wangys/urbanLifeline
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

dify

Browse Source
This commit is contained in:
wangys
2025-12-01 17:21:38 +08:00
parent 32fee2b8ab
commit fab8c13cb3
7511 changed files with 996300 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

62
dify/api/tasks/annotation/add_annotation_to_index_task.py Normal file
View File

@@ -0,0 +1,62 @@
import logging
import time
import click
from celery import shared_task
from core.rag.datasource.vdb.vector_factory import Vector
from core.rag.models.document import Document
from extensions.ext_database import db
from models.dataset import Dataset
from services.dataset_service import DatasetCollectionBindingService
logger = logging.getLogger(__name__)
@shared_task(queue="dataset")
def add_annotation_to_index_task(
annotation_id: str, question: str, tenant_id: str, app_id: str, collection_binding_id: str
):
"""
Add annotation to index.
:param annotation_id: annotation id
:param question: question
:param tenant_id: tenant id
:param app_id: app id
:param collection_binding_id: embedding binding id
Usage: clean_dataset_task.delay(dataset_id, tenant_id, indexing_technique, index_struct)
"""
logger.info(click.style(f"Start build index for annotation: {annotation_id}", fg="green"))
start_at = time.perf_counter()
try:
dataset_collection_binding = DatasetCollectionBindingService.get_dataset_collection_binding_by_id_and_type(
collection_binding_id, "annotation"
)
dataset = Dataset(
id=app_id,
tenant_id=tenant_id,
indexing_technique="high_quality",
embedding_model_provider=dataset_collection_binding.provider_name,
embedding_model=dataset_collection_binding.model_name,
collection_binding_id=dataset_collection_binding.id,
)
document = Document(
page_content=question, metadata={"annotation_id": annotation_id, "app_id": app_id, "doc_id": annotation_id}
)
vector = Vector(dataset, attributes=["doc_id", "annotation_id", "app_id"])
vector.create([document], duplicate_check=True)
end_at = time.perf_counter()
logger.info(
click.style(
f"Build index successful for annotation: {annotation_id} latency: {end_at - start_at}",
fg="green",
)
)
except Exception:
logger.exception("Build index for annotation failed")
finally:
db.session.close()

94
dify/api/tasks/annotation/batch_import_annotations_task.py Normal file
View File

@@ -0,0 +1,94 @@
import logging
import time
import click
from celery import shared_task
from werkzeug.exceptions import NotFound
from core.rag.datasource.vdb.vector_factory import Vector
from core.rag.models.document import Document
from extensions.ext_database import db
from extensions.ext_redis import redis_client
from models.dataset import Dataset
from models.model import App, AppAnnotationSetting, MessageAnnotation
from services.dataset_service import DatasetCollectionBindingService
logger = logging.getLogger(__name__)
@shared_task(queue="dataset")
def batch_import_annotations_task(job_id: str, content_list: list[dict], app_id: str, tenant_id: str, user_id: str):
"""
Add annotation to index.
:param job_id: job_id
:param content_list: content list
:param app_id: app id
:param tenant_id: tenant id
:param user_id: user_id
"""
logger.info(click.style(f"Start batch import annotation: {job_id}", fg="green"))
start_at = time.perf_counter()
indexing_cache_key = f"app_annotation_batch_import_{str(job_id)}"
# get app info
app = db.session.query(App).where(App.id == app_id, App.tenant_id == tenant_id, App.status == "normal").first()
if app:
try:
documents = []
for content in content_list:
annotation = MessageAnnotation(
app_id=app.id, content=content["answer"], question=content["question"], account_id=user_id
)
db.session.add(annotation)
db.session.flush()
document = Document(
page_content=content["question"],
metadata={"annotation_id": annotation.id, "app_id": app_id, "doc_id": annotation.id},
)
documents.append(document)
# if annotation reply is enabled , batch add annotations' index
app_annotation_setting = (
db.session.query(AppAnnotationSetting).where(AppAnnotationSetting.app_id == app_id).first()
)
if app_annotation_setting:
dataset_collection_binding = (
DatasetCollectionBindingService.get_dataset_collection_binding_by_id_and_type(
app_annotation_setting.collection_binding_id, "annotation"
)
)
if not dataset_collection_binding:
raise NotFound("App annotation setting not found")
dataset = Dataset(
id=app_id,
tenant_id=tenant_id,
indexing_technique="high_quality",
embedding_model_provider=dataset_collection_binding.provider_name,
embedding_model=dataset_collection_binding.model_name,
collection_binding_id=dataset_collection_binding.id,
)
vector = Vector(dataset, attributes=["doc_id", "annotation_id", "app_id"])
vector.create(documents, duplicate_check=True)
db.session.commit()
redis_client.setex(indexing_cache_key, 600, "completed")
end_at = time.perf_counter()
logger.info(
click.style(
"Build index successful for batch import annotation: {} latency: {}".format(
job_id, end_at - start_at
),
fg="green",
)
)
except Exception as e:
db.session.rollback()
redis_client.setex(indexing_cache_key, 600, "error")
indexing_error_msg_key = f"app_annotation_batch_import_error_msg_{str(job_id)}"
redis_client.setex(indexing_error_msg_key, 600, str(e))
logger.exception("Build index for batch import annotations failed")
finally:
db.session.close()

44
dify/api/tasks/annotation/delete_annotation_index_task.py Normal file
View File

@@ -0,0 +1,44 @@
import logging
import time
import click
from celery import shared_task
from core.rag.datasource.vdb.vector_factory import Vector
from extensions.ext_database import db
from models.dataset import Dataset
from services.dataset_service import DatasetCollectionBindingService
logger = logging.getLogger(__name__)
@shared_task(queue="dataset")
def delete_annotation_index_task(annotation_id: str, app_id: str, tenant_id: str, collection_binding_id: str):
"""
Async delete annotation index task
"""
logger.info(click.style(f"Start delete app annotation index: {app_id}", fg="green"))
start_at = time.perf_counter()
try:
dataset_collection_binding = DatasetCollectionBindingService.get_dataset_collection_binding_by_id_and_type(
collection_binding_id, "annotation"
)
dataset = Dataset(
id=app_id,
tenant_id=tenant_id,
indexing_technique="high_quality",
collection_binding_id=dataset_collection_binding.id,
)
try:
vector = Vector(dataset, attributes=["doc_id", "annotation_id", "app_id"])
vector.delete_by_metadata_field("annotation_id", annotation_id)
except Exception:
logger.exception("Delete annotation index failed when annotation deleted.")
end_at = time.perf_counter()
logger.info(click.style(f"App annotations index deleted : {app_id} latency: {end_at - start_at}", fg="green"))
except Exception:
logger.exception("Annotation deleted index failed")
finally:
db.session.close()

71
dify/api/tasks/annotation/disable_annotation_reply_task.py Normal file
View File

@@ -0,0 +1,71 @@
import logging
import time
import click
from celery import shared_task
from sqlalchemy import exists, select
from core.rag.datasource.vdb.vector_factory import Vector
from extensions.ext_database import db
from extensions.ext_redis import redis_client
from models.dataset import Dataset
from models.model import App, AppAnnotationSetting, MessageAnnotation
logger = logging.getLogger(__name__)
@shared_task(queue="dataset")
def disable_annotation_reply_task(job_id: str, app_id: str, tenant_id: str):
"""
Async enable annotation reply task
"""
logger.info(click.style(f"Start delete app annotations index: {app_id}", fg="green"))
start_at = time.perf_counter()
# get app info
app = db.session.query(App).where(App.id == app_id, App.tenant_id == tenant_id, App.status == "normal").first()
annotations_exists = db.session.scalar(select(exists().where(MessageAnnotation.app_id == app_id)))
if not app:
logger.info(click.style(f"App not found: {app_id}", fg="red"))
db.session.close()
return
app_annotation_setting = db.session.query(AppAnnotationSetting).where(AppAnnotationSetting.app_id == app_id).first()
if not app_annotation_setting:
logger.info(click.style(f"App annotation setting not found: {app_id}", fg="red"))
db.session.close()
return
disable_app_annotation_key = f"disable_app_annotation_{str(app_id)}"
disable_app_annotation_job_key = f"disable_app_annotation_job_{str(job_id)}"
try:
dataset = Dataset(
id=app_id,
tenant_id=tenant_id,
indexing_technique="high_quality",
collection_binding_id=app_annotation_setting.collection_binding_id,
)
try:
if annotations_exists:
vector = Vector(dataset, attributes=["doc_id", "annotation_id", "app_id"])
vector.delete()
except Exception:
logger.exception("Delete annotation index failed when annotation deleted.")
redis_client.setex(disable_app_annotation_job_key, 600, "completed")
# delete annotation setting
db.session.delete(app_annotation_setting)
db.session.commit()
end_at = time.perf_counter()
logger.info(click.style(f"App annotations index deleted : {app_id} latency: {end_at - start_at}", fg="green"))
except Exception as e:
logger.exception("Annotation batch deleted index failed")
redis_client.setex(disable_app_annotation_job_key, 600, "error")
disable_app_annotation_error_key = f"disable_app_annotation_error_{str(job_id)}"
redis_client.setex(disable_app_annotation_error_key, 600, str(e))
finally:
redis_client.delete(disable_app_annotation_key)
db.session.close()

124
dify/api/tasks/annotation/enable_annotation_reply_task.py Normal file
View File

@@ -0,0 +1,124 @@
import logging
import time
import click
from celery import shared_task
from sqlalchemy import select
from core.rag.datasource.vdb.vector_factory import Vector
from core.rag.models.document import Document
from extensions.ext_database import db
from extensions.ext_redis import redis_client
from libs.datetime_utils import naive_utc_now
from models.dataset import Dataset
from models.model import App, AppAnnotationSetting, MessageAnnotation
from services.dataset_service import DatasetCollectionBindingService
logger = logging.getLogger(__name__)
@shared_task(queue="dataset")
def enable_annotation_reply_task(
job_id: str,
app_id: str,
user_id: str,
tenant_id: str,
score_threshold: float,
embedding_provider_name: str,
embedding_model_name: str,
):
"""
Async enable annotation reply task
"""
logger.info(click.style(f"Start add app annotation to index: {app_id}", fg="green"))
start_at = time.perf_counter()
# get app info
app = db.session.query(App).where(App.id == app_id, App.tenant_id == tenant_id, App.status == "normal").first()
if not app:
logger.info(click.style(f"App not found: {app_id}", fg="red"))
db.session.close()
return
annotations = db.session.scalars(select(MessageAnnotation).where(MessageAnnotation.app_id == app_id)).all()
enable_app_annotation_key = f"enable_app_annotation_{str(app_id)}"
enable_app_annotation_job_key = f"enable_app_annotation_job_{str(job_id)}"
try:
documents = []
dataset_collection_binding = DatasetCollectionBindingService.get_dataset_collection_binding(
embedding_provider_name, embedding_model_name, "annotation"
)
annotation_setting = db.session.query(AppAnnotationSetting).where(AppAnnotationSetting.app_id == app_id).first()
if annotation_setting:
if dataset_collection_binding.id != annotation_setting.collection_binding_id:
old_dataset_collection_binding = (
DatasetCollectionBindingService.get_dataset_collection_binding_by_id_and_type(
annotation_setting.collection_binding_id, "annotation"
)
)
if old_dataset_collection_binding and annotations:
old_dataset = Dataset(
id=app_id,
tenant_id=tenant_id,
indexing_technique="high_quality",
embedding_model_provider=old_dataset_collection_binding.provider_name,
embedding_model=old_dataset_collection_binding.model_name,
collection_binding_id=old_dataset_collection_binding.id,
)
old_vector = Vector(old_dataset, attributes=["doc_id", "annotation_id", "app_id"])
try:
old_vector.delete()
except Exception as e:
logger.info(click.style(f"Delete annotation index error: {str(e)}", fg="red"))
annotation_setting.score_threshold = score_threshold
annotation_setting.collection_binding_id = dataset_collection_binding.id
annotation_setting.updated_user_id = user_id
annotation_setting.updated_at = naive_utc_now()
db.session.add(annotation_setting)
else:
new_app_annotation_setting = AppAnnotationSetting(
app_id=app_id,
score_threshold=score_threshold,
collection_binding_id=dataset_collection_binding.id,
created_user_id=user_id,
updated_user_id=user_id,
)
db.session.add(new_app_annotation_setting)
dataset = Dataset(
id=app_id,
tenant_id=tenant_id,
indexing_technique="high_quality",
embedding_model_provider=embedding_provider_name,
embedding_model=embedding_model_name,
collection_binding_id=dataset_collection_binding.id,
)
if annotations:
for annotation in annotations:
document = Document(
page_content=annotation.question,
metadata={"annotation_id": annotation.id, "app_id": app_id, "doc_id": annotation.id},
)
documents.append(document)
vector = Vector(dataset, attributes=["doc_id", "annotation_id", "app_id"])
try:
vector.delete_by_metadata_field("app_id", app_id)
except Exception as e:
logger.info(click.style(f"Delete annotation index error: {str(e)}", fg="red"))
vector.create(documents)
db.session.commit()
redis_client.setex(enable_app_annotation_job_key, 600, "completed")
end_at = time.perf_counter()
logger.info(click.style(f"App annotations added to index: {app_id} latency: {end_at - start_at}", fg="green"))
except Exception as e:
logger.exception("Annotation batch created index failed")
redis_client.setex(enable_app_annotation_job_key, 600, "error")
enable_app_annotation_error_key = f"enable_app_annotation_error_{str(job_id)}"
redis_client.setex(enable_app_annotation_error_key, 600, str(e))
db.session.rollback()
finally:
redis_client.delete(enable_app_annotation_key)
db.session.close()

63
dify/api/tasks/annotation/update_annotation_to_index_task.py Normal file
View File

@@ -0,0 +1,63 @@
import logging
import time
import click
from celery import shared_task
from core.rag.datasource.vdb.vector_factory import Vector
from core.rag.models.document import Document
from extensions.ext_database import db
from models.dataset import Dataset
from services.dataset_service import DatasetCollectionBindingService
logger = logging.getLogger(__name__)
@shared_task(queue="dataset")
def update_annotation_to_index_task(
annotation_id: str, question: str, tenant_id: str, app_id: str, collection_binding_id: str
):
"""
Update annotation to index.
:param annotation_id: annotation id
:param question: question
:param tenant_id: tenant id
:param app_id: app id
:param collection_binding_id: embedding binding id
Usage: clean_dataset_task.delay(dataset_id, tenant_id, indexing_technique, index_struct)
"""
logger.info(click.style(f"Start update index for annotation: {annotation_id}", fg="green"))
start_at = time.perf_counter()
try:
dataset_collection_binding = DatasetCollectionBindingService.get_dataset_collection_binding_by_id_and_type(
collection_binding_id, "annotation"
)
dataset = Dataset(
id=app_id,
tenant_id=tenant_id,
indexing_technique="high_quality",
embedding_model_provider=dataset_collection_binding.provider_name,
embedding_model=dataset_collection_binding.model_name,
collection_binding_id=dataset_collection_binding.id,
)
document = Document(
page_content=question, metadata={"annotation_id": annotation_id, "app_id": app_id, "doc_id": annotation_id}
)
vector = Vector(dataset, attributes=["doc_id", "annotation_id", "app_id"])
vector.delete_by_metadata_field("annotation_id", annotation_id)
vector.add_texts([document])
end_at = time.perf_counter()
logger.info(
click.style(
f"Build index successful for annotation: {annotation_id} latency: {end_at - start_at}",
fg="green",
)
)
except Exception:
logger.exception("Build index for annotation failed")
finally:
db.session.close()