mirror of
https://github.com/bendtherules/ask262.git
synced 2026-08-18 21:31:46 +00:00
fix(agent-tools, setup): standardize metadata keys to lowercase and update HTML ingestion
- Renamed `partIndex`/`totalParts` to `partindex`/`totalparts` in `section_retriever.ts`, `spec_retriever.ts`, and document creation logic. - Adjusted sorting logic to use the new `partindex` field. - Updated metadata handling and string interpolation to reference the lowercase keys. - Fixed import path for `HTMLTextSplitter` and moved the file to `setup/textsplitters/HtmlTextSplitter.ts`. - Added HTML preprocessing utilities (`addNewlinesAfterBlocks`, `convertTablesToMarkdown`) in ingestion workflow. - Integrated table-to‑markdown conversion and newline insertion to improve text splitting and document structure.
This commit is contained in:
@@ -46,8 +46,8 @@ export function createSpecRetrieverTool(
|
||||
type: r.type,
|
||||
parentsectionid: r.parentsectionid,
|
||||
childrensectionids: r.childrensectionids,
|
||||
partIndex: r.partIndex,
|
||||
totalParts: r.totalParts,
|
||||
partindex: r.partindex,
|
||||
totalparts: r.totalparts,
|
||||
},
|
||||
}));
|
||||
|
||||
@@ -77,8 +77,8 @@ export function createSpecRetrieverTool(
|
||||
const sectionId = meta?.sectionid || "unknown";
|
||||
const sectionTitle = meta?.sectiontitle || "unknown";
|
||||
const partInfo =
|
||||
meta?.partIndex !== null && meta?.partIndex !== undefined
|
||||
? ` [part ${(meta.partIndex as number) + 1}/${meta.totalParts}]`
|
||||
meta?.partindex !== null && meta?.partindex !== undefined
|
||||
? ` [part ${(meta.partindex as number) + 1}/${meta.totalparts}]`
|
||||
: "";
|
||||
return `--- Section: ${sectionId} | "${sectionTitle}"${partInfo} (score: ${r.score.toFixed(2)}) ---\n${r.document.pageContent}`;
|
||||
})
|
||||
|
||||
Reference in New Issue
Block a user