dify/api/services/plugin/data_migration.py
Yeuoly 403e2d58b9
Introduce Plugins (#13836)
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
Signed-off-by: -LAN- <laipz8200@outlook.com>
Signed-off-by: xhe <xw897002528@gmail.com>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: takatost <takatost@gmail.com>
Co-authored-by: kurokobo <kuro664@gmail.com>
Co-authored-by: Novice Lee <novicelee@NoviPro.local>
Co-authored-by: zxhlyh <jasonapring2015@outlook.com>
Co-authored-by: AkaraChen <akarachen@outlook.com>
Co-authored-by: Yi <yxiaoisme@gmail.com>
Co-authored-by: Joel <iamjoel007@gmail.com>
Co-authored-by: JzoNg <jzongcode@gmail.com>
Co-authored-by: twwu <twwu@dify.ai>
Co-authored-by: Hiroshi Fujita <fujita-h@users.noreply.github.com>
Co-authored-by: AkaraChen <85140972+AkaraChen@users.noreply.github.com>
Co-authored-by: NFish <douxc512@gmail.com>
Co-authored-by: Wu Tianwei <30284043+WTW0313@users.noreply.github.com>
Co-authored-by: 非法操作 <hjlarry@163.com>
Co-authored-by: Novice <857526207@qq.com>
Co-authored-by: Hiroki Nagai <82458324+nagaihiroki-git@users.noreply.github.com>
Co-authored-by: Gen Sato <52241300+halogen22@users.noreply.github.com>
Co-authored-by: eux <euxuuu@gmail.com>
Co-authored-by: huangzhuo1949 <167434202+huangzhuo1949@users.noreply.github.com>
Co-authored-by: huangzhuo <huangzhuo1@xiaomi.com>
Co-authored-by: lotsik <lotsik@mail.ru>
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
Co-authored-by: nite-knite <nkCoding@gmail.com>
Co-authored-by: Jyong <76649700+JohnJyong@users.noreply.github.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: gakkiyomi <gakkiyomi@aliyun.com>
Co-authored-by: CN-P5 <heibai2006@gmail.com>
Co-authored-by: CN-P5 <heibai2006@qq.com>
Co-authored-by: Chuehnone <1897025+chuehnone@users.noreply.github.com>
Co-authored-by: yihong <zouzou0208@gmail.com>
Co-authored-by: Kevin9703 <51311316+Kevin9703@users.noreply.github.com>
Co-authored-by: -LAN- <laipz8200@outlook.com>
Co-authored-by: Boris Feld <lothiraldan@gmail.com>
Co-authored-by: mbo <himabo@gmail.com>
Co-authored-by: mabo <mabo@aeyes.ai>
Co-authored-by: Warren Chen <warren.chen830@gmail.com>
Co-authored-by: JzoNgKVO <27049666+JzoNgKVO@users.noreply.github.com>
Co-authored-by: jiandanfeng <chenjh3@wangsu.com>
Co-authored-by: zhu-an <70234959+xhdd123321@users.noreply.github.com>
Co-authored-by: zhaoqingyu.1075 <zhaoqingyu.1075@bytedance.com>
Co-authored-by: 海狸大師 <86974027+yenslife@users.noreply.github.com>
Co-authored-by: Xu Song <xusong.vip@gmail.com>
Co-authored-by: rayshaw001 <396301947@163.com>
Co-authored-by: Ding Jiatong <dingjiatong@gmail.com>
Co-authored-by: Bowen Liang <liangbowen@gf.com.cn>
Co-authored-by: JasonVV <jasonwangiii@outlook.com>
Co-authored-by: le0zh <newlight@qq.com>
Co-authored-by: zhuxinliang <zhuxinliang@didiglobal.com>
Co-authored-by: k-zaku <zaku99@outlook.jp>
Co-authored-by: luckylhb90 <luckylhb90@gmail.com>
Co-authored-by: hobo.l <hobo.l@binance.com>
Co-authored-by: jiangbo721 <365065261@qq.com>
Co-authored-by: 刘江波 <jiangbo721@163.com>
Co-authored-by: Shun Miyazawa <34241526+miya@users.noreply.github.com>
Co-authored-by: EricPan <30651140+Egfly@users.noreply.github.com>
Co-authored-by: crazywoola <427733928@qq.com>
Co-authored-by: sino <sino2322@gmail.com>
Co-authored-by: Jhvcc <37662342+Jhvcc@users.noreply.github.com>
Co-authored-by: lowell <lowell.hu@zkteco.in>
Co-authored-by: Boris Polonsky <BorisPolonsky@users.noreply.github.com>
Co-authored-by: Ademílson Tonato <ademilsonft@outlook.com>
Co-authored-by: Ademílson Tonato <ademilson.tonato@refurbed.com>
Co-authored-by: IWAI, Masaharu <iwaim.sub@gmail.com>
Co-authored-by: Yueh-Po Peng (Yabi) <94939112+y10ab1@users.noreply.github.com>
Co-authored-by: Jason <ggbbddjm@gmail.com>
Co-authored-by: Xin Zhang <sjhpzx@gmail.com>
Co-authored-by: yjc980121 <3898524+yjc980121@users.noreply.github.com>
Co-authored-by: heyszt <36215648+hieheihei@users.noreply.github.com>
Co-authored-by: Abdullah AlOsaimi <osaimiacc@gmail.com>
Co-authored-by: Abdullah AlOsaimi <189027247+osaimi@users.noreply.github.com>
Co-authored-by: Yingchun Lai <laiyingchun@apache.org>
Co-authored-by: Hash Brown <hi@xzd.me>
Co-authored-by: zuodongxu <192560071+zuodongxu@users.noreply.github.com>
Co-authored-by: Masashi Tomooka <tmokmss@users.noreply.github.com>
Co-authored-by: aplio <ryo.091219@gmail.com>
Co-authored-by: Obada Khalili <54270856+obadakhalili@users.noreply.github.com>
Co-authored-by: Nam Vu <zuzoovn@gmail.com>
Co-authored-by: Kei YAMAZAKI <1715090+kei-yamazaki@users.noreply.github.com>
Co-authored-by: TechnoHouse <13776377+deephbz@users.noreply.github.com>
Co-authored-by: Riddhimaan-Senapati <114703025+Riddhimaan-Senapati@users.noreply.github.com>
Co-authored-by: MaFee921 <31881301+2284730142@users.noreply.github.com>
Co-authored-by: te-chan <t-nakanome@sakura-is.co.jp>
Co-authored-by: HQidea <HQidea@users.noreply.github.com>
Co-authored-by: Joshbly <36315710+Joshbly@users.noreply.github.com>
Co-authored-by: xhe <xw897002528@gmail.com>
Co-authored-by: weiwenyan-dev <154779315+weiwenyan-dev@users.noreply.github.com>
Co-authored-by: ex_wenyan.wei <ex_wenyan.wei@tcl.com>
Co-authored-by: engchina <12236799+engchina@users.noreply.github.com>
Co-authored-by: engchina <atjapan2015@gmail.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: 呆萌闷油瓶 <253605712@qq.com>
Co-authored-by: Kemal <kemalmeler@outlook.com>
Co-authored-by: Lazy_Frog <4590648+lazyFrogLOL@users.noreply.github.com>
Co-authored-by: Yi Xiao <54782454+YIXIAO0@users.noreply.github.com>
Co-authored-by: Steven sun <98230804+Tuyohai@users.noreply.github.com>
Co-authored-by: steven <sunzwj@digitalchina.com>
Co-authored-by: Kalo Chin <91766386+fdb02983rhy@users.noreply.github.com>
Co-authored-by: Katy Tao <34019945+KatyTao@users.noreply.github.com>
Co-authored-by: depy <42985524+h4ckdepy@users.noreply.github.com>
Co-authored-by: 胡春东 <gycm520@gmail.com>
Co-authored-by: Junjie.M <118170653@qq.com>
Co-authored-by: MuYu <mr.muzea@gmail.com>
Co-authored-by: Naoki Takashima <39912547+takatea@users.noreply.github.com>
Co-authored-by: Summer-Gu <37869445+gubinjie@users.noreply.github.com>
Co-authored-by: Fei He <droxer.he@gmail.com>
Co-authored-by: ybalbert001 <120714773+ybalbert001@users.noreply.github.com>
Co-authored-by: Yuanbo Li <ybalbert@amazon.com>
Co-authored-by: douxc <7553076+douxc@users.noreply.github.com>
Co-authored-by: liuzhenghua <1090179900@qq.com>
Co-authored-by: Wu Jiayang <62842862+Wu-Jiayang@users.noreply.github.com>
Co-authored-by: Your Name <you@example.com>
Co-authored-by: kimjion <45935338+kimjion@users.noreply.github.com>
Co-authored-by: AugNSo <song.tiankai@icloud.com>
Co-authored-by: llinvokerl <38915183+llinvokerl@users.noreply.github.com>
Co-authored-by: liusurong.lsr <liusurong.lsr@alibaba-inc.com>
Co-authored-by: Vasu Negi <vasu-negi@users.noreply.github.com>
Co-authored-by: Hundredwz <1808096180@qq.com>
Co-authored-by: Xiyuan Chen <52963600+GareArc@users.noreply.github.com>
2025-02-17 17:05:13 +08:00

186 lines
8.2 KiB
Python

import json
import logging
import click
from core.entities import DEFAULT_PLUGIN_ID
from models.engine import db
logger = logging.getLogger(__name__)
class PluginDataMigration:
@classmethod
def migrate(cls) -> None:
cls.migrate_db_records("providers", "provider_name") # large table
cls.migrate_db_records("provider_models", "provider_name")
cls.migrate_db_records("provider_orders", "provider_name")
cls.migrate_db_records("tenant_default_models", "provider_name")
cls.migrate_db_records("tenant_preferred_model_providers", "provider_name")
cls.migrate_db_records("provider_model_settings", "provider_name")
cls.migrate_db_records("load_balancing_model_configs", "provider_name")
cls.migrate_datasets()
cls.migrate_db_records("embeddings", "provider_name") # large table
cls.migrate_db_records("dataset_collection_bindings", "provider_name")
cls.migrate_db_records("tool_builtin_providers", "provider")
@classmethod
def migrate_datasets(cls) -> None:
table_name = "datasets"
provider_column_name = "embedding_model_provider"
click.echo(click.style(f"Migrating [{table_name}] data for plugin", fg="white"))
processed_count = 0
failed_ids = []
while True:
sql = f"""select id, {provider_column_name} as provider_name, retrieval_model from {table_name}
where {provider_column_name} not like '%/%' and {provider_column_name} is not null and {provider_column_name} != ''
limit 1000"""
with db.engine.begin() as conn:
rs = conn.execute(db.text(sql))
current_iter_count = 0
for i in rs:
record_id = str(i.id)
provider_name = str(i.provider_name)
retrieval_model = i.retrieval_model
print(type(retrieval_model))
if record_id in failed_ids:
continue
retrieval_model_changed = False
if retrieval_model:
if (
"reranking_model" in retrieval_model
and "reranking_provider_name" in retrieval_model["reranking_model"]
and retrieval_model["reranking_model"]["reranking_provider_name"]
and "/" not in retrieval_model["reranking_model"]["reranking_provider_name"]
):
click.echo(
click.style(
f"[{processed_count}] Migrating {table_name} {record_id} "
f"(reranking_provider_name: "
f"{retrieval_model['reranking_model']['reranking_provider_name']})",
fg="white",
)
)
retrieval_model["reranking_model"]["reranking_provider_name"] = (
f"{DEFAULT_PLUGIN_ID}/{retrieval_model['reranking_model']['reranking_provider_name']}/{retrieval_model['reranking_model']['reranking_provider_name']}"
)
retrieval_model_changed = True
click.echo(
click.style(
f"[{processed_count}] Migrating [{table_name}] {record_id} ({provider_name})",
fg="white",
)
)
try:
# update provider name append with "langgenius/{provider_name}/{provider_name}"
params = {"record_id": record_id}
update_retrieval_model_sql = ""
if retrieval_model and retrieval_model_changed:
update_retrieval_model_sql = ", retrieval_model = :retrieval_model"
params["retrieval_model"] = json.dumps(retrieval_model)
sql = f"""update {table_name}
set {provider_column_name} =
concat('{DEFAULT_PLUGIN_ID}/', {provider_column_name}, '/', {provider_column_name})
{update_retrieval_model_sql}
where id = :record_id"""
conn.execute(db.text(sql), params)
click.echo(
click.style(
f"[{processed_count}] Migrated [{table_name}] {record_id} ({provider_name})",
fg="green",
)
)
except Exception:
failed_ids.append(record_id)
click.echo(
click.style(
f"[{processed_count}] Failed to migrate [{table_name}] {record_id} ({provider_name})",
fg="red",
)
)
logger.exception(
f"[{processed_count}] Failed to migrate [{table_name}] {record_id} ({provider_name})"
)
continue
current_iter_count += 1
processed_count += 1
if not current_iter_count:
break
click.echo(
click.style(f"Migrate [{table_name}] data for plugin completed, total: {processed_count}", fg="green")
)
@classmethod
def migrate_db_records(cls, table_name: str, provider_column_name: str) -> None:
click.echo(click.style(f"Migrating [{table_name}] data for plugin", fg="white"))
processed_count = 0
failed_ids = []
while True:
sql = f"""select id, {provider_column_name} as provider_name from {table_name}
where {provider_column_name} not like '%/%' and {provider_column_name} is not null and {provider_column_name} != ''
limit 1000"""
with db.engine.begin() as conn:
rs = conn.execute(db.text(sql))
current_iter_count = 0
for i in rs:
current_iter_count += 1
processed_count += 1
record_id = str(i.id)
provider_name = str(i.provider_name)
if record_id in failed_ids:
continue
click.echo(
click.style(
f"[{processed_count}] Migrating [{table_name}] {record_id} ({provider_name})",
fg="white",
)
)
try:
# update provider name append with "langgenius/{provider_name}/{provider_name}"
sql = f"""update {table_name}
set {provider_column_name} =
concat('{DEFAULT_PLUGIN_ID}/', {provider_column_name}, '/', {provider_column_name})
where id = :record_id"""
conn.execute(db.text(sql), {"record_id": record_id})
click.echo(
click.style(
f"[{processed_count}] Migrated [{table_name}] {record_id} ({provider_name})",
fg="green",
)
)
except Exception:
failed_ids.append(record_id)
click.echo(
click.style(
f"[{processed_count}] Failed to migrate [{table_name}] {record_id} ({provider_name})",
fg="red",
)
)
logger.exception(
f"[{processed_count}] Failed to migrate [{table_name}] {record_id} ({provider_name})"
)
continue
if not current_iter_count:
break
click.echo(
click.style(f"Migrate [{table_name}] data for plugin completed, total: {processed_count}", fg="green")
)