chore: Updating chunk id generation to ensure uniqueness

Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
This commit is contained in:
Francisco Javier Arceo 2025-07-03 23:34:38 -04:00
parent 4afd619c56
commit 0bd7a07454
3 changed files with 14 additions and 3 deletions

View file

@ -32,6 +32,14 @@ def test_generate_chunk_id():
]
def test_generate_chunk_id_with_window():
chunk = Chunk(content="test", metadata={"document_id": "doc-1"})
chunk_id1 = generate_chunk_id("doc-1", chunk, chunk_window="0-1")
chunk_id2 = generate_chunk_id("doc-1", chunk, chunk_window="1-2")
assert chunk_id1 == "149018fe-d0eb-0f8d-5f7f-726bdd2aeedb"
assert chunk_id2 == "4562c1ee-9971-1f3b-51a6-7d05e5211154"
def test_chunk_id():
# Test with existing chunk ID
chunk_with_id = Chunk(content="test", metadata={"document_id": "existing-id"})