phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-24 06:18:06 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix chunk deletion

Browse source
This commit is contained in:
Ashwin Bharambe 2025-08-12 14:13:53 -07:00
parent c0be74b93e
commit 88cfab2768
10 changed files with 102 additions and 49 deletions
Download patch file Download diff file Expand all files Collapse all files

19
llama_stack/providers/inline/vector_io/faiss/faiss.py
View file

@ -33,6 +33,7 @@ from llama_stack.providers.utils.kvstore import kvstore_impl
from llama_stack.providers.utils.kvstore.api import KVStore
from llama_stack.providers.utils.memory.openai_vector_store_mixin import OpenAIVectorStoreMixin
from llama_stack.providers.utils.memory.vector_store import (
ChunkForDeletion,
EmbeddingIndex,
VectorDBWithIndex,
)
@ -128,11 +129,12 @@ class FaissIndex(EmbeddingIndex):
# Save updated index
await self._save_index()
async def delete_chunk(self, chunk_id: str) -> None:
if chunk_id not in self.chunk_ids:
async def delete_chunks(self, chunks_for_deletion: list[ChunkForDeletion]) -> None:
chunk_ids = [c.chunk_id for c in chunks_for_deletion]
if not set(chunk_ids).issubset(self.chunk_ids):
return
async with self.chunk_id_lock:
def remove_chunk(chunk_id: str):
index = self.chunk_ids.index(chunk_id)
self.index.remove_ids(np.array([index]))
@ -146,6 +148,10 @@ class FaissIndex(EmbeddingIndex):
self.chunk_by_index = new_chunk_by_index
self.chunk_ids.pop(index)
async with self.chunk_id_lock:
for chunk_id in chunk_ids:
remove_chunk(chunk_id)
await self._save_index()
async def query_vector(
@ -297,8 +303,7 @@ class FaissVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorDBsProtocolPr
return await index.query_chunks(query, params)
async def delete_chunks(self, store_id: str, chunk_ids: list[str]) -> None:
"""Delete a chunk from a faiss index"""
async def delete_chunks(self, store_id: str, chunks_for_deletion: list[ChunkForDeletion]) -> None:
"""Delete chunks from a faiss index"""
faiss_index = self.cache[store_id].index
for chunk_id in chunk_ids:
await faiss_index.delete_chunk(chunk_id)
await faiss_index.delete_chunks(chunks_for_deletion)

24
llama_stack/providers/inline/vector_io/sqlite_vec/sqlite_vec.py
View file

@ -31,6 +31,7 @@ from llama_stack.providers.utils.memory.openai_vector_store_mixin import OpenAIV
from llama_stack.providers.utils.memory.vector_store import (
RERANKER_TYPE_RRF,
RERANKER_TYPE_WEIGHTED,
ChunkForDeletion,
EmbeddingIndex,
VectorDBWithIndex,
)
@ -426,34 +427,35 @@ class SQLiteVecIndex(EmbeddingIndex):
return QueryChunksResponse(chunks=chunks, scores=scores)
async def delete_chunk(self, chunk_id: str) -> None:
async def delete_chunks(self, chunks_for_deletion: list[ChunkForDeletion]) -> None:
"""Remove a chunk from the SQLite vector store."""
chunk_ids = [c.chunk_id for c in chunks_for_deletion]
def _delete_chunk():
def _delete_chunks():
connection = _create_sqlite_connection(self.db_path)
cur = connection.cursor()
try:
cur.execute("BEGIN TRANSACTION")
# Delete from metadata table
cur.execute(f"DELETE FROM {self.metadata_table} WHERE id = ?", (chunk_id,))
cur.execute(f"DELETE FROM {self.metadata_table} WHERE id = ANY(?)", (chunk_ids,))
# Delete from vector table
cur.execute(f"DELETE FROM {self.vector_table} WHERE id = ?", (chunk_id,))
cur.execute(f"DELETE FROM {self.vector_table} WHERE id = ANY(?)", (chunk_ids,))
# Delete from FTS table
cur.execute(f"DELETE FROM {self.fts_table} WHERE id = ?", (chunk_id,))
cur.execute(f"DELETE FROM {self.fts_table} WHERE id = ANY(?)", (chunk_ids,))
connection.commit()
except Exception as e:
connection.rollback()
logger.error(f"Error deleting chunk {chunk_id}: {e}")
logger.error(f"Error deleting chunks: {e}")
raise
finally:
cur.close()
connection.close()
await asyncio.to_thread(_delete_chunk)
await asyncio.to_thread(_delete_chunks)
class SQLiteVecVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorDBsProtocolPrivate):
@ -551,12 +553,10 @@ class SQLiteVecVectorIOAdapter(OpenAIVectorStoreMixin, VectorIO, VectorDBsProtoc
raise VectorStoreNotFoundError(vector_db_id)
return await index.query_chunks(query, params)
async def delete_chunks(self, store_id: str, chunk_ids: list[str]) -> None:
"""Delete a chunk from a sqlite_vec index."""
async def delete_chunks(self, store_id: str, chunks_for_deletion: list[ChunkForDeletion]) -> None:
"""Delete chunks from a sqlite_vec index."""
index = await self._get_and_cache_vector_db_index(store_id)
if not index:
raise VectorStoreNotFoundError(store_id)
for chunk_id in chunk_ids:
# Use the index's delete_chunk method
await index.index.delete_chunk(chunk_id)
await index.index.delete_chunks(chunks_for_deletion)