-
Notifications
You must be signed in to change notification settings - Fork 4
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Add new /ai-tools
site page with new /llms-full.txt
#284
base: main
Are you sure you want to change the base?
Conversation
|
desc "Generate raw markdown documentation for LLMs" | ||
task generate_llm_docs: ["examples:compile_queries"] do | ||
script_path = SITE_CONFIG_DIR / "script" / "generate_llm_docs.rb" | ||
sh "#{script_path} #{SITE_CONFIG_DIR}" |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
When it's ruby-calling-ruby I'd prefer to see it require
ing a class definition in a file and then calling methods on that class instead of shelling out and spawning another Ruby process.
"query-api/filtering/negation.md", | ||
"query-api/pagination.md", | ||
"query-api/sorting.md" | ||
] |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This feels likely to go out of date. If ordering is important, when we add or remove new markdown files, we want the CI build to guide us to update this list--is there some way you can wire that up?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Since this is a generated file, it should be git ignored I think.
- Contains: Query API, filtering, aggregations, and working GraphQL examples | ||
|
||
2. Share with your LLM: | ||
```text |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This is causing the build failure due to the validation added in #258.
I'm building with ElasticGraph. Here's the documentation: | ||
|
||
[Paste llms-full.txt content here] | ||
``` |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
It would be nice if users didn't have to type or copy/paste I'm building with ElasticGraph. Here's the documentation:
and then also paste the llms-full.txt
content. Can we provide a JS thing where the user clicks on an icon and the entire content of what they should paste goes into their clipboard?
3. Start building! Ask about: | ||
- Writing GraphQL queries | ||
- Setting up filters and aggregations | ||
- Optimizing pagination |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I have no idea what "Optimizing pagination" refers to. EG implements pagination and there's not really anything more or less optimal to do with it that I can think of...
Also should this mention things like defining schemas, configuration Elasticsearch/OpenSearch, etc?
New page to help developers use AI tools with ElasticGraph, by making it easier to pass the docs in to LLM's.
New llms-full.txt file (in markdown)
