Skip to content

WIP Add source/HTML chunking #38

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.

Sign up for GitHub

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

Draft
malberts wants to merge 1 commit into
base: master
Choose a base branch
from
Draft

WIP Add source/HTML chunking #38

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
34 changes: 26 additions & 8 deletions src/tools/get-page.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,6 +6,8 @@ import type { CallToolResult, TextContent, ToolAnnotations } from '@modelcontext
import { makeRestGetRequest } from '../common/utils.js';
import type { MwRestApiPageObject } from '../types/mwRestApi.js';

const CHUNK_SIZE = 90000;

enum ContentFormat {
noContent = 'noContent',
withSource = 'withSource',
Expand Down Expand Up @@ -84,17 +86,33 @@ function getPageToolResult( result: MwRestApiPageObject ): TextContent[] {
];

if ( result.source !== undefined ) {
results.push( {
type: 'text',
text: `Source:\n${ result.source }`
} );
const totalChunks = Math.ceil( result.source.length / CHUNK_SIZE );

for ( let i = 0; i < result.source.length; i += CHUNK_SIZE ) {
const currentChunk = Math.floor( i / CHUNK_SIZE ) + 1;
const prefix = `Source part ${ currentChunk }/${ totalChunks }:\n`;
const sourceChunk = result.source.slice( i, i + CHUNK_SIZE );

results.push( {
type: 'text',
text: `${ prefix }${ sourceChunk }`
} );
}
}

if ( result.html !== undefined ) {
results.push( {
type: 'text',
text: `HTML:\n${ result.html }`
} );
const totalChunks = Math.ceil( result.html.length / CHUNK_SIZE );

for ( let i = 0; i < result.html.length; i += CHUNK_SIZE ) {
const currentChunk = Math.floor( i / CHUNK_SIZE ) + 1;
const prefix = `HTML part ${ currentChunk }/${ totalChunks }:\n`;
const htmlChunk = result.html.slice( i, i + CHUNK_SIZE );

results.push( {
type: 'text',
text: `${ prefix }${ htmlChunk }`
} );
}
}

return results;
Expand Down