# trs: documentation

## Overview 🏕️

`trs` is a command line tool that leverages an LLM (OpenAI) to chat with and analyze cyber threat intelligence reports and blogs.

Supply a threat report to pre-built commands for summarization, MITRE TTP extraction, mindmap creation, and identification of detection opportunities, or run your own custom prompts against the report content.

Each URL's text content is stored in a Chroma vector database so you can have QnA / Retrieval-Augmented-Generation (RAG) chat sessions with the processed reports.

The OpenAI model `gpt-3.5-turbo-16k` is used in order to support larger contexts more easily, but feel free to swap this out for the `gpt-4-32k` model in the config if you have access.

* **Repo**: <https://github.com/deadbits/trs>

## Quick links

{% content-ref url="overview/install" %}
[install](https://trs.deadbits.ai/overview/install)
{% endcontent-ref %}

{% content-ref url="overview/use" %}
[use](https://trs.deadbits.ai/overview/use)
{% endcontent-ref %}

{% content-ref url="overview/screenshots" %}
[screenshots](https://trs.deadbits.ai/overview/screenshots)
{% endcontent-ref %}


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://trs.deadbits.ai/trs-documentation.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.