admin/dify
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

Feat/support multimodal embedding (#29115)

Browse Source 
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
This commit is contained in:
Jyong
2025-12-09 14:41:46 +08:00
committed by GitHub
parent 77cf8f6c27
commit 9affc546c6
78 changed files with 3230 additions and 713 deletions
Download Patch File Download Diff File Expand all files Collapse all files

31
api/tasks/deal_dataset_vector_index_task.py
View File

@@ -1,14 +1,14 @@
import logging
import time
from typing import Literal
import click
from celery import shared_task
from sqlalchemy import select
from core.rag.index_processor.constant.index_type import IndexType
from core.rag.index_processor.constant.doc_type import DocType
from core.rag.index_processor.constant.index_type import IndexStructureType
from core.rag.index_processor.index_processor_factory import IndexProcessorFactory
from core.rag.models.document import ChildDocument, Document
from core.rag.models.document import AttachmentDocument, ChildDocument, Document
from extensions.ext_database import db
from models.dataset import Dataset, DocumentSegment
from models.dataset import Document as DatasetDocument
@@ -17,7 +17,7 @@ logger = logging.getLogger(__name__)
@shared_task(queue="dataset")
def deal_dataset_vector_index_task(dataset_id: str, action: Literal["remove", "add", "update"]):
def deal_dataset_vector_index_task(dataset_id: str, action: str):
"""
Async deal dataset from index
:param dataset_id: dataset_id
@@ -32,7 +32,7 @@ def deal_dataset_vector_index_task(dataset_id: str, action: Literal["remove", "a
if not dataset:
raise Exception("Dataset not found")
index_type = dataset.doc_form or IndexType.PARAGRAPH_INDEX
index_type = dataset.doc_form or IndexStructureType.PARAGRAPH_INDEX
index_processor = IndexProcessorFactory(index_type).init_index_processor()
if action == "remove":
index_processor.clean(dataset, None, with_keywords=False)
@@ -119,6 +119,7 @@ def deal_dataset_vector_index_task(dataset_id: str, action: Literal["remove", "a
)
if segments:
documents = []
multimodal_documents = []
for segment in segments:
document = Document(
page_content=segment.content,
@@ -129,7 +130,7 @@ def deal_dataset_vector_index_task(dataset_id: str, action: Literal["remove", "a
"dataset_id": segment.dataset_id,
},
)
if dataset_document.doc_form == IndexType.PARENT_CHILD_INDEX:
if dataset_document.doc_form == IndexStructureType.PARENT_CHILD_INDEX:
child_chunks = segment.get_child_chunks()
if child_chunks:
child_documents = []
@@ -145,9 +146,25 @@ def deal_dataset_vector_index_task(dataset_id: str, action: Literal["remove", "a
)
child_documents.append(child_document)
document.children = child_documents
if dataset.is_multimodal:
for attachment in segment.attachments:
multimodal_documents.append(
AttachmentDocument(
page_content=attachment["name"],
metadata={
"doc_id": attachment["id"],
"doc_hash": "",
"document_id": segment.document_id,
"dataset_id": segment.dataset_id,
"doc_type": DocType.IMAGE,
},
)
)
documents.append(document)
# save vector index
index_processor.load(dataset, documents, with_keywords=False)
index_processor.load(
dataset, documents, multimodal_documents=multimodal_documents, with_keywords=False
)
db.session.query(DatasetDocument).where(DatasetDocument.id == dataset_document.id).update(
{"indexing_status": "completed"}, synchronize_session=False
)