feat: minifiy content api graphql schema #187
Merged
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Minifies our content API's GraphQL schema before injecting it into the
search_docstool description. This strips out insignificant whitespace and removes comments, reducing the character size by 75% (actual token savings are model-dependant but should be similar, e.g. ~76% for GPT tokenizer).This helps lower the amount of context that MCP clients need to load for their LLMs (translating to cost savings).
Are there downsides?
The main downside is stripping out comments, which usually benefit LLMs by giving them a richer description of how to use the API. I tested the minified version with Cursor and it successfully formed the GraphQL query with no errors:
I think the schema is pretty self-describing without the comments, so the benefit of removing the context is likely worth it.