feat: upgrade langchain (#430)

Co-authored-by: jyong <718720800@qq.com>
This commit is contained in:
John Wang
2023-06-25 16:49:14 +08:00
committed by GitHub
parent 1dee5de9b4
commit 3241e4015b
91 changed files with 2703 additions and 3153 deletions

View File

@@ -4,8 +4,7 @@ import time
import click
from celery import shared_task
from core.index.keyword_table_index import KeywordTableIndex
from core.index.vector_index import VectorIndex
from core.index.index import IndexBuilder
from extensions.ext_database import db
from models.dataset import DocumentSegment, Dataset, DatasetKeywordTable, DatasetQuery, DatasetProcessRule, \
AppDatasetJoin
@@ -33,29 +32,24 @@ def clean_dataset_task(dataset_id: str, tenant_id: str, indexing_technique: str,
index_struct=index_struct
)
vector_index = VectorIndex(dataset=dataset)
keyword_table_index = KeywordTableIndex(dataset=dataset)
documents = db.session.query(DocumentSegment).filter(DocumentSegment.dataset_id == dataset_id).all()
index_doc_ids = [document.id for document in documents]
segments = db.session.query(DocumentSegment).filter(DocumentSegment.dataset_id == dataset_id).all()
index_node_ids = [segment.index_node_id for segment in segments]
vector_index = IndexBuilder.get_index(dataset, 'high_quality')
kw_index = IndexBuilder.get_index(dataset, 'economy')
# delete from vector index
if dataset.indexing_technique == "high_quality":
for index_doc_id in index_doc_ids:
try:
vector_index.del_doc(index_doc_id)
except Exception:
logging.exception("Delete doc index failed when dataset deleted.")
continue
if vector_index:
try:
vector_index.delete()
except Exception:
logging.exception("Delete doc index failed when dataset deleted.")
# delete from keyword index
if index_node_ids:
try:
keyword_table_index.del_nodes(index_node_ids)
except Exception:
logging.exception("Delete nodes index failed when dataset deleted.")
try:
kw_index.delete()
except Exception:
logging.exception("Delete nodes index failed when dataset deleted.")
for document in documents:
db.session.delete(document)
@@ -63,7 +57,6 @@ def clean_dataset_task(dataset_id: str, tenant_id: str, indexing_technique: str,
for segment in segments:
db.session.delete(segment)
db.session.query(DatasetKeywordTable).filter(DatasetKeywordTable.dataset_id == dataset_id).delete()
db.session.query(DatasetProcessRule).filter(DatasetProcessRule.dataset_id == dataset_id).delete()
db.session.query(DatasetQuery).filter(DatasetQuery.dataset_id == dataset_id).delete()
db.session.query(AppDatasetJoin).filter(AppDatasetJoin.dataset_id == dataset_id).delete()