Kiroku is a multi-agent system that helps you organize and write documents.

I started writing it because during my PhD at Stanford, I had to go through a formal process to write papers and eventually the thesis, and I tried to follow these steps. The difference is that at that time, I was the student, and my advisor was reviewing my documents, and I got the idea: what if the writer becomes the advisor, and the multi-agent system becomes the student?

This flow has several advantages:

• It helps you organize the ideas in a better way because you can generate a sequence of paragraphs very quickly.
• It helps you change your communication through iterative evaluation of the message
• Recently, [1] suggested that LLMs help you can help complex topics by discussing with with the LLM.

(c) PhDCommics (www.phdcommics.com) of the advisor and the student

The original code was obtained from a short course From Harrison Chase and Rotem Weiss [2], but I believe not even the prompts resemble any of the prompts from original prompts. However, I do recognize and credit to them the original code that I used as a reference.

To run Kiroku, you need an OPENAI_API_KEY and a TAVILI_API_KEY.

To get an OPENAI_API_KEY, you can check https://platform.openai.com/docs/quickstart .

To get a TAVILY_API_KEY, you can check the site https://app.tavily.com/sign-in, and click "Sign in".

You must install requirements.tx to be able to run Kiroku.

cd kiroku
pip install -r requirements.txt

The initial configuration is specified in an YAML file with the following fields:

• title is a suggestion for the title or the final title to use (if suggest_title is false).
• suggest_title turns on recommendation for titles based on your original title.
• generate_citations: if true, it will generate citations and references.
• type_of_document: helps the Kiroku define whether it should use more technical terms, or whether we are trying to write children's stories.
• area_of_paper: together with hypothesis, it helps Kiroku to understand what to write.
• section_names: list of sections, as in the example below:

section_names:
- Introduction
- Related Work
- Architecture of Kiroku
- Results
- Conclusions
- References

• number_of_paragraphs: instructs Kiroku to write that many paragraphs per section.

number_of_paragraphs:
  "Introduction": 4
  "Related Work": 7
  "Architecture of Kiroku": 4
  "Results": 4
  "Conclusions": 3

• hypothesis tells Kiroku whether you want to establish something to be good or bad, and it will define the message.
• instructions: as you interact with the document giving instructions like "First paragraph of Introduction should discuss the revolution that was created with the lauch of ChaGPT", you may want to add some of them to the instruction so that in the next iteration, Kiroku will observe your recommendations. In Kiroku, instructions are appended into the hypothesis at this time, so you will not see them. I usually put \n\n after each instruction to assist the underlying LLM.
• results: I usually put it here as I fill this later on.
• references are references you want Kiroku to use during its search phase for information.
• number_of_queries tells Kiroku how many questions it will generate to Tavily to search for information.
• max_revisions tells Kiroku how many times it performs reflection and document writing upon analyzing reflection results (please note that setting this document to 1, it means no revision).
• temperature is the temperature of the LLM (usually I set it to a small number).

There is a script check_yaml that checks if the YAML file is consistent and it will not crash Kiroku.

I recommend putting all YAML files right now in the kikoku/proj direcotry. All images should be in kiroku/proj/images. Because of a limitation of Gradio, you need to specify images in the instructions or hypothesis as '/file=images/<your-image-file>' such as in the example /file=images/multi-agent.jpeg.

I recommend running writer as:

cd {where Kiroku directory is located}
WRITER_PROJECT_DIRECTORY=`pwd`/proj ./kiroku

Apache License 2.0 (see LICENSE.txt)

:-)

1. https://www.youtube.com/watch?v=om7VpIK90vE

2. Harrison Chase, Rotem Weiss. AI Agents in LangGraph. https://www.deeplearning.ai/short-courses/ai-agents-in-langgraph