apunkt/SurfSense
1
0
Fork 0
mirror of https://github.com/MODSetter/SurfSense.git synced 2026-04-26 09:16:22 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: implement and test index method

Browse source
This commit is contained in:
CREDO23 2026-02-25 01:40:30 +02:00
parent 497ed681d5
commit 61e50834e6
8 changed files with 218 additions and 31 deletions
Download patch file Download diff file Expand all files Collapse all files

2
surfsense_backend/app/indexing_pipeline/document_hashing.py
View file

@ -4,10 +4,12 @@ from app.indexing_pipeline.connector_document import ConnectorDocument
def compute_unique_identifier_hash(doc: ConnectorDocument) -> str:
"""Return a stable SHA-256 hash identifying a document by its source identity."""
combined = f"{doc.document_type.value}:{doc.unique_id}:{doc.search_space_id}"
return hashlib.sha256(combined.encode("utf-8")).hexdigest()
def compute_content_hash(doc: ConnectorDocument) -> str:
"""Return a SHA-256 hash of the document's content scoped to its search space."""
combined = f"{doc.search_space_id}:{doc.source_markdown}"
return hashlib.sha256(combined.encode("utf-8")).hexdigest()