ComfyUI Griptape Nodes

This repo creates a series of nodes that enable you to utilize the Griptape Python Framework with ComfyUI, integrating LLMs (Large Language Models) and AI into your workflow.

Instructions and tutorials

Watch the trailer and all the instructional videos on our YouTube Playlist.

The repo currently has a subset of Griptape nodes, with more to come soon. Current nodes can:

• Create Agents using these models:

  • Local - via Ollama and LM Studio
    • Llama 3
    • Mistral
    • etc..
  • Via Paid API Keys
    • OpenAI
    • Amazon Bedrock
    • Google Gemini
    • Anthropic Claude
    • Hugging Face (Note: Not all models featured on the Hugging Face Hub are supported by this driver. Models that are not supported by Hugging Face serverless inference will not work with this driver. Due to the limitations of Hugging Face serverless inference, only models that are than 10GB are supported.)

• Control agent behavior with access to [Rules and Rulesets][https://docs.griptape.ai/stable/griptape-framework/structures/rulesets/]

• Give Agents access to Tools:

  • Calculator
  • DateTime
  • WebScraper
  • FileManager
  • AudioTranscriptionClient
  • GriptapeCloudKnowledgeBaseClient

• Run specific Agent Tasks:

  • PromptTask
  • TextSummaryTask
  • ToolTask
  • ToolkitTask
  • PromptImageGenerationTask
  • ImageQueryTask
  • VariationImageGenerationTask (In Beta)

• Generate Images using these models:

  • OpenAI
  • Amazon Bedrock Stable Diffusion
  • Amazon Bedrock Titan
  • Leonardo.AI

• Audio

  • Transcribe Audio
  • Text to Voice via ElevenLabs API

Example

In this example, we're using three Image Description nodes to describe the given images. Those descriptions are then Merged into a single string which is used as inspiration for creating a new image using the Create Image from Text node, driven by an OpenAI Driver.

Using the nodes - Video Tutorials

1. Installation: https://youtu.be/L4-HnKH4BSI?si=Q7IqP-KnWug7JJ5s
2. Griptape Agents: https://youtu.be/wpQCciNel_A?si=WF_EogiZRGy0cQIm
3. Controlling which LLM your Agents use: https://youtu.be/JlPuyH5Ot5I?si=KMPjwN3wn4L4rUyg
4. Griptape Tools - Featuring Task Memory and Off-Prompt: https://youtu.be/TvEbv0vTZ5Q
5. Griptape Rulesets, and Image Creation: https://youtu.be/DK16ouQ_vSs
6. Image Generation with multiple drivers: https://youtu.be/Y4vxJmAZcho
7. Image Description, Parallel Image Description: https://youtu.be/OgYKIluSWWs?si=JUNxhvGohYM0YQaK
8. Audio Transcription: https://youtu.be/P4GVmm122B0?si=24b9c4v1LWk_n80T
9. Using Ollama as a Configuration Driver: https://youtu.be/jIq_TL5xmX0?si=ilfomN6Ka1G4hIEp
10. Combining Rulesets: https://youtu.be/3LDdiLwexp8?si=Oeb6ApEUTqIz6J6O
11. Integrating Text: https://youtu.be/_TVr2zZORnA?si=c6tN4pCEE3Qp0sBI
12. New Nodes & Quality of life improvements: https://youtu.be/M2YBxCfyPVo?si=pj3AFAhl2Tjpd_hw
13. Merge Input Data: https://youtu.be/wQ9lKaGWmZo?si=FgboU5iUg82pXRkC
14. Setting default agent configurations: https://youtu.be/IkioCcldEms?si=4uUu-y9UvIJWVBdE
15. Merge Text with dynamic inputs and custom separator: https://youtu.be/1fHAzKVPG4M?si=6JHe1NA2_a_nl9rG
16. Multiple Image Descriptions and Local Multi-Modal Models: https://youtu.be/KHz7CMyOk68?si=oQXud6NOtNHrXLez
17. WebSearch Node Now Allows for Driver Functionality in Griptape Nodes: https://youtu.be/4_dkfdVUnRI?si=DA4JvegV0mdHXPDP
18. Persistent Display Text: https://youtu.be/9229bN0EKlc?si=Or2eu3Nuh7lxgfEU
19. Convert an Agent to a Tool.. and give it to another Agent: https://youtu.be/CcRot5tVAU8?si=lA0v5kDH51nYWwgG

Recent Changelog

July 17, 2024

• Simplified API Keys by removing requirements for griptape_config.json. Now all keys are set in .env.
• Fixed bug where Griptape wouldn't launch if no OPENAI_API_KEY was set.

July 16, 2024

• Reorganized all the nodes so each class is in it's own file. should make things easier to maintain
• Added max_attemnpts_on_fail parameter to all Config nodes to allow the user to determine the number of retries they want when an agent fails. This maps to the max_attempts parameter in the Griptape Framework.
• NewNode: Audio Driver: Eleven Labs. Uses the ElevenLabs api. Takes a model, a voice, and the ELEVEN_LABS_API_KEY. https://elevenlabs.io/docs/voices/premade-voices#current-premade-voices
• NewNode: Griptape Run: Text to Speech task
• NewNode: Added AzureOpenAI Config node. To use this, you'll need to set up your Azure endpoint and get API keys. The two environment variables required are AZURE_OPENAI_ENDPOINT and AZURE_OPENAI_API_KEY. You will also require a deployment name. This is available in Azure OpenAI Studio
• Updated README

July 12, 2024

• Updated to Griptape v0.28.2
• New Node Griptape Config: OpenAI Compatable node. Allows you to connect to services like https://www.ohmygpt.com/ which are compatable with OpenAi's api.
• New Node HuggingFace Prompt Driver Config
• Reorganized a few files
• Removed unused DuckDuckGoTool now that Griptape supports drivers.

July 11, 2024

• The Display Text node no longer clears it's input if you disconnect it - which means you can use it as a way to generate a prompt, and then tweak it later.
• Added Convert Agent to Tool node, allowing you to create agents that have specific skills, and then give them to another agent to use when it feels it's appropriate.

July 10, 2024

• Updated to work with Griptape v0.28.1
• Image Description node now can handle multiple images at once, and works with Open Source llava.
• Fixed tool, config, ruleset, memory bugs for creating agents based on update to v0.28.0
• New Nodes Added WebSearch Drivers: DuckDuckGo and Google Search. To use Google Search, you must have two API keys - GOOGLE_API_KEY and GOOGLE_API_SEARCH_ID.

July 9, 2024

• Updated LMStudio and Ollama config nodes to use 127.0.0.1
• Updated Create Agent and Run Agent nodes to no longer cache their knowledge between runs. Now if the agent input isn't connected to anything, it will create a new agent on each run.

July 2, 2024

• All input nodes updated with dynamic inputs. Demonstration here: https://youtu.be/1fHAzKVPG4M?si=6JHe1NA2_a_nl9rG
• Fixed bug with Text to Combo node

Installation

1. ComfyUI

Install ComfyUI using the instructions for your particular operating system.

2. Use Ollama

If you'd like to run with a local LLM, you can use Ollama and install a model like llama3.

1. Download and install Ollama from their website: https://ollama.com

2. Download a model by running ollama run <model>. For example:

   ollama run llama3

3. You now have ollama available to you. To use it, follow the instructions in this YouTube video: https://youtu.be/jIq_TL5xmX0?si=0i-myC6tAqG8qbxR

3. Add API Keys to your environment

For advanced features, it's recommended to use a more powerful model. These are available from the providers listed bellow, and will require API keys.

Create a .env file

• In the base comfyUI folder, create a file called .env if it doesn't already exist
• Add an API key for each of the services you require. You will see a list of the appropriate keys below:

Note: Most nodes will work fine with just the OPENAI_API_KEY, so at least make sure you have that one.

OPENAI_API_KEY=
GOOGLE_API_KEY=
GOOGLE_API_SEARCH_ID=
AWS_ACCESS_KEY_ID=
AWS_SECRET_ACCESS_KEY=
AWS_DEFAULT_REGION=
LEONARDO_API_KEY=
ANTHROPIC_API_KEY=
VOYAGE_API_KEY=
GRIPTAPE_API_KEY=
HUGGINGFACE_HUB_ACCESS_TOKEN=
AZURE_OPENAI_ENDPOINT=
AZURE_OPENAI_API_KEY=
COHERE_API_KEY=
ELEVEN_LABS_API_KEY=

You can get the appropriate API keys from these respective sites:

• OPENAI_API_KEY: https://platform.openai.com/api-keys
• GOOGLE_API_KEY: https://makersuite.google.com/app/apikey
• AWS_ACCESS_KEY_ID & SECURITY_ACCESS_KEY:
  • Open the AWS Console
  • Click on your username near the top right and select Security Credentials
  • Click on Users in the sidebar
  • Click on your username
  • Click on the Security Credentials tab
  • Click Create Access Key
  • Click Show User Security Credentials
• LEONARDO_API_KEY: https://docs.leonardo.ai/docs/create-your-api-key
• ANTHROPIC_API_KEY: https://console.anthropic.com/settings/keys
• VOYAGE_API_KEY: https://dash.voyageai.com/
• HUGGINGFACE_HUB_ACCESS_TOKEN: https://huggingface.co/settings/tokens
• AZURE_OPENAI_ENDPOINT & AZURE_OPENAI_API_KEY: https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/switching-endpoints
• COHERE_API_KEY: https://dashboard.cohere.com/api-keys
• ELEVEN_LABS_API_KEY: https://elevenlabs.io/app/
  • Click on your username in the lower left
  • Choose Profile + API Key
  • Generate and copy the API key

4. Install Griptape-ComfyUI

There are two methods for installing the Griptape-ComfyUI repository. You can either download or git clone this repository inside the ComfyUI/custom_nodes, or use the ComfyUI Manager.

• Option A - ComfyUI Manager (Recommended)

  1. Install ComfyUI Manager by following the installation instructions.
  2. Click Manager in ComfyUI to bring up the ComfyUI Manager
  3. Search for "Griptape"
  4. Find the ComfyUI-Griptape repo.
  5. Click INSTALL
  6. Follow the rest of the instructions.

• Option B - Git Clone

  1. Open a terminal and input the following commands:

     cd /path/to/comfyUI
     cd custom_nodes
     git clone https://github.com/griptape-ai/ComfyUI-Griptape
     

5. Make sure libraries are loaded

Libraries should be installed automatically, but if you're having trouble, hopefully this can help.

There are certain libraries required for Griptape nodes that are called out in the requirements.txt file.

griptape[all]
python-dotenv

These should get installed automatically if you used the ComfyUI Manager installation method. However, if you're running into issues, please install them yourself either using pip or poetry, depending on your installation method.

• Option A - pip

  pip install "griptape[all]" python-dotenv 
  

• Option B - poetry

  poetry add "griptape[all]" python-dotenv 
  

6. Restart ComfyUI

Now if you restart comfyUI, you should see the Griptape menu when you click with the Right Mouse button.

If you don't see the menu, please come to our Discord and let us know what kind of errors you're getting - we would like to resolve them as soon as possible!

---

Troubleshooting

Torch issues

Griptape does install the torch requirement. Sometimes this may cause problems with ComfyUI where it grabs the wrong version of torch, especially if you're on Nvidia. As per the ComfyUI docs, you may need to unintall and re-install torch.

pip uninstall torch
pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu121

Griptape Not Updating

Sometimes you'll find that the Griptape library didn't get updated properly. This seems to be especially happening when using the ComfyUI Manager. You might see an error like:

ImportError: cannot import name 'OllamaPromptDriver' from 'griptape.drivers' (C:\Users\evkou\Documents\Sci_Arc\Sci_Arc_Studio\ComfyUi\ComfyUI_windows_portable\python_embeded\Lib\site-packages\griptape\drivers\__init__.py)

To resolve this, you must make sure Griptape is running with the appropriate version. Things to try:

• Update again via the ComfyUI Manager
• Uninstall & Re-install the Griptape nodes via the ComfyUI Manager
• In the terminal, go to your ComfyUI directory and type: python -m pip install griptape -U
• Reach out on Discord and ask for help.

API Keys

Griptape will use API keys set as environment variables. Please ensure you have your keys set in a .env file located in the base directory of comfyUI.

For example, my .env is located here in Windows: C:\Users\jason\Documents\GitHub\ComfyUI\.env

It's located here in MacOS: /Users/jason/Documents/GitHub/ComfyUI/.env

If you ever need to change your API keys, go ahead and update that file with the proper key and restart ComfyUI.

StabilityMatrix

If you are using StabilityMatrix to run ComfyUI, you may find that after you install Griptape you get an error like the following:

To resolve this, you'll need to update your torch installation. Follow these steps:

1. Click on Packages to go back to your list of installed Packages.
2. In the ComfyUI card, click the vertical ... menu.
3. Choose Python Packages to bring up your list of Python Packages.
4. In the list of Python Packages, search for torch to filter the list.
5. Select torch and click the - button to uninstall torch.
6. When prompted, click Uninstall
7. Click the + button to install a new package.
8. Enter the list of packages: torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu121
9. Click OK.
10. Wait for the install to complete.
11. Click Close.
12. Launch ComfyUI again.

---

Thank you

Massive thank you for help and inspiration from the following people and repos!

• Jovieux from https://github.com/Amorano/Jovimetrix
• rgthree https://github.com/rgthree/rgthree-comfy