mirror of
https://github.com/crewAIInc/crewAI-examples.git
synced 2026-04-23 03:00:08 -04:00
c4e8cb9030
Issue #183 reported that the markdown_validator example structure needs to be updated, this commit includes : - adding A config/ directory for YAML configuration files (agents.yaml, tasks.yaml). - adding dedicated tools/ folder for any helper utilities, such as markdownTools.py . - adding The crew.py module, which contains the logic for the MarkDownValidatorCrew. -adding main.py file, which now serves as the entry point for the project, and includes run and train functions.
1.4 KiB
1.4 KiB
AI Crew for Reviewing Markdown Syntax
Introduction
This project is an example using the CrewAI framework to automate the process reviewing a markdown file for syntax issues. A general assistant leverages a custom tool to get a list of markdown linting errors. It then summarizes those errors into a list of changes to make to the document.
Running the Script
This example uses the OpenAI API to call a model. This can be through a locally hosted solution like LM Studio, or the Open AI API endpoint with your API key.
=======
- Configure Environment: Rename
.env.exampleto.envand set up the environment variables the model, endpoint url, and api key. - Install Dependencies: Run
poetry install --no-root. - Install Dependencies: Run
poetry lock. - Execute the Script: Run
python main.py README.mdto see a list of recommended changes to this document.
Details & Explanation
- Running the Script: Execute
poetry run markdown_validator {filename}. The script will leverage the CrewAI framework to process the specified file and return a list of changes. - Running the Script with agent training: Execute
poetry run train {number_of_iterations} {filename}. The script will leverage the CrewAI framework to process the specified file and return a list of changes, and updates the changes according to the user's feedback.
License
This project is released under the MIT License.