open-code-interpreter 2.1

An innovative open-source Code Interpreter with (GPT,Gemini,PALM,LLaMa) models.

Hosting and Spaces:

Support Project:

Welcome to Code-Interpreter 🎉, an innovative open-source and free alternative to traditional Code Interpreters. This is powerful tool and it also leverages the power of GPT 3.5 Turbo,PALM 2,Groq,Claude, HuggingFace models like Code-llama, Mistral 7b, Wizard Coder, and many more to transform your instructions into executable code for free and safe to use environments and even has Vision Models for Image Processing available.

Code-Interpreter is more than just a code generator. It's a versatile tool that can execute a wide range of tasks. Whether you need to find files in your system 📂, save images from a website and convert them into a different format 🖼️, create a GIF 🎞️, edit videos 🎥, or even analyze files for data analysis and creating graphs 📊, Code-Interpreter can handle it all.

After processing your instructions, Code-Interpreter executes the generated code and provides you with the result. This makes it an invaluable tool for developers 💻, data scientists 🧪, and anyone who needs to quickly turn ideas into working code and now with Vision Models it can also process images and videos.

Designed with versatility in mind, Code-Interpreter works seamlessly on every operating system, including Windows, MacOS, and Linux. So, no matter what platform you're on, you can take advantage of this powerful tool 💪.

Experience the future of code interpretation with Code-Interpreter today! 🚀

Why this is Unique Interpreter?

The distinguishing feature of this interpreter, as compared to others, is its commitment to remain free 🆓. It does not require any model to download or follow to tedious processes or methods for execution. It is designed to be simple and free for all users and works on all major OS Windows,Linux,MacOS

Future Plans:

• 🎯 We plan to integrate GPT 3.5 models. 🎯 We have added support for GPT 3.5 models.
• 🌐 .We plan to provide Vertex AI (PALM 2) models.. We have added support for PALM-2 model using LiteLLM
• 🔗 We plan to provide API Base change using LiteLLM. Added Support for LiteLLM
• 🤖 More Hugging Face models with free-tier.
• 💻 Support for more Operating Systems.
• 📝 Support for Multi-Modal for Text and Vision.
• 📊 Support for Google and OpenAI Vision Models.
• 💻 Support for Local models via LLM Studio.
• 🔗 Support for Multi-Modal models from Anthropic AI.

Table of Contents

• Features
• Installation
• Usage
• Examples
• Settings
• Contributing
• Versioning
• License
• Acknowledgments

📥 Installation

Installtion with Python package manager.

To install Code-Interpreter, run the following command:

pip install open-code-interpreter

• To run the interpreter with Python:
  

interpreter -m 'gemini-pro' -md 'code' -dc

• Make sure you install required packages before running the interpreter.
  
• And you have API keys setup in the .env file.
  

Installtion with Git

To get started with Code-Interpreter, follow these steps:

1. Clone the repository:
   

git clone https://github.com/haseeb-heaven/code-interpreter.git
cd code-interpreter

2. Install the required packages:
   

pip install -r requirements.txt

3. Setup the Keys required.

API Key setup for All models.

Follow the steps below to obtain and set up the API keys for each service:

1. Obtain the API keys:

   • HuggingFace: Visit HuggingFace Tokens and get your Access Token.
   • Google Palm and Gemini: Visit Google AI Studio and click on the Create API Key button.
   • OpenAI: Visit OpenAI Dashboard, sign up or log in, navigate to the API section in your account dashboard, and click on the Create New Key button.
   • Groq AI: Obtain access here, then visit Groq AI Console, sign up or log in, navigate to the API section in your account, and click on the Create API Key button.
   • Anthropic AI: Obtain access here, then visit Anthropic AI Console, sign up or log in, navigate to the API Keys section in your account, and click on the Create Key button.

2. Save the API keys:

   • Create a .env file in your project root directory.
   • Open the .env file and add the following lines, replacing Your API Key with the respective keys:

export HUGGINGFACE_API_KEY="Your HuggingFace API Key"
export PALM_API_KEY="Your Google Palm API Key"
export GEMINI_API_KEY="Your Google Gemini API Key"
export OPENAI_API_KEY="Your OpenAI API Key"
export GROQ_API_KEY="Your Groq AI API Key"
export ANTHROPIC_API_KEY="Your Anthropic AI API Key"

Groq AI API Key setup.

Step 1: Obtain the GroqAI API key.

Step 2: Visit the following URL: Groq AI Console

Step 3: Sign up for an account or log in if you already have one.

Step 4: Navigate to the API section in your account.

Step 5: Click on the Create API Key button.

Step 6: The generated key is your API key. Please make sure to copy it and paste it in the required field below.

echo "GROQ_API_KEY=Your API Key" > .env

Anthropic AI API Key setup.

Step 1: Obtain the Anthropic Access by request.
Step 2: Obtain the Anthropic API Key Anthropic AI Console
Step 3: Sign up for an account or log in if you already have one.
Step 4: Navigate to the API Keys section in your account.
Step 5: Click on the Create Key button.
Step 6: The generated key is your API key. Please make sure to copy it and paste it in the required field below.

echo "ANTHROPIC_API_KEY=Your API Key" > .env

Offline models setup.

This Interpreter supports offline models via LM Studio so to download it from here and follow the steps below.

• Download any model from LM Studio like Phi-2,Code-Llama,Mistral.
• Then in the app go to Local Server option and select the model.
• Start the server and copy the URL.
• Open config file configs/offline-model.config and paste the URL in the api_base field.
• Now you can use the model with the interpreter set the model name to offline-model and run the interpreter.
  

4. Run the interpreter with Python:
   

Running with Python.

python interpreter.py -md 'code' -m 'gpt-3.5-turbo' -dc 

5. Run the interpreter directly:
   

Running Interpreter without Python (Executable MacOs/Linux only).

./interpreter -md 'code' -m 'gpt-3.5-turbo' -dc 

🌟 Features

• 🚀 Code Execution: Code-Interpreter can execute the code generated from your instructions.

• 💾 Code Save/Update: It has the ability to save the generated code for future use and edit the code if needed on the fly using advanced editor.

• 📡 Offline models: It has the ability to use offline models for code generation using LLM Studio.

• 📜 Command History: It has the ability to save all the commands as history.

• 📜 Command Mode: Commands entered with '/' are executed as commands like /execute or /edit.

• 🔄 Mode Selection: It allows you to select the mode of operation. You can choose from code for generating code, script for generating shell scripts, or command for generating single line commands.

• 🧠 Model Selection: You can set the model for code generation. By default, it uses the code-llama model.

• 🌐 Language Selection: You can set the interpreter language to Python or JavaScript. By default, it uses Python.

• 👀 Code Display: It can display the generated code in the output, allowing you to review the code before execution.

• 💻 Cross-Platform: Code-Interpreter works seamlessly on every operating system, including Windows, MacOS, and Linux.

• 🤝 Integration with HuggingFace: It leverages the power of HuggingFace models like Code-llama, Mistral 7b, Wizard Coder, and many more to transform your instructions into executable code.

• 🎯 Versatility: Whether you need to find files in your system, save images from a website and convert them into a different format, create a GIF, edit videos, or even analyze files for data analysis and creating graphs, Code-Interpreter can handle it all.

🛠️ Usage

To use Code-Interpreter, use the following command options:

• List of all modes are:
  

  • code - Generates code from your instructions.
  • script - Generates shell scripts from your instructions.
  • command - Generates single line commands from your instructions.
  • vision - Generates description of image or video.

• List of all models are (Contribute - MORE):
  

  • gpt-3.5-turbo - Generates code using the GPT 3.5 Turbo model.
  • gpt-4 - Generates code using the GPT 4 model.
  • gemini-pro - Generates code using the Gemini Pro model.
  • palm-2 - Generates code using the PALM 2 model.
  • claude-2 - Generates code using the AnthropicAI Claude-2 model.
  • claude-3 - Generates code using the AnthropicAI Claude-3 model.
  • groq-mixtral - Generates code using the Groq Mixtral model.
  • groq-llama2 - Generates code using the Groq Llama2 model.
  • code-llama - Generates code using the Code-llama model.
  • code-llama-phind - Generates code using the Code-llama Phind model.
  • mistral-7b - Generates code using the Mistral 7b model.
  • wizard-coder - Generates code using the Wizard Coder model.
  • star-chat - Generates code using the Star Chat model.
  • offline-model - Generates code using the Offline model.

• Basic usage (with least options)
  

python interpreter.py -dc

• Using different models (replace 'model-name' with your chosen model)
  

python interpreter.py -md 'code' -m 'model-name' -dc

• Using different modes (replace 'mode-name' with your chosen mode)
  

python interpreter.py -m 'model-name' -md 'mode-name'

• Using auto execution
  

python interpreter.py -m 'wizard-coder' -md 'code' -dc -e

• Saving the code
  

python interpreter.py -m 'code-llama' -md 'code' -s

• Selecting a language (replace 'language-name' with your chosen language)
  

python interpreter.py -m 'gemini-pro' -md 'code' -s -l 'language-name'

Interpreter Commands 🖥️

Here are the available commands:

• 📝 /save - Save the last code generated.
• ✏️ /edit - Edit the last code generated.
• ▶️ /execute - Execute the last code generated.
• 🔄 /mode - Change the mode of interpreter.
• 🔄 /model - Change the model for interpreter.
• 📦 /install - Install a package from npm or pip.
• 🌐 /language - Change the language of the interpreter.
• 🧹 /clear - Clear the screen.
• 🆘 /help - Display this help message.
• 🚪 /list - List all the models available.
• 📝 /version - Display the version of the interpreter.
• 🚪 /exit - Exit the interpreter.
• 📜 /log - Toggle different modes of logging.
• ⏫ /upgrade - Upgrade the interpreter.
• 💻 /shell - Access the shell.

⚙️ Settings

You can customize the settings of the current model from the .config file. It contains all the necessary parameters such as temperature, max_tokens, and more.

Steps to add your own custom API Server

To integrate your own API server for OpenAI instead of the default server, follow these steps:

1. Navigate to the Configs directory.
2. Open the configuration file for the model you want to modify. This could be either gpt-3.5-turbo.config or gpt-4.config.
3. Add the following line at the end of the file:

   api_base = https://my-custom-base.com
   

   Replace https://my-custom-base.com with the URL of your custom API server.
4. Save and close the file. Now, whenever you select the gpt-3.5-turbo or gpt-4 model, the system will automatically use your custom server.

Steps to add new Hugging Face model

1. 📋 Copy the .config file and rename it to configs/hf-model-new.config.
2. 🛠️ Modify the parameters of the model like start_sep, end_sep, skip_first_line.
3. 📝 Set the model name from Hugging Face to HF_MODEL = 'Model name here'.
4. 🚀 Now, you can use it like this: python interpreter.py -m 'hf-model-new' -md 'code' -e.
5. 📁 Make sure the -m 'hf-model-new' matches the config file inside the configs folder.

Star History

🤝 Contributing

If you're interested in contributing to Code-Interpreter, we'd love to have you! Please fork the repository and submit a pull request. We welcome all contributions and are always eager to hear your feedback and suggestions for improvements.

📌 Versioning

🚀 v1.0 - Initial release.
📊 v1.1 - Added Graphs and Charts support.
🔥 v1.2 - Added LiteLLM Support.
🌟 v1.3 - Added GPT 3.5 Support.
🌴 v1.4 - Added PALM 2 Support.
🎉 v1.5 - Added GPT 3.5/4 models official Support.
📝 v1.6 - Updated Code Interpreter for Documents files (JSON, CSV, XML).
🌴 v1.7 - Added Gemini Pro Vision Support for Image Processing.

🌟 v1.8 - Added Interpreter Commands Support:

• 1.8.1 - Added Interpreter Commands Debugging Support.
• 1.8.2 - Fixed Interpreter Commands
• 1.8.3 - Added Interpreter Commands Upgrade and Shell Support.
• 1.8.4 - Fixed Interpreter Model switcher Bug.

🗨️ v1.9 - Added new Chat mode 🗨️ for Chatting with your Files, Data and more.

• v1.9.1 - Fixed Unit Tests and History Args
• v1.9.2 - Updated Google Vision to adapt LiteLLM instead of Google GenAI.
• v1.9.3 - Added Local Models Support via LM Studio.

🔥 v2.0 - Added Groq-AI Models Fastest LLM with 500 Tokens/Sec with Code-LLaMa, Mixtral models.

• v2.0.1 - Added AnthropicAI Claude-2, Instant models.

🔥 v2.1 - Added AnhtorpicAI Claude-3 models powerful Opus,Sonnet,Haiku models.

📜 License

This project is licensed under the MIT License. For more details, please refer to the LICENSE file.

Please note the following additional licensing details:

• The GPT 3.5/4 models are provided by OpenAI and are governed by their own licensing terms. Please ensure you have read and agreed to their terms before using these models. More information can be found at OpenAI's Terms of Use.

• The PALM models are officially supported by the Google PALM 2 API. These models have their own licensing terms and support. Please ensure you have read and agreed to their terms before using these models. More information can be found at Google Generative AI's Terms of Service.

• The Hugging Face models are provided by Hugging Face Inc. and are governed by their own licensing terms. Please ensure you have read and agreed to their terms before using these models. More information can be found at Hugging Face's Terms of Service.

• The Anthropic AI models are provided by Anthropic AI and are governed by their own licensing terms. Please ensure you have read and agreed to their terms before using these models. More information can be found at Anthropic AI's Terms of Service.

🙏 Acknowledgments

• We would like to express our gratitude to HuggingFace,Google,META,OpenAI,GroqAI,AnthropicAI for providing the models.
• A special shout-out to the open-source community. Your continuous support and contributions are invaluable to us.

📝 Author

This project is created and maintained by Haseeb-Heaven.