1
0
Fork 0

fix: update doc

This commit is contained in:
Dylan Tientcheu 2025-07-24 11:16:17 +02:00
parent 4bcdedf8f1
commit a9b3d893f6
2 changed files with 9 additions and 5 deletions

View file

@ -10,7 +10,7 @@ These steps are especially valuable for large-scale sites using DocSearch-genera
**Note:** For more integration examples (Docusaurus, VitePress, Astro/Starlight, and generic setups), see the section at the bottom of this page.
:::
## Overview
## Overview
To maximize the quality of AskAI responses, configure your Crawler to create a dedicated index for Markdown content. This approach enables AskAI to work with structured, chunked records sourced from your documentation, support content, or any Markdown-based material—resulting in significantly more relevant and precise answers.
The steps below walk through how to set up your Crawler to index Markdown files specifically for AskAI.
@ -32,6 +32,7 @@ The steps below walk through how to set up your Crawler to index Markdown files
return helpers.splitTextIntoRecords({
text: helpers.markdown("main"), // Change "main" to match your content tag (e.g., "main", "article", etc.)
baseRecord: {
url,
objectID: url,
lang: language, // Add more attributes as needed
},
@ -103,7 +104,7 @@ docsearch({
- **Use clear, consistent titles in your markdown files** for better searchability.
- **Test your index** with AskAI to ensure relevant answers are returned.
- **Adjust `maxRecordBytes`** if you notice answers are too broad or too fragmented.
- **Adjust `maxRecordBytes`** if you notice answers are too broad or too fragmented.
- **Note:** Increasing `maxRecordBytes` may increase the token count for LLMs, which can affect the size of the context window and the cost of each AskAI response.
- **Keep your markdown well-structured** (use headings, lists, etc.) for optimal chunking.
- **Add attributes** like `lang`, `version`, or `tags` to your records and `attributesForFaceting` if you want to filter or facet in your search UI or AskAI.
@ -123,7 +124,7 @@ A: Lower the `maxRecordBytes` value to split content into smaller, more focused
---
For more details, see the [AskAI documentation](./askai.mdx) or contact support if you need help configuring your Crawler.
For more details, see the [AskAI documentation](./askai.mdx) or contact support if you need help configuring your Crawler.
---
@ -154,6 +155,7 @@ import TabItem from '@theme/TabItem';
return helpers.splitTextIntoRecords({
text: helpers.markdown("main"), // Change "main" to match your content tag (e.g., "main", "article", etc.)
baseRecord: {
url,
objectID: url,
// Add more optional attributes to the record
lang: language
@ -202,6 +204,7 @@ import TabItem from '@theme/TabItem';
return helpers.splitTextIntoRecords({
text: helpers.markdown("main"), // Change "main" to match your content tag (e.g., "main", "article", etc.)
baseRecord: {
url,
objectID: url,
lang: language, // Required for Docusaurus
language, // Required for Docusaurus
@ -251,6 +254,7 @@ import TabItem from '@theme/TabItem';
return helpers.splitTextIntoRecords({
text: helpers.markdown("main"), // Change "main" to match your content tag (e.g., "main", "article", etc.)
baseRecord: {
url,
objectID: url,
lang: language, // Required for VitePress
},
@ -294,6 +298,7 @@ import TabItem from '@theme/TabItem';
return helpers.splitTextIntoRecords({
text: helpers.markdown("main"), // Change "main" to match your content tag (e.g., "main", "article", etc.)
baseRecord: {
url,
objectID: url,
lang: language, // Required for Astro/StarLight
},
@ -320,4 +325,4 @@ import TabItem from '@theme/TabItem';
</Tabs>
> Each example shows how to extract common facets and configure your markdown index for AskAI. Adjust selectors and meta tag names as needed for your site.
> Each example shows how to extract common facets and configure your markdown index for AskAI. Adjust selectors and meta tag names as needed for your site.

View file

@ -476,7 +476,6 @@ html[data-theme='dark'] .header-github-link::before {
#tailwind ol,
#tailwind ul {
list-style: none;
margin: 0;
padding: 0;
}