Merge branch 'main' into undo-cli

.gitignore

@@ -26,4 +26,7 @@ dist/
 # Ignore misc directory
 misc/
 
-.vscode/
+.vscode/
+
+# Ignore litellm_uuid.txt
+litellm_uuid.txt

README.md

@@ -2,11 +2,11 @@
 
 <p align="center">
     <a href="https://discord.gg/6p3fD6rBVm">
-        <img alt="Discord" src="https://img.shields.io/discord/1146610656779440188?logo=discord&style=flat&logoColor=white">
+        <img alt="Discord" src="https://img.shields.io/discord/1146610656779440188?logo=discord&style=flat&logoColor=white"/>
     </a>
-    <a href="README_JA.md"><img src="https://img.shields.io/badge/ドキュメント-日本語-white.svg" alt="JA doc"></a>
-    <a href="README_ZH.md"><img src="https://img.shields.io/badge/文档-中文版-white.svg" alt="ZH doc"></a>
-    <img src="https://img.shields.io/static/v1?label=license&message=MIT&color=white&style=flat" alt="License">
+    <a href="README_JA.md"><img src="https://img.shields.io/badge/ドキュメント-日本語-white.svg" alt="JA doc"/></a>
+    <a href="README_ZH.md"><img src="https://img.shields.io/badge/文档-中文版-white.svg" alt="ZH doc"/></a>
+    <img src="https://img.shields.io/static/v1?label=license&message=MIT&color=white&style=flat" alt="License"/>
     <br><br>
     <b>Let language models run code on your computer.</b><br>
     An open-source, locally running implementation of OpenAI's Code Interpreter.<br>
@@ -218,9 +218,27 @@ You can activate debug mode by using it's flag (`interpreter --debug`), or mid-c
 ```shell
 $ interpreter
 ...
-> %debug # <- Turns on debug mode
+> %debug true <- Turns on debug mode
+
+> %debug false <- Turns off debug mode
 ```
 
+### Interactive Mode Commands
+
+In the interactive mode, you can use the below commands to enhance your experience. Here's a list of available commands:
+
+ **Available Commands:**                                                         
+ • `%debug [true/false]`: Toggle debug mode. Without arguments or with 'true', it 
+   enters debug mode. With 'false', it exits debug mode.                        
+ • `%reset`: Resets the current session.                                          
+ • `%save_message [path]`: Saves messages to a specified JSON path. If no path is 
+   provided, it defaults to 'messages.json'.                                    
+ • `%load_message [path]`: Loads messages from a specified JSON path. If no path  
+   is provided, it defaults to 'messages.json'.                                 
+ • `%help`: Show the help message.
+
+Feel free to try out these commands and let us know your feedback!
+
 ### Configuration with .env
 
 Open Interpreter allows you to set default behaviors using a .env file. This provides a flexible way to configure the interpreter without changing command-line arguments every time.

SECURITY.md

@@ -0,0 +1,41 @@
+# Open Interpreter Security Policy
+
+We take security seriously. Responsible reporting and disclosure of security
+vulnerabilities is important for the protection and privacy of our users. If you
+discover any security vulnerabilities, please follow these guidelines.
+
+Published security advisories are available on our [GitHub Security Advisories]
+page.
+
+To report a vulnerability, please draft a [new security advisory on GitHub]. Any
+fields that you are unsure of or don't understand can be left at their default
+values. The important part is that the vulnerability is reported. Once the
+security advisory draft has been created, we will validate the vulnerability and
+coordinate with you to fix it, release a patch, and responsibly disclose the
+vulnerability to the public. Read GitHub's documentation on [privately reporting
+a security vulnerability] for details.
+
+Please do not report undisclosed vulnerabilities on public sites or forums,
+including GitHub issues and pull requests. Reporting vulnerabilities to the
+public could allow attackers to exploit vulnerable applications before we have
+been able to release a patch and before applications have had time to install
+the patch. Once we have released a patch and sufficient time has passed for
+applications to install the patch, we will disclose the vulnerability to the
+public, at which time you will be free to publish details of the vulnerability
+on public sites and forums.
+
+If you have a fix for a security vulnerability, please do not submit a GitHub
+pull request. Instead, report the vulnerability as described in this policy.
+Once we have verified the vulnerability, we can create a [temporary private
+fork] to collaborate on a patch.
+
+We appreciate your cooperation in helping keep our users safe by following this
+policy.
+
+[github security advisories]: https://github.com/KillianLucas/open-interpreter/security/advisories
+[new security advisory on github]:
+  https://github.com/KillianLucas/open-interpreter/security/advisories/new
+[privately reporting a security vulnerability]:
+  https://docs.github.com/en/code-security/security-advisories/guidance-on-reporting-and-writing/privately-reporting-a-security-vulnerability
+[temporary private fork]:
+  https://docs.github.com/en/code-security/security-advisories/repository-security-advisories/collaborating-in-a-temporary-private-fork-to-resolve-a-repository-security-vulnerability

docs/GPU.md

@@ -26,16 +26,12 @@ benefit from offloading some of the work to your GPU.
 
     You may choose to install additional components if you like.
 
-2.  Once the CUDA Toolkit has finished installing, open a Command Prompt or
-    PowerShell window, and run the corresponding command. This ensures that the
+2.  Once the CUDA Toolkit has finished installing, open **x64 Native Tools Command
+    Prompt for VS 2022**, and run the following command. This ensures that the
     `CUDA_PATH` environment varilable is set.
 
     ```
-    # Command Prompt
     echo %CUDA_PATH%
-
-    # PowerShell
-    $env:CUDA_PATH
     ```
 
     If you don't get back something like this:
@@ -46,24 +42,19 @@ benefit from offloading some of the work to your GPU.
 
     Restart your computer, then repeat this step.
 
-3.  Once you have verified that the `CUDA_PATH` environment variable is set, run
-    the corresponding commands for your shell. This will reinstall the
-    `llama-cpp-python` package with NVIDIA GPU support.
+4.  Once you have verified that the `CUDA_PATH` environment variable is set, run
+    the following commands. This will reinstall the `llama-cpp-python` package
+    with NVIDIA GPU support.
 
     ```
-    # Command Prompt
     set FORCE_CMAKE=1 && set CMAKE_ARGS=-DLLAMA_CUBLAS=on
     pip install llama-cpp-python --force-reinstall --upgrade --no-cache-dir -vv
-
-    # PowerShell
-    $env:FORCE_CMAKE=1; $env:CMAKE_ARGS='-DLLAMA_CUBLAS=on'
-    pip install llama-cpp-python --force-reinstall --upgrade --no-cache-dir -vv
     ```
 
     The command should complete with no errors. If you receive an error, ask for
     help on [the Discord server](https://discord.gg/6p3fD6rBVm).
 
-4.  Once `llama-cpp-python` has been reinstalled, you can quickly check whether
+6.  Once `llama-cpp-python` has been reinstalled, you can quickly check whether
     GPU support has been installed and set up correctly by running the following
     command.
 
@@ -86,7 +77,7 @@ benefit from offloading some of the work to your GPU.
     False
     ```
 
-5.  Finally, run the following command to use Open Interpreter with a local
+7.  Finally, run the following command to use Open Interpreter with a local
     language model with GPU support.
 
     ```

docs/WINDOWS.md

@@ -30,10 +30,10 @@ The resolve this issue, perform the following steps.
 
     - C++ CMake tools for Windows
 
-3.  Once installed, open the Start menu, search for **Developer Command Prompt
-    for VS 2022**, and open it.
+3.  Once installed, open the Start menu, search for **x64 Native Tools Command
+    Prompt for VS 2022**, and open it.
 
-4.  Run the following command.
+5.  Run the following command.
 
     ```
     pip install llama-cpp-python --force-reinstall --upgrade --no-cache-dir

interpreter/code_interpreter.py

@@ -73,7 +73,7 @@ def run_html(html_content):
     "print_cmd": 'log "{}"'
   },
   "html": {
-    "open_subrocess": False,
+    "open_subprocess": False,
     "run_function": run_html,
   }
 }
@@ -150,10 +150,10 @@ def run(self):
     """
 
     # Should we keep a subprocess open? True by default
-    open_subrocess = language_map[self.language].get("open_subrocess", True)
+    open_subprocess = language_map[self.language].get("open_subprocess", True)
 
     # Start the subprocess if it hasn't been started
-    if not self.proc and open_subrocess:
+    if not self.proc and open_subprocess:
       try:
         self.start_process()
       except:

interpreter/get_hf_llm.py

@@ -121,10 +121,15 @@ def get_hf_llm(repo_id, debug_mode, context_window):
             if len(split_files) > 1:
                 # Download splits
                 for split_file in split_files:
+                    # Do we already have a file split downloaded?
+                    split_path = os.path.join(default_path, split_file)
+                    if os.path.exists(split_path):
+                        if not confirm_action(f"Split file {split_path} already exists. Download again?"):
+                            continue
                     hf_hub_download(repo_id=repo_id, filename=split_file, local_dir=default_path, local_dir_use_symlinks=False)
 
                 # Combine and delete splits
-                actually_combine_files(selected_model, split_files)
+                actually_combine_files(default_path, selected_model, split_files)
             else:
                 hf_hub_download(repo_id=repo_id, filename=selected_model, local_dir=default_path, local_dir_use_symlinks=False)
 
@@ -309,19 +314,21 @@ def group_and_combine_splits(models: List[Dict[str, Union[str, float]]]) -> List
     return list(grouped_files.values())
 
 
-def actually_combine_files(base_name: str, files: List[str]) -> None:
+def actually_combine_files(default_path: str, base_name: str, files: List[str]) -> None:
     """
     Combines files together and deletes the original split files.
 
     :param base_name: The base name for the combined file.
     :param files: List of files to be combined.
     """
     files.sort()    
-    with open(base_name, 'wb') as outfile:
+    base_path = os.path.join(default_path, base_name)
+    with open(base_path, 'wb') as outfile:
         for file in files:
-            with open(file, 'rb') as infile:
+            file_path = os.path.join(default_path, file)
+            with open(file_path, 'rb') as infile:
                 outfile.write(infile.read())
-            os.remove(file)
+            os.remove(file_path)
 
 def format_quality_choice(model, name_override = None) -> str:
     """