feat: Enhance wiki content processing with enriched image information and XML output
- Introduced `enrichChunkImageInfo` function to populate image information for text chunks by retrieving data from child chunks, ensuring that image-related content is not lost during processing. - Updated `reconstructContent` to `reconstructEnrichedContent`, allowing for the inclusion of OCR text and captions from images, improving the quality of content sent to the LLM. - Added `writeDedupItemXML` and `xmlEscape` functions to format entity and concept entries as structured XML, enhancing clarity and preventing nonsensical merges in deduplication prompts. - Refined the `deduplicateExtractedBatch` method to utilize the new XML formatting for better output consistency. These changes significantly improve the handling of image data and the overall clarity of deduplication prompts, contributing to a more effective wiki content management system.
This commit is contained in:
@@ -7,6 +7,7 @@ import (
|
||||
"regexp"
|
||||
"strings"
|
||||
|
||||
"github.com/Tencent/WeKnora/internal/searchutil"
|
||||
"github.com/Tencent/WeKnora/internal/types"
|
||||
"github.com/Tencent/WeKnora/internal/types/interfaces"
|
||||
)
|
||||
@@ -53,6 +54,41 @@ If neither query nor range is provided, it returns the beginning of the document
|
||||
}
|
||||
}
|
||||
|
||||
// enrichChunkImageInfo populates chunk.ImageInfo for a batch of parent text
|
||||
// chunks by looking up their image_ocr / image_caption children. Chunks that
|
||||
// already have a non-empty ImageInfo are left untouched.
|
||||
func enrichChunkImageInfo(
|
||||
ctx context.Context,
|
||||
chunkRepo interfaces.ChunkRepository,
|
||||
tenantID uint64,
|
||||
chunks []*types.Chunk,
|
||||
) {
|
||||
if len(chunks) == 0 || chunkRepo == nil {
|
||||
return
|
||||
}
|
||||
ids := make([]string, 0, len(chunks))
|
||||
for _, c := range chunks {
|
||||
if c.ImageInfo == "" && c.ID != "" {
|
||||
ids = append(ids, c.ID)
|
||||
}
|
||||
}
|
||||
if len(ids) == 0 {
|
||||
return
|
||||
}
|
||||
infoMap := searchutil.CollectImageInfoByChunkIDs(ctx, chunkRepo, tenantID, ids)
|
||||
if len(infoMap) == 0 {
|
||||
return
|
||||
}
|
||||
for _, c := range chunks {
|
||||
if c.ImageInfo != "" {
|
||||
continue
|
||||
}
|
||||
if merged, ok := infoMap[c.ID]; ok && merged != "" {
|
||||
c.ImageInfo = merged
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func enrichChunkContent(c *types.Chunk) string {
|
||||
content := c.Content
|
||||
if c.ImageInfo != "" {
|
||||
@@ -164,6 +200,12 @@ func (t *wikiReadSourceDocTool) Execute(ctx context.Context, args json.RawMessag
|
||||
break
|
||||
}
|
||||
|
||||
// Lazily enrich ImageInfo from image_ocr / image_caption child chunks.
|
||||
// Parent text chunks don't carry image_info themselves (see
|
||||
// image_multimodal.go); without this the source-doc reader would
|
||||
// silently drop OCR text and captions for image-heavy documents.
|
||||
enrichChunkImageInfo(ctx, t.chunkService.GetRepository(), knowledge.TenantID, chunks)
|
||||
|
||||
for _, c := range chunks {
|
||||
chunkNum := c.ChunkIndex + 1
|
||||
chunkContent := enrichChunkContent(c)
|
||||
|
||||
Reference in New Issue
Block a user