Tighten extract_items hoist annotation in _update_document_with_chunks
This commit is contained in:
parent
4cb85c5eaf
commit
4436673f10
1 changed files with 3 additions and 5 deletions
|
|
@ -18,7 +18,7 @@ from haiku.rag.client.titles import resolve_title
|
||||||
from haiku.rag.converters import get_converter
|
from haiku.rag.converters import get_converter
|
||||||
from haiku.rag.store.models.chunk import Chunk
|
from haiku.rag.store.models.chunk import Chunk
|
||||||
from haiku.rag.store.models.document import Document
|
from haiku.rag.store.models.document import Document
|
||||||
from haiku.rag.store.models.document_item import extract_items
|
from haiku.rag.store.models.document_item import DocumentItem, extract_items
|
||||||
from haiku.rag.telemetry import logfire
|
from haiku.rag.telemetry import logfire
|
||||||
|
|
||||||
if TYPE_CHECKING:
|
if TYPE_CHECKING:
|
||||||
|
|
@ -172,7 +172,7 @@ async def _update_document_with_chunks(
|
||||||
|
|
||||||
chunks = await ensure_chunks_embedded(client._config, chunks, client.embedder)
|
chunks = await ensure_chunks_embedded(client._config, chunks, client.embedder)
|
||||||
|
|
||||||
items: list | None = None
|
items: list[DocumentItem] | None = None
|
||||||
if docling_document is not None:
|
if docling_document is not None:
|
||||||
items = await asyncio.to_thread(
|
items = await asyncio.to_thread(
|
||||||
extract_items, document.id, docling_document, existing_picture_data
|
extract_items, document.id, docling_document, existing_picture_data
|
||||||
|
|
@ -297,9 +297,7 @@ async def _store_documents_with_chunks(
|
||||||
try:
|
try:
|
||||||
all_chunks: list[Chunk] = []
|
all_chunks: list[Chunk] = []
|
||||||
all_items = []
|
all_items = []
|
||||||
for doc, doc_chunks, item_list in zip(
|
for doc, doc_chunks, item_list in zip(created, embedded, all_item_lists):
|
||||||
created, embedded, all_item_lists
|
|
||||||
):
|
|
||||||
assert doc.id is not None
|
assert doc.id is not None
|
||||||
for order, chunk in enumerate(doc_chunks):
|
for order, chunk in enumerate(doc_chunks):
|
||||||
chunk.document_id = doc.id
|
chunk.document_id = doc.id
|
||||||
|
|
|
||||||
Loading…
Reference in a new issue