mirror of
https://github.com/infiniflow/ragflow.git
synced 2025-12-08 20:42:30 +08:00
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
@ -17,41 +17,92 @@ import datetime
|
||||
import json
|
||||
import logging
|
||||
import random
|
||||
import time
|
||||
|
||||
from timeit import default_timer as timer
|
||||
import trio
|
||||
|
||||
from agent.canvas import Graph
|
||||
from api.db.services.document_service import DocumentService
|
||||
from api.db.services.task_service import has_canceled, TaskService, CANVAS_DEBUG_DOC_ID
|
||||
from rag.utils.redis_conn import REDIS_CONN
|
||||
|
||||
|
||||
class Pipeline(Graph):
|
||||
def __init__(self, dsl: str, tenant_id=None, doc_id=None, task_id=None, flow_id=None):
|
||||
def __init__(self, dsl: str|dict, tenant_id=None, doc_id=None, task_id=None, flow_id=None):
|
||||
if isinstance(dsl, dict):
|
||||
dsl = json.dumps(dsl, ensure_ascii=False)
|
||||
super().__init__(dsl, tenant_id, task_id)
|
||||
if doc_id == CANVAS_DEBUG_DOC_ID:
|
||||
doc_id = None
|
||||
self._doc_id = doc_id
|
||||
self._flow_id = flow_id
|
||||
self._kb_id = None
|
||||
if doc_id:
|
||||
if self._doc_id:
|
||||
self._kb_id = DocumentService.get_knowledgebase_id(doc_id)
|
||||
assert self._kb_id, f"Can't find KB of this document: {doc_id}"
|
||||
if not self._kb_id:
|
||||
self._doc_id = None
|
||||
|
||||
def callback(self, component_name: str, progress: float | int | None = None, message: str = "") -> None:
|
||||
from rag.svr.task_executor import TaskCanceledException
|
||||
log_key = f"{self._flow_id}-{self.task_id}-logs"
|
||||
timestamp = timer()
|
||||
if has_canceled(self.task_id):
|
||||
progress = -1
|
||||
message += "[CANCEL]"
|
||||
try:
|
||||
bin = REDIS_CONN.get(log_key)
|
||||
obj = json.loads(bin.encode("utf-8"))
|
||||
if obj:
|
||||
if obj[-1]["component_name"] == component_name:
|
||||
obj[-1]["trace"].append({"progress": progress, "message": message, "datetime": datetime.datetime.now().strftime("%H:%M:%S")})
|
||||
if obj[-1]["component_id"] == component_name:
|
||||
obj[-1]["trace"].append(
|
||||
{
|
||||
"progress": progress,
|
||||
"message": message,
|
||||
"datetime": datetime.datetime.now().strftime("%H:%M:%S"),
|
||||
"timestamp": timestamp,
|
||||
"elapsed_time": timestamp - obj[-1]["trace"][-1]["timestamp"],
|
||||
}
|
||||
)
|
||||
else:
|
||||
obj.append({"component_name": component_name, "trace": [{"progress": progress, "message": message, "datetime": datetime.datetime.now().strftime("%H:%M:%S")}]})
|
||||
obj.append(
|
||||
{
|
||||
"component_id": component_name,
|
||||
"trace": [{"progress": progress, "message": message, "datetime": datetime.datetime.now().strftime("%H:%M:%S"), "timestamp": timestamp, "elapsed_time": 0}],
|
||||
}
|
||||
)
|
||||
else:
|
||||
obj = [{"component_name": component_name, "trace": [{"progress": progress, "message": message, "datetime": datetime.datetime.now().strftime("%H:%M:%S")}]}]
|
||||
REDIS_CONN.set_obj(log_key, obj, 60 * 10)
|
||||
obj = [
|
||||
{
|
||||
"component_id": component_name,
|
||||
"trace": [{"progress": progress, "message": message, "datetime": datetime.datetime.now().strftime("%H:%M:%S"), "timestamp": timestamp, "elapsed_time": 0}],
|
||||
}
|
||||
]
|
||||
if component_name != "END" and self._doc_id and self.task_id:
|
||||
percentage = 1.0 / len(self.components.items())
|
||||
finished = 0.0
|
||||
for o in obj:
|
||||
for t in o["trace"]:
|
||||
if t["progress"] < 0:
|
||||
finished = -1
|
||||
break
|
||||
if finished < 0:
|
||||
break
|
||||
finished += o["trace"][-1]["progress"] * percentage
|
||||
|
||||
msg = ""
|
||||
if len(obj[-1]["trace"]) == 1:
|
||||
msg += f"\n-------------------------------------\n[{self.get_component_name(o['component_id'])}]:\n"
|
||||
t = obj[-1]["trace"][-1]
|
||||
msg += "%s: %s\n" % (t["datetime"], t["message"])
|
||||
TaskService.update_progress(self.task_id, {"progress": finished, "progress_msg": msg})
|
||||
elif component_name == "END" and not self._doc_id:
|
||||
obj[-1]["trace"][-1]["dsl"] = json.loads(str(self))
|
||||
REDIS_CONN.set_obj(log_key, obj, 60 * 30)
|
||||
|
||||
except Exception as e:
|
||||
logging.exception(e)
|
||||
|
||||
if has_canceled(self.task_id):
|
||||
raise TaskCanceledException(message)
|
||||
|
||||
def fetch_logs(self):
|
||||
log_key = f"{self._flow_id}-{self.task_id}-logs"
|
||||
try:
|
||||
@ -62,34 +113,32 @@ class Pipeline(Graph):
|
||||
logging.exception(e)
|
||||
return []
|
||||
|
||||
def reset(self):
|
||||
super().reset()
|
||||
|
||||
async def run(self, **kwargs):
|
||||
log_key = f"{self._flow_id}-{self.task_id}-logs"
|
||||
try:
|
||||
REDIS_CONN.set_obj(log_key, [], 60 * 10)
|
||||
except Exception as e:
|
||||
logging.exception(e)
|
||||
|
||||
async def run(self, **kwargs):
|
||||
st = time.perf_counter()
|
||||
self.error = ""
|
||||
if not self.path:
|
||||
self.path.append("File")
|
||||
|
||||
if self._doc_id:
|
||||
DocumentService.update_by_id(
|
||||
self._doc_id, {"progress": random.randint(0, 5) / 100.0, "progress_msg": "Start the pipeline...", "process_begin_at": datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")}
|
||||
)
|
||||
|
||||
self.error = ""
|
||||
idx = len(self.path) - 1
|
||||
if idx == 0:
|
||||
cpn_obj = self.get_component_obj(self.path[0])
|
||||
await cpn_obj.invoke(**kwargs)
|
||||
if cpn_obj.error():
|
||||
self.error = "[ERROR]" + cpn_obj.error()
|
||||
else:
|
||||
idx += 1
|
||||
self.path.extend(cpn_obj.get_downstream())
|
||||
self.callback(cpn_obj.component_name, -1, self.error)
|
||||
|
||||
if self._doc_id:
|
||||
TaskService.update_progress(self.task_id, {
|
||||
"progress": random.randint(0, 5) / 100.0,
|
||||
"progress_msg": "Start the pipeline...",
|
||||
"begin_at": datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")})
|
||||
|
||||
idx = len(self.path) - 1
|
||||
cpn_obj = self.get_component_obj(self.path[idx])
|
||||
idx += 1
|
||||
self.path.extend(cpn_obj.get_downstream())
|
||||
|
||||
while idx < len(self.path) and not self.error:
|
||||
last_cpn = self.get_component_obj(self.path[idx - 1])
|
||||
@ -98,15 +147,28 @@ class Pipeline(Graph):
|
||||
async def invoke():
|
||||
nonlocal last_cpn, cpn_obj
|
||||
await cpn_obj.invoke(**last_cpn.output())
|
||||
#if inspect.iscoroutinefunction(cpn_obj.invoke):
|
||||
# await cpn_obj.invoke(**last_cpn.output())
|
||||
#else:
|
||||
# cpn_obj.invoke(**last_cpn.output())
|
||||
|
||||
async with trio.open_nursery() as nursery:
|
||||
nursery.start_soon(invoke)
|
||||
|
||||
if cpn_obj.error():
|
||||
self.error = "[ERROR]" + cpn_obj.error()
|
||||
self.callback(cpn_obj.component_name, -1, self.error)
|
||||
self.callback(cpn_obj._id, -1, self.error)
|
||||
break
|
||||
idx += 1
|
||||
self.path.extend(cpn_obj.get_downstream())
|
||||
|
||||
if self._doc_id:
|
||||
DocumentService.update_by_id(self._doc_id, {"progress": 1 if not self.error else -1, "progress_msg": "Pipeline finished...\n" + self.error, "process_duration": time.perf_counter() - st})
|
||||
self.callback("END", 1 if not self.error else -1, json.dumps(self.get_component_obj(self.path[-1]).output(), ensure_ascii=False))
|
||||
|
||||
if not self.error:
|
||||
return self.get_component_obj(self.path[-1]).output()
|
||||
|
||||
TaskService.update_progress(self.task_id, {
|
||||
"progress": -1,
|
||||
"progress_msg": f"[ERROR]: {self.error}"})
|
||||
|
||||
return {}
|
||||
|
||||
Reference in New Issue
Block a user