feat: improve assistant knowledge import and database compatibility
This commit is contained in:
1 parent
fbd8dec48f
commit
6b724bd00d
51 files changed
+4393
-1021
No files matched your search
+18
@@ -3,6 +3,7 @@
|
||||
from __future__ import annotations
|
||||
|
||||
from abc import ABC, abstractmethod
|
||||
from collections.abc import AsyncIterator
|
||||
from typing import Any
|
||||
|
||||
|
||||
@@ -35,6 +36,23 @@ class LlmWikiIndexStore(ABC):
|
||||
@abstractmethod
|
||||
async def load_vector_snapshot(self, mapping_id: str, fingerprint: str) -> dict[str, Any]: ...
|
||||
|
||||
async def iter_vector_snapshot_rows(
|
||||
self,
|
||||
mapping_id: str,
|
||||
fingerprint: str,
|
||||
*,
|
||||
batch_size: int = 1000,
|
||||
) -> AsyncIterator[dict[str, Any]]:
|
||||
"""Iterate vector rows for streaming export.
|
||||
|
||||
Implementations with a database backend should override this method so
|
||||
very large vector packages do not need to be materialized in memory.
|
||||
"""
|
||||
snapshot = await self.load_vector_snapshot(mapping_id, fingerprint)
|
||||
for row in snapshot.get("rows") or []:
|
||||
if isinstance(row, dict):
|
||||
yield row
|
||||
|
||||
@abstractmethod
|
||||
async def get_index_revision(self, mapping_id: str) -> tuple[int, str | None, str]: ...
|
||||
|
||||
|
||||
Reference in new issue
Block a user