Icon

CrewAI - AI-Agents solve your Tasks with Ollama

KNIME and CrewAI - use an AI-Agent system to let a local LLM like Llama3 solve your tasks

KNIME and CrewAI - use an AI-Agent system to let a local LLM like Llama3 solve your tasks

The agents will 'discuss' among themselves and come back with a (hopefully) perfect soltion to your task based on the instructions you gave

---
Adapted from:

Integrating Agent Frameworks into Low Code Tools: Making CrewAI work in KNIME
https://medium.com/p/a7fecb042915
https://hub.knime.com/lowcodeaiftw/spaces/Public/LLMs/CrewAI~lgdow45tWuhhb4fT/

by https://medium.com/@martindausa

Prerequisites:Ideally, the KNIME 4.7 (or higher) Version Installed including Python Integration Extension.Custom Python Environment set up including key KNIME Packages and CrewAI package aswell as Ollama (also pull the LLM models you want to use).cf. "py_knime_crewai.yml" in the /data/ folderLimitations (and ideas for future development) - by @martindausa:No support for "Tools" that the agents can use.Agents will try and use Tools regardless, and it seems this cannot be switched off in CrewAI.Recommendation: Put "YOU DO NOT NEED TO USE TOOLS." inside any Agent Descriptionand Task Description.Define Agents:Agent NameAgent GoalAgent BackstoryAgent Model (currently Llama3 / 3.1 and Mistral, vou can add more)Define Tasks:Task NameTask DescriptionAssign Agent to perform the TaskFlexibility to inject certain parameters into the task (ParameterName: ParameterValue) Define Agents and their models Define TasksNote: Any new task component needsInput from Agent Concat Node Concatenate Agent and Task OutputsNote:Add new Agents / Tasks by copying respective components.Make sure to add additional input ports to Concat nodes andconnect new Agents/tasks accordingly Kickoff your Agents - you can check the progress and the results in the log folder../data/chat/ollama_crewai_<...> Adapted from:Integrating Agent Frameworks into Low Code Tools: Making CrewAI work in KNIMEhttps://medium.com/p/a7fecb042915https://hub.knime.com/lowcodeaiftw/spaces/Public/LLMs/CrewAI~lgdow45tWuhhb4fT/by https://medium.com/@martindausa KNIME and CrewAI - use an AI-Agent system to let a local LLM like Llama3 solve your tasksThe agents will 'discuss' among themselves and come back with a (hopefully) perfect soltion to your task based on the instructions you gave Maybe download the whole LLM workflow group in order to get all the folders(https://hub.knime.com/mlauber71/spaces/LLM_Space/~17k4zAECNryrZw1X/) Make sure you have the Ollama models pulledlocally and they are runningollama pull mxbai-embed-largeollama pull mistral:instructollama pull llama3:instructollama pull llama3.1ollama run mistral:instructollama run llama3:instructollama run llama3.1 work in progress Blog Post WriterBlog Post BrainstormerBrainstorm"Create Blog Post Outline"Benefits of KNIME as a Data Analytics Toolcollect agentsTask DetailsTaskParameterDetailsWrite Blog PostCrewAI using localOllama / Llama3 / Mistralcurrent timeollama_crewai_olama_crewai_locate and create/data/ folderwith absolute pathscooperationmax iterationsPropagate Python environmentfor KNIME on MacOSX (Apple Scilicon)OR Windowswith Miniforge / Minicondaconfigure how to handle the environmentdefault = just check the namesDefine Agent Define Agent Define Task Concatenate Concatenate Concatenate Define Task Python Script Create Date&TimeRange create filename to collect Table Writer Merge Variables Collect LocalMetadata Agents Tasks TaskDetails Basic Settings conda_crewai_knime4 Prerequisites:Ideally, the KNIME 4.7 (or higher) Version Installed including Python Integration Extension.Custom Python Environment set up including key KNIME Packages and CrewAI package aswell as Ollama (also pull the LLM models you want to use).cf. "py_knime_crewai.yml" in the /data/ folderLimitations (and ideas for future development) - by @martindausa:No support for "Tools" that the agents can use.Agents will try and use Tools regardless, and it seems this cannot be switched off in CrewAI.Recommendation: Put "YOU DO NOT NEED TO USE TOOLS." inside any Agent Descriptionand Task Description.Define Agents:Agent NameAgent GoalAgent BackstoryAgent Model (currently Llama3 / 3.1 and Mistral, vou can add more)Define Tasks:Task NameTask DescriptionAssign Agent to perform the TaskFlexibility to inject certain parameters into the task (ParameterName: ParameterValue) Define Agents and their models Define TasksNote: Any new task component needsInput from Agent Concat Node Concatenate Agent and Task OutputsNote:Add new Agents / Tasks by copying respective components.Make sure to add additional input ports to Concat nodes andconnect new Agents/tasks accordingly Kickoff your Agents - you can check the progress and the results in the log folder../data/chat/ollama_crewai_<...> Adapted from:Integrating Agent Frameworks into Low Code Tools: Making CrewAI work in KNIMEhttps://medium.com/p/a7fecb042915https://hub.knime.com/lowcodeaiftw/spaces/Public/LLMs/CrewAI~lgdow45tWuhhb4fT/by https://medium.com/@martindausa KNIME and CrewAI - use an AI-Agent system to let a local LLM like Llama3 solve your tasksThe agents will 'discuss' among themselves and come back with a (hopefully) perfect soltion to your task based on the instructions you gave Maybe download the whole LLM workflow group in order to get all the folders(https://hub.knime.com/mlauber71/spaces/LLM_Space/~17k4zAECNryrZw1X/) Make sure you have the Ollama models pulledlocally and they are runningollama pull mxbai-embed-largeollama pull mistral:instructollama pull llama3:instructollama pull llama3.1ollama run mistral:instructollama run llama3:instructollama run llama3.1 work in progress Blog Post WriterBlog Post BrainstormerBrainstorm"Create Blog Post Outline"Benefits of KNIME as a Data Analytics Toolcollect agentsTask DetailsTaskParameterDetailsWrite Blog PostCrewAI using localOllama / Llama3 / Mistralcurrent timeollama_crewai_olama_crewai_locate and create/data/ folderwith absolute pathscooperationmax iterationsPropagate Python environmentfor KNIME on MacOSX (Apple Scilicon)OR Windowswith Miniforge / Minicondaconfigure how to handle the environmentdefault = just check the namesDefine Agent Define Agent Define Task Concatenate Concatenate Concatenate Define Task Python Script Create Date&TimeRange create filename to collect Table Writer Merge Variables Collect LocalMetadata Agents Tasks TaskDetails Basic Settings conda_crewai_knime4

Nodes

Extensions

Links

Download

To use this workflow in KNIME, download it from the below URL and open it in KNIME:

Download Workflow
Created by: marti
Created at: 2024-01-09
On NodePit since: 2024-08-20
Last update: 2024-09-16
Created with KNIME version: v4.7.8
Tags: crewaiai agentllmlarge language modelllama3ollama

Deploy, schedule, execute, and monitor your KNIME workflows locally, in the cloud or on-premises – with our brand new NodePit Runner.

Try NodePit Runner!