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

cleaned code

Browse Source
This commit is contained in:
Yannick Stephan
2025-02-09 15:25:58 +01:00
parent d1d422e5e4
commit c36c6743d6
2 changed files with 15 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
lightrag/base.py
View File

@@ -165,6 +165,7 @@ class DocStatus(str, Enum):
@dataclass
class DocProcessingStatus:
"""Document processing status data structure"""
content: str
"""Original content of the document"""
content_summary: str

16
lightrag/lightrag.py
View File

@@ -545,8 +545,12 @@ class LightRAG:
to_process_docs_ids = list(to_process_docs.keys())
# Get allready processed documents (text chunks and full docs)
text_chunks_processed_doc_ids = await self.text_chunks.filter_keys(to_process_docs_ids)
full_docs_processed_doc_ids = await self.full_docs.filter_keys(to_process_docs_ids)
text_chunks_processed_doc_ids = await self.text_chunks.filter_keys(
to_process_docs_ids
)
full_docs_processed_doc_ids = await self.full_docs.filter_keys(
to_process_docs_ids
)
# 2. split docs into chunks, insert chunks, update doc status
batch_size = self.addon_params.get("insert_batch_size", 10)
@@ -604,9 +608,7 @@ class LightRAG:
# Check if document already processed the doc
if id_doc not in full_docs_processed_doc_ids:
tasks[id_doc].append(
self.full_docs.upsert(
{id_doc: {"content": status_doc.content}}
)
self.full_docs.upsert({id_doc: {"content": status_doc.content}})
)
# Check if chunks already processed the doc
@@ -629,7 +631,9 @@ class LightRAG:
await self._insert_done()
except Exception as e:
logger.error(f"Failed to process document {id_doc_processing_status}: {str(e)}")
logger.error(
f"Failed to process document {id_doc_processing_status}: {str(e)}"
)
await self.doc_status.upsert(
{
id_doc_processing_status: {