fix: Added dataset generation logging functionality #9869 (#10180)

### What problem does this PR solve?

fix: Added dataset generation logging functionality #9869

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

api/apps/canvas_app.py

@@ -144,11 +144,10 @@ def run():
 
     if cvs.canvas_category == CanvasCategory.DataFlow:
         task_id = get_uuid()
-        flow_id = get_uuid()
+        ok, error_message = queue_dataflow(tenant_id=user_id, flow_id=req["id"], task_id=task_id, file=files[0], priority=0)
-        ok, error_message = queue_dataflow(dsl=cvs.dsl, tenant_id=user_id, file=files[0], task_id=task_id, flow_id=flow_id, priority=0)
         if not ok:
-            return server_error_response(error_message)
+            return get_data_error_result(message=error_message)
-        return get_json_result(data={"task_id": task_id, "message_id": flow_id})
+        return get_json_result(data={"message_id": task_id})
 
     try:
         canvas = Canvas(cvs.dsl, current_user.id, req["id"])

api/db/services/file_service.py

@@ -496,7 +496,7 @@ class FileService(CommonService):
             return ParserType.AUDIO.value
         if re.search(r"\.(ppt|pptx|pages)$", filename):
             return ParserType.PRESENTATION.value
-        if re.search(r"\.(eml)$", filename):
+        if re.search(r"\.(msg|eml)$", filename):
             return ParserType.EMAIL.value
         return default
 

api/db/services/task_service.py

@@ -472,14 +472,10 @@ def has_canceled(task_id):
     return False
 
 
-def queue_dataflow(dsl:str, tenant_id:str, task_id:str, flow_id:str=None, doc_id:str=None, file:dict=None, priority: int=0, callback=None) -> tuple[bool, str]:
+def queue_dataflow(tenant_id:str, flow_id:str, task_id:str, doc_id:str="x", file:dict=None, priority: int=0) -> tuple[bool, str]:
-    """
-    Returns a tuple (success: bool, error_message: str).
-    """
-    _ = callback
 
     task = dict(
-        id=get_uuid() if not task_id else task_id,
+        id=task_id,
         doc_id=doc_id,
         from_page=0,
         to_page=100000000,
@@ -490,15 +486,10 @@ def queue_dataflow(dsl:str, tenant_id:str, task_id:str, flow_id:str=None, doc_id
     TaskService.model.delete().where(TaskService.model.id == task["id"]).execute()
     bulk_insert_into_db(model=Task, data_source=[task], replace_on_conflict=True)
 
-    kb_id = DocumentService.get_knowledgebase_id(doc_id)
+    task["kb_id"] = DocumentService.get_knowledgebase_id(doc_id)
-    if not kb_id:
-        return False, f"Can't find KB of this document: {doc_id}"
-
-    task["kb_id"] = kb_id
     task["tenant_id"] = tenant_id
     task["task_type"] = "dataflow"
-    task["dsl"] = dsl
+    task["dataflow_id"] = flow_id
-    task["dataflow_id"] = get_uuid() if not flow_id else flow_id
     task["file"] = file
 
     if not REDIS_CONN.queue_product(

api/utils/file_utils.py

@@ -155,7 +155,7 @@ def filename_type(filename):
     if re.match(r".*\.pdf$", filename):
         return FileType.PDF.value
 
-    if re.match(r".*\.(eml|doc|docx|ppt|pptx|yml|xml|htm|json|jsonl|ldjson|csv|txt|ini|xls|xlsx|wps|rtf|hlp|pages|numbers|key|md|py|js|java|c|cpp|h|php|go|ts|sh|cs|kt|html|sql)$", filename):
+    if re.match(r".*\.(msg|eml|doc|docx|ppt|pptx|yml|xml|htm|json|jsonl|ldjson|csv|txt|ini|xls|xlsx|wps|rtf|hlp|pages|numbers|key|md|py|js|java|c|cpp|h|php|go|ts|sh|cs|kt|html|sql)$", filename):
         return FileType.DOC.value
 
     if re.match(r".*\.(wav|flac|ape|alac|wavpack|wv|mp3|aac|ogg|vorbis|opus)$", filename):

pyproject.toml

@@ -34,6 +34,7 @@ dependencies = [
     "elastic-transport==8.12.0",
     "elasticsearch==8.12.1",
     "elasticsearch-dsl==8.12.0",
+    "extract-msg>=0.39.0",
     "filelock==3.15.4",
     "flask==3.0.3",
     "flask-cors==5.0.0",

rag/app/email.py

@@ -78,7 +78,7 @@ def chunk(
     _add_content(msg, msg.get_content_type())
 
     sections = TxtParser.parser_txt("\n".join(text_txt)) + [
-        (line, "") for line in HtmlParser.parser_txt("\n".join(html_txt)) if line
+        (line, "") for line in HtmlParser.parser_txt("\n".join(html_txt), chunk_token_num=parser_config["chunk_token_num"]) if line
     ]
 
     st = timer()

rag/flow/base.py

@@ -35,9 +35,9 @@ class ProcessBase(ComponentBase):
     def __init__(self, pipeline, id, param: ProcessParamBase):
         super().__init__(pipeline, id, param)
         if hasattr(self._canvas, "callback"):
-            self.callback = partial(self._canvas.callback, self.component_name)
+            self.callback = partial(self._canvas.callback, id)
         else:
-            self.callback = partial(lambda *args, **kwargs: None, self.component_name)
+            self.callback = partial(lambda *args, **kwargs: None, id)
 
     async def invoke(self, **kwargs) -> dict[str, Any]:
         self.set_output("_created_time", time.perf_counter())

rag/flow/parser/parser.py

@@ -13,7 +13,9 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 import io
+import json
 import logging
+import os
 import random
 from functools import partial
 
@@ -57,7 +59,10 @@ class ParserParam(ProcessParamBase):
             "image": [
                 "text"
             ],
-            "email": [],
+            "email": [
+                "text",
+                "json"
+            ],
             "text": [
                 "text",
                 "json"
@@ -71,7 +76,6 @@ class ParserParam(ProcessParamBase):
         self.setups = {
             "pdf": {
                 "parse_method": "deepdoc",  # deepdoc/plain_text/vlm
-                "llm_id": "",
                 "lang": "Chinese",
                 "suffix": [
                     "pdf",
@@ -93,8 +97,8 @@ class ParserParam(ProcessParamBase):
                 ],
                 "output_format": "json",
             },
-            "markdown": {
+            "text&markdown": {
-                "suffix": ["md", "markdown", "mdx"],
+                "suffix": ["md", "markdown", "mdx", "txt"],
                 "output_format": "json",
             },
             "slides": {
@@ -112,7 +116,11 @@ class ParserParam(ProcessParamBase):
                 "output_format": "json",
             },
             "email": {
-                "fields": []
+                "suffix": [
+                  "eml", "msg"
+                ],
+                "fields": ["from", "to", "cc", "bcc", "date", "subject", "body", "attachments", "metadata"],
+                "output_format": "json",
             },
             "text": {
                 "suffix": [
@@ -147,13 +155,10 @@ class ParserParam(ProcessParamBase):
         pdf_config = self.setups.get("pdf", {})
         if pdf_config:
             pdf_parse_method = pdf_config.get("parse_method", "")
-            self.check_valid_value(pdf_parse_method.lower(), "Parse method abnormal.", ["deepdoc", "plain_text", "vlm"])
+            self.check_empty(pdf_parse_method, "Parse method abnormal.")
 
-            if pdf_parse_method not in ["deepdoc", "plain_text"]:
+            if pdf_parse_method.lower() not in ["deepdoc", "plain_text"]:
-                self.check_empty(pdf_config.get("llm_id"), "VLM")
+                self.check_empty(pdf_config.get("lang", ""), "Language")
-
-            pdf_language = pdf_config.get("lang", "")
-            self.check_empty(pdf_language, "Language")
 
             pdf_output_format = pdf_config.get("output_format", "")
             self.check_valid_value(pdf_output_format, "PDF output format abnormal.", self.allowed_output_format["pdf"])
@@ -194,6 +199,11 @@ class ParserParam(ProcessParamBase):
             audio_language = audio_config.get("lang", "")
             self.check_empty(audio_language, "Language")
 
+        email_config = self.setups.get("email", "")
+        if email_config:
+            email_output_format = email_config.get("output_format", "")
+            self.check_valid_value(email_output_format, "Email output format abnormal.", self.allowed_output_format["email"])
+
     def get_input_form(self) -> dict[str, dict]:
         return {}
 
@@ -212,8 +222,7 @@ class Parser(ProcessBase):
             lines, _ = PlainParser()(blob)
             bboxes = [{"text": t} for t, _ in lines]
         else:
-            assert conf.get("llm_id")
+            vision_model = LLMBundle(self._canvas._tenant_id, LLMType.IMAGE2TEXT, llm_name=conf.get("parse_method"), lang=self._param.setups["pdf"].get("lang"))
-            vision_model = LLMBundle(self._canvas._tenant_id, LLMType.IMAGE2TEXT, llm_name=conf.get("llm_id"), lang=self._param.setups["pdf"].get("lang"))
             lines, _ = VisionParser(vision_model=vision_model)(blob, callback=self.callback)
             bboxes = []
             for t, poss in lines:
@@ -222,6 +231,7 @@ class Parser(ProcessBase):
 
         if conf.get("output_format") == "json":
             self.set_output("json", bboxes)
+
         if conf.get("output_format") == "markdown":
             mkdn = ""
             for b in bboxes:
@@ -285,7 +295,6 @@ class Parser(ProcessBase):
 
     def _markdown(self, name, blob):
         from functools import reduce
-
         from rag.app.naive import Markdown as naive_markdown_parser
         from rag.nlp import concat_img
 
@@ -316,22 +325,6 @@ class Parser(ProcessBase):
         else:
             self.set_output("text", "\n".join([section_text for section_text, _ in sections]))
 
-    def _text(self, name, blob):
-        from deepdoc.parser.utils import get_text
-
-        self.callback(random.randint(1, 5) / 100.0, "Start to work on a text.")
-        conf = self._param.setups["text"]
-        self.set_output("output_format", conf["output_format"])
-
-        # parse binary to text
-        text_content = get_text(name, binary=blob)
-
-        if conf.get("output_format") == "json":
-            result = [{"text": text_content}]
-            self.set_output("json", result)
-        else:
-            result = text_content
-            self.set_output("text", result)
 
     def _image(self, from_upstream: ParserFromUpstream):
         from deepdoc.vision import OCR
@@ -353,7 +346,7 @@ class Parser(ProcessBase):
 
         else:
             # use VLM to describe the picture
-            cv_model = LLMBundle(self._canvas.get_tenant_id(), LLMType.IMAGE2TEXT, llm_name=conf["llm_id"], lang=lang)
+            cv_model = LLMBundle(self._canvas.get_tenant_id(), LLMType.IMAGE2TEXT, llm_name=conf["llm_id"],lang=lang)
             img_binary = io.BytesIO()
             img.save(img_binary, format="JPEG")
             img_binary.seek(0)
@@ -384,16 +377,134 @@ class Parser(ProcessBase):
 
             self.set_output("text", txt)
 
+    def _email(self, from_upstream: ParserFromUpstream):
+        self.callback(random.randint(1, 5) / 100.0, "Start to work on an email.")
+
+        blob = from_upstream.blob
+        name = from_upstream.name
+
+        email_content = {}
+        conf = self._param.setups["email"]
+        target_fields = conf["fields"]
+
+        _, ext = os.path.splitext(name)
+        if ext == ".eml":
+            # handle eml file
+            from email import policy
+            from email.parser import BytesParser
+
+            msg = BytesParser(policy=policy.default).parse(io.BytesIO(blob))
+            email_content['metadata'] = {}
+            # handle header info
+            for header, value in msg.items():
+                # get fields like from, to, cc, bcc, date, subject
+                if header.lower() in target_fields:
+                    email_content[header.lower()] = value
+                # get metadata
+                elif header.lower() not in ["from", "to", "cc", "bcc", "date", "subject"]:
+                    email_content["metadata"][header.lower()] = value
+            # get body
+            if "body" in target_fields:
+                body_text, body_html = [], []
+                def _add_content(m, content_type):
+                    if content_type == "text/plain":
+                        body_text.append(
+                            m.get_payload(decode=True).decode(m.get_content_charset())
+                        )
+                    elif content_type == "text/html":
+                        body_html.append(
+                            m.get_payload(decode=True).decode(m.get_content_charset())
+                        )
+                    elif "multipart" in content_type:
+                        if m.is_multipart():
+                            for part in m.iter_parts():
+                                _add_content(part, part.get_content_type())
+
+                _add_content(msg, msg.get_content_type())
+
+                email_content["text"] = body_text
+                email_content["text_html"] = body_html
+            # get attachment
+            if "attachments" in target_fields:
+                attachments = []
+                for part in msg.iter_attachments():
+                    content_disposition = part.get("Content-Disposition")
+                    if content_disposition:
+                        dispositions = content_disposition.strip().split(";")
+                        if dispositions[0].lower() == "attachment":
+                            filename = part.get_filename()
+                            payload = part.get_payload(decode=True)
+                            attachments.append({
+                                "filename": filename,
+                                "payload": payload,
+                            })
+                email_content["attachments"] = attachments
+        else:
+            # handle msg file
+            import extract_msg
+            print("handle a msg file.")
+            msg = extract_msg.Message(blob)
+            # handle header info
+            basic_content = {
+                "from": msg.sender,
+                "to": msg.to,
+                "cc": msg.cc,
+                "bcc": msg.bcc,
+                "date": msg.date,
+                "subject": msg.subject,
+            }
+            email_content.update({k: v for k, v in basic_content.items() if k in target_fields})
+            # get metadata
+            email_content['metadata'] = {
+                'message_id': msg.messageId,
+                'in_reply_to': msg.inReplyTo,
+            }
+            # get body
+            if "body" in target_fields:
+                email_content["text"] = msg.body  # usually empty. try text_html instead
+                email_content["text_html"] = msg.htmlBody
+            # get attachments
+            if "attachments" in target_fields:
+                attachments = []
+                for t in msg.attachments:
+                    attachments.append({
+                        "filename": t.name,
+                        "payload": t.data  # binary
+                    })
+                email_content["attachments"] = attachments
+
+        if conf["output_format"] == "json":
+            self.set_output("json", [email_content])
+        else:
+            content_txt = ''
+            for k, v in email_content.items():
+                if isinstance(v, str):
+                    # basic info
+                    content_txt += f'{k}:{v}' + "\n"
+                elif isinstance(v, dict):
+                    # metadata
+                    content_txt += f'{k}:{json.dumps(v)}' + "\n"
+                elif isinstance(v, list):
+                    # attachments or others
+                    for fb in v:
+                        if isinstance(fb, dict):
+                            # attachments
+                            content_txt += f'{fb["filename"]}:{fb["payload"]}' + "\n"
+                        else:
+                            # str, usually plain text
+                            content_txt += fb
+            self.set_output("text", content_txt)
+
     async def _invoke(self, **kwargs):
         function_map = {
             "pdf": self._pdf,
-            "markdown": self._markdown,
+            "text&markdown": self._markdown,
             "spreadsheet": self._spreadsheet,
             "slides": self._slides,
             "word": self._word,
-            "text": self._text,
             "image": self._image,
             "audio": self._audio,
+            "email": self._email,
         }
         try:
             from_upstream = ParserFromUpstream.model_validate(kwargs)

rag/flow/pipeline.py

@@ -18,7 +18,7 @@ import json
 import logging
 import random
 import time
-
+from timeit import default_timer as timer
 import trio
 
 from agent.canvas import Graph
@@ -38,25 +38,26 @@ class Pipeline(Graph):
 
     def callback(self, component_name: str, progress: float | int | None = None, message: str = "") -> None:
         log_key = f"{self._flow_id}-{self.task_id}-logs"
+        timestamp = timer()
         try:
             bin = REDIS_CONN.get(log_key)
             obj = json.loads(bin.encode("utf-8"))
             if obj:
-                if obj[-1]["component_name"] == component_name:
+                if obj[-1]["component_id"] == component_name:
-                    obj[-1]["trace"].append({"progress": progress, "message": message, "datetime": datetime.datetime.now().strftime("%H:%M:%S")})
+                    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")}]}]
+                obj = [{"component_id": component_name, "trace": [{"progress": progress, "message": message, "datetime": datetime.datetime.now().strftime("%H:%M:%S"), "timestamp": timestamp, "elapsed_time": 0}]}]
             REDIS_CONN.set_obj(log_key, obj, 60 * 30)
             if self._doc_id:
                 percentage = 1./len(self.components.items())
                 msg = ""
                 finished = 0.
                 for o in obj:
-                    if o['component_name'] == "END":
+                    if o['component_id'] == "END":
                         continue
-                    msg += f"\n[{o['component_name']}]:\n"
+                    msg += f"\n[{o['component_id']}]:\n"
                     for t in o["trace"]:
                         msg += "%s: %s\n"%(t["datetime"], t["message"])
                         if t["progress"] < 0:

rag/flow/tests/client.py

@@ -30,7 +30,7 @@ def print_logs(pipeline: Pipeline):
     while True:
         time.sleep(5)
         logs = pipeline.fetch_logs()
-        logs_str = json.dumps(logs)
+        logs_str = json.dumps(logs, ensure_ascii=False)
         if logs_str != last_logs:
             print(logs_str)
         last_logs = logs_str

rag/flow/tests/dsl_examples/general_pdf_all.json

@@ -89,6 +89,22 @@
                   "lang": "Chinese",
                   "llm_id": "SenseVoiceSmall",
                   "output_format": "json"
+                },
+                "email": {
+                  "suffix": [
+                    "msg"
+                  ],
+                  "fields": [
+                    "from",
+                    "to",
+                    "cc",
+                    "bcc",
+                    "date",
+                    "subject",
+                    "body",
+                    "attachments"
+                  ],
+                  "output_format": "json"
                 }
               }
           }

rag/svr/task_executor.py

@@ -20,8 +20,7 @@ import random
 import sys
 import threading
 import time
-
+from api.db.services.canvas_service import UserCanvasService
-from api.utils import get_uuid
 from api.utils.api_utils import timeout
 from api.utils.base64_image import image2id
 from api.utils.log_utils import init_root_logger, get_project_base_directory
@@ -29,7 +28,6 @@ from graphrag.general.index import run_graphrag
 from graphrag.utils import get_llm_cache, set_llm_cache, get_tags_from_cache, set_tags_to_cache
 from rag.flow.pipeline import Pipeline
 from rag.prompts import keyword_extraction, question_proposal, content_tagging
-
 import logging
 import os
 from datetime import datetime
@@ -45,10 +43,8 @@ import signal
 import trio
 import exceptiongroup
 import faulthandler
-
 import numpy as np
 from peewee import DoesNotExist
-
 from api.db import LLMType, ParserType
 from api.db.services.document_service import DocumentService
 from api.db.services.llm_service import LLMBundle
@@ -216,7 +212,11 @@ async def collect():
         return None, None
 
     canceled = False
-    task = TaskService.get_task(msg["id"])
+    if msg.get("doc_id", "") == "x":
+        task = msg
+    else:
+        task = TaskService.get_task(msg["id"])
+
     if task:
         canceled = has_canceled(task["id"])
     if not task or canceled:
@@ -229,9 +229,8 @@ async def collect():
     task_type = msg.get("task_type", "")
     task["task_type"] = task_type
     if task_type == "dataflow":
-        task["tenant_id"]=msg.get("tenant_id", "")
+        task["tenant_id"] = msg["tenant_id"]
-        task["dsl"] = msg.get("dsl", "")
+        task["dataflow_id"] = msg["dataflow_id"]
-        task["dataflow_id"] = msg.get("dataflow_id", get_uuid())
         task["kb_id"] = msg.get("kb_id", "")
     return redis_msg, task
 
@@ -460,13 +459,12 @@ async def embedding(docs, mdl, parser_config=None, callback=None):
     return tk_count, vector_size
 
 
-async def run_dataflow(dsl:str, tenant_id:str, doc_id:str, task_id:str, flow_id:str, callback=None):
+async def run_dataflow(task: dict):
-    _ = callback
+    dataflow_id = task["dataflow_id"]
-
+    e, cvs = UserCanvasService.get_by_id(dataflow_id)
-    pipeline = Pipeline(dsl=dsl, tenant_id=tenant_id, doc_id=doc_id, task_id=task_id, flow_id=flow_id)
+    pipeline = Pipeline(cvs.dsl, tenant_id=task["tenant_id"], doc_id=task["doc_id"], task_id=task["id"], flow_id=dataflow_id)
     pipeline.reset()
-
+    await pipeline.run(file=task.get("file"))
-    await pipeline.run()
 
 
 @timeout(3600)
@@ -513,6 +511,12 @@ async def run_raptor(row, chat_mdl, embd_mdl, vector_size, callback=None):
 
 @timeout(60*60*2, 1)
 async def do_handle_task(task):
+    task_type = task.get("task_type", "")
+
+    if task_type == "dataflow" and task.get("doc_id", "") == "x":
+        await run_dataflow(task)
+        return
+
     task_id = task["id"]
     task_from_page = task["from_page"]
     task_to_page = task["to_page"]
@@ -526,6 +530,7 @@ async def do_handle_task(task):
     task_parser_config = task["parser_config"]
     task_start_ts = timer()
 
+
     # prepare the progress callback function
     progress_callback = partial(set_progress, task_id, task_from_page, task_to_page)
 
@@ -554,13 +559,11 @@ async def do_handle_task(task):
 
     init_kb(task, vector_size)
 
-    task_type = task.get("task_type", "")
     if task_type == "dataflow":
-        task_dataflow_dsl = task["dsl"]
+        await run_dataflow(task)
-        task_dataflow_id = task["dataflow_id"]
-        await run_dataflow(dsl=task_dataflow_dsl, tenant_id=task_tenant_id, doc_id=task_doc_id, task_id=task_id, flow_id=task_dataflow_id, callback=None)
         return
-    elif task_type == "raptor":
+
+    if task_type == "raptor":
         # bind LLM for raptor
         chat_model = LLMBundle(task_tenant_id, LLMType.CHAT, llm_name=task_llm_id, lang=task_language)
         # run RAPTOR

uv.lock

@@ -1,5 +1,5 @@
 version = 1
-revision = 1
+revision = 3
 requires-python = ">=3.10, <3.13"
 resolution-markers = [
     "python_full_version >= '3.12' and sys_platform == 'darwin'",
@@ -861,6 +861,15 @@ wheels = [
     { url = "https://mirrors.aliyun.com/pypi/packages/d1/d6/3965ed04c63042e047cb6a3e6ed1a63a35087b6a609aa3a15ed8ac56c221/colorama-0.4.6-py2.py3-none-any.whl", hash = "sha256:4f1d9991f5acc0ca119f9d443620b77f9d6b33703e51011c16baf57afb285fc6" },
 ]
 
+[[package]]
+name = "colorclass"
+version = "2.2.2"
+source = { registry = "https://mirrors.aliyun.com/pypi/simple" }
+sdist = { url = "https://mirrors.aliyun.com/pypi/packages/d7/1a/31ff00a33569a3b59d65bbdc445c73e12f92ad28195b7ace299f68b9af70/colorclass-2.2.2.tar.gz", hash = "sha256:6d4fe287766166a98ca7bc6f6312daf04a0481b1eda43e7173484051c0ab4366" }
+wheels = [
+    { url = "https://mirrors.aliyun.com/pypi/packages/30/b6/daf3e2976932da4ed3579cff7a30a53d22ea9323ee4f0d8e43be60454897/colorclass-2.2.2-py2.py3-none-any.whl", hash = "sha256:6f10c273a0ef7a1150b1120b6095cbdd68e5cf36dfd5d0fc957a2500bbf99a55" },
+]
+
 [[package]]
 name = "coloredlogs"
 version = "15.0.1"
@@ -873,6 +882,15 @@ wheels = [
     { url = "https://mirrors.aliyun.com/pypi/packages/a7/06/3d6badcf13db419e25b07041d9c7b4a2c331d3f4e7134445ec5df57714cd/coloredlogs-15.0.1-py2.py3-none-any.whl", hash = "sha256:612ee75c546f53e92e70049c9dbfcc18c935a2b9a53b66085ce9ef6a6e5c0934" },
 ]
 
+[[package]]
+name = "compressed-rtf"
+version = "1.0.7"
+source = { registry = "https://mirrors.aliyun.com/pypi/simple" }
+sdist = { url = "https://mirrors.aliyun.com/pypi/packages/b7/0c/929a4e8ef9d7143f54d77dadb5f370cc7b98534b1bd6e1124d0abe8efb24/compressed_rtf-1.0.7.tar.gz", hash = "sha256:7c30859334839f3cdc7d10796af5b434bb326b9df7cb5a65e95a8eacb2951b0e" }
+wheels = [
+    { url = "https://mirrors.aliyun.com/pypi/packages/07/1d/62f5bf92e12335eb63517f42671ed78512d48bbc69e02a942dd7b90f03f0/compressed_rtf-1.0.7-py3-none-any.whl", hash = "sha256:b7904921d78c67a0a4b7fff9fb361a00ae2b447b6edca010ce321cd98fa0fcc0" },
+]
+
 [[package]]
 name = "contourpy"
 version = "1.3.2"
@@ -1322,6 +1340,23 @@ wheels = [
     { url = "https://mirrors.aliyun.com/pypi/packages/fc/da/8376678b4a9ae0f9418d93df9c9cf851dced49c95ceb38daac6651e38f7a/duckduckgo_search-7.5.5-py3-none-any.whl", hash = "sha256:c71a0661aa436f215d9a05d653af424affb58825ab3e79f3b788053cbdee9ebc" },
 ]
 
+[[package]]
+name = "easygui"
+version = "0.98.3"
+source = { registry = "https://mirrors.aliyun.com/pypi/simple" }
+sdist = { url = "https://mirrors.aliyun.com/pypi/packages/cc/ad/e35f7a30272d322be09dc98592d2f55d27cc933a7fde8baccbbeb2bd9409/easygui-0.98.3.tar.gz", hash = "sha256:d653ff79ee1f42f63b5a090f2f98ce02335d86ad8963b3ce2661805cafe99a04" }
+wheels = [
+    { url = "https://mirrors.aliyun.com/pypi/packages/8e/a7/b276ff776533b423710a285c8168b52551cb2ab0855443131fdc7fd8c16f/easygui-0.98.3-py2.py3-none-any.whl", hash = "sha256:33498710c68b5376b459cd3fc48d1d1f33822139eb3ed01defbc0528326da3ba" },
+]
+
+[[package]]
+name = "ebcdic"
+version = "1.1.1"
+source = { registry = "https://mirrors.aliyun.com/pypi/simple" }
+wheels = [
+    { url = "https://mirrors.aliyun.com/pypi/packages/0d/2f/633031205333bee5f9f93761af8268746aa75f38754823aabb8570eb245b/ebcdic-1.1.1-py2.py3-none-any.whl", hash = "sha256:33b4cb729bc2d0bf46cc1847b0e5946897cb8d3f53520c5b9aa5fa98d7e735f1" },
+]
+
 [[package]]
 name = "editdistance"
 version = "0.8.1"
@@ -1435,6 +1470,24 @@ wheels = [
     { url = "https://mirrors.aliyun.com/pypi/packages/36/f4/c6e662dade71f56cd2f3735141b265c3c79293c109549c1e6933b0651ffc/exceptiongroup-1.3.0-py3-none-any.whl", hash = "sha256:4d111e6e0c13d0644cad6ddaa7ed0261a0b36971f6d23e7ec9b4b9097da78a10" },
 ]
 
+[[package]]
+name = "extract-msg"
+version = "0.55.0"
+source = { registry = "https://mirrors.aliyun.com/pypi/simple" }
+dependencies = [
+    { name = "beautifulsoup4" },
+    { name = "compressed-rtf" },
+    { name = "ebcdic" },
+    { name = "olefile" },
+    { name = "red-black-tree-mod" },
+    { name = "rtfde" },
+    { name = "tzlocal" },
+]
+sdist = { url = "https://mirrors.aliyun.com/pypi/packages/5e/65/c70afb3b119a44b3ee36b029485dc15326cf3a7c50da19a1ecbbf949c5d1/extract_msg-0.55.0.tar.gz", hash = "sha256:cf08283498c3dfcc7f894dad1579f52e3ced9fb76b865c2355cbe757af8a54e1" }
+wheels = [
+    { url = "https://mirrors.aliyun.com/pypi/packages/53/81/87d5241036046ea17c5c8db228f4c9e04e07e53b627015d4496a99449aaf/extract_msg-0.55.0-py3-none-any.whl", hash = "sha256:baf0cdee9a8d267b70c366bc57ceb03dbfa1e7ab2dca6824169a7fe623f0917c" },
+]
+
 [[package]]
 name = "fake-http-header"
 version = "0.3.5"
@@ -2893,6 +2946,15 @@ wheels = [
     { url = "https://mirrors.aliyun.com/pypi/packages/92/b0/8f08df3f0fa584c4132937690c6dd33e0a116f963ecf2b35567f614e0ca7/langfuse-3.2.1-py3-none-any.whl", hash = "sha256:07a84e8c1eed6ac8e149bdda1431fd866e4aee741b66124316336fb2bc7e6a32" },
 ]
 
+[[package]]
+name = "lark"
+version = "1.1.9"
+source = { registry = "https://mirrors.aliyun.com/pypi/simple" }
+sdist = { url = "https://mirrors.aliyun.com/pypi/packages/2c/e1/804b6196b3fbdd0f8ba785fc62837b034782a891d6f663eea2f30ca23cfa/lark-1.1.9.tar.gz", hash = "sha256:15fa5236490824c2c4aba0e22d2d6d823575dcaf4cdd1848e34b6ad836240fba" }
+wheels = [
+    { url = "https://mirrors.aliyun.com/pypi/packages/e7/9c/eef7c591e6dc952f3636cfe0df712c0f9916cedf317810a3bb53ccb65cdd/lark-1.1.9-py3-none-any.whl", hash = "sha256:a0dd3a87289f8ccbb325901e4222e723e7d745dbfc1803eaf5f3d2ace19cf2db" },
+]
+
 [[package]]
 name = "litellm"
 version = "1.75.5.post1"
@@ -3377,6 +3439,19 @@ wheels = [
     { url = "https://mirrors.aliyun.com/pypi/packages/b1/ef/27dd35a7049c9a4f4211c6cd6a8c9db0a50647546f003a5867827ec45391/msgspec-0.19.0-cp312-cp312-win_amd64.whl", hash = "sha256:067f0de1c33cfa0b6a8206562efdf6be5985b988b53dd244a8e06f993f27c8c0" },
 ]
 
+[[package]]
+name = "msoffcrypto-tool"
+version = "5.4.2"
+source = { registry = "https://mirrors.aliyun.com/pypi/simple" }
+dependencies = [
+    { name = "cryptography" },
+    { name = "olefile" },
+]
+sdist = { url = "https://mirrors.aliyun.com/pypi/packages/d2/b7/0fd6573157e0ec60c0c470e732ab3322fba4d2834fd24e1088d670522a01/msoffcrypto_tool-5.4.2.tar.gz", hash = "sha256:44b545adba0407564a0cc3d6dde6ca36b7c0fdf352b85bca51618fa1d4817370" }
+wheels = [
+    { url = "https://mirrors.aliyun.com/pypi/packages/03/54/7f6d3d9acad083dae8c22d9ab483b657359a1bf56fee1d7af88794677707/msoffcrypto_tool-5.4.2-py3-none-any.whl", hash = "sha256:274fe2181702d1e5a107ec1b68a4c9fea997a44972ae1cc9ae0cb4f6a50fef0e" },
+]
+
 [[package]]
 name = "multidict"
 version = "6.6.3"
@@ -3726,6 +3801,32 @@ wheels = [
     { url = "https://mirrors.aliyun.com/pypi/packages/9e/4e/0d0c945463719429b7bd21dece907ad0bde437a2ff12b9b12fee94722ab0/nvidia_nvtx_cu12-12.6.77-py3-none-manylinux2014_x86_64.whl", hash = "sha256:6574241a3ec5fdc9334353ab8c479fe75841dbe8f4532a8fc97ce63503330ba1" },
 ]
 
+[[package]]
+name = "olefile"
+version = "0.47"
+source = { registry = "https://mirrors.aliyun.com/pypi/simple" }
+sdist = { url = "https://mirrors.aliyun.com/pypi/packages/69/1b/077b508e3e500e1629d366249c3ccb32f95e50258b231705c09e3c7a4366/olefile-0.47.zip", hash = "sha256:599383381a0bf3dfbd932ca0ca6515acd174ed48870cbf7fee123d698c192c1c" }
+wheels = [
+    { url = "https://mirrors.aliyun.com/pypi/packages/17/d3/b64c356a907242d719fc668b71befd73324e47ab46c8ebbbede252c154b2/olefile-0.47-py2.py3-none-any.whl", hash = "sha256:543c7da2a7adadf21214938bb79c83ea12b473a4b6ee4ad4bf854e7715e13d1f" },
+]
+
+[[package]]
+name = "oletools"
+version = "0.60.2"
+source = { registry = "https://mirrors.aliyun.com/pypi/simple" }
+dependencies = [
+    { name = "colorclass" },
+    { name = "easygui" },
+    { name = "msoffcrypto-tool", marker = "(platform_python_implementation != 'PyPy' and sys_platform == 'darwin') or (platform_python_implementation != 'PyPy' and sys_platform == 'win32') or (sys_platform != 'darwin' and sys_platform != 'win32')" },
+    { name = "olefile" },
+    { name = "pcodedmp" },
+    { name = "pyparsing" },
+]
+sdist = { url = "https://mirrors.aliyun.com/pypi/packages/5c/2f/037f40e44706d542b94a2312ccc33ee2701ebfc9a83b46b55263d49ce55a/oletools-0.60.2.zip", hash = "sha256:ad452099f4695ffd8855113f453348200d195ee9fa341a09e197d66ee7e0b2c3" }
+wheels = [
+    { url = "https://mirrors.aliyun.com/pypi/packages/ac/ff/05257b7183279b80ecec6333744de23f48f0faeeba46c93e6d13ce835515/oletools-0.60.2-py2.py3-none-any.whl", hash = "sha256:72ad8bd748fd0c4e7b5b4733af770d11543ebb2bf2697455f99f975fcd50cc96" },
+]
+
 [[package]]
 name = "ollama"
 version = "0.2.1"
@@ -4188,6 +4289,19 @@ wheels = [
     { url = "https://mirrors.aliyun.com/pypi/packages/87/2b/b50d3d08ea0fc419c183a84210571eba005328efa62b6b98bc28e9ead32a/patsy-1.0.1-py2.py3-none-any.whl", hash = "sha256:751fb38f9e97e62312e921a1954b81e1bb2bcda4f5eeabaf94db251ee791509c" },
 ]
 
+[[package]]
+name = "pcodedmp"
+version = "1.2.6"
+source = { registry = "https://mirrors.aliyun.com/pypi/simple" }
+dependencies = [
+    { name = "oletools" },
+    { name = "win-unicode-console", marker = "platform_python_implementation != 'PyPy' and sys_platform == 'win32'" },
+]
+sdist = { url = "https://mirrors.aliyun.com/pypi/packages/3d/20/6d461e29135f474408d0d7f95b2456a9ba245560768ee51b788af10f7429/pcodedmp-1.2.6.tar.gz", hash = "sha256:025f8c809a126f45a082ffa820893e6a8d990d9d7ddb68694b5a9f0a6dbcd955" }
+wheels = [
+    { url = "https://mirrors.aliyun.com/pypi/packages/ba/72/b380fb5c89d89c3afafac8cf02a71a45f4f4a4f35531ca949a34683962d1/pcodedmp-1.2.6-py2.py3-none-any.whl", hash = "sha256:4441f7c0ab4cbda27bd4668db3b14f36261d86e5059ce06c0828602cbe1c4278" },
+]
+
 [[package]]
 name = "pdfminer-six"
 version = "20221105"
@@ -5300,6 +5414,7 @@ dependencies = [
     { name = "elastic-transport" },
     { name = "elasticsearch" },
     { name = "elasticsearch-dsl" },
+    { name = "extract-msg" },
     { name = "filelock" },
     { name = "flasgger" },
     { name = "flask" },
@@ -5452,6 +5567,7 @@ requires-dist = [
     { name = "elastic-transport", specifier = "==8.12.0" },
     { name = "elasticsearch", specifier = "==8.12.1" },
     { name = "elasticsearch-dsl", specifier = "==8.12.0" },
+    { name = "extract-msg", specifier = ">=0.39.0" },
     { name = "fastembed", marker = "(platform_machine != 'x86_64' and extra == 'full') or (sys_platform == 'darwin' and extra == 'full')", specifier = ">=0.3.6,<0.4.0" },
     { name = "fastembed-gpu", marker = "platform_machine == 'x86_64' and sys_platform != 'darwin' and extra == 'full'", specifier = ">=0.3.6,<0.4.0" },
     { name = "filelock", specifier = "==3.15.4" },
@@ -5630,6 +5746,12 @@ wheels = [
     { url = "https://mirrors.aliyun.com/pypi/packages/c2/5a/2f2e7fc026d5e64b5408aa3fbe0296a6407b8481196cae4daacacb3a3ae0/readerwriterlock-1.0.9-py3-none-any.whl", hash = "sha256:8c4b704e60d15991462081a27ef46762fea49b478aa4426644f2146754759ca7" },
 ]
 
+[[package]]
+name = "red-black-tree-mod"
+version = "1.22"
+source = { registry = "https://mirrors.aliyun.com/pypi/simple" }
+sdist = { url = "https://mirrors.aliyun.com/pypi/packages/48/75/bfa342a2ebfc9623b701f1c6995b9906fd6dd2cedf6bce777d09e23303ac/red-black-tree-mod-1.22.tar.gz", hash = "sha256:38e3652903a2bf96379c27c2082ca0b7b905158662dd7ef0c97f4fd93a9aa908" }
+
 [[package]]
 name = "referencing"
 version = "0.36.2"
@@ -5883,6 +6005,19 @@ wheels = [
     { url = "https://mirrors.aliyun.com/pypi/packages/64/8d/0133e4eb4beed9e425d9a98ed6e081a55d195481b7632472be1af08d2f6b/rsa-4.9.1-py3-none-any.whl", hash = "sha256:68635866661c6836b8d39430f97a996acbd61bfa49406748ea243539fe239762" },
 ]
 
+[[package]]
+name = "rtfde"
+version = "0.1.2.1"
+source = { registry = "https://mirrors.aliyun.com/pypi/simple" }
+dependencies = [
+    { name = "lark" },
+    { name = "oletools" },
+]
+sdist = { url = "https://mirrors.aliyun.com/pypi/packages/66/f1/3fafc33cd80cc605509ced36dbbb74c3c365d5859b0b57b6500e4a8ca8a5/rtfde-0.1.2.1.tar.gz", hash = "sha256:ea2653fb163ef1e9fdd1b0849bef88b0ba82537f860d4aca5b2c49f556efaaaa" }
+wheels = [
+    { url = "https://mirrors.aliyun.com/pypi/packages/b6/dd/641e9cf68d4242aaf7ce9653498009d8925080b6664993988bd50468932a/rtfde-0.1.2.1-py3-none-any.whl", hash = "sha256:c44dfa923a435c54cdbdd0e0f5352a4075542af317af061f82f2d4f032271645" },
+]
+
 [[package]]
 name = "ruamel-base"
 version = "1.0.0"
@@ -6890,6 +7025,18 @@ wheels = [
     { url = "https://mirrors.aliyun.com/pypi/packages/5c/23/c7abc0ca0a1526a0774eca151daeb8de62ec457e77262b66b359c3c7679e/tzdata-2025.2-py2.py3-none-any.whl", hash = "sha256:1a403fada01ff9221ca8044d701868fa132215d84beb92242d9acd2147f667a8" },
 ]
 
+[[package]]
+name = "tzlocal"
+version = "5.3.1"
+source = { registry = "https://mirrors.aliyun.com/pypi/simple" }
+dependencies = [
+    { name = "tzdata", marker = "sys_platform == 'win32'" },
+]
+sdist = { url = "https://mirrors.aliyun.com/pypi/packages/8b/2e/c14812d3d4d9cd1773c6be938f89e5735a1f11a9f184ac3639b93cef35d5/tzlocal-5.3.1.tar.gz", hash = "sha256:cceffc7edecefea1f595541dbd6e990cb1ea3d19bf01b2809f362a03dd7921fd" }
+wheels = [
+    { url = "https://mirrors.aliyun.com/pypi/packages/c2/14/e2a54fabd4f08cd7af1c07030603c3356b74da07f7cc056e600436edfa17/tzlocal-5.3.1-py3-none-any.whl", hash = "sha256:eb1a66c3ef5847adf7a834f1be0800581b683b5608e74f86ecbcef8ab91bb85d" },
+]
+
 [[package]]
 name = "umap-learn"
 version = "0.5.6"
@@ -7134,6 +7281,12 @@ dependencies = [
 ]
 sdist = { url = "https://mirrors.aliyun.com/pypi/packages/67/35/25e68fbc99e672127cc6fbb14b8ec1ba3dfef035bf1e4c90f78f24a80b7d/wikipedia-1.4.0.tar.gz", hash = "sha256:db0fad1829fdd441b1852306e9856398204dc0786d2996dd2e0c8bb8e26133b2" }
 
+[[package]]
+name = "win-unicode-console"
+version = "0.5"
+source = { registry = "https://mirrors.aliyun.com/pypi/simple" }
+sdist = { url = "https://mirrors.aliyun.com/pypi/packages/89/8d/7aad74930380c8972ab282304a2ff45f3d4927108bb6693cabcc9fc6a099/win_unicode_console-0.5.zip", hash = "sha256:d4142d4d56d46f449d6f00536a73625a871cba040f0bc1a2e305a04578f07d1e" }
+
 [[package]]
 name = "win32-setctime"
 version = "1.2.0"

web/src/components/data-pipeline-select/index.tsx

@@ -20,17 +20,10 @@ interface IProps {
   isMult?: boolean;
 }
 
-const data = [
-  { id: '1', name: 'data-pipeline-1' },
-  { id: '2', name: 'data-pipeline-2' },
-  { id: '3', name: 'data-pipeline-3' },
-  { id: '4', name: 'data-pipeline-4' },
-];
 export function DataFlowSelect(props: IProps) {
   const { toDataPipeline, formFieldName, isMult = true } = props;
   const { t } = useTranslate('knowledgeConfiguration');
   const form = useFormContext();
-  console.log('data-pipline form', form);
   const toDataPipLine = () => {
     toDataPipeline?.();
   };

web/src/components/parse-configuration/graph-rag-form-fields.tsx

@@ -1,6 +1,10 @@
 import { DocumentParserType } from '@/constants/knowledge';
 import { useTranslate } from '@/hooks/common-hooks';
 import { cn } from '@/lib/utils';
+import {
+  GenerateLogButton,
+  GenerateType,
+} from '@/pages/dataset/dataset/generate-button/generate';
 import { upperFirst } from 'lodash';
 import { useCallback, useMemo } from 'react';
 import { useFormContext, useWatch } from 'react-hook-form';
@@ -47,6 +51,7 @@ export const showGraphRagItems = (parserId: DocumentParserType | undefined) => {
 type GraphRagItemsProps = {
   marginBottom?: boolean;
   className?: string;
+  showGenerateItem?: boolean;
 };
 
 export function UseGraphRagFormField() {
@@ -88,6 +93,7 @@ export function UseGraphRagFormField() {
 // The three types "table", "resume" and "one" do not display this configuration.
 const GraphRagItems = ({
   marginBottom = false,
+  showGenerateItem = false,
   className = 'p-10',
 }: GraphRagItemsProps) => {
   const { t } = useTranslate('knowledgeConfiguration');
@@ -210,6 +216,18 @@ const GraphRagItems = ({
               </FormItem>
             )}
           />
+          {showGenerateItem && (
+            <div className="w-full flex items-center">
+              <div className="text-sm whitespace-nowrap w-1/4">
+                {t('extractKnowledgeGraph')}
+              </div>
+              <GenerateLogButton
+                className="w-3/4 text-text-secondary"
+                status={1}
+                type={GenerateType.KnowledgeGraph}
+              />
+            </div>
+          )}
         </>
       )}
     </FormContainer>

web/src/components/parse-configuration/raptor-form-fields.tsx

@@ -1,6 +1,10 @@
 import { FormLayout } from '@/constants/form';
 import { DocumentParserType } from '@/constants/knowledge';
 import { useTranslate } from '@/hooks/common-hooks';
+import {
+  GenerateLogButton,
+  GenerateType,
+} from '@/pages/dataset/dataset/generate-button/generate';
 import random from 'lodash/random';
 import { Shuffle } from 'lucide-react';
 import { useCallback } from 'react';
@@ -52,7 +56,11 @@ const Prompt = 'parser_config.raptor.prompt';
 
 // The three types "table", "resume" and "one" do not display this configuration.
 
-const RaptorFormFields = () => {
+const RaptorFormFields = ({
+  showGenerateItem = false,
+}: {
+  showGenerateItem?: boolean;
+}) => {
   const form = useFormContext();
   const { t } = useTranslate('knowledgeConfiguration');
   const useRaptor = useWatch({ name: UseRaptorField });
@@ -211,6 +219,18 @@ const RaptorFormFields = () => {
               </FormItem>
             )}
           />
+          {showGenerateItem && (
+            <div className="w-full flex items-center">
+              <div className="text-sm whitespace-nowrap w-1/4">
+                {t('extractRaptor')}
+              </div>
+              <GenerateLogButton
+                className="w-3/4 text-text-secondary"
+                status={1}
+                type={GenerateType.Raptor}
+              />
+            </div>
+          )}
         </div>
       )}
     </>

web/src/components/ui/modal/modal.tsx

@@ -75,21 +75,21 @@ const Modal: ModalType = ({
 
   const handleCancel = useCallback(() => {
     onOpenChange?.(false);
-    onCancel?.();
+    // onCancel?.();
-  }, [onOpenChange, onCancel]);
+  }, [onOpenChange]);
 
   const handleOk = useCallback(() => {
     onOpenChange?.(true);
-    onOk?.();
+    // onOk?.();
-  }, [onOpenChange, onOk]);
+  }, [onOpenChange]);
   const handleChange = (open: boolean) => {
     onOpenChange?.(open);
     console.log('open', open, onOpenChange);
     if (open) {
-      handleOk();
+      onOk?.();
     }
     if (!open) {
-      handleCancel();
+      onCancel?.();
     }
   };
   const footEl = useMemo(() => {

web/src/locales/en.ts

@@ -102,13 +102,15 @@ export default {
       noMoreData: `That's all. Nothing more.`,
     },
     knowledgeDetails: {
+      notGenerated: 'Not generated',
+      generatedOn: 'Generated on',
+      subbarFiles: 'Files',
       generateKnowledgeGraph:
         'This will extract entities and relationships from all your documents in this dataset. The process may take a while to complete.',
       generateRaptor:
         'This will extract entities and relationships from all your documents in this dataset. The process may take a while to complete.',
       generate: 'Generate',
       raptor: 'Raptor',
-      knowledgeGraph: 'Knowledge Graph',
       processingType: 'Processing Type',
       dataPipeline: 'Data Pipeline',
       operations: 'Operations',
@@ -138,12 +140,12 @@ export default {
       testing: 'Retrieval testing',
       files: 'files',
       configuration: 'Configuration',
-      knowledgeGraph: 'Knowledge graph',
+      knowledgeGraph: 'Knowledge Graph',
       name: 'Name',
       namePlaceholder: 'Please input name!',
       doc: 'Docs',
       datasetDescription:
-        '😉 Please wait for your files to finish parsing before starting an AI-powered chat.',
+        'Please wait for your files to finish parsing before starting an AI-powered chat.',
       addFile: 'Add file',
       searchFiles: 'Search your files',
       localFiles: 'Local files',
@@ -261,6 +263,22 @@ export default {
       reRankModelWaring: 'Re-rank model is very time consuming.',
     },
     knowledgeConfiguration: {
+      deleteGenerateModalContent: `
+        <p>Deleting the generated <strong class='text-text-primary'>{{type}}</strong>  results 
+        will remove all derived entities and relationships from this dataset. 
+        Your original files will remain intact.<p>
+        <br/>
+        Do you want to continue?
+      `,
+      extractRaptor: 'Extract Raptor',
+      extractKnowledgeGraph: 'Extract Knowledge Graph',
+      filterPlaceholder: 'please input filter',
+      fileFilterTip: '',
+      fileFilter: 'File Filter',
+      setDefaultTip: '',
+      setDefault: 'Set as Default',
+      eidtLinkDataPipeline: 'Edit Data Pipeline',
+      linkPipelineSetTip: 'Manage data pipeline linkage with this dataset',
       default: 'Default',
       dataPipeline: 'Data Pipeline',
       linkDataPipeline: 'Link Data Pipeline',
@@ -1646,6 +1664,13 @@ This delimiter is used to split the input text into several text pieces echo of
       <p>To keep them, please click Rerun to re-run the current stage.</p> `,
       changeStepModalConfirmText: 'Switch Anyway',
       changeStepModalCancelText: 'Cancel',
+      unlinkPipelineModalTitle: 'Unlink data pipeline',
+      unlinkPipelineModalContent: `
+      <p>Once unlinked, this Dataset will no longer be connected to the current Data Pipeline.</p> 
+      <p>Files that are already being parsed  will continue until completion</p> 
+      <p>Files that are not yet parsed will no longer be processed</p> <br/>
+      <p>Are you sure you want to proceed?</p> `,
+      unlinkPipelineModalConfirmText: 'Unlink',
     },
     dataflow: {
       parser: 'Parser',

web/src/locales/zh.ts

@@ -94,9 +94,11 @@ export default {
       noMoreData: '没有更多数据了',
     },
     knowledgeDetails: {
+      notGenerated: '未生成',
+      generatedOn: '生成于',
+      subbarFiles: '文件列表',
       generate: '生成',
       raptor: 'Raptor',
-      knowledgeGraph: '知识图谱',
       processingType: '处理类型',
       dataPipeline: '数据管道',
       operations: '操作',
@@ -130,7 +132,7 @@ export default {
       name: '名称',
       namePlaceholder: '请输入名称',
       doc: '文档',
-      datasetDescription: '😉 解析成功后才能问答哦。',
+      datasetDescription: '解析成功后才能问答哦。',
       addFile: '新增文件',
       searchFiles: '搜索文件',
       localFiles: '本地文件',
@@ -246,6 +248,22 @@ export default {
       theDocumentBeingParsedCannotBeDeleted: '正在解析的文档不能被删除',
     },
     knowledgeConfiguration: {
+      deleteGenerateModalContent: `
+        <p>删除生成的 <strong class='text-text-primary'>{{type}}</strong> 结果
+          将从此数据集中移除所有派生实体和关系。
+          您的原始文件将保持不变。<p>
+          <br/>
+          是否要继续？
+      `,
+      extractRaptor: '从文档中提取Raptor',
+      extractKnowledgeGraph: '从文档中提取知识图谱',
+      filterPlaceholder: '请输入',
+      fileFilterTip: '',
+      fileFilter: '正则匹配表达式',
+      setDefaultTip: '',
+      setDefault: '设置默认',
+      eidtLinkDataPipeline: '编辑数据流',
+      linkPipelineSetTip: '管理与此数据集的数据管道链接',
       default: '默认',
       dataPipeline: '数据流',
       linkDataPipeline: '关联数据流',
@@ -1556,6 +1574,13 @@ General：实体和关系提取提示来自 GitHub - microsoft/graphrag：基于
       <p>要保留这些更改，请点击“重新运行”以重新运行当前阶段。</p> `,
       changeStepModalConfirmText: '继续切换',
       changeStepModalCancelText: '取消',
+      unlinkPipelineModalTitle: '解绑数据流',
+      unlinkPipelineModalContent: `
+      <p>一旦取消链接，该数据集将不再连接到当前数据管道。</p> 
+      <p>正在解析的文件将继续解析，直到完成。</p> 
+      <p>尚未解析的文件将不再被处理。</p> <br/>
+      <p>你确定要继续吗?</p> `,
+      unlinkPipelineModalConfirmText: '解绑',
     },
     dataflow: {
       parser: '解析器',

web/src/pages/dataset/dataset-overview/index.tsx

@@ -2,7 +2,7 @@ import SvgIcon from '@/components/svg-icon';
 import { useIsDarkTheme } from '@/components/theme-provider';
 import { parseColorToRGBA } from '@/utils/common-util';
 import { CircleQuestionMark } from 'lucide-react';
-import { FC, useMemo, useState } from 'react';
+import { FC, useEffect, useMemo, useState } from 'react';
 import { useTranslation } from 'react-i18next';
 import { LogTabs } from './dataset-common';
 import { DatasetFilter } from './dataset-filter';
@@ -74,25 +74,35 @@ const FileLogsPage: FC = () => {
   const [active, setActive] = useState<(typeof LogTabs)[keyof typeof LogTabs]>(
     LogTabs.FILE_LOGS,
   );
-  const topMockData = {
+  const [topAllData, setTopAllData] = useState({
     totalFiles: {
-      value: 2827,
+      value: 0,
-      precent: 12.5,
+      precent: 0,
     },
     downloads: {
-      value: 28,
+      value: 0,
-      success: 8,
+      success: 0,
-      failed: 2,
+      failed: 0,
     },
     processing: {
-      value: 156,
+      value: 0,
-      success: 8,
+      success: 0,
-      failed: 2,
+      failed: 0,
     },
-  };
+  });
 
   const { data: topData } = useFetchOverviewTital();
   console.log('topData --> ', topData);
+  useEffect(() => {
+    setTopAllData({
+      ...topAllData,
+      processing: {
+        value: topData?.processing || 0,
+        success: topData?.finished || 0,
+        failed: topData?.failed || 0,
+      },
+    });
+  }, [topData, topAllData]);
 
   const mockData = useMemo(() => {
     if (active === LogTabs.FILE_LOGS) {
@@ -161,7 +171,7 @@ const FileLogsPage: FC = () => {
       <div className="grid grid-cols-3 md:grid-cols-3 gap-4 mb-6">
         <StatCard
           title="Total Files"
-          value={topMockData.totalFiles.value}
+          value={topAllData.totalFiles.value}
           icon={
             isDark ? (
               <SvgIcon name="data-flow/total-files-icon" width={40} />
@@ -172,15 +182,15 @@ const FileLogsPage: FC = () => {
         >
           <div>
             <span className="text-accent-primary">
-              {topMockData.totalFiles.precent > 0 ? '+' : ''}
+              {topAllData.totalFiles.precent > 0 ? '+' : ''}
-              {topMockData.totalFiles.precent}%{' '}
+              {topAllData.totalFiles.precent}%{' '}
             </span>
             from last week
           </div>
         </StatCard>
         <StatCard
           title="Downloading"
-          value={topMockData.downloads.value}
+          value={topAllData.downloads.value}
           icon={
             isDark ? (
               <SvgIcon name="data-flow/data-icon" width={40} />
@@ -190,13 +200,13 @@ const FileLogsPage: FC = () => {
           }
         >
           <CardFooterProcess
-            success={topMockData.downloads.success}
+            success={topAllData.downloads.success}
-            failed={topMockData.downloads.failed}
+            failed={topAllData.downloads.failed}
           />
         </StatCard>
         <StatCard
           title="Processing"
-          value={topMockData.processing.value}
+          value={topAllData.processing.value}
           icon={
             isDark ? (
               <SvgIcon name="data-flow/processing-icon" width={40} />
@@ -206,8 +216,8 @@ const FileLogsPage: FC = () => {
           }
         >
           <CardFooterProcess
-            success={topMockData.processing.success}
+            success={topAllData.processing.success}
-            failed={topMockData.processing.failed}
+            failed={topAllData.processing.failed}
           />
         </StatCard>
       </div>

web/src/pages/dataset/dataset-overview/overview-table.tsx

@@ -65,25 +65,25 @@ export const getFileLogsTableColumns = (
 ) => {
   // const { t } = useTranslate('knowledgeDetails');
   const columns: ColumnDef<DocumentLog>[] = [
-    {
+    // {
-      id: 'select',
+    //   id: 'select',
-      header: ({ table }) => (
+    //   header: ({ table }) => (
-        <input
+    //     <input
-          type="checkbox"
+    //       type="checkbox"
-          checked={table.getIsAllRowsSelected()}
+    //       checked={table.getIsAllRowsSelected()}
-          onChange={table.getToggleAllRowsSelectedHandler()}
+    //       onChange={table.getToggleAllRowsSelectedHandler()}
-          className="rounded bg-gray-900 text-blue-500 focus:ring-blue-500"
+    //       className="rounded bg-gray-900 text-blue-500 focus:ring-blue-500"
-        />
+    //     />
-      ),
+    //   ),
-      cell: ({ row }) => (
+    //   cell: ({ row }) => (
-        <input
+    //     <input
-          type="checkbox"
+    //       type="checkbox"
-          checked={row.getIsSelected()}
+    //       checked={row.getIsSelected()}
-          onChange={row.getToggleSelectedHandler()}
+    //       onChange={row.getToggleSelectedHandler()}
-          className="rounded border-gray-600 bg-gray-900 text-blue-500 focus:ring-blue-500"
+    //       className="rounded border-gray-600 bg-gray-900 text-blue-500 focus:ring-blue-500"
-        />
+    //     />
-      ),
+    //   ),
-    },
+    // },
     {
       accessorKey: 'id',
       header: 'ID',
@@ -156,7 +156,7 @@ export const getFileLogsTableColumns = (
       id: 'operations',
       header: t('operations'),
       cell: ({ row }) => (
-        <div className="flex justify-start space-x-2">
+        <div className="flex justify-start space-x-2 opacity-0 group-hover:opacity-100 transition-opacity">
           <Button
             variant="ghost"
             size="sm"
@@ -189,25 +189,25 @@ export const getDatasetLogsTableColumns = (
 ) => {
   // const { t } = useTranslate('knowledgeDetails');
   const columns: ColumnDef<DocumentLog>[] = [
-    {
+    // {
-      id: 'select',
+    // id: 'select',
-      header: ({ table }) => (
+    // header: ({ table }) => (
-        <input
+    //   <input
-          type="checkbox"
+    //     type="checkbox"
-          checked={table.getIsAllRowsSelected()}
+    //     checked={table.getIsAllRowsSelected()}
-          onChange={table.getToggleAllRowsSelectedHandler()}
+    //     onChange={table.getToggleAllRowsSelectedHandler()}
-          className="rounded bg-gray-900 text-blue-500 focus:ring-blue-500"
+    //     className="rounded bg-gray-900 text-blue-500 focus:ring-blue-500"
-        />
+    //   />
-      ),
+    // ),
-      cell: ({ row }) => (
+    // cell: ({ row }) => (
-        <input
+    //   <input
-          type="checkbox"
+    //     type="checkbox"
-          checked={row.getIsSelected()}
+    //     checked={row.getIsSelected()}
-          onChange={row.getToggleSelectedHandler()}
+    //     onChange={row.getToggleSelectedHandler()}
-          className="rounded border-gray-600 bg-gray-900 text-blue-500 focus:ring-blue-500"
+    //     className="rounded border-gray-600 bg-gray-900 text-blue-500 focus:ring-blue-500"
-        />
+    //   />
-      ),
+    // ),
-    },
+    // },
     {
       accessorKey: 'id',
       header: 'ID',
@@ -251,7 +251,7 @@ export const getDatasetLogsTableColumns = (
       id: 'operations',
       header: t('operations'),
       cell: ({ row }) => (
-        <div className="flex justify-start space-x-2">
+        <div className="flex justify-start space-x-2 opacity-0 group-hover:opacity-100 transition-opacity">
           <Button
             variant="ghost"
             size="sm"

web/src/pages/dataset/dataset-setting/components/link-data-pipeline.tsx

@@ -1,21 +1,61 @@
 import { IconFont } from '@/components/icon-font';
 import { RAGFlowAvatar } from '@/components/ragflow-avatar';
 import { Button } from '@/components/ui/button';
+import { Modal } from '@/components/ui/modal/modal';
+import { omit } from 'lodash';
 import { Link, Settings2, Unlink } from 'lucide-react';
 import { useState } from 'react';
 import { useTranslation } from 'react-i18next';
+import { z } from 'zod';
+import { linkPiplineFormSchema } from '../form-schema';
 import LinkDataPipelineModal from './link-data-pipline-modal';
 
 interface DataPipelineItemProps {
+  id: string;
   name: string;
   avatar?: string;
   isDefault?: boolean;
   linked?: boolean;
-  openLinkModalFunc?: (open: boolean) => void;
+  openLinkModalFunc?: (open: boolean, data?: IDataPipelineNodeProps) => void;
 }
 const DataPipelineItem = (props: DataPipelineItemProps) => {
   const { t } = useTranslation();
   const { name, avatar, isDefault, linked, openLinkModalFunc } = props;
+  const openUnlinkModal = () => {
+    Modal.show({
+      visible: true,
+      className: '!w-[560px]',
+      title: t('dataflowParser.unlinkPipelineModalTitle'),
+      children: (
+        <div
+          className="text-sm text-text-secondary"
+          dangerouslySetInnerHTML={{
+            __html: t('dataflowParser.unlinkPipelineModalContent'),
+          }}
+        ></div>
+      ),
+      onVisibleChange: () => {
+        Modal.hide();
+      },
+      footer: (
+        <div className="flex justify-end gap-2">
+          <Button variant={'outline'} onClick={() => Modal.hide()}>
+            {t('dataflowParser.changeStepModalCancelText')}
+          </Button>
+          <Button
+            variant={'secondary'}
+            className="!bg-state-error text-bg-base"
+            onClick={() => {
+              Modal.hide();
+            }}
+          >
+            {t('dataflowParser.unlinkPipelineModalConfirmText')}
+          </Button>
+        </div>
+      ),
+    });
+  };
+
   return (
     <div className="flex items-center justify-between gap-1 px-2 rounded-lg border">
       <div className="flex items-center gap-1">
@@ -28,42 +68,89 @@ const DataPipelineItem = (props: DataPipelineItemProps) => {
         )}
       </div>
       <div className="flex gap-1 items-center">
-        <Button variant={'transparent'} className="border-none">
+        <Button
+          variant={'transparent'}
+          className="border-none"
+          type="button"
+          onClick={() =>
+            openLinkModalFunc?.(true, { ...omit(props, ['openLinkModalFunc']) })
+          }
+        >
           <Settings2 />
         </Button>
         {!isDefault && (
-          <Button
+          <>
-            variant={'transparent'}
+            {linked && (
-            className="border-none"
+              <Button
-            onClick={() => {
+                type="button"
-              openLinkModalFunc?.(true);
+                variant={'transparent'}
-            }}
+                className="border-none"
-          >
+                onClick={() => {
-            {linked ? <Link /> : <Unlink />}
+                  openUnlinkModal();
-          </Button>
+                }}
+              >
+                <Unlink />
+              </Button>
+            )}
+          </>
         )}
       </div>
     </div>
   );
 };
+
+export interface IDataPipelineNodeProps {
+  id: string;
+  name: string;
+  avatar?: string;
+  isDefault?: boolean;
+  linked?: boolean;
+}
 const LinkDataPipeline = () => {
   const { t } = useTranslation();
   const [openLinkModal, setOpenLinkModal] = useState(false);
+  const [currentDataPipeline, setCurrentDataPipeline] =
+    useState<IDataPipelineNodeProps>();
   const testNode = [
     {
+      id: '1',
       name: 'Data Pipeline 1',
       avatar: 'https://avatars.githubusercontent.com/u/10656201?v=4',
       isDefault: true,
       linked: true,
     },
     {
+      id: '2',
       name: 'Data Pipeline 2',
       avatar: 'https://avatars.githubusercontent.com/u/10656201?v=4',
       linked: false,
     },
+    {
+      id: '3',
+      name: 'Data Pipeline 3',
+      avatar: 'https://avatars.githubusercontent.com/u/10656201?v=4',
+      linked: false,
+    },
+    {
+      id: '4',
+      name: 'Data Pipeline 4',
+      avatar: 'https://avatars.githubusercontent.com/u/10656201?v=4',
+      linked: true,
+    },
   ];
-  const openLinkModalFunc = (open: boolean) => {
+  const openLinkModalFunc = (open: boolean, data?: IDataPipelineNodeProps) => {
+    console.log('open', open, data);
     setOpenLinkModal(open);
+    if (data) {
+      setCurrentDataPipeline(data);
+    } else {
+      setCurrentDataPipeline(undefined);
+    }
+  };
+  const handleLinkOrEditSubmit = (
+    data: z.infer<typeof linkPiplineFormSchema>,
+  ) => {
+    console.log('handleLinkOrEditSubmit', data);
   };
   return (
     <div className="flex flex-col gap-2">
@@ -74,9 +161,15 @@ const LinkDataPipeline = () => {
         </div>
         <div className="flex justify-between items-center">
           <div className="text-center text-xs text-text-secondary">
-            Manage data pipeline linkage with this dataset
+            {t('knowledgeConfiguration.linkPipelineSetTip')}
           </div>
-          <Button variant={'transparent'}>
+          <Button
+            type="button"
+            variant={'transparent'}
+            onClick={() => {
+              openLinkModalFunc?.(true);
+            }}
+          >
             <Link />
             <span className="text-xs text-text-primary">
               {t('knowledgeConfiguration.linkDataPipeline')}
@@ -94,10 +187,12 @@ const LinkDataPipeline = () => {
         ))}
       </section>
       <LinkDataPipelineModal
+        data={currentDataPipeline}
         open={openLinkModal}
         setOpen={(open: boolean) => {
           openLinkModalFunc(open);
         }}
+        onSubmit={handleLinkOrEditSubmit}
       />
     </div>
   );

web/src/pages/dataset/dataset-setting/components/link-data-pipline-modal.tsx

@@ -10,32 +10,53 @@ import {
   FormMessage,
 } from '@/components/ui/form';
 import { Modal } from '@/components/ui/modal/modal';
+import { Switch } from '@/components/ui/switch';
 import { useNavigatePage } from '@/hooks/logic-hooks/navigate-hooks';
 import { zodResolver } from '@hookform/resolvers/zod';
 import { t } from 'i18next';
 import { useForm } from 'react-hook-form';
 import { z } from 'zod';
-import { linkPiplineFormSchema } from '../form-schema';
+import { pipelineFormSchema } from '../form-schema';
+import { IDataPipelineNodeProps } from './link-data-pipeline';
 
 const LinkDataPipelineModal = ({
+  data,
   open,
   setOpen,
+  onSubmit,
 }: {
+  data: IDataPipelineNodeProps | undefined;
   open: boolean;
   setOpen: (open: boolean) => void;
+  onSubmit?: (data: any) => void;
 }) => {
-  const form = useForm<z.infer<typeof linkPiplineFormSchema>>({
+  const isEdit = !!data;
-    resolver: zodResolver(linkPiplineFormSchema),
+  const form = useForm<z.infer<typeof pipelineFormSchema>>({
-    defaultValues: { data_flow: ['888'], file_filter: '' },
+    resolver: zodResolver(pipelineFormSchema),
+    defaultValues: {
+      data_flow: [],
+      set_default: false,
+      file_filter: '',
+    },
   });
   //   const [open, setOpen] = useState(false);
   const { navigateToAgents } = useNavigatePage();
   const handleFormSubmit = (values: any) => {
-    console.log(values);
+    console.log(values, data);
+    const param = {
+      ...data,
+      ...values,
+    };
+    onSubmit?.(param);
   };
   return (
     <Modal
-      title={t('knowledgeConfiguration.linkDataPipeline')}
+      className="!w-[560px]"
+      title={
+        !isEdit
+          ? t('knowledgeConfiguration.linkDataPipeline')
+          : t('knowledgeConfiguration.eidtLinkDataPipeline')
+      }
       open={open}
       onOpenChange={setOpen}
       showfooter={false}
@@ -43,10 +64,12 @@ const LinkDataPipelineModal = ({
       <Form {...form}>
         <form onSubmit={form.handleSubmit(handleFormSubmit)}>
           <div className="flex flex-col gap-4 ">
-            <DataFlowSelect
+            {!isEdit && (
-              toDataPipeline={navigateToAgents}
+              <DataFlowSelect
-              formFieldName="data_flow"
+                toDataPipeline={navigateToAgents}
-            />
+                formFieldName="data_flow"
+              />
+            )}
             <FormField
               control={form.control}
               name={'file_filter'}
@@ -65,7 +88,9 @@ const LinkDataPipelineModal = ({
                     <div className="text-muted-foreground">
                       <FormControl>
                         <Input
-                          placeholder={t('dataFlowPlaceholder')}
+                          placeholder={t(
+                            'knowledgeConfiguration.filterPlaceholder',
+                          )}
                           {...field}
                         />
                       </FormControl>
@@ -78,11 +103,56 @@ const LinkDataPipelineModal = ({
                 </FormItem>
               )}
             />
+            {isEdit && (
+              <FormField
+                control={form.control}
+                name={'set_default'}
+                render={({ field }) => (
+                  <FormItem className=" items-center space-y-0 ">
+                    <div className="flex flex-col gap-1">
+                      <div className="flex gap-2 justify-between ">
+                        <FormLabel
+                          tooltip={t('knowledgeConfiguration.setDefaultTip')}
+                          className="text-sm text-text-primary whitespace-wrap "
+                        >
+                          {t('knowledgeConfiguration.setDefault')}
+                        </FormLabel>
+                      </div>
+
+                      <div className="text-muted-foreground">
+                        <FormControl>
+                          <Switch
+                            value={field.value}
+                            onCheckedChange={field.onChange}
+                          />
+                        </FormControl>
+                      </div>
+                    </div>
+                    <div className="flex pt-1">
+                      <div className="w-full"></div>
+                      <FormMessage />
+                    </div>
+                  </FormItem>
+                )}
+              />
+            )}
             <div className="flex justify-end gap-1">
-              <Button type="reset" variant={'outline'} className="btn-primary">
+              <Button
+                type="button"
+                variant={'outline'}
+                className="btn-primary"
+                onClick={() => {
+                  setOpen(false);
+                }}
+              >
                 {t('modal.cancelText')}
               </Button>
-              <Button type="submit" variant={'default'} className="btn-primary">
+              <Button
+                type="button"
+                variant={'default'}
+                className="btn-primary"
+                onClick={form.handleSubmit(handleFormSubmit)}
+              >
                 {t('modal.okText')}
               </Button>
             </div>

web/src/pages/dataset/dataset-setting/form-schema.ts

@@ -72,7 +72,17 @@ export const formSchema = z.object({
   // icon: z.array(z.instanceof(File)),
 });
 
-export const linkPiplineFormSchema = z.object({
+export const pipelineFormSchema = z.object({
-  data_flow: z.array(z.string()),
+  data_flow: z.array(z.string()).optional(),
+  set_default: z.boolean().optional(),
   file_filter: z.string().optional(),
 });
+
+export const linkPiplineFormSchema = pipelineFormSchema.pick({
+  data_flow: true,
+  file_filter: true,
+});
+export const editPiplineFormSchema = pipelineFormSchema.pick({
+  set_default: true,
+  file_filter: true,
+});

web/src/pages/dataset/dataset-setting/index.tsx

@@ -86,9 +86,12 @@ export default function DatasetSettings() {
                 <GeneralForm></GeneralForm>
                 <Divider />
 
-                <GraphRagItems className="border-none p-0"></GraphRagItems>
+                <GraphRagItems
+                  className="border-none p-0"
+                  showGenerateItem={true}
+                ></GraphRagItems>
                 <Divider />
-                <RaptorFormFields></RaptorFormFields>
+                <RaptorFormFields showGenerateItem={true}></RaptorFormFields>
                 <Divider />
                 <LinkDataPipeline />
               </MainContainer>

web/src/pages/dataset/dataset/generate-button/generate.tsx

@@ -6,16 +6,20 @@ import {
   DropdownMenuItem,
   DropdownMenuTrigger,
 } from '@/components/ui/dropdown-menu';
+import { Modal } from '@/components/ui/modal/modal';
+import { cn } from '@/lib/utils';
 import { toFixed } from '@/utils/common-util';
 import { t } from 'i18next';
 import { lowerFirst } from 'lodash';
-import { CirclePause, WandSparkles } from 'lucide-react';
+import { CirclePause, Trash2, WandSparkles } from 'lucide-react';
 import { useState } from 'react';
+import { useTranslation } from 'react-i18next';
 import { generateStatus, useFetchGenerateData } from './hook';
-
+export enum GenerateType {
-const MenuItem: React.FC<{ name: 'KnowledgeGraph' | 'Raptor' }> = ({
+  KnowledgeGraph = 'KnowledgeGraph',
-  name,
+  Raptor = 'Raptor',
-}) => {
+}
+const MenuItem: React.FC<{ name: GenerateType }> = ({ name }) => {
   console.log(name, 'pppp');
   const iconKeyMap = {
     KnowledgeGraph: 'knowledgegraph',
@@ -111,3 +115,102 @@ const Generate: React.FC = () => {
 };
 
 export default Generate;
+
+export type IGenerateLogProps = {
+  id?: string;
+  status: 0 | 1;
+  message?: string;
+  created_at?: string;
+  updated_at?: string;
+  type?: GenerateType;
+  className?: string;
+  onDelete?: () => void;
+};
+export const GenerateLogButton = (props: IGenerateLogProps) => {
+  const { t } = useTranslation();
+  const {
+    id,
+    status,
+    message,
+    created_at,
+    updated_at,
+    type,
+    className,
+    onDelete,
+  } = props;
+  const handleDelete = () => {
+    Modal.show({
+      visible: true,
+      className: '!w-[560px]',
+      title:
+        t('common.delete') +
+        ' ' +
+        (type === GenerateType.KnowledgeGraph
+          ? t('knowledgeDetails.knowledgeGraph')
+          : t('knowledgeDetails.raptor')),
+      children: (
+        <div
+          className="text-sm text-text-secondary"
+          dangerouslySetInnerHTML={{
+            __html: t('knowledgeConfiguration.deleteGenerateModalContent', {
+              type:
+                type === GenerateType.KnowledgeGraph
+                  ? t('knowledgeDetails.knowledgeGraph')
+                  : t('knowledgeDetails.raptor'),
+            }),
+          }}
+        ></div>
+      ),
+      onVisibleChange: () => {
+        Modal.hide();
+      },
+      footer: (
+        <div className="flex justify-end gap-2">
+          <Button
+            type="button"
+            variant={'outline'}
+            onClick={() => Modal.hide()}
+          >
+            {t('dataflowParser.changeStepModalCancelText')}
+          </Button>
+          <Button
+            type="button"
+            variant={'secondary'}
+            className="!bg-state-error text-text-primary"
+            onClick={() => {
+              Modal.hide();
+            }}
+          >
+            {t('common.delete')}
+          </Button>
+        </div>
+      ),
+    });
+  };
+  return (
+    <div
+      className={cn('flex bg-bg-card rounded-md py-1 px-3', props.className)}
+    >
+      <div className="flex items-center justify-between w-full">
+        {status === 1 && (
+          <>
+            <div>
+              {message || t('knowledgeDetails.generatedOn')}
+              {created_at}
+            </div>
+            <Trash2
+              size={14}
+              className="cursor-pointer"
+              onClick={(e) => {
+                console.log('delete');
+                handleDelete();
+                e.stopPropagation();
+              }}
+            />
+          </>
+        )}
+        {status === 0 && <div>{t('knowledgeDetails.notGenerated')}</div>}
+      </div>
+    </div>
+  );
+};

web/src/pages/dataset/dataset/index.tsx

@@ -75,7 +75,7 @@ export default function Dataset() {
           filters={filters}
           leftPanel={
             <div className="items-start">
-              <div className="pb-1">{t('knowledgeDetails.dataset')}</div>
+              <div className="pb-1">{t('knowledgeDetails.subbarFiles')}</div>
               <div className="text-text-sub-title-invert text-sm">
                 {t('knowledgeDetails.datasetDescription')}
               </div>

web/src/pages/dataset/sidebar/index.tsx

@@ -9,7 +9,7 @@ import { cn, formatBytes } from '@/lib/utils';
 import { Routes } from '@/routes';
 import { formatPureDate } from '@/utils/date';
 import { isEmpty } from 'lodash';
-import { Banknote, Database, FileSearch2, GitGraph } from 'lucide-react';
+import { Banknote, FileSearch2, FolderOpen, GitGraph } from 'lucide-react';
 import { useMemo } from 'react';
 import { useTranslation } from 'react-i18next';
 import { useHandleMenuClick } from './hooks';
@@ -34,8 +34,8 @@ export function SideBar({ refreshCount }: PropType) {
       //   key: Routes.DataSetOverview,
       // },
       {
-        icon: Database,
+        icon: FolderOpen,
-        label: t(`knowledgeDetails.dataset`),
+        label: t(`knowledgeDetails.subbarFiles`),
         key: Routes.DatasetBase,
       },
       {