Chat
-response = client.chat("Hello, how are you?")
-
-# Chat with web search (if your API endpoint supports it)
-response = client.chat("What's the latest news about AI?", web_search=True)
-
-# Generate shell command
-command = client.generate_shell_command("list all files")
-
-# Generate code
-code = client.generate_code("create a python function that calculates fibonacci numbers")
-```
-
-## Configuration
-
-### Command Line Options
-
-You can configure the client using the following options:
-
-- `--api-key`: API key for the service
-- `--base-url`: Base URL for the API
-- `--model`: Model to use
-- `--web-search`: Enable web search capability (Note: Your API endpoint must support this feature)
-- `--config`: Path to a custom configuration file
-- `--config-index`: Index of the configuration to use from the config file (default: 0)
-- `--show-config`: Show configuration details and exit.
-- `--all`: Used with `--show-config` to display details for all configurations.
-
-### Configuration File
-
-nGPT uses a configuration file stored in the standard user config directory for your operating system:
-
-- **Linux**: `~/.config/ngpt/ngpt.conf` or `$XDG_CONFIG_HOME/ngpt/ngpt.conf`
-- **macOS**: `~/Library/Application Support/ngpt/ngpt.conf`
-- **Windows**: `%APPDATA%\ngpt\ngpt.conf`
-
-The configuration file uses a JSON list format, allowing you to store multiple configurations. You can select which configuration to use with the `--config-index` argument (or by default, index 0 is used).
-
-#### Multiple Configurations Example (`ngpt.conf`)
-```json
-[
-  {
-    "api_key": "your-openai-api-key-here",
-    "base_url": "https://api.openai.com/v1/",
-    "provider": "OpenAI",
-    "model": "gpt-4o"
-  },
-  {
-    "api_key": "your-groq-api-key-here",
-    "base_url": "https://api.groq.com/openai/v1/",
-    "provider": "Groq",
-    "model": "llama3-70b-8192"
-  },
-  {
-    "api_key": "your-ollama-key-if-needed",
-    "base_url": "http://localhost:11434/v1/",
-    "provider": "Ollama-Local",
-    "model": "llama3"
-  }
-]
-```
-
-### Configuration Priority
-
-nGPT determines configuration values in the following order (highest priority first):
-
-1. Command line arguments (`--api-key`, `--base-url`, `--model`)
-2. Environment variables (`OPENAI_API_KEY`, `OPENAI_BASE_URL`, `OPENAI_MODEL`)
-3. Configuration file (selected by `--config-index`, defaults to index 0)
-4. Default values
-
-## Special Features
-
-### OS-Aware Shell Commands
-
-Shell command generation is OS-aware, providing appropriate commands for your operating system (Windows, macOS, or Linux) and shell type (bash, powershell, etc.).
-
-### Clean Code Generation
-
-Code generation uses an improved prompt that ensures only clean code is returned, without markdown formatting or unnecessary explanations.
-
-## Implementation Notes
-
-This library uses direct HTTP requests instead of the OpenAI client library, allowing it to work with custom API endpoints that support additional parameters like `provider` and `web_search`. All parameters are sent directly in the request body, similar to the format shown in the curl example.
-
-## License
-
-This project is licensed under the MIT License. See the [LICENSE](LICENSE) file for details.