phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-15 01:26:10 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

chore: Updating chunk id generation to ensure uniqueness (#2618)

Browse source 
# What does this PR do?
This handles an edge case for `generate_chunk_id` if the concatenation
of the `document_id` and `chunk_text` combination are not unique. Adding
the window location ensures uniqueness.

## Test Plan
Added unit test

Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
This commit is contained in:
Francisco Arceo 2025-07-04 00:56:35 -04:00 • committed by GitHub
parent 4afd619c56
commit ea80ea63ac
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 14 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

8
tests/unit/providers/vector_io/test_chunk_utils.py
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"})