gardel/lightrag
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge pull request #890 from YanSte/paralle-4

Browse Source 
fixed the behaviour Multi paralle
This commit is contained in:
Yannick Stephan
2025-02-20 00:11:37 +01:00
committed by GitHub
parent f52c53b41c 80a61d7e7a
commit bf720b131b
1 changed files with 17 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
lightrag/lightrag.py
View File

@@ -809,18 +809,6 @@ class LightRAG:
doc_id, status_doc = doc_id_processing_status doc_id, status_doc = doc_id_processing_status
# Update status in processing # Update status in processing
doc_status_id = compute_mdhash_id(status_doc.content, prefix="doc-") doc_status_id = compute_mdhash_id(status_doc.content, prefix="doc-")
await self.doc_status.upsert(
{
doc_status_id: {
"status": DocStatus.PROCESSING,
"updated_at": datetime.now().isoformat(),
"content": status_doc.content,
"content_summary": status_doc.content_summary,
"content_length": status_doc.content_length,
"created_at": status_doc.created_at,
}
}
)
# Generate chunks from document # Generate chunks from document
chunks: dict[str, Any] = { chunks: dict[str, Any] = {
compute_mdhash_id(dp["content"], prefix="chunk-"): { compute_mdhash_id(dp["content"], prefix="chunk-"): {
@@ -839,13 +827,28 @@ class LightRAG:
# Process document (text chunks and full docs) in parallel # Process document (text chunks and full docs) in parallel
tasks = [ tasks = [
self.doc_status.upsert(
{
doc_status_id: {
"status": DocStatus.PROCESSING,
"updated_at": datetime.now().isoformat(),
"content": status_doc.content,
"content_summary": status_doc.content_summary,
"content_length": status_doc.content_length,
"created_at": status_doc.created_at,
}
}
),
self.chunks_vdb.upsert(chunks), self.chunks_vdb.upsert(chunks),
self._process_entity_relation_graph(chunks), self._process_entity_relation_graph(chunks),
self.full_docs.upsert( self.full_docs.upsert(
{doc_id: {"content": status_doc.content}} {doc_id: {"content": status_doc.content}}
), ),
self.text_chunks.upsert(chunks), self.text_chunks.upsert(chunks),
self.doc_status.upsert( ]
try:
await asyncio.gather(*tasks)
await self.doc_status.upsert(
{ {
doc_status_id: { doc_status_id: {
"status": DocStatus.PROCESSED, "status": DocStatus.PROCESSED,
@@ -857,11 +860,7 @@ class LightRAG:
"updated_at": datetime.now().isoformat(), "updated_at": datetime.now().isoformat(),
} }
} }
), )
]
try:
await asyncio.gather(*tasks)
except Exception as e: except Exception as e:
logger.error(f"Failed to process document {doc_id}: {str(e)}") logger.error(f"Failed to process document {doc_id}: {str(e)}")
await self.doc_status.upsert( await self.doc_status.upsert(