Feat/dify rag (#2528)

Co-authored-by: jyong <jyong@dify.ai>
This commit is contained in:
Jyong
2024-02-22 23:31:57 +08:00
committed by GitHub
parent 97fe817186
commit 6c4e6bf1d6
119 changed files with 3181 additions and 5892 deletions

View File

@@ -4,10 +4,10 @@ import time
import click
from celery import shared_task
from langchain.schema import Document
from werkzeug.exceptions import NotFound
from core.index.index import IndexBuilder
from core.rag.index_processor.index_processor_factory import IndexProcessorFactory
from core.rag.models.document import Document
from extensions.ext_database import db
from extensions.ext_redis import redis_client
from models.dataset import DocumentSegment
@@ -60,15 +60,9 @@ def enable_segment_to_index_task(segment_id: str):
logging.info(click.style('Segment {} document status is invalid, pass.'.format(segment.id), fg='cyan'))
return
index_processor = IndexProcessorFactory(dataset_document.doc_form).init_index_processor()
# save vector index
index = IndexBuilder.get_index(dataset, 'high_quality')
if index:
index.add_texts([document], duplicate_check=True)
# save keyword index
index = IndexBuilder.get_index(dataset, 'economy')
if index:
index.add_texts([document])
index_processor.load(dataset, [document])
end_at = time.perf_counter()
logging.info(click.style('Segment enabled to index: {} latency: {}'.format(segment.id, end_at - start_at), fg='green'))