apunkt/PageIndex
1
0
Fork 0
mirror of https://github.com/VectifyAI/PageIndex.git synced 2026-04-24 23:56:21 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 2

fix tutorials

Browse source
This commit is contained in:
Ray 2025-08-30 05:15:35 +08:00
parent 66c1493f79
commit 6fed3087a2
3 changed files with 74 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

2
tutorials/doc-search/metadata.md
View file

@ -1,7 +1,7 @@
## Document Search by Metadata
<Callout>PageIndex with metadata support is in closed beta. Fill out this form to request early access to this feature.</Callout>
<callout>PageIndex with metadata support is in closed beta. Fill out this form to request early access to this feature.</callout>
For documents that can be easily distinguished by metadata, we recommend using metadata to search the documents.
This method is ideal for the following document types:

4
tutorials/doc-search/semantics.md
View file

@ -18,7 +18,9 @@ For each query, conduct a vector-based search to get top-K chunks with their cor
For each document, calculate a relevance score. Let N be the number of content chunks associated with each document, and let **ChunkScore**(n) be the relevance score of chunk n. The document score is computed as:
$\text{DocScore}=\frac{1}{\sqrt{N+1}}\sum_{n=1}^N \text{ChunkScore}(n)$
$$
\text{DocScore}=\frac{1}{\sqrt{N+1}}\sum_{n=1}^N \text{ChunkScore}(n)
$$
- The sum aggregates relevance from all related chunks.
- The +1 inside the square root ensures the formula handles nodes with zero chunks.