Do not install extensions requirements by default (#5621)

Colab-TextGen-GPU.ipynb

@@ -72,7 +72,6 @@
         "  with open('temp_requirements.txt', 'w') as file:\n",
         "      file.write('\\n'.join(textgen_requirements))\n",
         "\n",
-        "  !pip install -r extensions/openai/requirements.txt --upgrade\n",
         "  !pip install -r temp_requirements.txt --upgrade\n",
         "\n",
         "  print(\"\\033[1;32;1m\\n --> If you see a warning about \\\"previously imported packages\\\", just ignore it.\\033[0;37;0m\")\n",

README.md

@@ -46,8 +46,9 @@ The script uses Miniconda to set up a Conda environment in the `installer_files`
 If you ever need to install something manually in the `installer_files` environment, you can launch an interactive shell using the cmd script: `cmd_linux.sh`, `cmd_windows.bat`, `cmd_macos.sh`, or `cmd_wsl.bat`.
 
 * There is no need to run any of those scripts (`start_`, `update_`, or `cmd_`) as admin/root.
+* To install the requirements for extensions, you can use the `extensions_reqs` script for your OS. At the end, this script will install the main requirements for the project to make sure that they take precedence in case of version conflicts.
 * For additional instructions about AMD and WSL setup, consult [the documentation](https://github.com/oobabooga/text-generation-webui/wiki).
-* For automated installation, you can use the `GPU_CHOICE`, `USE_CUDA118`, `LAUNCH_AFTER_INSTALL`, and `INSTALL_EXTENSIONS` environment variables. For instance: `GPU_CHOICE=A USE_CUDA118=FALSE LAUNCH_AFTER_INSTALL=FALSE INSTALL_EXTENSIONS=FALSE ./start_linux.sh`.
+* For automated installation, you can use the `GPU_CHOICE`, `USE_CUDA118`, and `LAUNCH_AFTER_INSTALL` environment variables. For instance: `GPU_CHOICE=A USE_CUDA118=FALSE LAUNCH_AFTER_INSTALL=FALSE ./start_linux.sh`.
 
 ### Manual installation using Conda
 

docker/amd/Dockerfile

@@ -13,7 +13,7 @@ RUN --mount=type=cache,target=/var/cache/apt,sharing=locked,rw \
 WORKDIR /home/app/
 RUN git clone https://github.com/oobabooga/text-generation-webui.git 
 WORKDIR /home/app/text-generation-webui
-RUN GPU_CHOICE=B USE_CUDA118=FALSE LAUNCH_AFTER_INSTALL=FALSE INSTALL_EXTENSIONS=TRUE ./start_linux.sh --verbose
+RUN GPU_CHOICE=B USE_CUDA118=FALSE LAUNCH_AFTER_INSTALL=FALSE ./start_linux.sh --verbose
 COPY CMD_FLAGS.txt /home/app/text-generation-webui/
 EXPOSE ${CONTAINER_PORT:-7860} ${CONTAINER_API_PORT:-5000} ${CONTAINER_API_STREAM_PORT:-5005}
 WORKDIR /home/app/text-generation-webui

docker/cpu/Dockerfile

@@ -17,7 +17,7 @@ RUN --mount=type=cache,target=/var/cache/apt,sharing=locked,rw \
 WORKDIR /home/app/
 RUN git clone https://github.com/oobabooga/text-generation-webui.git 
 WORKDIR /home/app/text-generation-webui
-RUN GPU_CHOICE=N USE_CUDA118=FALSE LAUNCH_AFTER_INSTALL=FALSE INSTALL_EXTENSIONS=TRUE ./start_linux.sh --verbose
+RUN GPU_CHOICE=N USE_CUDA118=FALSE LAUNCH_AFTER_INSTALL=FALSE ./start_linux.sh --verbose
 COPY CMD_FLAGS.txt /home/app/text-generation-webui/
 EXPOSE ${CONTAINER_PORT:-7860} ${CONTAINER_API_PORT:-5000} ${CONTAINER_API_STREAM_PORT:-5005}
 # set umask to ensure group read / write at runtime

docker/intel/Dockerfile

@@ -13,7 +13,7 @@ RUN --mount=type=cache,target=/var/cache/apt,sharing=locked,rw \
 WORKDIR /home/app/
 RUN git clone https://github.com/oobabooga/text-generation-webui.git 
 WORKDIR /home/app/text-generation-webui
-RUN GPU_CHOICE=D USE_CUDA118=FALSE LAUNCH_AFTER_INSTALL=FALSE INSTALL_EXTENSIONS=TRUE ./start_linux.sh --verbose
+RUN GPU_CHOICE=D USE_CUDA118=FALSE LAUNCH_AFTER_INSTALL=FALSE ./start_linux.sh --verbose
 COPY CMD_FLAGS.txt /home/app/text-generation-webui/
 EXPOSE ${CONTAINER_PORT:-7860} ${CONTAINER_API_PORT:-5000} ${CONTAINER_API_STREAM_PORT:-5005}
 # set umask to ensure group read / write at runtime

docker/nvidia/Dockerfile

@@ -13,7 +13,7 @@ RUN --mount=type=cache,target=/var/cache/apt,sharing=locked,rw \
 WORKDIR /home/app/
 RUN git clone https://github.com/oobabooga/text-generation-webui.git 
 WORKDIR /home/app/text-generation-webui
-RUN GPU_CHOICE=A USE_CUDA118=FALSE LAUNCH_AFTER_INSTALL=FALSE INSTALL_EXTENSIONS=TRUE ./start_linux.sh --verbose
+RUN GPU_CHOICE=A USE_CUDA118=FALSE LAUNCH_AFTER_INSTALL=FALSE ./start_linux.sh --verbose
 COPY CMD_FLAGS.txt /home/app/text-generation-webui/
 EXPOSE ${CONTAINER_PORT:-7860} ${CONTAINER_API_PORT:-5000} ${CONTAINER_API_STREAM_PORT:-5005}
 WORKDIR /home/app/text-generation-webui

docs/12 - OpenAI API.md

@@ -7,12 +7,6 @@ The main API for this project is meant to be a drop-in replacement to the OpenAI
 * It doesn't connect to OpenAI.
 * It doesn't use the openai-python library.
 
-If you did not use the one-click installers, you may need to install the requirements first:
-
-```
-pip install -r extensions/openai/requirements.txt
-```
-
 ### Starting the API
 
 Add `--api` to your command-line flags.

extensions/openai/requirements.txt

@@ -1,4 +0,0 @@
-SpeechRecognition==3.10.0
-flask_cloudflared==0.0.14
-sse-starlette==1.6.5
-tiktoken

extensions_reqs_linux.sh

@@ -0,0 +1,26 @@
+#!/bin/bash
+
+cd "$(dirname "${BASH_SOURCE[0]}")"
+
+if [[ "$(pwd)" =~ " " ]]; then echo This script relies on Miniconda which can not be silently installed under a path with spaces. && exit; fi
+
+# deactivate existing conda envs as needed to avoid conflicts
+{ conda deactivate && conda deactivate && conda deactivate; } 2> /dev/null
+
+# config
+CONDA_ROOT_PREFIX="$(pwd)/installer_files/conda"
+INSTALL_ENV_DIR="$(pwd)/installer_files/env"
+
+# environment isolation
+export PYTHONNOUSERSITE=1
+unset PYTHONPATH
+unset PYTHONHOME
+export CUDA_PATH="$INSTALL_ENV_DIR"
+export CUDA_HOME="$CUDA_PATH"
+
+# activate installer env
+source "$CONDA_ROOT_PREFIX/etc/profile.d/conda.sh" # otherwise conda complains about 'shell not initialized' (needed when running in a script)
+conda activate "$INSTALL_ENV_DIR"
+
+# update installer env
+python one_click.py --install-extensions && echo -e "\nDone!"

extensions_reqs_macos.sh

@@ -0,0 +1,26 @@
+#!/bin/bash
+
+cd "$(dirname "${BASH_SOURCE[0]}")"
+
+if [[ "$(pwd)" =~ " " ]]; then echo This script relies on Miniconda which can not be silently installed under a path with spaces. && exit; fi
+
+# deactivate existing conda envs as needed to avoid conflicts
+{ conda deactivate && conda deactivate && conda deactivate; } 2> /dev/null
+
+# config
+CONDA_ROOT_PREFIX="$(pwd)/installer_files/conda"
+INSTALL_ENV_DIR="$(pwd)/installer_files/env"
+
+# environment isolation
+export PYTHONNOUSERSITE=1
+unset PYTHONPATH
+unset PYTHONHOME
+export CUDA_PATH="$INSTALL_ENV_DIR"
+export CUDA_HOME="$CUDA_PATH"
+
+# activate installer env
+source "$CONDA_ROOT_PREFIX/etc/profile.d/conda.sh" # otherwise conda complains about 'shell not initialized' (needed when running in a script)
+conda activate "$INSTALL_ENV_DIR"
+
+# update installer env
+python one_click.py --install-extensions && echo -e "\nDone!"

extensions_reqs_windows.bat

@@ -0,0 +1,37 @@
+@echo off
+
+cd /D "%~dp0"
+
+set PATH=%PATH%;%SystemRoot%\system32
+
+echo "%CD%"| findstr /C:" " >nul && echo This script relies on Miniconda which can not be silently installed under a path with spaces. && goto end
+
+@rem fix failed install when installing to a separate drive
+set TMP=%cd%\installer_files
+set TEMP=%cd%\installer_files
+
+@rem deactivate existing conda envs as needed to avoid conflicts
+(call conda deactivate && call conda deactivate && call conda deactivate) 2>nul
+
+@rem config
+set CONDA_ROOT_PREFIX=%cd%\installer_files\conda
+set INSTALL_ENV_DIR=%cd%\installer_files\env
+
+@rem environment isolation
+set PYTHONNOUSERSITE=1
+set PYTHONPATH=
+set PYTHONHOME=
+set "CUDA_PATH=%INSTALL_ENV_DIR%"
+set "CUDA_HOME=%CUDA_PATH%"
+
+@rem activate installer env
+call "%CONDA_ROOT_PREFIX%\condabin\conda.bat" activate "%INSTALL_ENV_DIR%" || ( echo. && echo Miniconda hook not found. && goto end )
+
+@rem update installer env
+call python one_click.py --install-extensions && (
+    echo.
+    echo Done!
+)
+
+:end
+pause

extensions_reqs_wsl.sh

@@ -0,0 +1,11 @@
+@echo off
+
+cd /D "%~dp0"
+
+set PATH=%PATH%;%SystemRoot%\system32
+
+@rem sed -i 's/\x0D$//' ./wsl.sh converts newlines to unix format in the wsl script   calling wsl.sh with 'update' will run updater
+call wsl -e bash -lic "sed -i 's/\x0D$//' ./wsl.sh; source ./wsl.sh install-extensions"
+
+:end
+pause

one_click.py

@@ -246,7 +246,7 @@ def install_webui():
         if "USE_CUDA118" in os.environ:
             use_cuda118 = "Y" if os.environ.get("USE_CUDA118", "").lower() in ("yes", "y", "true", "1", "t", "on") else "N"
         else:
-            print("\nDo you want to use CUDA 11.8 instead of 12.1? Only choose this option if your GPU is very old (Kepler or older).\nFor RTX and GTX series GPUs, say \"N\". If unsure, say \"N\".\n")
+            print("\nDo you want to use CUDA 11.8 instead of 12.1? Only choose this option if your GPU is very old (Kepler or older).\n\nFor RTX and GTX series GPUs, say \"N\".\nIf unsure, say \"N\".\n")
             use_cuda118 = input("Input (Y/N)> ").upper().strip('"\'').strip()
             while use_cuda118 not in 'YN':
                 print("Invalid choice. Please try again.")
@@ -295,6 +295,15 @@ def install_webui():
     update_requirements(initial_installation=True)
 
 
+def install_extensions_requirements():
+    print_big_message("Installing extensions requirements.\nSome of these may fail on Windows. Don\'t worry if you see error messages. They will not affect the main program.")
+    extensions = [foldername for foldername in os.listdir('extensions') if os.path.isfile(os.path.join('extensions', foldername, 'requirements.txt'))]
+    for i, extension in enumerate(extensions):
+        print(f"\n\n--- [{i+1}/{len(extensions)}]: {extension}\n\n")
+        extension_req_path = os.path.join("extensions", extension, "requirements.txt")
+        run_cmd(f"python -m pip install -r {extension_req_path} --upgrade", assert_success=False, environment=True)
+
+
 def update_requirements(initial_installation=False):
     # Create .git directory if missing
     if not os.path.exists(os.path.join(script_dir, ".git")):
@@ -317,24 +326,6 @@ def update_requirements(initial_installation=False):
             print_big_message(f"File '{file_name}' was updated during 'git pull'. Please run the script again.")
             exit(1)
 
-    # Extensions requirements are installed only during the initial install by default.
-    # That can be changed with the INSTALL_EXTENSIONS environment variable.
-    install = initial_installation
-    if "INSTALL_EXTENSIONS" in os.environ:
-        install = os.environ["INSTALL_EXTENSIONS"].lower() in ("yes", "y", "true", "1", "t", "on")
-
-    if install:
-        print_big_message("Installing extensions requirements.")
-        skip = ['superbooga', 'superboogav2', 'coqui_tts']  # Fail to install on Windows
-        extensions = [foldername for foldername in os.listdir('extensions') if os.path.isfile(os.path.join('extensions', foldername, 'requirements.txt'))]
-        extensions = [x for x in extensions if x not in skip]
-        for i, extension in enumerate(extensions):
-            print(f"\n\n--- [{i+1}/{len(extensions)}]: {extension}\n\n")
-            extension_req_path = os.path.join("extensions", extension, "requirements.txt")
-            run_cmd(f"python -m pip install -r {extension_req_path} --upgrade", assert_success=False, environment=True)
-    elif initial_installation:
-        print_big_message("Will not install extensions due to INSTALL_EXTENSIONS environment variable.")
-
     # Update PyTorch
     if not initial_installation:
         update_pytorch()
@@ -379,11 +370,6 @@ def update_requirements(initial_installation=False):
         run_cmd(f"python -m pip uninstall -y {package_name}", environment=True)
         print(f"Uninstalled {package_name}")
 
-    # Make sure that API requirements are installed (temporary)
-    extension_req_path = os.path.join("extensions", "openai", "requirements.txt")
-    if os.path.exists(extension_req_path):
-        run_cmd(f"python -m pip install -r {extension_req_path} --upgrade", environment=True)
-
     # Install/update the project requirements
     run_cmd("python -m pip install -r temp_requirements.txt --upgrade", assert_success=True, environment=True)
     os.remove('temp_requirements.txt')
@@ -409,18 +395,24 @@ if __name__ == "__main__":
 
     parser = argparse.ArgumentParser(add_help=False)
     parser.add_argument('--update', action='store_true', help='Update the web UI.')
+    parser.add_argument('--install-extensions', action='store_true', help='Install extensions requirements.')
     args, _ = parser.parse_known_args()
 
     if args.update:
         update_requirements()
+    elif args.install_extensions:
+        install_extensions_requirements()
+        update_requirements()
     else:
-        # If webui has already been installed, skip and run
         if not is_installed():
             install_webui()
             os.chdir(script_dir)
 
+            script_name = "extensions_reqs_windows.bat" if is_windows() else ("extensions_reqs_linux.sh" if is_linux() else "extensions_reqs_macos.sh")
+            print_big_message(f"The installation is finished.\n\nIf you wish to install or update extensions requirements, you can\nrun the following script at any time: {script_name}.")
+
         if os.environ.get("LAUNCH_AFTER_INSTALL", "").lower() in ("no", "n", "false", "0", "f", "off"):
-            print_big_message("Install finished successfully and will now exit due to LAUNCH_AFTER_INSTALL.")
+            print_big_message("Will now exit due to LAUNCH_AFTER_INSTALL.")
             sys.exit()
 
         # Check if a model has been downloaded yet
@@ -432,7 +424,7 @@ if __name__ == "__main__":
             model_dir = 'models'
 
         if len([item for item in glob.glob(f'{model_dir}/*') if not item.endswith(('.txt', '.yaml'))]) == 0:
-            print_big_message("WARNING: You haven't downloaded any model yet.\nOnce the web UI launches, head over to the \"Model\" tab and download one.")
+            print_big_message("You haven't downloaded any model yet.\nOnce the web UI launches, head over to the \"Model\" tab and download one.")
 
         # Workaround for llama-cpp-python loading paths in CUDA env vars even if they do not exist
         conda_path_bin = os.path.join(conda_env_path, "bin")

requirements.txt

@@ -23,6 +23,12 @@ transformers==4.38.*
 tqdm
 wandb
 
+# API
+SpeechRecognition==3.10.0
+flask_cloudflared==0.0.14
+sse-starlette==1.6.5
+tiktoken
+
 # bitsandbytes
 bitsandbytes==0.42.*; platform_system != "Windows"
 https://github.com/oobabooga/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.42.0-py3-none-win_amd64.whl; platform_system == "Windows"

requirements_amd.txt

@@ -23,6 +23,12 @@ transformers==4.38.*
 tqdm
 wandb
 
+# API
+SpeechRecognition==3.10.0
+flask_cloudflared==0.0.14
+sse-starlette==1.6.5
+tiktoken
+
 # llama-cpp-python (CPU only, AVX2)
 https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.55+cpuavx2-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
 https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.55+cpuavx2-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"

requirements_amd_noavx2.txt

@@ -23,6 +23,12 @@ transformers==4.38.*
 tqdm
 wandb
 
+# API
+SpeechRecognition==3.10.0
+flask_cloudflared==0.0.14
+sse-starlette==1.6.5
+tiktoken
+
 # llama-cpp-python (CPU only, no AVX2)
 https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.55+cpuavx-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
 https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.55+cpuavx-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"

requirements_apple_intel.txt

@@ -23,6 +23,12 @@ transformers==4.38.*
 tqdm
 wandb
 
+# API
+SpeechRecognition==3.10.0
+flask_cloudflared==0.0.14
+sse-starlette==1.6.5
+tiktoken
+
 # Mac wheels
 https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.55-cp311-cp311-macosx_11_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.11"
 https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.55-cp310-cp310-macosx_11_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.10"

requirements_apple_silicon.txt

@@ -23,6 +23,12 @@ transformers==4.38.*
 tqdm
 wandb
 
+# API
+SpeechRecognition==3.10.0
+flask_cloudflared==0.0.14
+sse-starlette==1.6.5
+tiktoken
+
 # Mac wheels
 https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.55-cp311-cp311-macosx_11_0_arm64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.11"
 https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.55-cp310-cp310-macosx_11_0_arm64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.10"

requirements_cpu_only.txt

@@ -23,6 +23,12 @@ transformers==4.38.*
 tqdm
 wandb
 
+# API
+SpeechRecognition==3.10.0
+flask_cloudflared==0.0.14
+sse-starlette==1.6.5
+tiktoken
+
 # llama-cpp-python (CPU only, AVX2)
 https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.55+cpuavx2-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
 https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.55+cpuavx2-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"

requirements_cpu_only_noavx2.txt

@@ -23,6 +23,12 @@ transformers==4.38.*
 tqdm
 wandb
 
+# API
+SpeechRecognition==3.10.0
+flask_cloudflared==0.0.14
+sse-starlette==1.6.5
+tiktoken
+
 # llama-cpp-python (CPU only, no AVX2)
 https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.55+cpuavx-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
 https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.55+cpuavx-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"

requirements_noavx2.txt

@@ -23,6 +23,12 @@ transformers==4.38.*
 tqdm
 wandb
 
+# API
+SpeechRecognition==3.10.0
+flask_cloudflared==0.0.14
+sse-starlette==1.6.5
+tiktoken
+
 # bitsandbytes
 bitsandbytes==0.42.*; platform_system != "Windows"
 https://github.com/oobabooga/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.42.0-py3-none-win_amd64.whl; platform_system == "Windows"

requirements_nowheels.txt

@@ -22,3 +22,9 @@ tensorboard
 transformers==4.38.*
 tqdm
 wandb
+
+# API
+SpeechRecognition==3.10.0
+flask_cloudflared==0.0.14
+sse-starlette==1.6.5
+tiktoken

wsl.sh

@@ -108,5 +108,6 @@ fi
 # setup installer env   update env if called with 'wsl.sh update'
 case "$1" in
 ("update") python one_click.py --update;;
+("install-extensions") python one_click.py --install-extensions;;
 (*) python one_click.py $@;;
 esac