NVIDIA / NVIDIA/TensorRT-Model-Connect
Feature: Make documentation LLM friendly
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 254
- Forks
- 58
- Avg merge
- 1d 7h
- Merged PRs (30d)
- 235
Description
Request type
Improvement to existing behavior
Problem and use case
A few modern docs pages have a "Copy For LLM" Button that allows the user to copy the documentation page as a Markdown for an Agent or LLM that doesn't have access to the code checkout.
Sometimes it prepends a details block that has information not visible in the rendered documentation.
{{< details >}}
...
{{< /details >}}
They also have "Open in [WEB-APP]" button where they add link that LLM friendly page to an LLM provider query.
[WEB-APP]/new?q=Read from [LLM-FRIENDLY-LINK] and answer my follow-up questions about it.
Currently the only way to achieve a similar workflow in TensorRT-Model-Connect is to either go to the GitHub page and fish out the .md file yourself or to CTRL+A which has HTML artifacts & might miss some context.
Proposed outcome
Allow an LLM to be able to natively access the raw markdown or make the documentation generally more LLM friendly that doesn't have full code context.
Model and target details
No response
Alternatives considered
No response
Additional context
No response
Submission checks
- I searched open and closed issues and found no duplicate request.
- I removed secrets, private/internal evidence, personal paths, and restricted artifacts.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
The issue names no files, tests, or entry points. Start by locating the documentation pages and any existing “Copy For LLM” or “Open in” controls; done means defining and implementing a documented way for users or LLMs to access the relevant raw Markdown and hidden details.
Written by the indexing model from the issue text.
Assessment
- Domain
- documentation
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Active
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100