Feat: Use data pipeline to visualize the parsing configuration of the knowledge base (#10423)

### What problem does this PR solve?

#9869

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

---------

Signed-off-by: dependabot[bot] <support@github.com>
Signed-off-by: jinhai <haijin.chn@gmail.com>
Signed-off-by: Jin Hai <haijin.chn@gmail.com>
Co-authored-by: chanx <1243304602@qq.com>
Co-authored-by: balibabu <cike8899@users.noreply.github.com>
Co-authored-by: Lynn <lynn_inf@hotmail.com>
Co-authored-by: 纷繁下的无奈 <zhileihuang@126.com>
Co-authored-by: huangzl <huangzl@shinemo.com>
Co-authored-by: writinwaters <93570324+writinwaters@users.noreply.github.com>
Co-authored-by: Wilmer <33392318@qq.com>
Co-authored-by: Adrian Weidig <adrianweidig@gmx.net>
Co-authored-by: Zhichang Yu <yuzhichang@gmail.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Yongteng Lei <yongtengrey@outlook.com>
Co-authored-by: Liu An <asiro@qq.com>
Co-authored-by: buua436 <66937541+buua436@users.noreply.github.com>
Co-authored-by: BadwomanCraZY <511528396@qq.com>
Co-authored-by: cucusenok <31804608+cucusenok@users.noreply.github.com>
Co-authored-by: Russell Valentine <russ@coldstonelabs.org>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Billy Bao <newyorkupperbay@gmail.com>
Co-authored-by: Zhedong Cen <cenzhedong2@126.com>
Co-authored-by: TensorNull <129579691+TensorNull@users.noreply.github.com>
Co-authored-by: TensorNull <tensor.null@gmail.com>
Co-authored-by: TeslaZY <TeslaZY@outlook.com>
Co-authored-by: Ajay <160579663+aybanda@users.noreply.github.com>
Co-authored-by: AB <aj@Ajays-MacBook-Air.local>
Co-authored-by: 天海蒼灆 <huangaoqin@tecpie.com>
Co-authored-by: He Wang <wanghechn@qq.com>
Co-authored-by: Atsushi Hatakeyama <atu729@icloud.com>
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
Co-authored-by: Mohamed Mathari <155896313+melmathari@users.noreply.github.com>
Co-authored-by: Mohamed Mathari <nocodeventure@Mac-mini-van-Mohamed.fritz.box>
Co-authored-by: Stephen Hu <stephenhu@seismic.com>
Co-authored-by: Shaun Zhang <zhangwfjh@users.noreply.github.com>
Co-authored-by: zhimeng123 <60221886+zhimeng123@users.noreply.github.com>
Co-authored-by: mxc <mxc@example.com>
Co-authored-by: Dominik Novotný <50611433+SgtMarmite@users.noreply.github.com>
Co-authored-by: EVGENY M <168018528+rjohny55@users.noreply.github.com>
Co-authored-by: mcoder6425 <mcoder64@gmail.com>
Co-authored-by: lemsn <lemsn@msn.com>
Co-authored-by: lemsn <lemsn@126.com>
Co-authored-by: Adrian Gora <47756404+adagora@users.noreply.github.com>
Co-authored-by: Womsxd <45663319+Womsxd@users.noreply.github.com>
Co-authored-by: FatMii <39074672+FatMii@users.noreply.github.com>
This commit is contained in:
Kevin Hu
2025-10-09 12:36:19 +08:00
committed by GitHub
parent ef0aecea3b
commit cbf04ee470
490 changed files with 10630 additions and 30688 deletions

View File

@ -19,15 +19,19 @@ import re
import sys
from functools import partial
import flask
import trio
from flask import request, Response
from flask_login import login_required, current_user
from agent.component.llm import LLM
from agent.component import LLM
from api import settings
from api.db import CanvasCategory, FileType
from api.db.services.canvas_service import CanvasTemplateService, UserCanvasService, API4ConversationService
from api.db.services.document_service import DocumentService
from api.db.services.file_service import FileService
from api.db.services.pipeline_operation_log_service import PipelineOperationLogService
from api.db.services.task_service import queue_dataflow, CANVAS_DEBUG_DOC_ID, TaskService
from api.db.services.user_service import TenantService
from api.db.services.user_canvas_version import UserCanvasVersionService
from api.settings import RetCode
@ -35,10 +39,12 @@ from api.utils import get_uuid
from api.utils.api_utils import get_json_result, server_error_response, validate_request, get_data_error_result
from agent.canvas import Canvas
from peewee import MySQLDatabase, PostgresqlDatabase
from api.db.db_models import APIToken
from api.db.db_models import APIToken, Task
import time
from api.utils.file_utils import filename_type, read_potential_broken_pdf
from rag.flow.pipeline import Pipeline
from rag.nlp import search
from rag.utils.redis_conn import REDIS_CONN
@ -48,14 +54,6 @@ def templates():
return get_json_result(data=[c.to_dict() for c in CanvasTemplateService.query(canvas_category=CanvasCategory.Agent)])
@manager.route('/list', methods=['GET']) # noqa: F821
@login_required
def canvas_list():
return get_json_result(data=sorted([c.to_dict() for c in \
UserCanvasService.query(user_id=current_user.id, canvas_category=CanvasCategory.Agent)], key=lambda x: x["update_time"]*-1)
)
@manager.route('/rm', methods=['POST']) # noqa: F821
@validate_request("canvas_ids")
@login_required
@ -77,9 +75,10 @@ def save():
if not isinstance(req["dsl"], str):
req["dsl"] = json.dumps(req["dsl"], ensure_ascii=False)
req["dsl"] = json.loads(req["dsl"])
cate = req.get("canvas_category", CanvasCategory.Agent)
if "id" not in req:
req["user_id"] = current_user.id
if UserCanvasService.query(user_id=current_user.id, title=req["title"].strip(), canvas_category=CanvasCategory.Agent):
if UserCanvasService.query(user_id=current_user.id, title=req["title"].strip(), canvas_category=cate):
return get_data_error_result(message=f"{req['title'].strip()} already exists.")
req["id"] = get_uuid()
if not UserCanvasService.save(**req):
@ -148,6 +147,14 @@ def run():
if not isinstance(cvs.dsl, str):
cvs.dsl = json.dumps(cvs.dsl, ensure_ascii=False)
if cvs.canvas_category == CanvasCategory.DataFlow:
task_id = get_uuid()
Pipeline(cvs.dsl, tenant_id=current_user.id, doc_id=CANVAS_DEBUG_DOC_ID, task_id=task_id, flow_id=req["id"])
ok, error_message = queue_dataflow(tenant_id=user_id, flow_id=req["id"], task_id=task_id, file=files[0], priority=0)
if not ok:
return get_data_error_result(message=error_message)
return get_json_result(data={"message_id": task_id})
try:
canvas = Canvas(cvs.dsl, current_user.id, req["id"])
except Exception as e:
@ -173,6 +180,44 @@ def run():
return resp
@manager.route('/rerun', methods=['POST']) # noqa: F821
@validate_request("id", "dsl", "component_id")
@login_required
def rerun():
req = request.json
doc = PipelineOperationLogService.get_documents_info(req["id"])
if not doc:
return get_data_error_result(message="Document not found.")
doc = doc[0]
if 0 < doc["progress"] < 1:
return get_data_error_result(message=f"`{doc['name']}` is processing...")
if settings.docStoreConn.indexExist(search.index_name(current_user.id), doc["kb_id"]):
settings.docStoreConn.delete({"doc_id": doc["id"]}, search.index_name(current_user.id), doc["kb_id"])
doc["progress_msg"] = ""
doc["chunk_num"] = 0
doc["token_num"] = 0
DocumentService.clear_chunk_num_when_rerun(doc["id"])
DocumentService.update_by_id(id, doc)
TaskService.filter_delete([Task.doc_id == id])
dsl = req["dsl"]
dsl["path"] = [req["component_id"]]
PipelineOperationLogService.update_by_id(req["id"], {"dsl": dsl})
queue_dataflow(tenant_id=current_user.id, flow_id=req["id"], task_id=get_uuid(), doc_id=doc["id"], priority=0, rerun=True)
return get_json_result(data=True)
@manager.route('/cancel/<task_id>', methods=['PUT']) # noqa: F821
@login_required
def cancel(task_id):
try:
REDIS_CONN.set(f"{task_id}-cancel", "x")
except Exception as e:
logging.exception(e)
return get_json_result(data=True)
@manager.route('/reset', methods=['POST']) # noqa: F821
@validate_request("id")
@login_required
@ -399,22 +444,32 @@ def getversion( version_id):
return get_json_result(data=f"Error getting history file: {e}")
@manager.route('/listteam', methods=['GET']) # noqa: F821
@manager.route('/list', methods=['GET']) # noqa: F821
@login_required
def list_canvas():
keywords = request.args.get("keywords", "")
page_number = int(request.args.get("page", 1))
items_per_page = int(request.args.get("page_size", 150))
page_number = int(request.args.get("page", 0))
items_per_page = int(request.args.get("page_size", 0))
orderby = request.args.get("orderby", "create_time")
desc = request.args.get("desc", True)
try:
canvas_category = request.args.get("canvas_category")
if request.args.get("desc", "true").lower() == "false":
desc = False
else:
desc = True
owner_ids = [id for id in request.args.get("owner_ids", "").strip().split(",") if id]
if not owner_ids:
tenants = TenantService.get_joined_tenants_by_user_id(current_user.id)
tenants = [m["tenant_id"] for m in tenants]
tenants.append(current_user.id)
canvas, total = UserCanvasService.get_by_tenant_ids(
[m["tenant_id"] for m in tenants], current_user.id, page_number,
items_per_page, orderby, desc, keywords, canvas_category=CanvasCategory.Agent)
return get_json_result(data={"canvas": canvas, "total": total})
except Exception as e:
return server_error_response(e)
tenants, current_user.id, page_number,
items_per_page, orderby, desc, keywords, canvas_category)
else:
tenants = owner_ids
canvas, total = UserCanvasService.get_by_tenant_ids(
tenants, current_user.id, 0,
0, orderby, desc, keywords, canvas_category)
return get_json_result(data={"canvas": canvas, "total": total})
@manager.route('/setting', methods=['POST']) # noqa: F821
@ -499,3 +554,11 @@ def prompts():
#"context_ranking": RANK_MEMORY,
"citation_guidelines": CITATION_PROMPT_TEMPLATE
})
@manager.route('/download', methods=['GET']) # noqa: F821
def download():
id = request.args.get("id")
created_by = request.args.get("created_by")
blob = FileService.get_blob(created_by, id)
return flask.make_response(blob)