Fix: meta data filter with AND logic operations. (#9687)

### What problem does this PR solve?

Close #9648

### Type of change

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

agent/canvas.py

@@ -131,7 +131,16 @@ class Canvas:
 
         self.path = self.dsl["path"]
         self.history = self.dsl["history"]
-        self.globals = self.dsl["globals"]
+        if "globals" in self.dsl:
+            self.globals = self.dsl["globals"]
+        else:
+            self.globals = {
+            "sys.query": "",
+            "sys.user_id": "",
+            "sys.conversation_turns": 0,
+            "sys.files": []
+        }
+            
         self.retrieval = self.dsl["retrieval"]
         self.memory = self.dsl.get("memory", [])
 
@@ -417,7 +426,7 @@ class Canvas:
         convs = []
         if window_size <= 0:
             return convs
-        for role, obj in self.history[window_size * -1:]:
+        for role, obj in self.history[window_size * -2:]:
             if isinstance(obj, dict):
                 convs.append({"role": role, "content": obj.get("content", "")})
             else:

agent/component/base.py

@@ -36,7 +36,7 @@ _IS_RAW_CONF = "_is_raw_conf"
 
 class ComponentParamBase(ABC):
     def __init__(self):
-        self.message_history_window_size = 22
+        self.message_history_window_size = 13
         self.inputs = {}
         self.outputs = {}
         self.description = ""

agent/component/llm.py

@@ -18,11 +18,8 @@ import logging
 import os
 import re
 from typing import Any, Generator
-
 import json_repair
-from copy import deepcopy
 from functools import partial
-
 from api.db import LLMType
 from api.db.services.llm_service import LLMBundle
 from api.db.services.tenant_llm_service import TenantLLMService
@@ -130,7 +127,7 @@ class LLM(ComponentBase):
 
         args = {}
         vars = self.get_input_elements() if not self._param.debug_inputs else self._param.debug_inputs
-        prompt = self._param.sys_prompt
+        sys_prompt = self._param.sys_prompt
         for k, o in vars.items():
             args[k] = o["value"]
             if not isinstance(args[k], str):
@@ -141,14 +138,18 @@ class LLM(ComponentBase):
             self.set_input_value(k, args[k])
 
         msg = self._canvas.get_history(self._param.message_history_window_size)[:-1]
-        msg.extend(deepcopy(self._param.prompts))
+        for p in self._param.prompts:
-        prompt = self.string_format(prompt, args)
+            if msg and msg[-1]["role"] == p["role"]:
+                continue
+            msg.append(p)
+
+        sys_prompt = self.string_format(sys_prompt, args)
         for m in msg:
             m["content"] = self.string_format(m["content"], args)
         if self._param.cite and self._canvas.get_reference()["chunks"]:
-            prompt += citation_prompt()
+            sys_prompt += citation_prompt()
 
-        return prompt, msg
+        return sys_prompt, msg
 
     def _generate(self, msg:list[dict], **kwargs) -> str:
         if not self.imgs:

agent/tools/code_exec.py

@@ -156,7 +156,7 @@ class CodeExec(ToolBase, ABC):
             self.set_output("_ERROR", "construct code request error: " + str(e))
 
         try:
-            resp = requests.post(url=f"http://{settings.SANDBOX_HOST}:9385/run", json=code_req, timeout=10)
+            resp = requests.post(url=f"http://{settings.SANDBOX_HOST}:9385/run", json=code_req, timeout=os.environ.get("COMPONENT_EXEC_TIMEOUT", 10*60))
             logging.info(f"http://{settings.SANDBOX_HOST}:9385/run", code_req, resp.status_code)
             if resp.status_code != 200:
                 resp.raise_for_status()

api/apps/sdk/chat.py

@@ -150,10 +150,10 @@ def update(tenant_id, chat_id):
     if not DialogService.query(tenant_id=tenant_id, id=chat_id, status=StatusEnum.VALID.value):
         return get_error_data_result(message="You do not own the chat")
     req = request.json
-    ids = req.get("dataset_ids")
+    ids = req.get("dataset_ids", [])
     if "show_quotation" in req:
         req["do_refer"] = req.pop("show_quotation")
-    if ids is not None:
+    if ids:
         for kb_id in ids:
             kbs = KnowledgebaseService.accessible(kb_id=kb_id, user_id=tenant_id)
             if not kbs:

api/apps/sdk/dify_retrieval.py

@@ -24,6 +24,7 @@ from api.db.services.llm_service import LLMBundle
 from api import settings
 from api.utils.api_utils import validate_request, build_error_result, apikey_required
 from rag.app.tag import label_question
+from api.db.services.dialog_service import meta_filter
 
 
 @manager.route('/dify/retrieval', methods=['POST'])  # noqa: F821
@@ -37,18 +38,23 @@ def retrieval(tenant_id):
     retrieval_setting = req.get("retrieval_setting", {})
     similarity_threshold = float(retrieval_setting.get("score_threshold", 0.0))
     top = int(retrieval_setting.get("top_k", 1024))
+    metadata_condition = req.get("metadata_condition",{})
+    metas = DocumentService.get_meta_by_kbs([kb_id])
  
+    doc_ids = []
     try:
 
         e, kb = KnowledgebaseService.get_by_id(kb_id)
         if not e:
             return build_error_result(message="Knowledgebase not found!", code=settings.RetCode.NOT_FOUND)
 
-        if kb.tenant_id != tenant_id:
-            return build_error_result(message="Knowledgebase not found!", code=settings.RetCode.NOT_FOUND)
-
         embd_mdl = LLMBundle(kb.tenant_id, LLMType.EMBEDDING.value, llm_name=kb.embd_id)
-
+        print(metadata_condition)
+        print("after",convert_conditions(metadata_condition))
+        doc_ids.extend(meta_filter(metas, convert_conditions(metadata_condition)))
+        print("doc_ids",doc_ids)
+        if not doc_ids and metadata_condition is not None:
+            doc_ids = ['-999']
         ranks = settings.retrievaler.retrieval(
             question,
             embd_mdl,
@@ -59,6 +65,7 @@ def retrieval(tenant_id):
             similarity_threshold=similarity_threshold,
             vector_similarity_weight=0.3,
             top=top,
+            doc_ids=doc_ids,
             rank_feature=label_question(question, [kb])
         )
 
@@ -67,6 +74,7 @@ def retrieval(tenant_id):
                                                    [tenant_id],
                                                    [kb_id],
                                                    embd_mdl,
+                                                   doc_ids,
                                                    LLMBundle(kb.tenant_id, LLMType.CHAT))
             if ck["content_with_weight"]:
                 ranks["chunks"].insert(0, ck)
@@ -93,3 +101,20 @@ def retrieval(tenant_id):
             )
         logging.exception(e)
         return build_error_result(message=str(e), code=settings.RetCode.SERVER_ERROR)
+
+def convert_conditions(metadata_condition):
+    if metadata_condition is None:
+        metadata_condition = {}
+    op_mapping = {
+        "is": "=",
+        "not is": "≠"
+    }
+    return [
+    {
+        "op": op_mapping.get(cond["comparison_operator"], cond["comparison_operator"]),
+        "key": cond["name"],
+        "value": cond["value"]
+    }
+    for cond in metadata_condition.get("conditions", [])
+]
+

api/apps/sdk/session.py

@@ -84,18 +84,10 @@ def create_agent_session(tenant_id, agent_id):
     session_id=get_uuid()
     canvas = Canvas(cvs.dsl, tenant_id, agent_id)
     canvas.reset()
-    conv = {
-        "id": session_id,
-        "dialog_id": cvs.id,
-        "user_id": user_id,
-        "message": [],
-        "source": "agent",
-        "dsl": cvs.dsl
-    }
-    API4ConversationService.save(**conv)
     
     cvs.dsl = json.loads(str(canvas))
     conv = {"id": session_id, "dialog_id": cvs.id, "user_id": user_id, "message": [{"role": "assistant", "content": canvas.get_prologue()}], "source": "agent", "dsl": cvs.dsl}
+    API4ConversationService.save(**conv)
     conv["agent_id"] = conv.pop("dialog_id")
     return get_result(data=conv)
 
@@ -450,37 +442,26 @@ def agents_completion_openai_compatibility(tenant_id, agent_id):
 def agent_completions(tenant_id, agent_id):
     req = request.json
 
-    ans = {}
+
     if req.get("stream", True):
-
+        resp = Response(agent_completion(tenant_id=tenant_id, agent_id=agent_id, **req), mimetype="text/event-stream")
-        def generate():
-            for answer in agent_completion(tenant_id=tenant_id, agent_id=agent_id, **req):
-                if isinstance(answer, str):
-                    try:
-                        ans = json.loads(answer[5:])  # remove "data:"
-                    except Exception:
-                        continue
-
-                if ans.get("event") != "message":
-                    continue
-
-                yield answer
-
-            yield "data:[DONE]\n\n"
-
-        resp = Response(generate(), mimetype="text/event-stream")
         resp.headers.add_header("Cache-control", "no-cache")
         resp.headers.add_header("Connection", "keep-alive")
         resp.headers.add_header("X-Accel-Buffering", "no")
         resp.headers.add_header("Content-Type", "text/event-stream; charset=utf-8")
         return resp
-
+    result = {}
     for answer in agent_completion(tenant_id=tenant_id, agent_id=agent_id, **req):
         try:
             ans = json.loads(answer[5:])  # remove "data:"
+            if not result:
+                result = ans.copy()
+            else:
+                result["data"]["answer"] += ans["data"]["answer"]
+                result["data"]["reference"] = ans["data"].get("reference", [])
         except Exception as e:
-            return get_result(data=f"**ERROR**: {str(e)}")
+            return get_error_data_result(str(e))
-    return get_result(data=ans)
+    return result
 
 
 @manager.route("/chats/<chat_id>/sessions", methods=["GET"])  # noqa: F821
@@ -581,6 +562,9 @@ def list_agent_session(tenant_id, agent_id):
                             "chunks" in conv["reference"][chunk_num]):
                         chunks = conv["reference"][chunk_num]["chunks"]
                         for chunk in chunks:
+                            # Ensure chunk is a dictionary before calling get method
+                            if not isinstance(chunk, dict):
+                                continue
                             new_chunk = {
                                 "id": chunk.get("chunk_id", chunk.get("id")),
                                 "content": chunk.get("content_with_weight", chunk.get("content")),
@@ -909,7 +893,7 @@ def ask_about_embedded():
     def stream():
         nonlocal req, uid
         try:
-            for ans in ask(req["question"], req["kb_ids"], uid, search_config):
+            for ans in ask(req["question"], req["kb_ids"], uid, search_config=search_config):
                 yield "data:" + json.dumps({"code": 0, "message": "", "data": ans}, ensure_ascii=False) + "\n\n"
         except Exception as e:
             yield "data:" + json.dumps({"code": 500, "message": str(e), "data": {"answer": "**ERROR**: " + str(e), "reference": []}}, ensure_ascii=False) + "\n\n"

api/db/services/canvas_service.py

@@ -134,6 +134,25 @@ class UserCanvasService(CommonService):
             return False
         return True
 
+
+def structure_answer(conv, ans, message_id, session_id):
+    if not conv:
+        return ans
+    content = ""
+    if ans["event"] == "message":
+        if ans["data"].get("start_to_think") is True:
+            content = "<think>"
+        elif ans["data"].get("end_to_think") is True:
+            content = "</think>"
+        else:
+            content = ans["data"]["content"]
+
+    reference = ans["data"].get("reference")
+    result = {"id": message_id, "session_id": session_id, "answer": content}
+    if reference:
+        result["reference"] = [reference]
+    return result
+
 def completion(tenant_id, agent_id, session_id=None, **kwargs):
     query = kwargs.get("query", "") or kwargs.get("question", "")
     files = kwargs.get("files", [])
@@ -163,7 +182,8 @@ def completion(tenant_id, agent_id, session_id=None, **kwargs):
             "user_id": user_id,
             "message": [],
             "source": "agent",
-            "dsl": cvs.dsl
+            "dsl": cvs.dsl,
+            "reference": []
         }
         API4ConversationService.save(**conv)
         conv = API4Conversation(**conv)
@@ -176,13 +196,14 @@ def completion(tenant_id, agent_id, session_id=None, **kwargs):
     })
     txt = ""
     for ans in canvas.run(query=query, files=files, user_id=user_id, inputs=inputs):
-        ans["session_id"] = session_id
+        ans = structure_answer(conv, ans, message_id, session_id)
-        if ans["event"] == "message":
+        txt += ans["answer"]
-            txt += ans["data"]["content"]
+        if ans.get("answer") or ans.get("reference"):
-        yield "data:" + json.dumps(ans, ensure_ascii=False) + "\n\n"
+            yield "data:" + json.dumps({"code": 0, "data": ans},
+                                       ensure_ascii=False) + "\n\n"
 
     conv.message.append({"role": "assistant", "content": txt, "created_at": time.time(), "id": message_id})
-    conv.reference = canvas.get_reference()
+    conv.reference.append(canvas.get_reference())
     conv.errors = canvas.error
     conv.dsl = str(canvas)
     conv = conv.to_dict()
@@ -211,11 +232,9 @@ def completionOpenAI(tenant_id, agent_id, question, session_id=None, stream=True
                     except Exception as e:
                         logging.exception(f"Agent OpenAI-Compatible completionOpenAI parse answer failed: {e}")
                         continue
-
+                if not ans["data"]["answer"]:
-                if ans.get("event") != "message":
                     continue
-
+                content_piece = ans["data"]["answer"]
-                content_piece = ans["data"]["content"]
                 completion_tokens += len(tiktokenenc.encode(content_piece))
 
                 yield "data: " + json.dumps(
@@ -260,9 +279,9 @@ def completionOpenAI(tenant_id, agent_id, question, session_id=None, stream=True
             ):
                 if isinstance(ans, str):
                     ans = json.loads(ans[5:])
-                if ans.get("event") != "message":
+                if not ans["data"]["answer"]:
                     continue
-                all_content += ans["data"]["content"]
+                all_content += ans["data"]["answer"]
 
             completion_tokens = len(tiktokenenc.encode(all_content))
 

api/db/services/dialog_service.py

@@ -256,10 +256,10 @@ def repair_bad_citation_formats(answer: str, kbinfos: dict, idx: set):
 
 
 def meta_filter(metas: dict, filters: list[dict]):
-    doc_ids = []
+    doc_ids = set([])
 
     def filter_out(v2docs, operator, value):
-        nonlocal doc_ids
+        ids = []
         for input, docids in v2docs.items():
             try:
                 input = float(input)
@@ -284,16 +284,24 @@ def meta_filter(metas: dict, filters: list[dict]):
                 ]:
                 try:
                     if all(conds):
-                        doc_ids.extend(docids)
+                        ids.extend(docids)
+                        break
                 except Exception:
                     pass
+        return ids
 
     for k, v2docs in metas.items():
         for f in filters:
             if k != f["key"]:
                 continue
-            filter_out(v2docs, f["op"], f["value"])
+            ids = filter_out(v2docs, f["op"], f["value"])
-    return doc_ids
+            if not doc_ids:
+                doc_ids = set(ids)
+            else:
+                doc_ids = doc_ids & set(ids)
+            if not doc_ids:
+                return []
+    return list(doc_ids)
 
 
 def chat(dialog, messages, stream=True, **kwargs):

api/db/services/llm_service.py

@@ -152,7 +152,7 @@ class LLMBundle(LLM4Tenant):
 
     def describe_with_prompt(self, image, prompt):
         if self.langfuse:
-            generation = self.language.start_generation(trace_context=self.trace_context, name="describe_with_prompt", metadata={"model": self.llm_name, "prompt": prompt})
+            generation = self.langfuse.start_generation(trace_context=self.trace_context, name="describe_with_prompt", metadata={"model": self.llm_name, "prompt": prompt})
 
         txt, used_tokens = self.mdl.describe_with_prompt(image, prompt)
         if not TenantLLMService.increase_usage(self.tenant_id, self.llm_type, used_tokens):

api/utils/api_utils.py

@@ -17,6 +17,7 @@ import asyncio
 import functools
 import json
 import logging
+import os
 import queue
 import random
 import threading
@@ -667,7 +668,10 @@ def timeout(seconds: float | int = None, attempts: int = 2, *, exception: Option
 
             for a in range(attempts):
                 try:
-                    result = result_queue.get(timeout=seconds)
+                    if os.environ.get("ENABLE_TIMEOUT_ASSERTION"):
+                        result = result_queue.get(timeout=seconds)
+                    else:
+                        result = result_queue.get()
                     if isinstance(result, Exception):
                         raise result
                     return result
@@ -682,7 +686,10 @@ def timeout(seconds: float | int = None, attempts: int = 2, *, exception: Option
 
             for a in range(attempts):
                 try:
-                    with trio.fail_after(seconds):
+                    if os.environ.get("ENABLE_TIMEOUT_ASSERTION"):
+                        with trio.fail_after(seconds):
+                            return await func(*args, **kwargs)
+                    else:
                         return await func(*args, **kwargs)
                 except trio.TooSlowError:
                     if a < attempts - 1:

deepdoc/parser/__init__.py

@@ -14,13 +14,15 @@
 #  limitations under the License.
 #
 
-from .pdf_parser import RAGFlowPdfParser as PdfParser, PlainParser
 from .docx_parser import RAGFlowDocxParser as DocxParser
 from .excel_parser import RAGFlowExcelParser as ExcelParser
-from .ppt_parser import RAGFlowPptParser as PptParser
 from .html_parser import RAGFlowHtmlParser as HtmlParser
 from .json_parser import RAGFlowJsonParser as JsonParser
+from .markdown_parser import MarkdownElementExtractor
 from .markdown_parser import RAGFlowMarkdownParser as MarkdownParser
+from .pdf_parser import PlainParser
+from .pdf_parser import RAGFlowPdfParser as PdfParser
+from .ppt_parser import RAGFlowPptParser as PptParser
 from .txt_parser import RAGFlowTxtParser as TxtParser
 
 __all__ = [
@@ -33,4 +35,6 @@ __all__ = [
     "JsonParser",
     "MarkdownParser",
     "TxtParser",
+    "MarkdownElementExtractor",
 ]
+

deepdoc/parser/markdown_parser.py

@@ -17,8 +17,10 @@
 
 import re
 
+import mistune
 from markdown import markdown
 
+
 class RAGFlowMarkdownParser:
     def __init__(self, chunk_token_num=128):
         self.chunk_token_num = int(chunk_token_num)
@@ -35,40 +37,44 @@ class RAGFlowMarkdownParser:
                 table_list.append(raw_table)
                 if separate_tables:
                     # Skip this match (i.e., remove it)
-                    new_text += working_text[last_end:match.start()] + "\n\n"
+                    new_text += working_text[last_end : match.start()] + "\n\n"
                 else:
                     # Replace with rendered HTML
-                    html_table = markdown(raw_table, extensions=['markdown.extensions.tables']) if render else raw_table
+                    html_table = markdown(raw_table, extensions=["markdown.extensions.tables"]) if render else raw_table
-                    new_text += working_text[last_end:match.start()] + html_table + "\n\n"
+                    new_text += working_text[last_end : match.start()] + html_table + "\n\n"
                 last_end = match.end()
             new_text += working_text[last_end:]
             return new_text
 
-        if "|" in markdown_text: # for optimize performance
+        if "|" in markdown_text:  # for optimize performance
             # Standard Markdown table
             border_table_pattern = re.compile(
-                r'''
+                r"""
                 (?:\n|^)
                 (?:\|.*?\|.*?\|.*?\n)
                 (?:\|(?:\s*[:-]+[-| :]*\s*)\|.*?\n)
                 (?:\|.*?\|.*?\|.*?\n)+
-            ''', re.VERBOSE)
+            """,
+                re.VERBOSE,
+            )
             working_text = replace_tables_with_rendered_html(border_table_pattern, tables)
 
             # Borderless Markdown table
             no_border_table_pattern = re.compile(
-                r'''
+                r"""
                 (?:\n|^)
                 (?:\S.*?\|.*?\n)
                 (?:(?:\s*[:-]+[-| :]*\s*).*?\n)
                 (?:\S.*?\|.*?\n)+
-                ''', re.VERBOSE)
+                """,
+                re.VERBOSE,
+            )
             working_text = replace_tables_with_rendered_html(no_border_table_pattern, tables)
 
-        if "<table>" in working_text.lower(): # for optimize performance
+        if "<table>" in working_text.lower():  # for optimize performance
-            #HTML table extraction - handle possible html/body wrapper tags
+            # HTML table extraction - handle possible html/body wrapper tags
             html_table_pattern = re.compile(
-            r'''
+                r"""
             (?:\n|^)
             \s*
             (?:
@@ -83,9 +89,10 @@ class RAGFlowMarkdownParser:
             )
             \s*
             (?=\n|$)
-            ''',
+            """,
-            re.VERBOSE | re.DOTALL | re.IGNORECASE
+                re.VERBOSE | re.DOTALL | re.IGNORECASE,
             )
+
             def replace_html_tables():
                 nonlocal working_text
                 new_text = ""
@@ -94,9 +101,9 @@ class RAGFlowMarkdownParser:
                     raw_table = match.group()
                     tables.append(raw_table)
                     if separate_tables:
-                        new_text += working_text[last_end:match.start()] + "\n\n"
+                        new_text += working_text[last_end : match.start()] + "\n\n"
                     else:
-                        new_text += working_text[last_end:match.start()] + raw_table + "\n\n"
+                        new_text += working_text[last_end : match.start()] + raw_table + "\n\n"
                     last_end = match.end()
                 new_text += working_text[last_end:]
                 working_text = new_text
@@ -104,3 +111,163 @@ class RAGFlowMarkdownParser:
             replace_html_tables()
 
         return working_text, tables
+
+
+class MarkdownElementExtractor:
+    def __init__(self, markdown_content):
+        self.markdown_content = markdown_content
+        self.lines = markdown_content.split("\n")
+        self.ast_parser = mistune.create_markdown(renderer="ast")
+        self.ast_nodes = self.ast_parser(markdown_content)
+
+    def extract_elements(self):
+        """Extract individual elements (headers, code blocks, lists, etc.)"""
+        sections = []
+
+        i = 0
+        while i < len(self.lines):
+            line = self.lines[i]
+
+            if re.match(r"^#{1,6}\s+.*$", line):
+                # header
+                element = self._extract_header(i)
+                sections.append(element["content"])
+                i = element["end_line"] + 1
+            elif line.strip().startswith("```"):
+                # code block
+                element = self._extract_code_block(i)
+                sections.append(element["content"])
+                i = element["end_line"] + 1
+            elif re.match(r"^\s*[-*+]\s+.*$", line) or re.match(r"^\s*\d+\.\s+.*$", line):
+                # list block
+                element = self._extract_list_block(i)
+                sections.append(element["content"])
+                i = element["end_line"] + 1
+            elif line.strip().startswith(">"):
+                # blockquote
+                element = self._extract_blockquote(i)
+                sections.append(element["content"])
+                i = element["end_line"] + 1
+            elif line.strip():
+                # text block (paragraphs and inline elements until next block element)
+                element = self._extract_text_block(i)
+                sections.append(element["content"])
+                i = element["end_line"] + 1
+            else:
+                i += 1
+
+        sections = [section for section in sections if section.strip()]
+        return sections
+
+    def _extract_header(self, start_pos):
+        return {
+            "type": "header",
+            "content": self.lines[start_pos],
+            "start_line": start_pos,
+            "end_line": start_pos,
+        }
+
+    def _extract_code_block(self, start_pos):
+        end_pos = start_pos
+        content_lines = [self.lines[start_pos]]
+
+        # Find the end of the code block
+        for i in range(start_pos + 1, len(self.lines)):
+            content_lines.append(self.lines[i])
+            end_pos = i
+            if self.lines[i].strip().startswith("```"):
+                break
+
+        return {
+            "type": "code_block",
+            "content": "\n".join(content_lines),
+            "start_line": start_pos,
+            "end_line": end_pos,
+        }
+
+    def _extract_list_block(self, start_pos):
+        end_pos = start_pos
+        content_lines = []
+
+        i = start_pos
+        while i < len(self.lines):
+            line = self.lines[i]
+            # check if this line is a list item or continuation of a list
+            if (
+                re.match(r"^\s*[-*+]\s+.*$", line)
+                or re.match(r"^\s*\d+\.\s+.*$", line)
+                or (i > start_pos and not line.strip())
+                or (i > start_pos and re.match(r"^\s{2,}[-*+]\s+.*$", line))
+                or (i > start_pos and re.match(r"^\s{2,}\d+\.\s+.*$", line))
+                or (i > start_pos and re.match(r"^\s+\w+.*$", line))
+            ):
+                content_lines.append(line)
+                end_pos = i
+                i += 1
+            else:
+                break
+
+        return {
+            "type": "list_block",
+            "content": "\n".join(content_lines),
+            "start_line": start_pos,
+            "end_line": end_pos,
+        }
+
+    def _extract_blockquote(self, start_pos):
+        end_pos = start_pos
+        content_lines = []
+
+        i = start_pos
+        while i < len(self.lines):
+            line = self.lines[i]
+            if line.strip().startswith(">") or (i > start_pos and not line.strip()):
+                content_lines.append(line)
+                end_pos = i
+                i += 1
+            else:
+                break
+
+        return {
+            "type": "blockquote",
+            "content": "\n".join(content_lines),
+            "start_line": start_pos,
+            "end_line": end_pos,
+        }
+
+    def _extract_text_block(self, start_pos):
+        """Extract a text block (paragraphs, inline elements) until next block element"""
+        end_pos = start_pos
+        content_lines = [self.lines[start_pos]]
+
+        i = start_pos + 1
+        while i < len(self.lines):
+            line = self.lines[i]
+            # stop if we encounter a block element
+            if re.match(r"^#{1,6}\s+.*$", line) or line.strip().startswith("```") or re.match(r"^\s*[-*+]\s+.*$", line) or re.match(r"^\s*\d+\.\s+.*$", line) or line.strip().startswith(">"):
+                break
+            elif not line.strip():
+                # check if the next line is a block element
+                if i + 1 < len(self.lines) and (
+                    re.match(r"^#{1,6}\s+.*$", self.lines[i + 1])
+                    or self.lines[i + 1].strip().startswith("```")
+                    or re.match(r"^\s*[-*+]\s+.*$", self.lines[i + 1])
+                    or re.match(r"^\s*\d+\.\s+.*$", self.lines[i + 1])
+                    or self.lines[i + 1].strip().startswith(">")
+                ):
+                    break
+                else:
+                    content_lines.append(line)
+                    end_pos = i
+                    i += 1
+            else:
+                content_lines.append(line)
+                end_pos = i
+                i += 1
+
+        return {
+            "type": "text_block",
+            "content": "\n".join(content_lines),
+            "start_line": start_pos,
+            "end_line": end_pos,
+        }

docs/references/http_api_reference.md

@@ -3501,7 +3501,7 @@ Failure:
 
 ### Generate related questions
 
-**POST** `/v1/sessions/related_questions`
+**POST** `/api/v1/sessions/related_questions`
 
 Generates five to ten alternative question strings from the user's original query to retrieve more relevant search results.
 
@@ -3516,7 +3516,7 @@ The chat model autonomously determines the number of questions to generate based
 #### Request
 
 - Method: POST
-- URL: `/v1/sessions/related_questions`
+- URL: `/api/v1/sessions/related_questions`
 - Headers:
   - `'content-Type: application/json'`
   - `'Authorization: Bearer <YOUR_LOGIN_TOKEN>'`
@@ -3528,7 +3528,7 @@ The chat model autonomously determines the number of questions to generate based
 
 ```bash
 curl --request POST \
-     --url http://{address}/v1/sessions/related_questions \
+     --url http://{address}/api/v1/sessions/related_questions \
      --header 'Content-Type: application/json' \
      --header 'Authorization: Bearer <YOUR_LOGIN_TOKEN>' \
      --data '

graphrag/entity_resolution.py

@@ -15,6 +15,7 @@
 #
 import logging
 import itertools
+import os
 import re
 from dataclasses import dataclass
 from typing import Any, Callable
@@ -106,7 +107,8 @@ class EntityResolution(Extractor):
             nonlocal remain_candidates_to_resolve, callback
             async with semaphore:
                 try:
-                    with trio.move_on_after(280) as cancel_scope:
+                    enable_timeout_assertion = os.environ.get("ENABLE_TIMEOUT_ASSERTION")
+                    with trio.move_on_after(280 if enable_timeout_assertion else 1000000000) as cancel_scope:
                         await self._resolve_candidate(candidate_batch, result_set, result_lock)
                         remain_candidates_to_resolve = remain_candidates_to_resolve - len(candidate_batch[1])
                         callback(msg=f"Resolved {len(candidate_batch[1])} pairs, {remain_candidates_to_resolve} are remained to resolve. ")
@@ -169,7 +171,8 @@ class EntityResolution(Extractor):
         logging.info(f"Created resolution prompt {len(text)} bytes for {len(candidate_resolution_i[1])} entity pairs of type {candidate_resolution_i[0]}")
         async with chat_limiter:
             try:
-                with trio.move_on_after(240) as cancel_scope:
+                enable_timeout_assertion = os.environ.get("ENABLE_TIMEOUT_ASSERTION")
+                with trio.move_on_after(280 if enable_timeout_assertion else 1000000000) as cancel_scope:
                     response = await trio.to_thread.run_sync(self._chat, text, [{"role": "user", "content": "Output:"}], {})
                 if cancel_scope.cancelled_caught:
                     logging.warning("_resolve_candidate._chat timeout, skipping...")

graphrag/general/community_reports_extractor.py

@@ -7,6 +7,7 @@ Reference:
 
 import logging
 import json
+import os
 import re
 from typing import Callable
 from dataclasses import dataclass
@@ -51,6 +52,7 @@ class CommunityReportsExtractor(Extractor):
         self._max_report_length = max_report_length or 1500
 
     async def __call__(self, graph: nx.Graph, callback: Callable | None = None):
+        enable_timeout_assertion = os.environ.get("ENABLE_TIMEOUT_ASSERTION")
         for node_degree in graph.degree:
             graph.nodes[str(node_degree[0])]["rank"] = int(node_degree[1])
 
@@ -92,7 +94,7 @@ class CommunityReportsExtractor(Extractor):
             text = perform_variable_replacements(self._extraction_prompt, variables=prompt_variables)
             async with chat_limiter:
                 try:
-                    with trio.move_on_after(180) as cancel_scope:
+                    with trio.move_on_after(180 if enable_timeout_assertion else 1000000000) as cancel_scope:
                         response = await trio.to_thread.run_sync( self._chat, text, [{"role": "user", "content": "Output:"}], {})
                     if cancel_scope.cancelled_caught:
                         logging.warning("extract_community_report._chat timeout, skipping...")

graphrag/general/extractor.py

@@ -47,7 +47,7 @@ class Extractor:
         self._language = language
         self._entity_types = entity_types or DEFAULT_ENTITY_TYPES
 
-    @timeout(60*5)
+    @timeout(60*20)
     def _chat(self, system, history, gen_conf={}):
         hist = deepcopy(history)
         conf = deepcopy(gen_conf)

graphrag/general/index.py

@@ -15,6 +15,8 @@
 #
 import json
 import logging
+import os
+
 import networkx as nx
 import trio
 
@@ -49,6 +51,7 @@ async def run_graphrag(
     embedding_model,
     callback,
 ):
+    enable_timeout_assertion=os.environ.get("ENABLE_TIMEOUT_ASSERTION")
     start = trio.current_time()
     tenant_id, kb_id, doc_id = row["tenant_id"], str(row["kb_id"]), row["doc_id"]
     chunks = []
@@ -57,7 +60,7 @@ async def run_graphrag(
     ):
         chunks.append(d["content_with_weight"])
 
-    with trio.fail_after(max(120, len(chunks)*120)):
+    with trio.fail_after(max(120, len(chunks)*60*10) if enable_timeout_assertion else 10000000000):
         subgraph = await generate_subgraph(
             LightKGExt
             if "method" not in row["kb_parser_config"].get("graphrag", {}) or row["kb_parser_config"]["graphrag"]["method"] != "general"

graphrag/light/graph_prompt.py

@@ -130,7 +130,36 @@ Output:
 
 PROMPTS[
     "entiti_continue_extraction"
-] = """MANY entities were missed in the last extraction.  Add them below using the same format:
+] = """
+MANY entities and relationships were missed in the last extraction. Please find only the missing entities and relationships from previous text.
+
+---Remember Steps---
+
+1. Identify all entities. For each identified entity, extract the following information:
+- entity_name: Name of the entity, use same language as input text. If English, capitalized the name
+- entity_type: One of the following types: [{entity_types}]
+- entity_description: Provide a comprehensive description of the entity's attributes and activities *based solely on the information present in the input text*. **Do not infer or hallucinate information not explicitly stated.** If the text provides insufficient information to create a comprehensive description, state "Description not available in text."
+Format each entity as ("entity"{tuple_delimiter}<entity_name>{tuple_delimiter}<entity_type>{tuple_delimiter}<entity_description>)
+
+2. From the entities identified in step 1, identify all pairs of (source_entity, target_entity) that are *clearly related* to each other.
+For each pair of related entities, extract the following information:
+- source_entity: name of the source entity, as identified in step 1
+- target_entity: name of the target entity, as identified in step 1
+- relationship_description: explanation as to why you think the source entity and the target entity are related to each other
+- relationship_strength: a numeric score indicating strength of the relationship between the source entity and target entity
+- relationship_keywords: one or more high-level key words that summarize the overarching nature of the relationship, focusing on concepts or themes rather than specific details
+Format each relationship as ("relationship"{tuple_delimiter}<source_entity>{tuple_delimiter}<target_entity>{tuple_delimiter}<relationship_description>{tuple_delimiter}<relationship_keywords>{tuple_delimiter}<relationship_strength>)
+
+3. Identify high-level key words that summarize the main concepts, themes, or topics of the entire text. These should capture the overarching ideas present in the document.
+Format the content-level key words as ("content_keywords"{tuple_delimiter}<high_level_keywords>)
+
+4. Return output in {language} as a single list of all the entities and relationships identified in steps 1 and 2. Use **{record_delimiter}** as the list delimiter.
+
+5. When finished, output {completion_delimiter}
+
+---Output---
+
+Add new entities and relations below using the same format, and do not include entities and relations that have been previously extracted. :
 """
 
 PROMPTS[

graphrag/utils.py

@@ -307,6 +307,7 @@ def chunk_id(chunk):
 
 async def graph_node_to_chunk(kb_id, embd_mdl, ent_name, meta, chunks):
     global chat_limiter
+    enable_timeout_assertion=os.environ.get("ENABLE_TIMEOUT_ASSERTION")
     chunk = {
         "id": get_uuid(),
         "important_kwd": [ent_name],
@@ -324,7 +325,7 @@ async def graph_node_to_chunk(kb_id, embd_mdl, ent_name, meta, chunks):
     ebd = get_embed_cache(embd_mdl.llm_name, ent_name)
     if ebd is None:
         async with chat_limiter:
-            with trio.fail_after(3):
+            with trio.fail_after(3 if enable_timeout_assertion else 30000000):
                 ebd, _ = await trio.to_thread.run_sync(lambda: embd_mdl.encode([ent_name]))
         ebd = ebd[0]
         set_embed_cache(embd_mdl.llm_name, ent_name, ebd)
@@ -362,6 +363,7 @@ def get_relation(tenant_id, kb_id, from_ent_name, to_ent_name, size=1):
 
 
 async def graph_edge_to_chunk(kb_id, embd_mdl, from_ent_name, to_ent_name, meta, chunks):
+    enable_timeout_assertion=os.environ.get("ENABLE_TIMEOUT_ASSERTION")
     chunk = {
         "id": get_uuid(),
         "from_entity_kwd": from_ent_name,
@@ -380,7 +382,7 @@ async def graph_edge_to_chunk(kb_id, embd_mdl, from_ent_name, to_ent_name, meta,
     ebd = get_embed_cache(embd_mdl.llm_name, txt)
     if ebd is None:
         async with chat_limiter:
-            with trio.fail_after(3):
+            with trio.fail_after(3 if enable_timeout_assertion else 300000000):
                 ebd, _ = await trio.to_thread.run_sync(lambda: embd_mdl.encode([txt+f": {meta['description']}"]))
         ebd = ebd[0]
         set_embed_cache(embd_mdl.llm_name, txt, ebd)
@@ -514,9 +516,10 @@ async def set_graph(tenant_id: str, kb_id: str, embd_mdl, graph: nx.Graph, chang
         callback(msg=f"set_graph converted graph change to {len(chunks)} chunks in {now - start:.2f}s.")
     start = now
 
+    enable_timeout_assertion=os.environ.get("ENABLE_TIMEOUT_ASSERTION")
     es_bulk_size = 4
     for b in range(0, len(chunks), es_bulk_size):
-        with trio.fail_after(3):
+        with trio.fail_after(3 if enable_timeout_assertion else 30000000):
             doc_store_result = await trio.to_thread.run_sync(lambda: settings.docStoreConn.insert(chunks[b:b + es_bulk_size], search.index_name(tenant_id), kb_id))
         if b % 100 == es_bulk_size and callback:
             callback(msg=f"Insert chunks: {b}/{len(chunks)}")

mcp/server/server.py

@@ -16,6 +16,9 @@
 
 import json
 import logging
+import random
+import time
+from collections import OrderedDict
 from collections.abc import AsyncIterator
 from contextlib import asynccontextmanager
 from functools import wraps
@@ -53,6 +56,13 @@ JSON_RESPONSE = True
 
 
 class RAGFlowConnector:
+    _MAX_DATASET_CACHE = 32
+    _MAX_DOCUMENT_CACHE = 128
+    _CACHE_TTL = 300
+
+    _dataset_metadata_cache: OrderedDict[str, tuple[dict, float | int]] = OrderedDict()  # "dataset_id" -> (metadata, expiry_ts)
+    _document_metadata_cache: OrderedDict[str, tuple[list[tuple[str, dict]], float | int]] = OrderedDict()  # "dataset_id" -> ([(document_id, doc_metadata)], expiry_ts)
+
     def __init__(self, base_url: str, version="v1"):
         self.base_url = base_url
         self.version = version
@@ -72,6 +82,43 @@ class RAGFlowConnector:
         res = requests.get(url=self.api_url + path, params=params, headers=self.authorization_header, json=json)
         return res
 
+    def _is_cache_valid(self, ts):
+        return time.time() < ts
+
+    def _get_expiry_timestamp(self):
+        offset = random.randint(-30, 30)
+        return time.time() + self._CACHE_TTL + offset
+
+    def _get_cached_dataset_metadata(self, dataset_id):
+        entry = self._dataset_metadata_cache.get(dataset_id)
+        if entry:
+            data, ts = entry
+            if self._is_cache_valid(ts):
+                self._dataset_metadata_cache.move_to_end(dataset_id)
+                return data
+        return None
+
+    def _set_cached_dataset_metadata(self, dataset_id, metadata):
+        self._dataset_metadata_cache[dataset_id] = (metadata, self._get_expiry_timestamp())
+        self._dataset_metadata_cache.move_to_end(dataset_id)
+        if len(self._dataset_metadata_cache) > self._MAX_DATASET_CACHE:
+            self._dataset_metadata_cache.popitem(last=False)
+
+    def _get_cached_document_metadata_by_dataset(self, dataset_id):
+        entry = self._document_metadata_cache.get(dataset_id)
+        if entry:
+            data_list, ts = entry
+            if self._is_cache_valid(ts):
+                self._document_metadata_cache.move_to_end(dataset_id)
+                return {doc_id: doc_meta for doc_id, doc_meta in data_list}
+        return None
+
+    def _set_cached_document_metadata_by_dataset(self, dataset_id, doc_id_meta_list):
+        self._document_metadata_cache[dataset_id] = (doc_id_meta_list, self._get_expiry_timestamp())
+        self._document_metadata_cache.move_to_end(dataset_id)
+        if len(self._document_metadata_cache) > self._MAX_DOCUMENT_CACHE:
+            self._document_metadata_cache.popitem(last=False)
+
     def list_datasets(self, page: int = 1, page_size: int = 1000, orderby: str = "create_time", desc: bool = True, id: str | None = None, name: str | None = None):
         res = self._get("/datasets", {"page": page, "page_size": page_size, "orderby": orderby, "desc": desc, "id": id, "name": name})
         if not res:
@@ -87,10 +134,38 @@ class RAGFlowConnector:
         return ""
 
     def retrieval(
-        self, dataset_ids, document_ids=None, question="", page=1, page_size=30, similarity_threshold=0.2, vector_similarity_weight=0.3, top_k=1024, rerank_id: str | None = None, keyword: bool = False
+        self,
+        dataset_ids,
+        document_ids=None,
+        question="",
+        page=1,
+        page_size=30,
+        similarity_threshold=0.2,
+        vector_similarity_weight=0.3,
+        top_k=1024,
+        rerank_id: str | None = None,
+        keyword: bool = False,
+        force_refresh: bool = False,
     ):
         if document_ids is None:
             document_ids = []
+        
+        # If no dataset_ids provided or empty list, get all available dataset IDs
+        if not dataset_ids:
+            dataset_list_str = self.list_datasets()
+            dataset_ids = []
+            
+            # Parse the dataset list to extract IDs
+            if dataset_list_str:
+                for line in dataset_list_str.strip().split('\n'):
+                    if line.strip():
+                        try:
+                            dataset_info = json.loads(line.strip())
+                            dataset_ids.append(dataset_info["id"])
+                        except (json.JSONDecodeError, KeyError):
+                            # Skip malformed lines
+                            continue
+        
         data_json = {
             "page": page,
             "page_size": page_size,
@@ -110,12 +185,127 @@ class RAGFlowConnector:
 
         res = res.json()
         if res.get("code") == 0:
+            data = res["data"]
             chunks = []
-            for chunk_data in res["data"].get("chunks"):
+
-                chunks.append(json.dumps(chunk_data, ensure_ascii=False))
+            # Cache document metadata and dataset information
-            return [types.TextContent(type="text", text="\n".join(chunks))]
+            document_cache, dataset_cache = self._get_document_metadata_cache(dataset_ids, force_refresh=force_refresh)
+
+            # Process chunks with enhanced field mapping including per-chunk metadata
+            for chunk_data in data.get("chunks", []):
+                enhanced_chunk = self._map_chunk_fields(chunk_data, dataset_cache, document_cache)
+                chunks.append(enhanced_chunk)
+
+            # Build structured response (no longer need response-level document_metadata)
+            response = {
+                "chunks": chunks,
+                "pagination": {
+                    "page": data.get("page", page),
+                    "page_size": data.get("page_size", page_size),
+                    "total_chunks": data.get("total", len(chunks)),
+                    "total_pages": (data.get("total", len(chunks)) + page_size - 1) // page_size,
+                },
+                "query_info": {
+                    "question": question,
+                    "similarity_threshold": similarity_threshold,
+                    "vector_weight": vector_similarity_weight,
+                    "keyword_search": keyword,
+                    "dataset_count": len(dataset_ids),
+                },
+            }
+
+            return [types.TextContent(type="text", text=json.dumps(response, ensure_ascii=False))]
+
         raise Exception([types.TextContent(type="text", text=res.get("message"))])
 
+    def _get_document_metadata_cache(self, dataset_ids, force_refresh=False):
+        """Cache document metadata for all documents in the specified datasets"""
+        document_cache = {}
+        dataset_cache = {}
+
+        try:
+            for dataset_id in dataset_ids:
+                dataset_meta = None if force_refresh else self._get_cached_dataset_metadata(dataset_id)
+                if not dataset_meta:
+                    # First get dataset info for name
+                    dataset_res = self._get("/datasets", {"id": dataset_id, "page_size": 1})
+                    if dataset_res and dataset_res.status_code == 200:
+                        dataset_data = dataset_res.json()
+                        if dataset_data.get("code") == 0 and dataset_data.get("data"):
+                            dataset_info = dataset_data["data"][0]
+                            dataset_meta = {"name": dataset_info.get("name", "Unknown"), "description": dataset_info.get("description", "")}
+                            self._set_cached_dataset_metadata(dataset_id, dataset_meta)
+                if dataset_meta:
+                    dataset_cache[dataset_id] = dataset_meta
+
+                docs = None if force_refresh else self._get_cached_document_metadata_by_dataset(dataset_id)
+                if docs is None:
+                    docs_res = self._get(f"/datasets/{dataset_id}/documents")
+                    docs_data = docs_res.json()
+                    if docs_data.get("code") == 0 and docs_data.get("data", {}).get("docs"):
+                        doc_id_meta_list = []
+                        docs = {}
+                        for doc in docs_data["data"]["docs"]:
+                            doc_id = doc.get("id")
+                            if not doc_id:
+                                continue
+                            doc_meta = {
+                                "document_id": doc_id,
+                                "name": doc.get("name", ""),
+                                "location": doc.get("location", ""),
+                                "type": doc.get("type", ""),
+                                "size": doc.get("size"),
+                                "chunk_count": doc.get("chunk_count"),
+                                # "chunk_method": doc.get("chunk_method", ""),
+                                "create_date": doc.get("create_date", ""),
+                                "update_date": doc.get("update_date", ""),
+                                # "process_begin_at": doc.get("process_begin_at", ""),
+                                # "process_duration": doc.get("process_duration"),
+                                # "progress": doc.get("progress"),
+                                # "progress_msg": doc.get("progress_msg", ""),
+                                # "status": doc.get("status", ""),
+                                # "run": doc.get("run", ""),
+                                "token_count": doc.get("token_count"),
+                                # "source_type": doc.get("source_type", ""),
+                                "thumbnail": doc.get("thumbnail", ""),
+                                "dataset_id": doc.get("dataset_id", dataset_id),
+                                "meta_fields": doc.get("meta_fields", {}),
+                                # "parser_config": doc.get("parser_config", {})
+                            }
+                            doc_id_meta_list.append((doc_id, doc_meta))
+                            docs[doc_id] = doc_meta
+                        self._set_cached_document_metadata_by_dataset(dataset_id, doc_id_meta_list)
+                if docs:
+                    document_cache.update(docs)
+
+        except Exception:
+            # Gracefully handle metadata cache failures
+            pass
+
+        return document_cache, dataset_cache
+
+    def _map_chunk_fields(self, chunk_data, dataset_cache, document_cache):
+        """Preserve all original API fields and add per-chunk document metadata"""
+        # Start with ALL raw data from API (preserve everything like original version)
+        mapped = dict(chunk_data)
+
+        # Add dataset name enhancement
+        dataset_id = chunk_data.get("dataset_id") or chunk_data.get("kb_id")
+        if dataset_id and dataset_id in dataset_cache:
+            mapped["dataset_name"] = dataset_cache[dataset_id]["name"]
+        else:
+            mapped["dataset_name"] = "Unknown"
+
+        # Add document name convenience field
+        mapped["document_name"] = chunk_data.get("document_keyword", "")
+
+        # Add per-chunk document metadata
+        document_id = chunk_data.get("document_id")
+        if document_id and document_id in document_cache:
+            mapped["document_metadata"] = document_cache[document_id]
+
+        return mapped
+
 
 class RAGFlowCtx:
     def __init__(self, connector: RAGFlowConnector):
@@ -195,7 +385,58 @@ async def list_tools(*, connector) -> list[types.Tool]:
                         "items": {"type": "string"},
                         "description": "Optional array of document IDs to search within."
                     },
-                    "question": {"type": "string", "description": "The question or query to search for."},
+                    "question": {
+                        "type": "string",
+                        "description": "The question or query to search for."
+                    },
+                    "page": {
+                        "type": "integer",
+                        "description": "Page number for pagination",
+                        "default": 1,
+                        "minimum": 1,
+                    },
+                    "page_size": {
+                        "type": "integer",
+                        "description": "Number of results to return per page (default: 10, max recommended: 50 to avoid token limits)",
+                        "default": 10,
+                        "minimum": 1,
+                        "maximum": 100,
+                    },
+                    "similarity_threshold": {
+                        "type": "number",
+                        "description": "Minimum similarity threshold for results",
+                        "default": 0.2,
+                        "minimum": 0.0,
+                        "maximum": 1.0,
+                    },
+                    "vector_similarity_weight": {
+                        "type": "number",
+                        "description": "Weight for vector similarity vs term similarity",
+                        "default": 0.3,
+                        "minimum": 0.0,
+                        "maximum": 1.0,
+                    },
+                    "keyword": {
+                        "type": "boolean",
+                        "description": "Enable keyword-based search",
+                        "default": False,
+                    },
+                    "top_k": {
+                        "type": "integer",
+                        "description": "Maximum results to consider before ranking",
+                        "default": 1024,
+                        "minimum": 1,
+                        "maximum": 1024,
+                    },
+                    "rerank_id": {
+                        "type": "string",
+                        "description": "Optional reranking model identifier",
+                    },
+                    "force_refresh": {
+                        "type": "boolean",
+                        "description": "Set to true only if fresh dataset and document metadata is explicitly required. Otherwise, cached metadata is used (default: false).",
+                        "default": False,
+                    },
                 },
                 "required": ["question"],
             },
@@ -209,6 +450,16 @@ async def call_tool(name: str, arguments: dict, *, connector) -> list[types.Text
     if name == "ragflow_retrieval":
         document_ids = arguments.get("document_ids", [])
         dataset_ids = arguments.get("dataset_ids", [])
+        question = arguments.get("question", "")
+        page = arguments.get("page", 1)
+        page_size = arguments.get("page_size", 10)
+        similarity_threshold = arguments.get("similarity_threshold", 0.2)
+        vector_similarity_weight = arguments.get("vector_similarity_weight", 0.3)
+        keyword = arguments.get("keyword", False)
+        top_k = arguments.get("top_k", 1024)
+        rerank_id = arguments.get("rerank_id")
+        force_refresh = arguments.get("force_refresh", False)
+
         
         # If no dataset_ids provided or empty list, get all available dataset IDs
         if not dataset_ids:
@@ -229,7 +480,15 @@ async def call_tool(name: str, arguments: dict, *, connector) -> list[types.Text
         return connector.retrieval(
             dataset_ids=dataset_ids,
             document_ids=document_ids,
-            question=arguments["question"],
+            question=question,
+            page=page,
+            page_size=page_size,
+            similarity_threshold=similarity_threshold,
+            vector_similarity_weight=vector_similarity_weight,
+            keyword=keyword,
+            top_k=top_k,
+            rerank_id=rerank_id,
+            force_refresh=force_refresh,
         )
     raise ValueError(f"Tool not found: {name}")
 

pyproject.toml

@@ -45,7 +45,7 @@ dependencies = [
     "html-text==0.6.2",
     "httpx[socks]==0.27.2",
     "huggingface-hub>=0.25.0,<0.26.0",
-    "infinity-sdk==0.6.0-dev4",
+    "infinity-sdk==0.6.0.dev5",
     "infinity-emb>=0.0.66,<0.0.67",
     "itsdangerous==2.1.2",
     "json-repair==0.35.0",

rag/app/naive.py

@@ -30,7 +30,7 @@ from tika import parser
 
 from api.db import LLMType
 from api.db.services.llm_service import LLMBundle
-from deepdoc.parser import DocxParser, ExcelParser, HtmlParser, JsonParser, MarkdownParser, PdfParser, TxtParser
+from deepdoc.parser import DocxParser, ExcelParser, HtmlParser, JsonParser, MarkdownElementExtractor, MarkdownParser, PdfParser, TxtParser
 from deepdoc.parser.figure_parser import VisionFigureParser, vision_figure_parser_figure_data_wrapper
 from deepdoc.parser.pdf_parser import PlainParser, VisionParser
 from rag.nlp import concat_img, find_codec, naive_merge, naive_merge_with_images, naive_merge_docx, rag_tokenizer, tokenize_chunks, tokenize_chunks_with_images, tokenize_table
@@ -289,7 +289,7 @@ class Pdf(PdfParser):
             return [(b["text"], self._line_tag(b, zoomin)) for b in self.boxes], tbls, figures
         else:
             tbls = self._extract_table_figure(True, zoomin, True, True)
-            # self._naive_vertical_merge()
+            self._naive_vertical_merge()
             self._concat_downward()
             # self._filter_forpages()
             logging.info("layouts cost: {}s".format(timer() - first_start))
@@ -350,17 +350,14 @@ class Markdown(MarkdownParser):
         else:
             with open(filename, "r") as f:
                 txt = f.read()
+
         remainder, tables = self.extract_tables_and_remainder(f'{txt}\n', separate_tables=separate_tables)
-        sections = []
+
+        extractor = MarkdownElementExtractor(txt)
+        element_sections = extractor.extract_elements()
+        sections = [(element, "") for element in element_sections]
+
         tbls = []
-        for sec in remainder.split("\n"):
-            if sec.strip().find("#") == 0:
-                sections.append((sec, ""))
-            elif sections and sections[-1][0].strip().find("#") == 0:
-                sec_, _ = sections.pop(-1)
-                sections.append((sec_ + "\n" + sec, ""))
-            else:
-                sections.append((sec, ""))
         for table in tables:
             tbls.append(((None, markdown(table, extensions=['markdown.extensions.tables'])), ""))
         return sections, tbls

rag/llm/__init__.py

@@ -36,6 +36,7 @@ class SupportedLiteLLMProvider(StrEnum):
     Nvidia = "NVIDIA"
     TogetherAI = "TogetherAI"
     Anthropic = "Anthropic"
+    Ollama = "Ollama"
 
 
 FACTORY_DEFAULT_BASE_URL = {
@@ -59,6 +60,7 @@ LITELLM_PROVIDER_PREFIX = {
     SupportedLiteLLMProvider.Nvidia: "nvidia_nim/",
     SupportedLiteLLMProvider.TogetherAI: "together_ai/",
     SupportedLiteLLMProvider.Anthropic: "",  # don't need a prefix
+    SupportedLiteLLMProvider.Ollama: "ollama_chat/",
 }
 
 ChatModel = globals().get("ChatModel", {})

rag/llm/chat_model.py

@@ -29,7 +29,6 @@ import json_repair
 import litellm
 import openai
 import requests
-from ollama import Client
 from openai import OpenAI
 from openai.lib.azure import AzureOpenAI
 from strenum import StrEnum
@@ -112,6 +111,32 @@ class Base(ABC):
     def _clean_conf(self, gen_conf):
         if "max_tokens" in gen_conf:
             del gen_conf["max_tokens"]
+
+        allowed_conf = {
+            "temperature",
+            "max_completion_tokens",
+            "top_p",
+            "stream",
+            "stream_options",
+            "stop",
+            "n",
+            "presence_penalty",
+            "frequency_penalty",
+            "functions",
+            "function_call",
+            "logit_bias",
+            "user",
+            "response_format",
+            "seed",
+            "tools",
+            "tool_choice",
+            "logprobs",
+            "top_logprobs",
+            "extra_headers",
+        }
+
+        gen_conf = {k: v for k, v in gen_conf.items() if k in allowed_conf}
+
         return gen_conf
 
     def _chat(self, history, gen_conf, **kwargs):
@@ -657,73 +682,6 @@ class ZhipuChat(Base):
         return super().chat_streamly_with_tools(system, history, gen_conf)
 
 
-class OllamaChat(Base):
-    _FACTORY_NAME = "Ollama"
-
-    def __init__(self, key, model_name, base_url=None, **kwargs):
-        super().__init__(key, model_name, base_url=base_url, **kwargs)
-
-        self.client = Client(host=base_url) if not key or key == "x" else Client(host=base_url, headers={"Authorization": f"Bearer {key}"})
-        self.model_name = model_name
-        self.keep_alive = kwargs.get("ollama_keep_alive", int(os.environ.get("OLLAMA_KEEP_ALIVE", -1)))
-
-    def _clean_conf(self, gen_conf):
-        options = {}
-        if "max_tokens" in gen_conf:
-            options["num_predict"] = gen_conf["max_tokens"]
-        for k in ["temperature", "top_p", "presence_penalty", "frequency_penalty"]:
-            if k not in gen_conf:
-                continue
-            options[k] = gen_conf[k]
-        return options
-
-    def _chat(self, history, gen_conf={}, **kwargs):
-        # Calculate context size
-        ctx_size = self._calculate_dynamic_ctx(history)
-
-        gen_conf["num_ctx"] = ctx_size
-        response = self.client.chat(model=self.model_name, messages=history, options=gen_conf, keep_alive=self.keep_alive)
-        ans = response["message"]["content"].strip()
-        token_count = response.get("eval_count", 0) + response.get("prompt_eval_count", 0)
-        return ans, token_count
-
-    def chat_streamly(self, system, history, gen_conf={}, **kwargs):
-        if system:
-            history.insert(0, {"role": "system", "content": system})
-        if "max_tokens" in gen_conf:
-            del gen_conf["max_tokens"]
-        try:
-            # Calculate context size
-            ctx_size = self._calculate_dynamic_ctx(history)
-            options = {"num_ctx": ctx_size}
-            if "temperature" in gen_conf:
-                options["temperature"] = gen_conf["temperature"]
-            if "max_tokens" in gen_conf:
-                options["num_predict"] = gen_conf["max_tokens"]
-            if "top_p" in gen_conf:
-                options["top_p"] = gen_conf["top_p"]
-            if "presence_penalty" in gen_conf:
-                options["presence_penalty"] = gen_conf["presence_penalty"]
-            if "frequency_penalty" in gen_conf:
-                options["frequency_penalty"] = gen_conf["frequency_penalty"]
-
-            ans = ""
-            try:
-                response = self.client.chat(model=self.model_name, messages=history, stream=True, options=options, keep_alive=self.keep_alive)
-                for resp in response:
-                    if resp["done"]:
-                        token_count = resp.get("prompt_eval_count", 0) + resp.get("eval_count", 0)
-                        yield token_count
-                    ans = resp["message"]["content"]
-                    yield ans
-            except Exception as e:
-                yield ans + "\n**ERROR**: " + str(e)
-            yield 0
-        except Exception as e:
-            yield "**ERROR**: " + str(e)
-            yield 0
-
-
 class LocalAIChat(Base):
     _FACTORY_NAME = "LocalAI"
 
@@ -1396,7 +1354,7 @@ class Ai302Chat(Base):
 
 
 class LiteLLMBase(ABC):
-    _FACTORY_NAME = ["Tongyi-Qianwen", "Bedrock", "Moonshot", "xAI", "DeepInfra", "Groq", "Cohere", "Gemini", "DeepSeek", "NVIDIA", "TogetherAI", "Anthropic"]
+    _FACTORY_NAME = ["Tongyi-Qianwen", "Bedrock", "Moonshot", "xAI", "DeepInfra", "Groq", "Cohere", "Gemini", "DeepSeek", "NVIDIA", "TogetherAI", "Anthropic", "Ollama"]
 
     def __init__(self, key, model_name, base_url=None, **kwargs):
         self.timeout = int(os.environ.get("LM_TIMEOUT_SECONDS", 600))

rag/prompts/prompts.py

@@ -114,6 +114,8 @@ def kb_prompt(kbinfos, max_tokens, hash_id=False):
     docs = {d.id: d.meta_fields for d in docs}
 
     def draw_node(k, line):
+        if line is not None and not isinstance(line, str):
+            line = str(line)
         if not line:
             return ""
         return f"\n├── {k}: " + re.sub(r"\n+", " ", line, flags=re.DOTALL)

rag/raptor.py

@@ -42,9 +42,12 @@ class RecursiveAbstractiveProcessing4TreeOrganizedRetrieval:
         self._prompt = prompt
         self._max_token = max_token
 
-    @timeout(60)
+    @timeout(60*20)
     async def _chat(self, system, history, gen_conf):
-        response = get_llm_cache(self._llm_model.llm_name, system, history, gen_conf)
+        response = await trio.to_thread.run_sync(
+            lambda: get_llm_cache(self._llm_model.llm_name, system, history, gen_conf)
+        )
+
         if response:
             return response
         response = await trio.to_thread.run_sync(
@@ -53,19 +56,23 @@ class RecursiveAbstractiveProcessing4TreeOrganizedRetrieval:
         response = re.sub(r"^.*</think>", "", response, flags=re.DOTALL)
         if response.find("**ERROR**") >= 0:
             raise Exception(response)
-        set_llm_cache(self._llm_model.llm_name, system, response, history, gen_conf)
+        await trio.to_thread.run_sync(
+            lambda: set_llm_cache(self._llm_model.llm_name, system, response, history, gen_conf)
+        )
         return response
 
-    @timeout(2)
+    @timeout(20)
     async def _embedding_encode(self, txt):
-        response = get_embed_cache(self._embd_model.llm_name, txt)
+        response = await trio.to_thread.run_sync(
+            lambda: get_embed_cache(self._embd_model.llm_name, txt)
+        )
         if response is not None:
             return response
         embds, _ = await trio.to_thread.run_sync(lambda: self._embd_model.encode([txt]))
         if len(embds) < 1 or len(embds[0]) < 1:
             raise Exception("Embedding error: ")
         embds = embds[0]
-        set_embed_cache(self._embd_model.llm_name, txt, embds)
+        await trio.to_thread.run_sync(lambda: set_embed_cache(self._embd_model.llm_name, txt, embds))
         return embds
 
     def _get_optimal_clusters(self, embeddings: np.ndarray, random_state: int):
@@ -86,7 +93,7 @@ class RecursiveAbstractiveProcessing4TreeOrganizedRetrieval:
         layers = [(0, len(chunks))]
         start, end = 0, len(chunks)
 
-        @timeout(60)
+        @timeout(60*20)
         async def summarize(ck_idx: list[int]):
             nonlocal chunks
             texts = [chunks[i][0] for i in ck_idx]

rag/svr/task_executor.py

@@ -21,7 +21,7 @@ import sys
 import threading
 import time
 
-from api.utils.api_utils import timeout, is_strong_enough
+from api.utils.api_utils import timeout
 from api.utils.log_utils import init_root_logger, get_project_base_directory
 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
@@ -478,8 +478,6 @@ async def embedding(docs, mdl, parser_config=None, callback=None):
 
 @timeout(3600)
 async def run_raptor(row, chat_mdl, embd_mdl, vector_size, callback=None):
-    # Pressure test for GraphRAG task
-    await is_strong_enough(chat_mdl, embd_mdl)
     chunks = []
     vctr_nm = "q_%d_vec"%vector_size
     for d in settings.retrievaler.chunk_list(row["doc_id"], row["tenant_id"], [str(row["kb_id"])],
@@ -553,7 +551,6 @@ async def do_handle_task(task):
     try:
         # bind embedding model
         embedding_model = LLMBundle(task_tenant_id, LLMType.EMBEDDING, llm_name=task_embedding_id, lang=task_language)
-        await is_strong_enough(None, embedding_model)
         vts, _ = embedding_model.encode(["ok"])
         vector_size = len(vts[0])
     except Exception as e:
@@ -568,7 +565,6 @@ async def do_handle_task(task):
     if task.get("task_type", "") == "raptor":
         # bind LLM for raptor
         chat_model = LLMBundle(task_tenant_id, LLMType.CHAT, llm_name=task_llm_id, lang=task_language)
-        await is_strong_enough(chat_model, None)
         # run RAPTOR
         async with kg_limiter:
             chunks, token_count = await run_raptor(task, chat_model, embedding_model, vector_size, progress_callback)
@@ -580,7 +576,6 @@ async def do_handle_task(task):
         graphrag_conf = task["kb_parser_config"].get("graphrag", {})
         start_ts = timer()
         chat_model = LLMBundle(task_tenant_id, LLMType.CHAT, llm_name=task_llm_id, lang=task_language)
-        await is_strong_enough(chat_model, None)
         with_resolution = graphrag_conf.get("resolution", False)
         with_community = graphrag_conf.get("community", False)
         async with kg_limiter:

sandbox/executor_manager/core/config.py

@@ -22,7 +22,7 @@ from util import format_timeout_duration, parse_timeout_duration
 from core.container import init_containers, teardown_containers
 from core.logger import logger
 
-TIMEOUT = 10
+TIMEOUT = parse_timeout_duration(os.getenv("SANDBOX_TIMEOUT", "10s"))
 
 
 @asynccontextmanager
@@ -39,6 +39,5 @@ async def _lifespan(app: FastAPI):
 
 
 def init():
-    TIMEOUT = parse_timeout_duration(os.getenv("SANDBOX_TIMEOUT"))
     logger.info(f"Global timeout: {format_timeout_duration(TIMEOUT)}")
     return _lifespan

uv.lock

@@ -2603,7 +2603,7 @@ wheels = [
 
 [[package]]
 name = "infinity-sdk"
-version = "0.6.0.dev4"
+version = "0.6.0.dev5"
 source = { registry = "https://mirrors.aliyun.com/pypi/simple" }
 dependencies = [
     { name = "numpy" },
@@ -2620,7 +2620,7 @@ dependencies = [
     { name = "thrift" },
 ]
 wheels = [
-    { url = "https://mirrors.aliyun.com/pypi/packages/d4/cc/645ed8de15952940c7308a788036376583a5fc29fdcf3e4bc75b5ad0c881/infinity_sdk-0.6.0.dev4-py3-none-any.whl", hash = "sha256:f8f4bd8a44e3fae7b4228b5c9e9a16559b4905f50d2d7d0a3d18f39974613e7a" },
+    { url = "https://mirrors.aliyun.com/pypi/packages/fe/a4/6079bf9790f16badc01e7b79a28c90bec407cfcaa8a2ed37e4a68120f87a/infinity_sdk-0.6.0.dev5-py3-none-any.whl", hash = "sha256:510ac408d5cd9d3d4df33c7c0877f55c5ae8a6019e465190c86d58012a319179" },
 ]
 
 [[package]]
@@ -5471,7 +5471,7 @@ requires-dist = [
     { name = "httpx", extras = ["socks"], specifier = "==0.27.2" },
     { name = "huggingface-hub", specifier = ">=0.25.0,<0.26.0" },
     { name = "infinity-emb", specifier = ">=0.0.66,<0.0.67" },
-    { name = "infinity-sdk", specifier = "==0.6.0.dev4" },
+    { name = "infinity-sdk", specifier = "==0.6.0.dev5" },
     { name = "itsdangerous", specifier = "==2.1.2" },
     { name = "json-repair", specifier = "==0.35.0" },
     { name = "langfuse", specifier = ">=2.60.0" },

web/.eslintrc.js

@@ -14,7 +14,7 @@ module.exports = {
       'error',
       {
         '**/*.{jsx,tsx}': 'KEBAB_CASE',
-        '**/*.{js,ts}': 'KEBAB_CASE',
+        '**/*.{js,ts}': '[a-z0-9.-]*',
       },
     ],
     'check-file/folder-naming-convention': [

web/src/app.tsx

@@ -2,7 +2,6 @@ import { Toaster as Sonner } from '@/components/ui/sonner';
 import { Toaster } from '@/components/ui/toaster';
 import i18n from '@/locales/config';
 import { QueryClient, QueryClientProvider } from '@tanstack/react-query';
-import { ReactQueryDevtools } from '@tanstack/react-query-devtools';
 import { App, ConfigProvider, ConfigProviderProps, theme } from 'antd';
 import pt_BR from 'antd/lib/locale/pt_BR';
 import deDE from 'antd/locale/de_DE';
@@ -85,7 +84,7 @@ function Root({ children }: React.PropsWithChildren) {
         <Sonner position={'top-right'} expand richColors closeButton></Sonner>
         <Toaster />
       </ConfigProvider>
-      <ReactQueryDevtools buttonPosition={'top-left'} />
+      {/* <ReactQueryDevtools buttonPosition={'top-left'} initialIsOpen={false} /> */}
     </>
   );
 }

web/src/components/file-upload-dialog/index.tsx

@@ -8,47 +8,93 @@ import {
 } from '@/components/ui/dialog';
 import { Tabs, TabsContent, TabsList, TabsTrigger } from '@/components/ui/tabs';
 import { IModalProps } from '@/interfaces/common';
-import { Dispatch, SetStateAction, useCallback, useState } from 'react';
+import { zodResolver } from '@hookform/resolvers/zod';
+import { TFunction } from 'i18next';
+import { useForm } from 'react-hook-form';
 import { useTranslation } from 'react-i18next';
+import { z } from 'zod';
 import { FileUploader } from '../file-uploader';
+import { RAGFlowFormItem } from '../ragflow-form';
+import { Form } from '../ui/form';
+import { Switch } from '../ui/switch';
 
-type UploaderTabsProps = {
+function buildUploadFormSchema(t: TFunction) {
-  setFiles: Dispatch<SetStateAction<File[]>>;
+  const FormSchema = z.object({
+    parseOnCreation: z.boolean().optional(),
+    fileList: z
+      .array(z.instanceof(File))
+      .min(1, { message: t('fileManager.pleaseUploadAtLeastOneFile') }),
+  });
+
+  return FormSchema;
+}
+
+export type UploadFormSchemaType = z.infer<
+  ReturnType<typeof buildUploadFormSchema>
+>;
+
+const UploadFormId = 'UploadFormId';
+
+type UploadFormProps = {
+  submit: (values?: UploadFormSchemaType) => void;
+  showParseOnCreation?: boolean;
 };
-
+function UploadForm({ submit, showParseOnCreation }: UploadFormProps) {
-export function UploaderTabs({ setFiles }: UploaderTabsProps) {
   const { t } = useTranslation();
+  const FormSchema = buildUploadFormSchema(t);
+
+  type UploadFormSchemaType = z.infer<typeof FormSchema>;
+  const form = useForm<UploadFormSchemaType>({
+    resolver: zodResolver(FormSchema),
+    defaultValues: {
+      parseOnCreation: false,
+      fileList: [],
+    },
+  });
 
   return (
-    <Tabs defaultValue="account">
+    <Form {...form}>
-      <TabsList className="grid w-full grid-cols-2 mb-4">
+      <form
-        <TabsTrigger value="account">{t('fileManager.local')}</TabsTrigger>
+        onSubmit={form.handleSubmit(submit)}
-        <TabsTrigger value="password">{t('fileManager.s3')}</TabsTrigger>
+        id={UploadFormId}
-      </TabsList>
+        className="space-y-4"
-      <TabsContent value="account">
+      >
-        <FileUploader
+        {showParseOnCreation && (
-          maxFileCount={8}
+          <RAGFlowFormItem
-          maxSize={8 * 1024 * 1024}
+            name="parseOnCreation"
-          onValueChange={setFiles}
+            label={t('fileManager.parseOnCreation')}
-          accept={{ '*': [] }}
+          >
-        />
+            {(field) => (
-      </TabsContent>
+              <Switch
-      <TabsContent value="password">{t('common.comingSoon')}</TabsContent>
+                onCheckedChange={field.onChange}
-    </Tabs>
+                checked={field.value}
+              ></Switch>
+            )}
+          </RAGFlowFormItem>
+        )}
+        <RAGFlowFormItem name="fileList" label={t('fileManager.file')}>
+          {(field) => (
+            <FileUploader
+              value={field.value}
+              onValueChange={field.onChange}
+              accept={{ '*': [] }}
+            />
+          )}
+        </RAGFlowFormItem>
+      </form>
+    </Form>
   );
 }
 
+type FileUploadDialogProps = IModalProps<UploadFormSchemaType> &
+  Pick<UploadFormProps, 'showParseOnCreation'>;
 export function FileUploadDialog({
   hideModal,
   onOk,
   loading,
-}: IModalProps<File[]>) {
+  showParseOnCreation = false,
+}: FileUploadDialogProps) {
   const { t } = useTranslation();
-  const [files, setFiles] = useState<File[]>([]);
-
-  const handleOk = useCallback(() => {
-    onOk?.(files);
-  }, [files, onOk]);
 
   return (
     <Dialog open onOpenChange={hideModal}>
@@ -56,9 +102,21 @@ export function FileUploadDialog({
         <DialogHeader>
           <DialogTitle>{t('fileManager.uploadFile')}</DialogTitle>
         </DialogHeader>
-        <UploaderTabs setFiles={setFiles}></UploaderTabs>
+        <Tabs defaultValue="account">
+          <TabsList className="grid w-full grid-cols-2 mb-4">
+            <TabsTrigger value="account">{t('fileManager.local')}</TabsTrigger>
+            <TabsTrigger value="password">{t('fileManager.s3')}</TabsTrigger>
+          </TabsList>
+          <TabsContent value="account">
+            <UploadForm
+              submit={onOk!}
+              showParseOnCreation={showParseOnCreation}
+            ></UploadForm>
+          </TabsContent>
+          <TabsContent value="password">{t('common.comingSoon')}</TabsContent>
+        </Tabs>
         <DialogFooter>
-          <ButtonLoading type="submit" onClick={handleOk} loading={loading}>
+          <ButtonLoading type="submit" loading={loading} form={UploadFormId}>
             {t('common.save')}
           </ButtonLoading>
         </DialogFooter>

web/src/components/file-uploader.tsx

@@ -15,6 +15,7 @@ import { Progress } from '@/components/ui/progress';
 import { ScrollArea } from '@/components/ui/scroll-area';
 import { useControllableState } from '@/hooks/use-controllable-state';
 import { cn, formatBytes } from '@/lib/utils';
+import { useTranslation } from 'react-i18next';
 
 function isFileWithPreview(file: File): file is File & { preview: string } {
   return 'preview' in file && typeof file.preview === 'string';
@@ -168,14 +169,14 @@ export function FileUploader(props: FileUploaderProps) {
     accept = {
       'image/*': [],
     },
-    maxSize = 1024 * 1024 * 2,
+    maxSize = 1024 * 1024 * 10000000,
-    maxFileCount = 1,
+    maxFileCount = 100000000000,
     multiple = false,
     disabled = false,
     className,
     ...dropzoneProps
   } = props;
-
+  const { t } = useTranslation();
   const [files, setFiles] = useControllableState({
     prop: valueProp,
     onChange: onValueChange,
@@ -267,7 +268,7 @@ export function FileUploader(props: FileUploaderProps) {
           <div
             {...getRootProps()}
             className={cn(
-              'group relative grid h-52 w-full cursor-pointer place-items-center rounded-lg border-2 border-dashed border-muted-foreground/25 px-5 py-2.5 text-center transition hover:bg-muted/25',
+              'group relative grid h-72 w-full cursor-pointer place-items-center rounded-lg border-2 border-dashed border-muted-foreground/25 px-5 py-2.5 text-center transition hover:bg-muted/25',
               'ring-offset-background focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-ring focus-visible:ring-offset-2',
               isDragActive && 'border-muted-foreground/50',
               isDisabled && 'pointer-events-none opacity-60',
@@ -298,14 +299,15 @@ export function FileUploader(props: FileUploaderProps) {
                 </div>
                 <div className="flex flex-col gap-px">
                   <p className="font-medium text-muted-foreground">
-                    Drag {`'n'`} drop files here, or click to select files
+                    {t('knowledgeDetails.uploadTitle')}
                   </p>
                   <p className="text-sm text-muted-foreground/70">
-                    You can upload
+                    {t('knowledgeDetails.uploadDescription')}
+                    {/* You can upload
                     {maxFileCount > 1
                       ? ` ${maxFileCount === Infinity ? 'multiple' : maxFileCount}
                       files (up to ${formatBytes(maxSize)} each)`
-                      : ` a file with ${formatBytes(maxSize)}`}
+                      : ` a file with ${formatBytes(maxSize)}`} */}
                   </p>
                 </div>
               </div>

web/src/components/home-card.tsx

@@ -1,6 +1,7 @@
 import { RAGFlowAvatar } from '@/components/ragflow-avatar';
 import { Card, CardContent } from '@/components/ui/card';
 import { formatDate } from '@/utils/date';
+import { ReactNode } from 'react';
 
 interface IProps {
   data: {
@@ -11,8 +12,9 @@ interface IProps {
   };
   onClick?: () => void;
   moreDropdown: React.ReactNode;
+  sharedBadge?: ReactNode;
 }
-export function HomeCard({ data, onClick, moreDropdown }: IProps) {
+export function HomeCard({ data, onClick, moreDropdown, sharedBadge }: IProps) {
   return (
     <Card
       className="bg-bg-card  border-colors-outline-neutral-standard"
@@ -31,7 +33,7 @@ export function HomeCard({ data, onClick, moreDropdown }: IProps) {
         </div>
         <div className="flex flex-col justify-between gap-1 flex-1 h-full w-[calc(100%-50px)]">
           <section className="flex justify-between">
-            <div className="text-[20px] font-bold w-80% leading-5">
+            <div className="text-[20px] font-bold w-80% leading-5 text-ellipsis overflow-hidden">
               {data.name}
             </div>
             {moreDropdown}
@@ -41,10 +43,11 @@ export function HomeCard({ data, onClick, moreDropdown }: IProps) {
             <div className="whitespace-nowrap overflow-hidden text-ellipsis">
               {data.description}
             </div>
-            <div>
+            <div className="flex justify-between items-center">
               <p className="text-sm opacity-80">
                 {formatDate(data.update_time)}
               </p>
+              {sharedBadge}
             </div>
           </section>
         </div>

web/src/components/layout-recognize-form-field.tsx

@@ -68,7 +68,7 @@ export function LayoutRecognizeFormField() {
             <div className="flex items-center">
               <FormLabel
                 tooltip={t('layoutRecognizeTip')}
-                className="text-sm text-muted-foreground whitespace-nowrap w-1/4"
+                className="text-sm text-muted-foreground whitespace-wrap w-1/4"
               >
                 {t('layoutRecognize')}
               </FormLabel>

web/src/components/list-filter-bar/index.tsx

@@ -1,5 +1,5 @@
 import { cn } from '@/lib/utils';
-import { ChevronDown } from 'lucide-react';
+import { Funnel } from 'lucide-react';
 import React, {
   ChangeEventHandler,
   PropsWithChildren,
@@ -25,20 +25,20 @@ export const FilterButton = React.forwardRef<
 >(({ count = 0, ...props }, ref) => {
   return (
     <Button variant="secondary" {...props} ref={ref}>
-      <span
+      {/* <span
         className={cn({
           'text-text-primary': count > 0,
           'text-text-sub-title-invert': count === 0,
         })}
       >
         Filter
-      </span>
+      </span> */}
       {count > 0 && (
         <span className="rounded-full bg-text-badge px-1 text-xs ">
           {count}
         </span>
       )}
-      <ChevronDown />
+      <Funnel />
     </Button>
   );
 });

web/src/components/llm-select/next.tsx

@@ -2,6 +2,7 @@ import { LlmModelType } from '@/constants/knowledge';
 import { useComposeLlmOptionsByModelTypes } from '@/hooks/llm-hooks';
 import * as SelectPrimitive from '@radix-ui/react-select';
 import { forwardRef, memo, useMemo, useState } from 'react';
+import { useTranslation } from 'react-i18next';
 import { LlmSettingFieldItems } from '../llm-setting-items/next';
 import { Popover, PopoverContent, PopoverTrigger } from '../ui/popover';
 import { Select, SelectTrigger, SelectValue } from '../ui/select';
@@ -20,6 +21,7 @@ const NextInnerLLMSelect = forwardRef<
   React.ElementRef<typeof SelectPrimitive.Trigger>,
   NextInnerLLMSelectProps
 >(({ value, disabled, filter, showSpeech2TextModel = false }, ref) => {
+  const { t } = useTranslation();
   const [isPopoverOpen, setIsPopoverOpen] = useState(false);
 
   const ttsModel = useMemo(() => {
@@ -49,7 +51,7 @@ const NextInnerLLMSelect = forwardRef<
             }}
             ref={ref}
           >
-            <SelectValue>
+            <SelectValue placeholder={t('common.pleaseSelect')}>
               {
                 modelOptions
                   .flatMap((x) => x.options)

web/src/components/llm-setting-items/slider.tsx

@@ -19,6 +19,7 @@ type SliderInputSwitchFormFieldProps = {
   name: string;
   label: string;
   defaultValue?: number;
+  onChange?: (value: number) => void;
   className?: string;
   checkName: string;
 };
@@ -30,6 +31,7 @@ export function SliderInputSwitchFormField({
   label,
   name,
   defaultValue,
+  onChange,
   className,
   checkName,
 }: SliderInputSwitchFormFieldProps) {
@@ -66,6 +68,10 @@ export function SliderInputSwitchFormField({
             <FormControl>
               <SingleFormSlider
                 {...field}
+                onChange={(value: number) => {
+                  onChange?.(value);
+                  field.onChange(value);
+                }}
                 max={max}
                 min={min}
                 step={step}
@@ -80,6 +86,10 @@ export function SliderInputSwitchFormField({
                 min={min}
                 step={step}
                 {...field}
+                onChange={(value: number) => {
+                  onChange?.(value);
+                  field.onChange(value);
+                }}
               ></NumberInput>
             </FormControl>
           </div>

web/src/components/metadata-filter/index.tsx

@@ -58,7 +58,10 @@ export function MetadataFilter({ prefix = '' }: MetadataFilterProps) {
           name={methodName}
           tooltip={t('metadataTip')}
         >
-          <SelectWithSearch options={MetadataOptions} />
+          <SelectWithSearch
+            options={MetadataOptions}
+            triggerClassName="!bg-bg-input"
+          />
         </RAGFlowFormItem>
       )}
       {hasKnowledge && metadata === DatasetMetadata.Manual && (

web/src/components/originui/select-with-search.tsx

@@ -28,6 +28,7 @@ import {
   PopoverTrigger,
 } from '@/components/ui/popover';
 import { cn } from '@/lib/utils';
+import { t } from 'i18next';
 import { RAGFlowSelectOptionType } from '../ui/select';
 import { Separator } from '../ui/separator';
 
@@ -114,7 +115,9 @@ export const SelectWithSearch = forwardRef<
                 <span className="leading-none truncate">{selectLabel}</span>
               </span>
             ) : (
-              <span className="text-muted-foreground">Select value</span>
+              <span className="text-muted-foreground">
+                {t('common.selectPlaceholder')}
+              </span>
             )}
             <div className="flex items-center justify-between">
               {value && allowClear && (

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

@@ -3,7 +3,7 @@ import { DocumentParserType } from '@/constants/knowledge';
 import { useTranslate } from '@/hooks/common-hooks';
 import random from 'lodash/random';
 import { Plus } from 'lucide-react';
-import { useCallback, useEffect } from 'react';
+import { useCallback } from 'react';
 import { useFormContext, useWatch } from 'react-hook-form';
 import { SliderInputFormField } from '../slider-input-form-field';
 import { Button } from '../ui/button';
@@ -57,15 +57,19 @@ const RaptorFormFields = () => {
   const form = useFormContext();
   const { t } = useTranslate('knowledgeConfiguration');
   const useRaptor = useWatch({ name: UseRaptorField });
-  useEffect(() => {
+
-    if (useRaptor) {
+  const changeRaptor = useCallback(
-      form.setValue(MaxTokenField, 256);
+    (isUseRaptor: boolean) => {
-      form.setValue(ThresholdField, 0.1);
+      if (isUseRaptor) {
-      form.setValue(MaxCluster, 64);
+        form.setValue(MaxTokenField, 256);
-      form.setValue(RandomSeedField, 0);
+        form.setValue(ThresholdField, 0.1);
-      form.setValue(Prompt, t('promptText'));
+        form.setValue(MaxCluster, 64);
-    }
+        form.setValue(RandomSeedField, 0);
-  }, [form, useRaptor, t]);
+        form.setValue(Prompt, t('promptText'));
+      }
+    },
+    [form],
+  );
 
   const handleGenerate = useCallback(() => {
     form.setValue(RandomSeedField, random(10000));
@@ -97,7 +101,10 @@ const RaptorFormFields = () => {
                   <FormControl>
                     <Switch
                       checked={field.value}
-                      onCheckedChange={field.onChange}
+                      onCheckedChange={(e) => {
+                        changeRaptor(e);
+                        field.onChange(e);
+                      }}
                     ></Switch>
                   </FormControl>
                 </div>
@@ -127,7 +134,13 @@ const RaptorFormFields = () => {
                     </FormLabel>
                     <div className="w-3/4">
                       <FormControl>
-                        <Textarea {...field} rows={8} />
+                        <Textarea
+                          {...field}
+                          rows={8}
+                          onChange={(e) => {
+                            field.onChange(e?.target?.value);
+                          }}
+                        />
                       </FormControl>
                     </div>
                   </div>

web/src/components/ragflow-form.tsx

@@ -5,6 +5,7 @@ import {
   FormLabel,
   FormMessage,
 } from '@/components/ui/form';
+import { cn } from '@/lib/utils';
 import { ReactNode, cloneElement, isValidElement } from 'react';
 import { ControllerRenderProps, useFormContext } from 'react-hook-form';
 
@@ -13,6 +14,7 @@ type RAGFlowFormItemProps = {
   label: ReactNode;
   tooltip?: ReactNode;
   children: ReactNode | ((field: ControllerRenderProps) => ReactNode);
+  horizontal?: boolean;
 };
 
 export function RAGFlowFormItem({
@@ -20,6 +22,7 @@ export function RAGFlowFormItem({
   label,
   tooltip,
   children,
+  horizontal = false,
 }: RAGFlowFormItemProps) {
   const form = useFormContext();
   return (
@@ -27,8 +30,14 @@ export function RAGFlowFormItem({
       control={form.control}
       name={name}
       render={({ field }) => (
-        <FormItem>
+        <FormItem
-          <FormLabel tooltip={tooltip}>{label}</FormLabel>
+          className={cn({
+            'flex items-center': horizontal,
+          })}
+        >
+          <FormLabel tooltip={tooltip} className={cn({ 'w-1/4': horizontal })}>
+            {label}
+          </FormLabel>
           <FormControl>
             {typeof children === 'function'
               ? children(field)

web/src/components/shared-badge.tsx

@@ -8,9 +8,5 @@ export function SharedBadge({ children }: PropsWithChildren) {
     return null;
   }
 
-  return (
+  return <span className="bg-bg-card rounded-sm px-1 text-xs">{children}</span>;
-    <span className="bg-text-secondary rounded-sm px-1 text-bg-base text-xs">
-      {children}
-    </span>
-  );
 }

web/src/components/ui/button.tsx

@@ -17,7 +17,7 @@ const buttonVariants = cva(
         outline:
           'border bg-background shadow-xs hover:bg-accent hover:text-accent-foreground dark:bg-input/30 dark:border-input dark:hover:bg-input/50',
         secondary:
-          'bg-secondary text-secondary-foreground shadow-xs hover:bg-secondary/80',
+          'bg-bg-input text-secondary-foreground shadow-xs hover:bg-bg-input/80',
         ghost:
           'hover:bg-accent hover:text-accent-foreground dark:hover:bg-accent/50',
         link: 'text-primary underline-offset-4 hover:underline',

web/src/components/ui/input.tsx

@@ -116,7 +116,10 @@ export { ExpandedInput, Input, SearchInput };
 
 type NumberInputProps = { onChange?(value: number): void } & InputProps;
 
-export const NumberInput = ({ onChange, ...props }: NumberInputProps) => {
+export const NumberInput = React.forwardRef<
+  HTMLInputElement,
+  NumberInputProps & { value: Value; onChange(value: Value): void }
+>(function NumberInput({ onChange, ...props }, ref) {
   return (
     <Input
       type="number"
@@ -125,6 +128,7 @@ export const NumberInput = ({ onChange, ...props }: NumberInputProps) => {
         onChange?.(value === '' ? 0 : Number(value)); // convert to number
       }}
       {...props}
+      ref={ref}
     ></Input>
   );
-};
+});

web/src/components/ui/multi-select.tsx

@@ -209,8 +209,16 @@ export const MultiSelect = React.forwardRef<
     const [isAnimating, setIsAnimating] = React.useState(false);
 
     React.useEffect(() => {
-      setSelectedValues(defaultValue);
+      if (!selectedValues && props.value) {
-    }, [defaultValue]);
+        setSelectedValues(props.value as string[]);
+      }
+    }, [props.value, selectedValues]);
+
+    React.useEffect(() => {
+      if (!selectedValues && !props.value && defaultValue) {
+        setSelectedValues(defaultValue);
+      }
+    }, [defaultValue, props.value, selectedValues]);
 
     const flatOptions = React.useMemo(() => {
       return options.flatMap((option) =>
@@ -291,15 +299,18 @@ export const MultiSelect = React.forwardRef<
                         variant="secondary"
                         className={cn(
                           isAnimating ? 'animate-bounce' : '',
+                          'px-1',
                           multiSelectVariants({ variant }),
                         )}
                         style={{ animationDuration: `${animation}s` }}
                       >
-                        <div className="flex items-center gap-1">
+                        <div className="flex justify-between items-center gap-1">
                           {IconComponent && (
                             <IconComponent className="h-4 w-4" />
                           )}
-                          <div>{option?.label}</div>
+                          <div className="max-w-28 text-ellipsis overflow-hidden">
+                            {option?.label}
+                          </div>
                           <XCircle
                             className="h-4 w-4 cursor-pointer"
                             onClick={(event) => {

web/src/components/ui/progress.tsx

@@ -12,13 +12,13 @@ const Progress = React.forwardRef<
   <ProgressPrimitive.Root
     ref={ref}
     className={cn(
-      'relative h-4 w-full overflow-hidden rounded-full bg-secondary',
+      'relative h-4 w-full overflow-hidden rounded-full bg-bg-accent',
       className,
     )}
     {...props}
   >
     <ProgressPrimitive.Indicator
-      className="h-full w-full flex-1 bg-primary transition-all"
+      className="h-full w-full flex-1 bg-accent-primary transition-all"
       style={{ transform: `translateX(-${100 - (value || 0)}%)` }}
     />
   </ProgressPrimitive.Root>

web/src/components/ui/segmented.tsx

@@ -23,6 +23,7 @@ export interface SegmentedProps
   prefixCls?: string;
   direction?: 'ltr' | 'rtl';
   motionName?: string;
+  activeClassName?: string;
 }
 
 export function Segmented({
@@ -30,6 +31,7 @@ export function Segmented({
   value,
   onChange,
   className,
+  activeClassName,
 }: SegmentedProps) {
   const [selectedValue, setSelectedValue] = React.useState<
     SegmentedValue | undefined
@@ -57,9 +59,12 @@ export function Segmented({
             className={cn(
               'inline-flex items-center px-6 py-2 text-base font-normal rounded-3xl cursor-pointer',
               {
-                'bg-text-primary': selectedValue === actualValue,
+                'text-bg-base bg-metallic-gradient border-b-[#00BEB4] border-b-2':
-                'text-bg-base': selectedValue === actualValue,
+                  selectedValue === actualValue,
               },
+              activeClassName && selectedValue === actualValue
+                ? activeClassName
+                : '',
             )}
             onClick={() => handleOnChange(actualValue)}
           >

web/src/components/ui/textarea.tsx

@@ -54,7 +54,7 @@ const Textarea = forwardRef<HTMLTextAreaElement, TextareaProps>(
     return (
       <textarea
         className={cn(
-          'flex min-h-[80px] w-full bg-bg-card rounded-md border border-input px-3 py-2 text-base ring-offset-background placeholder:text-muted-foreground focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-ring focus-visible:ring-offset-2 disabled:cursor-not-allowed disabled:opacity-50 md:text-sm overflow-hidden',
+          'flex min-h-[80px] w-full bg-bg-input rounded-md border border-input px-3 py-2 text-base ring-offset-background placeholder:text-muted-foreground focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-ring focus-visible:ring-offset-2 disabled:cursor-not-allowed disabled:opacity-50 md:text-sm overflow-hidden',
           className,
         )}
         rows={autoSize?.minRows ?? props.rows ?? undefined}

web/src/constants/permission.ts

@@ -0,0 +1,4 @@
+export enum PermissionRole {
+  Me = 'me',
+  Team = 'team',
+}

web/src/hooks/use-document-request.ts

@@ -1,4 +1,5 @@
 import { useHandleFilterSubmit } from '@/components/list-filter-bar/use-handle-filter-submit';
+import { ResponseType } from '@/interfaces/database/base';
 import {
   IDocumentInfo,
   IDocumentInfoFilter,
@@ -45,9 +46,9 @@ export const useUploadNextDocument = () => {
     data,
     isPending: loading,
     mutateAsync,
-  } = useMutation({
+  } = useMutation<ResponseType<IDocumentInfo[]>, Error, File[]>({
     mutationKey: [DocumentApiAction.UploadDocument],
-    mutationFn: async (fileList: File[]) => {
+    mutationFn: async (fileList) => {
       const formData = new FormData();
       formData.append('kb_id', id!);
       fileList.forEach((file: any) => {

web/src/hooks/use-llm-request.ts

@@ -8,9 +8,13 @@ import {
 } from '@/interfaces/database/llm';
 import { buildLlmUuid } from '@/utils/llm-util';
 
+export const enum LLMApiAction {
+  LlmList = 'llmList',
+}
+
 export const useFetchLlmList = (modelType?: LlmModelType) => {
   const { data } = useQuery<IThirdAiModelCollection>({
-    queryKey: ['llmList'],
+    queryKey: [LLMApiAction.LlmList],
     initialData: {},
     queryFn: async () => {
       const { data } = await userService.llm_list({ model_type: modelType });

web/src/hooks/use-user-setting-request.tsx

@@ -0,0 +1,464 @@
+import message from '@/components/ui/message';
+import { LanguageTranslationMap } from '@/constants/common';
+import { ResponseGetType } from '@/interfaces/database/base';
+import { IToken } from '@/interfaces/database/chat';
+import { ITenantInfo } from '@/interfaces/database/knowledge';
+import { ILangfuseConfig } from '@/interfaces/database/system';
+import {
+  ISystemStatus,
+  ITenant,
+  ITenantUser,
+  IUserInfo,
+} from '@/interfaces/database/user-setting';
+import { ISetLangfuseConfigRequestBody } from '@/interfaces/request/system';
+import userService, {
+  addTenantUser,
+  agreeTenant,
+  deleteTenantUser,
+  listTenant,
+  listTenantUser,
+} from '@/services/user-service';
+import { useMutation, useQuery, useQueryClient } from '@tanstack/react-query';
+import { Modal } from 'antd';
+import DOMPurify from 'dompurify';
+import { isEmpty } from 'lodash';
+import { useCallback, useMemo, useState } from 'react';
+import { useTranslation } from 'react-i18next';
+import { history } from 'umi';
+
+export const enum UserSettingApiAction {
+  UserInfo = 'userInfo',
+  TenantInfo = 'tenantInfo',
+  SaveSetting = 'saveSetting',
+  FetchManualSystemTokenList = 'fetchManualSystemTokenList',
+  FetchSystemTokenList = 'fetchSystemTokenList',
+  RemoveSystemToken = 'removeSystemToken',
+  CreateSystemToken = 'createSystemToken',
+  ListTenantUser = 'listTenantUser',
+  AddTenantUser = 'addTenantUser',
+  DeleteTenantUser = 'deleteTenantUser',
+  ListTenant = 'listTenant',
+  AgreeTenant = 'agreeTenant',
+  SetLangfuseConfig = 'setLangfuseConfig',
+  DeleteLangfuseConfig = 'deleteLangfuseConfig',
+  FetchLangfuseConfig = 'fetchLangfuseConfig',
+}
+
+export const useFetchUserInfo = (): ResponseGetType<IUserInfo> => {
+  const { i18n } = useTranslation();
+
+  const { data, isFetching: loading } = useQuery({
+    queryKey: [UserSettingApiAction.UserInfo],
+    initialData: {},
+    gcTime: 0,
+    queryFn: async () => {
+      const { data } = await userService.user_info();
+      if (data.code === 0) {
+        i18n.changeLanguage(
+          LanguageTranslationMap[
+            data.data.language as keyof typeof LanguageTranslationMap
+          ],
+        );
+      }
+      return data?.data ?? {};
+    },
+  });
+
+  return { data, loading };
+};
+
+export const useFetchTenantInfo = (
+  showEmptyModelWarn = false,
+): ResponseGetType<ITenantInfo> => {
+  const { t } = useTranslation();
+  const { data, isFetching: loading } = useQuery({
+    queryKey: [UserSettingApiAction.TenantInfo],
+    initialData: {},
+    gcTime: 0,
+    queryFn: async () => {
+      const { data: res } = await userService.get_tenant_info();
+      if (res.code === 0) {
+        // llm_id is chat_id
+        // asr_id is speech2txt
+        const { data } = res;
+        if (
+          showEmptyModelWarn &&
+          (isEmpty(data.embd_id) || isEmpty(data.llm_id))
+        ) {
+          Modal.warning({
+            title: t('common.warn'),
+            content: (
+              <div
+                dangerouslySetInnerHTML={{
+                  __html: DOMPurify.sanitize(t('setting.modelProvidersWarn')),
+                }}
+              ></div>
+            ),
+            onOk() {
+              history.push('/user-setting/model');
+            },
+          });
+        }
+        data.chat_id = data.llm_id;
+        data.speech2text_id = data.asr_id;
+
+        return data;
+      }
+
+      return res;
+    },
+  });
+
+  return { data, loading };
+};
+
+export const useSelectParserList = (): Array<{
+  value: string;
+  label: string;
+}> => {
+  const { data: tenantInfo } = useFetchTenantInfo(true);
+
+  const parserList = useMemo(() => {
+    const parserArray: Array<string> = tenantInfo?.parser_ids?.split(',') ?? [];
+    return parserArray.map((x) => {
+      const arr = x.split(':');
+      return { value: arr[0], label: arr[1] };
+    });
+  }, [tenantInfo]);
+
+  return parserList;
+};
+
+export const useSaveSetting = () => {
+  const queryClient = useQueryClient();
+  const { t } = useTranslation();
+  const {
+    data,
+    isPending: loading,
+    mutateAsync,
+  } = useMutation({
+    mutationKey: [UserSettingApiAction.SaveSetting],
+    mutationFn: async (
+      userInfo: { new_password: string } | Partial<IUserInfo>,
+    ) => {
+      const { data } = await userService.setting(userInfo);
+      if (data.code === 0) {
+        message.success(t('message.modified'));
+        queryClient.invalidateQueries({ queryKey: ['userInfo'] });
+      }
+      return data?.code;
+    },
+  });
+
+  return { data, loading, saveSetting: mutateAsync };
+};
+
+export const useFetchSystemVersion = () => {
+  const [version, setVersion] = useState('');
+  const [loading, setLoading] = useState(false);
+
+  const fetchSystemVersion = useCallback(async () => {
+    try {
+      setLoading(true);
+      const { data } = await userService.getSystemVersion();
+      if (data.code === 0) {
+        setVersion(data.data);
+        setLoading(false);
+      }
+    } catch (error) {
+      setLoading(false);
+    }
+  }, []);
+
+  return { fetchSystemVersion, version, loading };
+};
+
+export const useFetchSystemStatus = () => {
+  const [systemStatus, setSystemStatus] = useState<ISystemStatus>(
+    {} as ISystemStatus,
+  );
+  const [loading, setLoading] = useState(false);
+
+  const fetchSystemStatus = useCallback(async () => {
+    setLoading(true);
+    const { data } = await userService.getSystemStatus();
+    if (data.code === 0) {
+      setSystemStatus(data.data);
+      setLoading(false);
+    }
+  }, []);
+
+  return {
+    systemStatus,
+    fetchSystemStatus,
+    loading,
+  };
+};
+
+export const useFetchManualSystemTokenList = () => {
+  const {
+    data,
+    isPending: loading,
+    mutateAsync,
+  } = useMutation({
+    mutationKey: [UserSettingApiAction.FetchManualSystemTokenList],
+    mutationFn: async () => {
+      const { data } = await userService.listToken();
+
+      return data?.data ?? [];
+    },
+  });
+
+  return { data, loading, fetchSystemTokenList: mutateAsync };
+};
+
+export const useFetchSystemTokenList = () => {
+  const {
+    data,
+    isFetching: loading,
+    refetch,
+  } = useQuery<IToken[]>({
+    queryKey: [UserSettingApiAction.FetchSystemTokenList],
+    initialData: [],
+    gcTime: 0,
+    queryFn: async () => {
+      const { data } = await userService.listToken();
+
+      return data?.data ?? [];
+    },
+  });
+
+  return { data, loading, refetch };
+};
+
+export const useRemoveSystemToken = () => {
+  const queryClient = useQueryClient();
+  const { t } = useTranslation();
+
+  const {
+    data,
+    isPending: loading,
+    mutateAsync,
+  } = useMutation({
+    mutationKey: [UserSettingApiAction.RemoveSystemToken],
+    mutationFn: async (token: string) => {
+      const { data } = await userService.removeToken({}, token);
+      if (data.code === 0) {
+        message.success(t('message.deleted'));
+        queryClient.invalidateQueries({
+          queryKey: [UserSettingApiAction.FetchSystemTokenList],
+        });
+      }
+      return data?.data ?? [];
+    },
+  });
+
+  return { data, loading, removeToken: mutateAsync };
+};
+
+export const useCreateSystemToken = () => {
+  const queryClient = useQueryClient();
+
+  const {
+    data,
+    isPending: loading,
+    mutateAsync,
+  } = useMutation({
+    mutationKey: [UserSettingApiAction.CreateSystemToken],
+    mutationFn: async (params: Record<string, any>) => {
+      const { data } = await userService.createToken(params);
+      if (data.code === 0) {
+        queryClient.invalidateQueries({
+          queryKey: [UserSettingApiAction.FetchSystemTokenList],
+        });
+      }
+      return data?.data ?? [];
+    },
+  });
+
+  return { data, loading, createToken: mutateAsync };
+};
+
+export const useListTenantUser = () => {
+  const { data: tenantInfo } = useFetchTenantInfo();
+  const tenantId = tenantInfo.tenant_id;
+  const {
+    data,
+    isFetching: loading,
+    refetch,
+  } = useQuery<ITenantUser[]>({
+    queryKey: [UserSettingApiAction.ListTenantUser, tenantId],
+    initialData: [],
+    gcTime: 0,
+    enabled: !!tenantId,
+    queryFn: async () => {
+      const { data } = await listTenantUser(tenantId);
+
+      return data?.data ?? [];
+    },
+  });
+
+  return { data, loading, refetch };
+};
+
+export const useAddTenantUser = () => {
+  const { data: tenantInfo } = useFetchTenantInfo();
+  const queryClient = useQueryClient();
+  const {
+    data,
+    isPending: loading,
+    mutateAsync,
+  } = useMutation({
+    mutationKey: [UserSettingApiAction.AddTenantUser],
+    mutationFn: async (email: string) => {
+      const { data } = await addTenantUser(tenantInfo.tenant_id, email);
+      if (data.code === 0) {
+        queryClient.invalidateQueries({
+          queryKey: [UserSettingApiAction.ListTenantUser],
+        });
+      }
+      return data?.code;
+    },
+  });
+
+  return { data, loading, addTenantUser: mutateAsync };
+};
+
+export const useDeleteTenantUser = () => {
+  const { data: tenantInfo } = useFetchTenantInfo();
+  const queryClient = useQueryClient();
+  const { t } = useTranslation();
+
+  const {
+    data,
+    isPending: loading,
+    mutateAsync,
+  } = useMutation({
+    mutationKey: [UserSettingApiAction.DeleteTenantUser],
+    mutationFn: async ({
+      userId,
+      tenantId,
+    }: {
+      userId: string;
+      tenantId?: string;
+    }) => {
+      const { data } = await deleteTenantUser({
+        tenantId: tenantId ?? tenantInfo.tenant_id,
+        userId,
+      });
+      if (data.code === 0) {
+        message.success(t('message.deleted'));
+        queryClient.invalidateQueries({
+          queryKey: [UserSettingApiAction.ListTenantUser],
+        });
+        queryClient.invalidateQueries({
+          queryKey: [UserSettingApiAction.ListTenant],
+        });
+      }
+      return data?.data ?? [];
+    },
+  });
+
+  return { data, loading, deleteTenantUser: mutateAsync };
+};
+
+export const useListTenant = () => {
+  const { data: tenantInfo } = useFetchTenantInfo();
+  const tenantId = tenantInfo.tenant_id;
+  const {
+    data,
+    isFetching: loading,
+    refetch,
+  } = useQuery<ITenant[]>({
+    queryKey: [UserSettingApiAction.ListTenant, tenantId],
+    initialData: [],
+    gcTime: 0,
+    enabled: !!tenantId,
+    queryFn: async () => {
+      const { data } = await listTenant();
+
+      return data?.data ?? [];
+    },
+  });
+
+  return { data, loading, refetch };
+};
+
+export const useAgreeTenant = () => {
+  const queryClient = useQueryClient();
+  const { t } = useTranslation();
+
+  const {
+    data,
+    isPending: loading,
+    mutateAsync,
+  } = useMutation({
+    mutationKey: [UserSettingApiAction.AgreeTenant],
+    mutationFn: async (tenantId: string) => {
+      const { data } = await agreeTenant(tenantId);
+      if (data.code === 0) {
+        message.success(t('message.operated'));
+        queryClient.invalidateQueries({
+          queryKey: [UserSettingApiAction.ListTenant],
+        });
+      }
+      return data?.data ?? [];
+    },
+  });
+
+  return { data, loading, agreeTenant: mutateAsync };
+};
+
+export const useSetLangfuseConfig = () => {
+  const { t } = useTranslation();
+  const {
+    data,
+    isPending: loading,
+    mutateAsync,
+  } = useMutation({
+    mutationKey: [UserSettingApiAction.SetLangfuseConfig],
+    mutationFn: async (params: ISetLangfuseConfigRequestBody) => {
+      const { data } = await userService.setLangfuseConfig(params);
+      if (data.code === 0) {
+        message.success(t('message.operated'));
+      }
+      return data?.code;
+    },
+  });
+
+  return { data, loading, setLangfuseConfig: mutateAsync };
+};
+
+export const useDeleteLangfuseConfig = () => {
+  const { t } = useTranslation();
+  const {
+    data,
+    isPending: loading,
+    mutateAsync,
+  } = useMutation({
+    mutationKey: [UserSettingApiAction.DeleteLangfuseConfig],
+    mutationFn: async () => {
+      const { data } = await userService.deleteLangfuseConfig();
+      if (data.code === 0) {
+        message.success(t('message.deleted'));
+      }
+      return data?.code;
+    },
+  });
+
+  return { data, loading, deleteLangfuseConfig: mutateAsync };
+};
+
+export const useFetchLangfuseConfig = () => {
+  const { data, isFetching: loading } = useQuery<ILangfuseConfig>({
+    queryKey: [UserSettingApiAction.FetchLangfuseConfig],
+    gcTime: 0,
+    queryFn: async () => {
+      const { data } = await userService.getLangfuseConfig();
+
+      return data?.data;
+    },
+  });
+
+  return { data, loading };
+};

web/src/layouts/bell-button.tsx

@@ -0,0 +1,28 @@
+import { Button } from '@/components/ui/button';
+import { useNavigateWithFromState } from '@/hooks/route-hook';
+import { useListTenant } from '@/hooks/use-user-setting-request';
+import { TenantRole } from '@/pages/user-setting/constants';
+import { BellRing } from 'lucide-react';
+import { useCallback, useMemo } from 'react';
+
+export function BellButton() {
+  const { data } = useListTenant();
+  const navigate = useNavigateWithFromState();
+
+  const showBell = useMemo(() => {
+    return data.some((x) => x.role === TenantRole.Invite);
+  }, [data]);
+
+  const handleBellClick = useCallback(() => {
+    navigate('/user-setting/team');
+  }, [navigate]);
+
+  return showBell ? (
+    <Button variant={'ghost'} onClick={handleBellClick}>
+      <div className="relative">
+        <BellRing className="size-4 " />
+        <span className="absolute size-1 rounded -right-1 -top-1 bg-red-600"></span>
+      </div>
+    </Button>
+  ) : null;
+}

web/src/layouts/next-header.tsx

@@ -31,6 +31,7 @@ import {
 import React, { useCallback, useMemo } from 'react';
 import { useTranslation } from 'react-i18next';
 import { useLocation } from 'umi';
+import { BellButton } from './bell-button';
 
 const handleDocHelpCLick = () => {
   window.open('https://ragflow.io/docs/dev/category/guides', 'target');
@@ -53,12 +54,6 @@ export function Header() {
     changeLanguage(key);
   };
 
-  // const { data } = useListTenant();
-
-  // const showBell = useMemo(() => {
-  //   return data.some((x) => x.role === TenantRole.Invite);
-  // }, [data]);
-
   const items = LanguageList.map((x) => ({
     key: x,
     label: <span>{LanguageMap[x as keyof typeof LanguageMap]}</span>,
@@ -68,10 +63,6 @@ export function Header() {
     setTheme(theme === ThemeEnum.Dark ? ThemeEnum.Light : ThemeEnum.Dark);
   }, [setTheme, theme]);
 
-  // const handleBellClick = useCallback(() => {
-  //   navigate('/user-setting/team');
-  // }, [navigate]);
-
   const tagsData = useMemo(
     () => [
       { path: Routes.Root, name: t('header.Root'), icon: House },
@@ -160,6 +151,7 @@ export function Header() {
         <Button variant={'ghost'} onClick={onThemeClick}>
           {theme === 'light' ? <Sun /> : <Moon />}
         </Button>
+        <BellButton></BellButton>
         <div className="relative">
           <RAGFlowAvatar
             name={nickname}

web/src/locales/en.ts

@@ -1,6 +1,7 @@
 export default {
   translation: {
     common: {
+      selectPlaceholder: 'select value',
       delete: 'Delete',
       deleteModalTitle: 'Are you sure to delete this item?',
       ok: 'Yes',
@@ -70,7 +71,7 @@ export default {
       review: 'from 500+ reviews',
     },
     header: {
-      knowledgeBase: 'Knowledge Base',
+      knowledgeBase: 'Dataset',
       chat: 'Chat',
       register: 'Register',
       signin: 'Sign in',
@@ -86,7 +87,7 @@ export default {
     knowledgeList: {
       welcome: 'Welcome back',
       description: 'Which knowledge bases will you use today?',
-      createKnowledgeBase: 'Create knowledge base',
+      createKnowledgeBase: 'Create Dataset',
       name: 'Name',
       namePlaceholder: 'Please input name!',
       doc: 'Docs',
@@ -94,6 +95,16 @@ export default {
       noMoreData: `That's all. Nothing more.`,
     },
     knowledgeDetails: {
+      created: 'Created',
+      learnMore: 'Learn More',
+      general: 'General',
+      chunkMethodTab: 'Chunk Method',
+      testResults: 'Test Results',
+      testSetting: 'Test Setting',
+      retrievalTesting: 'Retrieval Testing',
+      retrievalTestingDescription:
+        'Conduct a retrieval test to check if RAGFlow can recover the intended content for the LLM.',
+      Parse: 'Parse',
       dataset: 'Dataset',
       testing: 'Retrieval testing',
       files: 'files',
@@ -479,6 +490,7 @@ This auto-tagging feature enhances retrieval by adding another layer of domain-s
       improvise: 'Improvise',
       precise: 'Precise',
       balance: 'Balance',
+      custom: 'Custom',
       freedomTip: `A shortcut to 'Temperature', 'Top P', 'Presence penalty', and 'Frequency penalty' settings, indicating the freedom level of the model. This parameter has three options: Select 'Improvise' to produce more creative responses; select 'Precise' (default) to produce more conservative responses; 'Balance' is a middle ground between 'Improvise' and 'Precise'.`,
       temperature: 'Temperature',
       temperatureMessage: 'Temperature is required',
@@ -845,6 +857,7 @@ This auto-tagging feature enhances retrieval by adding another layer of domain-s
       uploadLimit:
         'Each file must not exceed 10MB, and the total number of files must not exceed 128.',
       destinationFolder: 'Destination folder',
+      pleaseUploadAtLeastOneFile: 'Please upload at least one file',
     },
     flow: {
       cite: 'Cite',
@@ -1441,6 +1454,7 @@ This delimiter is used to split the input text into several text pieces echo of
       showQueryMindmap: 'Show Query Mindmap',
       embedApp: 'Embed App',
       relatedSearch: 'Related Search',
+      descriptionValue: 'You are an intelligent assistant.',
       okText: 'Save',
       cancelText: 'Cancel',
     },

web/src/locales/fr.ts

@@ -240,9 +240,8 @@ export default {
       promptTip:
         'Décrivez la tâche attendue du LLM, ses réponses, ses exigences, etc. Utilisez `/` pour afficher les variables disponibles.',
       promptMessage: 'Le prompt est requis',
-      promptText: `Veuillez résumer les paragraphes suivants. Attention aux chiffres, ne pas inventer. Paragraphes suivants : {cluster_content
+      promptText: `Veuillez résumer les paragraphes suivants. Attention aux chiffres, ne pas inventer. Paragraphes suivants : {cluster_content}
-      }
+  Le contenu à résumer est ci-dessus.`,
-    Le contenu à résumer est ci-dessus.`,
       maxToken: 'Nombre maximal de tokens',
       maxTokenTip: 'Nombre maximal de tokens générés par résumé.',
       maxTokenMessage: 'Nombre maximal de tokens requis',

web/src/locales/zh-traditional.ts

@@ -454,6 +454,7 @@ export default {
       improvise: '即興創作',
       precise: '精確',
       balance: '平衡',
+      custom: '自定義',
       freedomTip: `“精確”意味著法學碩士會保守並謹慎地回答你的問題。“即興發揮”意味著你希望法學碩士能夠自由地暢所欲言。“平衡”是謹慎與自由之間的平衡。`,
       temperature: '溫度',
       temperatureMessage: '溫度是必填項',

web/src/locales/zh.ts

@@ -1,6 +1,7 @@
 export default {
   translation: {
     common: {
+      selectPlaceholder: '请选择',
       delete: '删除',
       deleteModalTitle: '确定删除吗?',
       ok: '是',
@@ -86,6 +87,16 @@ export default {
       noMoreData: '没有更多数据了',
     },
     knowledgeDetails: {
+      created: '创建于',
+      learnMore: '了解更多',
+      general: '通用',
+      chunkMethodTab: '切片方法',
+      testResults: '测试结果',
+      testSetting: '测试设置',
+      retrievalTesting: '知识检索测试',
+      retrievalTestingDescription:
+        '进行检索测试，检查 RAGFlow 是否能够为大语言模型（LLM）恢复预期的内容。',
+      Parse: '解析',
       dataset: '数据集',
       testing: '检索测试',
       configuration: '配置',
@@ -477,6 +488,7 @@ General：实体和关系提取提示来自 GitHub - microsoft/graphrag：基于
       improvise: '即兴创作',
       precise: '精确',
       balance: '平衡',
+      custom: '自定义',
       freedomTip: `“精确”意味着大语言模型会保守并谨慎地回答你的问题。 “即兴发挥”意味着你希望大语言模型能够自由地畅所欲言。 “平衡”是谨慎与自由之间的平衡。`,
       temperature: '温度',
       temperatureMessage: '温度是必填项',
@@ -799,6 +811,7 @@ General：实体和关系提取提示来自 GitHub - microsoft/graphrag：基于
       fileError: '文件错误',
       uploadLimit: '文件大小不能超过10M，文件总数不超过128个',
       destinationFolder: '目标文件夹',
+      pleaseUploadAtLeastOneFile: '请上传至少一个文件',
     },
     flow: {
       flow: '工作流',
@@ -1344,6 +1357,7 @@ General：实体和关系提取提示来自 GitHub - microsoft/graphrag：基于
       showQueryMindmap: '显示查询思维导图',
       embedApp: '嵌入网站',
       relatedSearch: '相关搜索',
+      descriptionValue: '你是一位智能助手。',
       okText: '保存',
       cancelText: '返回',
     },

web/src/pages/agent/chat/use-send-agent-message.ts

@@ -4,6 +4,7 @@ import {
   useHandleMessageInputChange,
   useSelectDerivedMessages,
 } from '@/hooks/logic-hooks';
+import { useFetchAgent } from '@/hooks/use-agent-request';
 import {
   IEventList,
   IInputEvent,
@@ -188,11 +189,7 @@ export const useSendAgentMessage = (
     return answerList[0]?.message_id;
   }, [answerList]);
 
-  useEffect(() => {
+  const { refetch } = useFetchAgent();
-    if (answerList[0]?.session_id) {
-      setSessionId(answerList[0]?.session_id);
-    }
-  }, [answerList]);
 
   const { findReferenceByMessageId } = useFindMessageReference(answerList);
   const prologue = useGetBeginNodePrologue();
@@ -250,7 +247,7 @@ export const useSendAgentMessage = (
           setValue(message.content);
           removeLatestMessage();
         } else {
-          // refetch(); // pull the message list after sending the message successfully
+          refetch(); // pull the message list after sending the message successfully
         }
       } catch (error) {
         console.log('🚀 ~ useSendAgentMessage ~ error:', error);
@@ -258,28 +255,30 @@ export const useSendAgentMessage = (
     },
     [
       agentId,
-      sessionId,
-      send,
-      clearUploadResponseList,
       inputs,
       beginParams,
       uploadResponseList,
+      sessionId,
+      send,
+      clearUploadResponseList,
       setValue,
       removeLatestMessage,
+      refetch,
     ],
   );
 
   const sendFormMessage = useCallback(
-    (body: { id?: string; inputs: Record<string, BeginQuery> }) => {
+    async (body: { id?: string; inputs: Record<string, BeginQuery> }) => {
-      send({ ...body, session_id: sessionId });
       addNewestOneQuestion({
         content: Object.entries(body.inputs)
           .map(([key, val]) => `${key}: ${val.value}`)
           .join('<br/>'),
         role: MessageType.User,
       });
+      await send({ ...body, session_id: sessionId });
+      refetch();
     },
-    [addNewestOneQuestion, send, sessionId],
+    [addNewestOneQuestion, refetch, send, sessionId],
   );
 
   // reset session
@@ -346,6 +345,12 @@ export const useSendAgentMessage = (
     }
   }, [addEventList, answerList, addEventListFun, messageId]);
 
+  useEffect(() => {
+    if (answerList[0]?.session_id) {
+      setSessionId(answerList[0]?.session_id);
+    }
+  }, [answerList]);
+
   return {
     value,
     sendLoading: !done,

web/src/pages/agent/index.tsx

@@ -210,7 +210,9 @@ export default function Agent() {
         ></EmbedDialog>
       )}
       {versionDialogVisible && (
-        <VersionDialog hideModal={hideVersionDialog}></VersionDialog>
+        <DropdownProvider>
+          <VersionDialog hideModal={hideVersionDialog}></VersionDialog>
+        </DropdownProvider>
       )}
       {settingDialogVisible && (
         <SettingDialog hideModal={hideSettingDialog}></SettingDialog>

web/src/pages/agent/upload-agent-dialog/upload-agent-form.tsx

@@ -63,7 +63,6 @@ export function UploadAgentForm({ hideModal, onOk }: IModalProps<any>) {
                   value={field.value}
                   onValueChange={field.onChange}
                   maxFileCount={1}
-                  maxSize={4 * 1024 * 1024}
                   accept={{ '*.json': [FileMimeType.Json] }}
                 />
               </FormControl>

web/src/pages/chunk/parsed-result/add-knowledge/components/knowledge-chunk/index.less

@@ -35,7 +35,7 @@
 
   .documentPreview {
     // width: 40%;
-    height: calc(100vh - 130px);
+    height: calc(100vh - 180px);
     overflow: auto;
   }
 

web/src/pages/dataset/dataset/constant.ts

@@ -3,15 +3,15 @@ import { RunningStatus } from '@/constants/knowledge';
 export const RunningStatusMap = {
   [RunningStatus.UNSTART]: {
     label: 'UNSTART',
-    color: 'cyan',
+    color: 'var(--accent-primary)',
   },
   [RunningStatus.RUNNING]: {
     label: 'Parsing',
-    color: 'blue',
+    color: 'var(--team-member)',
   },
-  [RunningStatus.CANCEL]: { label: 'CANCEL', color: 'orange' },
+  [RunningStatus.CANCEL]: { label: 'CANCEL', color: 'var(--state-warning)' },
-  [RunningStatus.DONE]: { label: 'SUCCESS', color: 'blue' },
+  [RunningStatus.DONE]: { label: 'SUCCESS', color: 'var(--state-success)' },
-  [RunningStatus.FAIL]: { label: 'FAIL', color: 'red' },
+  [RunningStatus.FAIL]: { label: 'FAIL', color: 'var(--state-error' },
 };
 
 export * from '@/constants/knowledge';

web/src/pages/dataset/dataset/dataset-action-cell.tsx

@@ -11,7 +11,7 @@ import { IDocumentInfo } from '@/interfaces/database/document';
 import { formatFileSize } from '@/utils/common-util';
 import { formatDate } from '@/utils/date';
 import { downloadDocument } from '@/utils/file-util';
-import { ArrowDownToLine, FolderPen, ScrollText, Trash2 } from 'lucide-react';
+import { Download, Eye, PenLine, Trash2 } from 'lucide-react';
 import { useCallback } from 'react';
 import { UseRenameDocumentShowType } from './use-rename-document';
 import { isParserRunning } from './utils';
@@ -57,12 +57,12 @@ export function DatasetActionCell({
         disabled={isRunning}
         onClick={handleRename}
       >
-        <FolderPen />
+        <PenLine />
       </Button>
       <HoverCard>
         <HoverCardTrigger>
           <Button variant="ghost" disabled={isRunning} size={'sm'}>
-            <ScrollText />
+            <Eye />
           </Button>
         </HoverCardTrigger>
         <HoverCardContent className="w-[40vw] max-h-[40vh] overflow-auto">
@@ -93,7 +93,7 @@ export function DatasetActionCell({
           disabled={isRunning}
           size={'sm'}
         >
-          <ArrowDownToLine />
+          <Download />
         </Button>
       )}
       <ConfirmDeleteDialog onOk={handleRemove}>

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

@@ -164,7 +164,7 @@ export function DatasetTable({
           )}
         </TableBody>
       </Table>
-      <div className="flex items-center justify-end  py-4">
+      <div className="flex items-center justify-end  py-4 absolute bottom-3 right-3">
         <div className="space-x-2">
           <RAGFlowPagination
             {...pick(pagination, 'current', 'pageSize')}

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

@@ -111,6 +111,7 @@ export default function Dataset() {
           hideModal={hideDocumentUploadModal}
           onOk={onDocumentUploadOk}
           loading={documentUploadLoading}
+          showParseOnCreation
         ></FileUploadDialog>
       )}
       {createVisible && (

web/src/pages/dataset/dataset/parsing-card.tsx

@@ -17,7 +17,7 @@ function Dot({ run }: { run: RunningStatus }) {
   const runningStatus = RunningStatusMap[run];
   return (
     <span
-      className={'size-2 inline-block rounded'}
+      className={'size-1 inline-block rounded'}
       style={{ backgroundColor: runningStatus.color }}
     ></span>
   );
@@ -89,7 +89,7 @@ export function ParsingCard({ record }: IProps) {
   return (
     <HoverCard>
       <HoverCardTrigger asChild>
-        <Button variant={'ghost'} size={'sm'}>
+        <Button variant={'transparent'} className="border-none" size={'sm'}>
           <Dot run={record.run}></Dot>
         </Button>
       </HoverCardTrigger>

web/src/pages/dataset/dataset/parsing-status-cell.tsx

@@ -14,7 +14,7 @@ import {
 import { Progress } from '@/components/ui/progress';
 import { Separator } from '@/components/ui/separator';
 import { IDocumentInfo } from '@/interfaces/database/document';
-import { CircleX, Play, RefreshCw } from 'lucide-react';
+import { CircleX, RefreshCw } from 'lucide-react';
 import { useCallback } from 'react';
 import { useTranslation } from 'react-i18next';
 import { RunningStatus } from './constant';
@@ -24,11 +24,13 @@ import { useHandleRunDocumentByIds } from './use-run-document';
 import { UseSaveMetaShowType } from './use-save-meta';
 import { isParserRunning } from './utils';
 const IconMap = {
-  [RunningStatus.UNSTART]: <Play />,
+  [RunningStatus.UNSTART]: (
-  [RunningStatus.RUNNING]: <CircleX />,
+    <div className="w-0 h-0 border-l-[10px] border-l-accent-primary border-t-8 border-r-4 border-b-8 border-transparent"></div>
-  [RunningStatus.CANCEL]: <RefreshCw />,
+  ),
-  [RunningStatus.DONE]: <RefreshCw />,
+  [RunningStatus.RUNNING]: <CircleX size={14} color="var(--state-error)" />,
-  [RunningStatus.FAIL]: <RefreshCw />,
+  [RunningStatus.CANCEL]: <RefreshCw size={14} color="var(--accent-primary)" />,
+  [RunningStatus.DONE]: <RefreshCw size={14} color="var(--accent-primary)" />,
+  [RunningStatus.FAIL]: <RefreshCw size={14} color="var(--accent-primary)" />,
 };
 
 export function ParsingStatusCell({
@@ -60,11 +62,11 @@ export function ParsingStatusCell({
   }, [record, showSetMetaModal]);
 
   return (
-    <section className="flex gap-2 items-center">
+    <section className="flex gap-8 items-center">
-      <div className="w-28 flex items-center justify-between">
+      <div className="w-fit flex items-center justify-between">
         <DropdownMenu>
           <DropdownMenuTrigger asChild>
-            <Button variant={'ghost'} size={'sm'}>
+            <Button variant={'transparent'} className="border-none" size={'sm'}>
               {parser_id === 'naive' ? 'general' : parser_id}
             </Button>
           </DropdownMenuTrigger>
@@ -77,7 +79,6 @@ export function ParsingStatusCell({
             </DropdownMenuItem>
           </DropdownMenuContent>
         </DropdownMenu>
-        <Separator orientation="vertical" className="h-2.5" />
       </div>
       <ConfirmDeleteDialog
         title={t(`knowledgeDetails.redo`, { chunkNum: chunk_num })}
@@ -85,17 +86,17 @@ export function ParsingStatusCell({
         onOk={handleOperationIconClick(true)}
         onCancel={handleOperationIconClick(false)}
       >
-        <Button
+        <div
-          variant={'ghost'}
+          className="cursor-pointer flex items-center gap-3"
-          size={'sm'}
           onClick={
             isZeroChunk || isRunning
               ? handleOperationIconClick(false)
               : () => {}
           }
         >
+          <Separator orientation="vertical" className="h-2.5" />
           {operationIcon}
-        </Button>
+        </div>
       </ConfirmDeleteDialog>
       {isParserRunning(run) ? (
         <HoverCard>

web/src/pages/dataset/dataset/use-dataset-table-columns.tsx

@@ -65,7 +65,8 @@ export function useDatasetTableColumns({
       header: ({ column }) => {
         return (
           <Button
-            variant="ghost"
+            variant="transparent"
+            className="border-none"
             onClick={() => column.toggleSorting(column.getIsSorted() === 'asc')}
           >
             {t('name')}
@@ -103,7 +104,8 @@ export function useDatasetTableColumns({
       header: ({ column }) => {
         return (
           <Button
-            variant="ghost"
+            variant="transparent"
+            className="border-none"
             onClick={() => column.toggleSorting(column.getIsSorted() === 'asc')}
           >
             {t('uploadDate')}
@@ -141,7 +143,7 @@ export function useDatasetTableColumns({
     },
     {
       accessorKey: 'run',
-      header: t('parsingStatus'),
+      header: t('Parse'),
       // meta: { cellClassName: 'min-w-[20vw]' },
       cell: ({ row }) => {
         return (

web/src/pages/dataset/dataset/use-upload-document.ts

@@ -1,5 +1,9 @@
+import { UploadFormSchemaType } from '@/components/file-upload-dialog';
 import { useSetModalState } from '@/hooks/common-hooks';
-import { useUploadNextDocument } from '@/hooks/use-document-request';
+import {
+  useRunDocument,
+  useUploadNextDocument,
+} from '@/hooks/use-document-request';
 import { getUnSupportedFilesCount } from '@/utils/document-util';
 import { useCallback } from 'react';
 
@@ -10,14 +14,24 @@ export const useHandleUploadDocument = () => {
     showModal: showDocumentUploadModal,
   } = useSetModalState();
   const { uploadDocument, loading } = useUploadNextDocument();
+  const { runDocumentByIds } = useRunDocument();
 
   const onDocumentUploadOk = useCallback(
-    async (fileList: File[]): Promise<number | undefined> => {
+    async ({ fileList, parseOnCreation }: UploadFormSchemaType) => {
       if (fileList.length > 0) {
-        const ret: any = await uploadDocument(fileList);
+        const ret = await uploadDocument(fileList);
         if (typeof ret?.message !== 'string') {
           return;
         }
+
+        if (ret.code === 0 && parseOnCreation) {
+          runDocumentByIds({
+            documentIds: ret.data.map((x) => x.id),
+            run: 1,
+            shouldDelete: false,
+          });
+        }
+
         const count = getUnSupportedFilesCount(ret?.message);
         /// 500 error code indicates that some file types are not supported
         let code = ret?.code;
@@ -31,7 +45,7 @@ export const useHandleUploadDocument = () => {
         return code;
       }
     },
-    [uploadDocument, hideDocumentUploadModal],
+    [uploadDocument, runDocumentByIds, hideDocumentUploadModal],
   );
 
   return {

web/src/pages/dataset/index.tsx

@@ -19,7 +19,7 @@ export default function DatasetWrapper() {
   const { data } = useFetchKnowledgeBaseConfiguration();
 
   return (
-    <section>
+    <section className="flex h-full flex-col w-full">
       <PageHeader>
         <Breadcrumb>
           <BreadcrumbList>
@@ -30,12 +30,14 @@ export default function DatasetWrapper() {
             </BreadcrumbItem>
             <BreadcrumbSeparator />
             <BreadcrumbItem>
-              <BreadcrumbPage>{data.name}</BreadcrumbPage>
+              <BreadcrumbPage className="w-28 whitespace-nowrap text-ellipsis overflow-hidden">
+                {data.name}
+              </BreadcrumbPage>
             </BreadcrumbItem>
           </BreadcrumbList>
         </Breadcrumb>
       </PageHeader>
-      <div className="flex flex-1">
+      <div className="flex flex-1 min-h-0">
         <SideBar></SideBar>
         <div className="flex-1">
           <Outlet />

web/src/pages/dataset/setting/chunk-method-form.tsx

@@ -66,10 +66,10 @@ export function ChunkMethodForm() {
   }, [finalParserId]);
 
   return (
-    <>
+    <section className="h-full flex flex-col">
-      <section className="overflow-auto max-h-[76vh]">
+      <div className="overflow-auto flex-1 min-h-0">
         <ConfigurationComponent></ConfigurationComponent>
-      </section>
+      </div>
       <div className="text-right pt-4 flex justify-end gap-3">
         <Button
           type="reset"
@@ -112,6 +112,6 @@ export function ChunkMethodForm() {
           {t('knowledgeConfiguration.save')}
         </Button>
       </div>
-    </>
+    </section>
   );
 }

web/src/pages/dataset/setting/chunk-method-learn-more.tsx

@@ -1,4 +1,6 @@
 import { Button } from '@/components/ui/button';
+import { cn } from '@/lib/utils';
+import { t } from 'i18next';
 import { X } from 'lucide-react';
 import { useState } from 'react';
 import CategoryPanel from './category-panel';
@@ -14,20 +16,22 @@ export default ({
 
   return (
     <div
-      style={{
+      className={cn('hidden flex-1', {
-        display: tab === 'chunkMethodForm' ? 'block' : 'none',
+        'flex flex-col': tab === 'chunkMethodForm',
-      }}
+      })}
     >
-      <Button
+      <div>
-        variant="outline"
+        <Button
-        onClick={() => {
+          variant="outline"
-          setVisible(!visible);
+          onClick={() => {
-        }}
+            setVisible(!visible);
-      >
+          }}
-        Learn More
+        >
-      </Button>
+          {t('knowledgeDetails.learnMore')}
+        </Button>
+      </div>
       <div
-        className="bg-[#FFF]/10 p-[20px] rounded-[12px] mt-[10px] relative"
+        className="bg-[#FFF]/10 p-[20px] rounded-[12px] mt-[10px] relative flex-1 overflow-auto"
         style={{ display: visible ? 'block' : 'none' }}
       >
         <CategoryPanel chunkMethod={parserId}></CategoryPanel>

web/src/pages/dataset/setting/configuration/common-item.tsx

@@ -29,7 +29,7 @@ export function ChunkMethodItem() {
           <div className="flex items-center">
             <FormLabel
               tooltip={t('chunkMethodTip')}
-              className="text-sm text-muted-foreground whitespace-nowrap w-1/4"
+              className="text-sm text-muted-foreground whitespace-wrap w-1/4"
             >
               {t('chunkMethod')}
             </FormLabel>
@@ -69,7 +69,7 @@ export function EmbeddingModelItem() {
           <div className="flex items-center">
             <FormLabel
               tooltip={t('embeddingModelTip')}
-              className="text-sm text-muted-foreground whitespace-nowrap w-1/4"
+              className="text-sm text-muted-foreground whitespace-wrap w-1/4"
             >
               {t('embeddingModel')}
             </FormLabel>

web/src/pages/dataset/setting/general-form.tsx

@@ -1,6 +1,8 @@
 import { FormContainer } from '@/components/form-container';
+import { SelectWithSearch } from '@/components/originui/select-with-search';
+import { RAGFlowFormItem } from '@/components/ragflow-form';
 import { Avatar, AvatarFallback, AvatarImage } from '@/components/ui/avatar';
-import { Button } from '@/components/ui/button';
+import { Button, ButtonLoading } from '@/components/ui/button';
 import {
   FormControl,
   FormField,
@@ -9,9 +11,10 @@ import {
   FormMessage,
 } from '@/components/ui/form';
 import { Input } from '@/components/ui/input';
+import { PermissionRole } from '@/constants/permission';
 import { useUpdateKnowledge } from '@/hooks/knowledge-hooks';
 import { transformFile2Base64 } from '@/utils/file-util';
-import { Loader2Icon, Pencil, Upload } from 'lucide-react';
+import { Pencil, Upload } from 'lucide-react';
 import { useEffect, useMemo, useState } from 'react';
 import { useFormContext } from 'react-hook-form';
 import { useTranslation } from 'react-i18next';
@@ -33,6 +36,13 @@ export function GeneralForm() {
   const parser_id = defaultValues['parser_id'];
   const { id: kb_id } = useParams();
 
+  const teamOptions = useMemo(() => {
+    return Object.values(PermissionRole).map((x) => ({
+      label: t('knowledgeConfiguration.' + x),
+      value: x,
+    }));
+  }, [t]);
+
   // init avatar file if it exists in defaultValues
   useEffect(() => {
     if (!avatarFile) {
@@ -171,24 +181,35 @@ export function GeneralForm() {
             );
           }}
         />
+        <RAGFlowFormItem
+          name="permission"
+          label={t('knowledgeConfiguration.permissions')}
+          tooltip={t('knowledgeConfiguration.permissionsTip')}
+          horizontal
+        >
+          <SelectWithSearch
+            options={teamOptions}
+            triggerClassName="w-3/4"
+          ></SelectWithSearch>
+        </RAGFlowFormItem>
       </FormContainer>
       <div className="text-right pt-4 flex justify-end gap-3">
         <Button
           type="reset"
-          className="bg-transparent text-color-white hover:bg-transparent border-gray-500 border-[1px]"
+          variant={'outline'}
           onClick={() => {
             form.reset();
           }}
         >
           {t('knowledgeConfiguration.cancel')}
         </Button>
-        <Button
+        <ButtonLoading
           type="button"
-          disabled={submitLoading}
+          loading={submitLoading}
           onClick={() => {
             (async () => {
-              let isValidate = await form.formControl.trigger('name');
+              let isValidate = await form.trigger('name');
-              const { name, description } = form.formState.values;
+              const { name, description, permission } = form.getValues();
               const avatar = avatarBase64Str;
 
               if (isValidate) {
@@ -198,14 +219,14 @@ export function GeneralForm() {
                   name,
                   description,
                   avatar,
+                  permission,
                 });
               }
             })();
           }}
         >
-          {submitLoading && <Loader2Icon className="animate-spin" />}
           {t('knowledgeConfiguration.save')}
-        </Button>
+        </ButtonLoading>
       </div>
     </>
   );

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

@@ -6,6 +6,7 @@ import {
   TabsTrigger,
 } from '@/components/ui/tabs-underlined';
 import { DocumentParserType } from '@/constants/knowledge';
+import { PermissionRole } from '@/constants/permission';
 import { zodResolver } from '@hookform/resolvers/zod';
 import { useState } from 'react';
 import { useForm, useWatch } from 'react-hook-form';
@@ -43,7 +44,7 @@ export default function DatasetSettings() {
     defaultValues: {
       name: '',
       parser_id: DocumentParserType.Naive,
-      permission: 'me',
+      permission: PermissionRole.Me,
       parser_config: {
         layout_recognize: DocumentType.DeepDOC,
         chunk_token_num: 512,
@@ -81,22 +82,23 @@ export default function DatasetSettings() {
   }
 
   return (
-    <section className="p-5 ">
+    <section className="p-5 h-full flex flex-col">
       <TopTitle
         title={t('knowledgeDetails.configuration')}
         description={t('knowledgeConfiguration.titleDescription')}
       ></TopTitle>
-      <div className="flex gap-14">
+      <div className="flex gap-14 flex-1 min-h-0">
         <Form {...form}>
           <form
             onSubmit={form.handleSubmit(onSubmit)}
-            className="space-y-6 basis-full min-w-[1000px] max-w-[1000px]"
+            className="space-y-6 flex-1"
           >
             <Tabs
               defaultValue="generalForm"
               onValueChange={(val) => {
                 setCurrentTab(val);
               }}
+              className="h-full flex flex-col"
             >
               <TabsList className="grid bg-transparent grid-cols-2 rounded-none text-foreground">
                 <TabsTrigger
@@ -105,7 +107,7 @@ export default function DatasetSettings() {
                 >
                   <div className="flex w-full h-full justify-center	items-center">
                     <span className="h-full group-data-[state=active]:border-b-2 border-foreground	">
-                      General
+                      {t('knowledgeDetails.general')}
                     </span>
                   </div>
                 </TabsTrigger>
@@ -115,15 +117,15 @@ export default function DatasetSettings() {
                 >
                   <div className="flex w-full h-full justify-center	items-center">
                     <span className="h-full group-data-[state=active]:border-b-2 border-foreground	">
-                      Chunk Method
+                      {t('knowledgeDetails.chunkMethodTab')}
                     </span>
                   </div>
                 </TabsTrigger>
               </TabsList>
-              <TabsContent value="generalForm">
+              <TabsContent value="generalForm" className="flex-1 min-h-0">
                 <GeneralForm></GeneralForm>
               </TabsContent>
-              <TabsContent value="chunkMethodForm">
+              <TabsContent value="chunkMethodForm" className="flex-1 min-h-0">
                 <ChunkMethodForm></ChunkMethodForm>
               </TabsContent>
             </Tabs>

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

@@ -62,15 +62,19 @@ export function SideBar({ refreshCount }: PropType) {
           name={data.name}
           className="size-16"
         ></RAGFlowAvatar>
-        <div className=" text-text-secondary text-xs space-y-1">
+        <div className=" text-text-secondary text-xs space-y-1 overflow-hidden">
-          <h3 className="text-lg font-semibold line-clamp-1 text-text-primary">
+          <h3 className="text-lg font-semibold line-clamp-1 text-text-primary text-ellipsis overflow-hidden">
             {data.name}
           </h3>
           <div className="flex justify-between">
-            <span>{data.doc_num} files</span>
+            <span>
+              {data.doc_num} {t('knowledgeDetails.files')}
+            </span>
             <span>{formatBytes(data.size)}</span>
           </div>
-          <div>Created {formatPureDate(data.create_time)}</div>
+          <div>
+            {t('knowledgeDetails.created')} {formatPureDate(data.create_time)}
+          </div>
         </div>
       </div>
 

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

@@ -1,4 +1,5 @@
 import { useTestRetrieval } from '@/hooks/use-knowledge-request';
+import { t } from 'i18next';
 import { useState } from 'react';
 import { TopTitle } from '../dataset-title';
 import TestingForm from './testing-form';
@@ -23,8 +24,8 @@ export default function RetrievalTesting() {
     <div className="p-5">
       <section className="flex justify-between items-center">
         <TopTitle
-          title={'Retrieval testing'}
+          title={t('knowledgeDetails.retrievalTesting')}
-          description={`Conduct a retrieval test to check if RAGFlow can recover the intended content for the LLM.`}
+          description={t('knowledgeDetails.retrievalTestingDescription')}
         ></TopTitle>
         {/* <Button>Save as Preset</Button> */}
       </section>
@@ -33,7 +34,7 @@ export default function RetrievalTesting() {
           <div className="p-4 flex-1">
             <div className="flex justify-between pb-2.5">
               <span className="text-text-primary font-semibold text-2xl">
-                Test setting
+                {t('knowledgeDetails.testSetting')}
               </span>
               {/* <Button variant={'outline'} onClick={addCount}>
                 <Plus /> Add New Test

web/src/pages/dataset/testing/testing-result.tsx

@@ -6,6 +6,7 @@ import { RAGFlowPagination } from '@/components/ui/ragflow-pagination';
 import { useTranslate } from '@/hooks/common-hooks';
 import { useTestRetrieval } from '@/hooks/use-knowledge-request';
 import { ITestingChunk } from '@/interfaces/database/knowledge';
+import { t } from 'i18next';
 import camelCase from 'lodash/camelCase';
 import { useMemo } from 'react';
 
@@ -66,7 +67,7 @@ export function TestingResult({
     <div className="p-4 flex-1">
       <div className="flex justify-between pb-2.5">
         <span className="text-text-primary font-semibold text-2xl">
-          Test results
+          {t('knowledgeDetails.testResults')}
         </span>
         <FilterPopover
           filters={filters}

web/src/pages/datasets/dataset-card.tsx

@@ -1,11 +1,11 @@
 import { HomeCard } from '@/components/home-card';
 import { MoreButton } from '@/components/more-button';
+import { SharedBadge } from '@/components/shared-badge';
 import { Card, CardContent } from '@/components/ui/card';
 import { useNavigatePage } from '@/hooks/logic-hooks/navigate-hooks';
 import { IKnowledge } from '@/interfaces/database/knowledge';
 import { ChevronRight } from 'lucide-react';
 import { DatasetDropdown } from './dataset-dropdown';
-import { useDisplayOwnerName } from './use-display-owner';
 import { useRenameDataset } from './use-rename-dataset';
 
 export type DatasetCardProps = {
@@ -17,9 +17,6 @@ export function DatasetCard({
   showDatasetRenameModal,
 }: DatasetCardProps) {
   const { navigateToDataset } = useNavigatePage();
-  const displayOwnerName = useDisplayOwnerName();
-
-  const owner = displayOwnerName(dataset.tenant_id, dataset.nickname);
 
   return (
     <HomeCard
@@ -32,6 +29,7 @@ export function DatasetCard({
           <MoreButton></MoreButton>
         </DatasetDropdown>
       }
+      sharedBadge={<SharedBadge>{dataset.nickname}</SharedBadge>}
       onClick={navigateToDataset(dataset.id)}
     />
   );
@@ -41,7 +39,7 @@ export function SeeAllCard() {
   const { navigateToDatasetList } = useNavigatePage();
 
   return (
-    <Card className="w-40" onClick={navigateToDatasetList}>
+    <Card className="w-40 flex-none h-full" onClick={navigateToDatasetList}>
       <CardContent className="p-2.5 pt-1 w-full h-full flex items-center justify-center gap-1.5 text-text-secondary">
         See All <ChevronRight className="size-4" />
       </CardContent>

web/src/pages/datasets/dataset-creating-dialog.tsx

@@ -1,4 +1,4 @@
-import { Button } from '@/components/ui/button';
+import { ButtonLoading } from '@/components/ui/button';
 import {
   Dialog,
   DialogContent,
@@ -74,7 +74,11 @@ export function InputForm({ onOk }: IModalProps<any>) {
   );
 }
 
-export function DatasetCreatingDialog({ hideModal, onOk }: IModalProps<any>) {
+export function DatasetCreatingDialog({
+  hideModal,
+  onOk,
+  loading,
+}: IModalProps<any>) {
   const { t } = useTranslation();
 
   return (
@@ -85,9 +89,9 @@ export function DatasetCreatingDialog({ hideModal, onOk }: IModalProps<any>) {
         </DialogHeader>
         <InputForm onOk={onOk}></InputForm>
         <DialogFooter>
-          <Button type="submit" form={FormId}>
+          <ButtonLoading type="submit" form={FormId} loading={loading}>
             {t('common.save')}
-          </Button>
+          </ButtonLoading>
         </DialogFooter>
       </DialogContent>
     </Dialog>

web/src/pages/files/use-upload-file.ts

@@ -1,3 +1,4 @@
+import { UploadFormSchemaType } from '@/components/file-upload-dialog';
 import { useSetModalState } from '@/hooks/common-hooks';
 import { useUploadFile } from '@/hooks/use-file-request';
 import { useCallback } from 'react';
@@ -13,7 +14,7 @@ export const useHandleUploadFile = () => {
   const id = useGetFolderId();
 
   const onFileUploadOk = useCallback(
-    async (fileList: File[]): Promise<number | undefined> => {
+    async ({ fileList }: UploadFormSchemaType): Promise<number | undefined> => {
       if (fileList.length > 0) {
         const ret: number = await uploadFile({ fileList, parentId: id });
         if (ret === 0) {

web/src/pages/home/applications.tsx

@@ -51,7 +51,8 @@ export function Applications() {
           options={options}
           value={val}
           onChange={handleChange}
-          className="bg-transparent"
+          className="bg-bg-card border border-border-button rounded-full"
+          activeClassName="bg-text-primary border-none"
         ></Segmented>
       </div>
       <div className="flex flex-wrap gap-4">

web/src/pages/home/datasets.tsx

@@ -30,17 +30,21 @@ export function Datasets() {
             <CardSkeleton />
           </div>
         ) : (
-          <div className="flex gap-4 flex-1">
+          <div className="grid gap-6 sm:grid-cols-1 md:grid-cols-2 lg:grid-cols-4 xl:grid-cols-6 2xl:grid-cols-8 max-h-[78vh] overflow-auto">
-            {kbs.slice(0, 6).map((dataset) => (
+            {kbs
-              <DatasetCard
+              ?.slice(0, 6)
-                key={dataset.id}
+              .map((dataset) => (
-                dataset={dataset}
+                <DatasetCard
-                showDatasetRenameModal={showDatasetRenameModal}
+                  key={dataset.id}
-              ></DatasetCard>
+                  dataset={dataset}
-            ))}
+                  showDatasetRenameModal={showDatasetRenameModal}
+                ></DatasetCard>
+              ))}
+            <div className="min-h-24">
+              <SeeAllCard></SeeAllCard>
+            </div>
           </div>
         )}
-        <SeeAllCard></SeeAllCard>
       </div>
       {datasetRenameVisible && (
         <RenameDialog

web/src/pages/next-chats/chat/app-settings/chat-basic-settings.tsx

@@ -14,6 +14,7 @@ import {
 } from '@/components/ui/form';
 import { Input } from '@/components/ui/input';
 import { Textarea } from '@/components/ui/textarea';
+import { Select, SelectContent, SelectItem, SelectTrigger, SelectValue } from '@/components/ui/select';
 import { useTranslate } from '@/hooks/common-hooks';
 import { useFormContext } from 'react-hook-form';
 
@@ -21,6 +22,17 @@ export default function ChatBasicSetting() {
   const { t } = useTranslate('chat');
   const form = useFormContext();
 
+  const languageOptions = [
+    { value: 'English', label: 'English' },
+    { value: 'Chinese', label: 'Chinese' },
+    { value: 'Spanish', label: 'Spanish' },
+    { value: 'French', label: 'French' },
+    { value: 'German', label: 'German' },
+    { value: 'Japanese', label: 'Japanese' },
+    { value: 'Korean', label: 'Korean' },
+    { value: 'Vietnamese', label: 'Vietnamese' },
+  ];
+
   return (
     <div className="space-y-8">
       <FormField
@@ -35,7 +47,6 @@ export default function ChatBasicSetting() {
                   value={field.value}
                   onValueChange={field.onChange}
                   maxFileCount={1}
-                  maxSize={4 * 1024 * 1024}
                 />
               </FormControl>
               <FormMessage />
@@ -56,6 +67,30 @@ export default function ChatBasicSetting() {
           </FormItem>
         )}
       />
+      <FormField
+        control={form.control}
+        name="language"
+        render={({ field }) => (
+          <FormItem>
+            <FormLabel>{t('language')}</FormLabel>
+            <Select onValueChange={field.onChange} defaultValue={field.value}>
+              <FormControl>
+                <SelectTrigger>
+                  <SelectValue placeholder={t('common.languagePlaceholder')} />
+                </SelectTrigger>
+              </FormControl>
+              <SelectContent>
+                {languageOptions.map((option) => (
+                  <SelectItem key={option.value} value={option.value}>
+                    {option.label}
+                  </SelectItem>
+                ))}
+              </SelectContent>
+            </Select>
+            <FormMessage />
+          </FormItem>
+        )}
+      />
       <FormField
         control={form.control}
         name="description"

web/src/pages/next-chats/chat/app-settings/chat-settings.tsx

@@ -9,6 +9,7 @@ import {
   setLLMSettingEnabledValues,
 } from '@/utils/form';
 import { zodResolver } from '@hookform/resolvers/zod';
+import { omit } from 'lodash';
 import { X } from 'lucide-react';
 import { useEffect } from 'react';
 import { useForm } from 'react-hook-form';
@@ -35,13 +36,18 @@ export function ChatSettings({ switchSettingVisible }: ChatSettingsProps) {
     shouldUnregister: true,
     defaultValues: {
       name: '',
+      icon: [],
       language: 'English',
+      description: '',
+      kb_ids: [],
       prompt_config: {
         quote: true,
         keyword: false,
         tts: false,
         use_kg: false,
         refine_multiturn: true,
+        system: '',
+        parameters: [],
       },
       top_n: 8,
       vector_similarity_weight: 0.2,
@@ -64,7 +70,7 @@ export function ChatSettings({ switchSettingVisible }: ChatSettingsProps) {
         ? await transformFile2Base64(icon[0])
         : '';
     setDialog({
-      ...data,
+      ...omit(data, 'operator_permission'),
       ...nextValues,
       icon: avatar,
       dialog_id: id,
@@ -89,25 +95,28 @@ export function ChatSettings({ switchSettingVisible }: ChatSettingsProps) {
   }, [data, form]);
 
   return (
-    <section className="p-5  w-[440px] border-l">
+    <section className="p-5  w-[440px] border-l flex flex-col">
       <div className="flex justify-between items-center text-base pb-2">
         {t('chat.chatSetting')}
         <X className="size-4 cursor-pointer" onClick={switchSettingVisible} />
       </div>
       <Form {...form}>
-        <form onSubmit={form.handleSubmit(onSubmit, onInvalid)}>
+        <form
-          <section className="space-y-6 overflow-auto max-h-[82vh] pr-4">
+          onSubmit={form.handleSubmit(onSubmit, onInvalid)}
+          className="flex-1 flex flex-col min-h-0"
+        >
+          <section className="space-y-6 overflow-auto flex-1 pr-4 min-h-0">
             <ChatBasicSetting></ChatBasicSetting>
             <Separator />
             <ChatPromptEngine></ChatPromptEngine>
             <Separator />
             <ChatModelSettings></ChatModelSettings>
           </section>
-          <div className="space-x-5 text-right">
+          <div className="space-x-5 text-right pt-4">
             <Button variant={'outline'} onClick={switchSettingVisible}>
               {t('chat.cancel')}
             </Button>
-            <ButtonLoading className=" my-4" type="submit" loading={loading}>
+            <ButtonLoading type="submit" loading={loading}>
               {t('common.save')}
             </ButtonLoading>
           </div>

web/src/pages/next-chats/chat/app-settings/use-chat-setting-schema.tsx

@@ -34,11 +34,11 @@ export function useChatSettingSchema() {
     name: z.string().min(1, { message: t('assistantNameMessage') }),
     icon: z.array(z.instanceof(File)),
     language: z.string().min(1, {
-      message: 'Username must be at least 2 characters.',
+      message: t('languageMessage'),
     }),
-    description: z.string(),
+    description: z.string().optional(),
     kb_ids: z.array(z.string()).min(0, {
-      message: 'Username must be at least 1 characters.',
+      message: t('knowledgeBasesMessage'),
     }),
     prompt_config: promptConfigSchema,
     ...rerankFormSchema,

web/src/pages/next-chats/chat/chat-box/multiple-chat-box.tsx

@@ -2,6 +2,8 @@ import { LargeModelFormFieldWithoutFilter } from '@/components/large-model-form-
 import { LlmSettingSchema } from '@/components/llm-setting-items/next';
 import { NextMessageInput } from '@/components/message-input/next';
 import MessageItem from '@/components/message-item';
+import PdfDrawer from '@/components/pdf-drawer';
+import { useClickDrawer } from '@/components/pdf-drawer/hooks';
 import { Button } from '@/components/ui/button';
 import { Card, CardContent, CardHeader, CardTitle } from '@/components/ui/card';
 import { Form } from '@/components/ui/form';
@@ -54,7 +56,8 @@ type ChatCardProps = {
 } & Pick<
   MultipleChatBoxProps,
   'controller' | 'removeChatBox' | 'addChatBox' | 'chatBoxIds'
->;
+> &
+  Pick<ReturnType<typeof useClickDrawer>, 'clickDocumentButton'>;
 
 const ChatCard = forwardRef(function ChatCard(
   {
@@ -66,6 +69,7 @@ const ChatCard = forwardRef(function ChatCard(
     chatBoxIds,
     derivedMessages,
     sendLoading,
+    clickDocumentButton,
   }: ChatCardProps,
   ref,
 ) {
@@ -178,6 +182,7 @@ const ChatCard = forwardRef(function ChatCard(
                   removeMessageById={removeMessageById}
                   regenerateMessage={regenerateMessage}
                   sendLoading={sendLoading}
+                  clickDocumentButton={clickDocumentButton}
                 ></MessageItem>
               );
             })}
@@ -211,6 +216,8 @@ export function MultipleChatBox({
   const { conversationId } = useGetChatSearchParams();
   const disabled = useGetSendButtonDisabled();
   const sendDisabled = useSendButtonDisabled(value);
+  const { visible, hideModal, documentId, selectedChunk, clickDocumentButton } =
+    useClickDrawer();
 
   return (
     <section className="h-full flex flex-col px-5">
@@ -227,6 +234,7 @@ export function MultipleChatBox({
             derivedMessages={messageRecord[id]}
             ref={setFormRef(id)}
             sendLoading={sendLoading}
+            clickDocumentButton={clickDocumentButton}
           ></ChatCard>
         ))}
       </div>
@@ -246,6 +254,14 @@ export function MultipleChatBox({
           onUpload={handleUploadFile}
         />
       </div>
+      {visible && (
+        <PdfDrawer
+          visible={visible}
+          hideModal={hideModal}
+          documentId={documentId}
+          chunk={selectedChunk}
+        ></PdfDrawer>
+      )}
     </section>
   );
 }

web/src/pages/next-chats/chat/chat-box/single-chat-box.tsx

@@ -1,5 +1,7 @@
 import { NextMessageInput } from '@/components/message-input/next';
 import MessageItem from '@/components/message-item';
+import PdfDrawer from '@/components/pdf-drawer';
+import { useClickDrawer } from '@/components/pdf-drawer/hooks';
 import { MessageType } from '@/constants/chat';
 import {
   useFetchConversation,
@@ -43,6 +45,8 @@ export function SingleChatBox({ controller }: IProps) {
   const { data: conversation } = useFetchConversation();
   const disabled = useGetSendButtonDisabled();
   const sendDisabled = useSendButtonDisabled(value);
+  const { visible, hideModal, documentId, selectedChunk, clickDocumentButton } =
+    useClickDrawer();
 
   return (
     <section className="flex flex-col p-5 h-full">
@@ -68,7 +72,7 @@ export function SingleChatBox({ controller }: IProps) {
                   },
                   message,
                 )}
-                // clickDocumentButton={clickDocumentButton}
+                clickDocumentButton={clickDocumentButton}
                 index={i}
                 removeMessageById={removeMessageById}
                 regenerateMessage={regenerateMessage}
@@ -94,6 +98,14 @@ export function SingleChatBox({ controller }: IProps) {
         onUpload={handleUploadFile}
         isUploading={isUploading}
       />
+      {visible && (
+        <PdfDrawer
+          visible={visible}
+          hideModal={hideModal}
+          documentId={documentId}
+          chunk={selectedChunk}
+        ></PdfDrawer>
+      )}
     </section>
   );
 }

web/src/pages/next-chats/chat/index.tsx

@@ -109,13 +109,12 @@ export default function Chat() {
 
         <Card className="flex-1 min-w-0 bg-transparent border h-full">
           <CardContent className="flex p-0 h-full">
-            <Card className="flex flex-col flex-1 bg-transparent">
+            <Card className="flex flex-col flex-1 bg-transparent min-w-0">
               <CardHeader
                 className={cn('p-5', { 'border-b': hasSingleChatBox })}
               >
                 <CardTitle className="flex justify-between items-center text-base">
-                  <div>{conversation.name}</div>
+                  <div className="truncate">{conversation.name}</div>
-
                   <Button
                     variant={'ghost'}
                     onClick={switchDebugMode}

web/src/pages/next-chats/chat/sessions.tsx

@@ -90,8 +90,8 @@ export function Sessions({
               'bg-bg-card': conversationId === x.id,
             })}
           >
-            <CardContent className="px-3 py-2 flex justify-between items-center group">
+            <CardContent className="px-3 py-2 flex justify-between items-center group gap-1">
-              {x.name}
+              <div className="truncate">{x.name}</div>
               <ConversationDropdown conversation={x}>
                 <MoreButton></MoreButton>
               </ConversationDropdown>

web/src/pages/next-chats/hooks/use-rename-chat.ts

@@ -1,5 +1,6 @@
 import { useSetModalState } from '@/hooks/common-hooks';
 import { useSetDialog } from '@/hooks/use-chat-request';
+import { useFetchTenantInfo } from '@/hooks/use-user-setting-request';
 import { IDialog } from '@/interfaces/database/chat';
 import { isEmpty, omit } from 'lodash';
 import { useCallback, useMemo, useState } from 'react';
@@ -14,6 +15,7 @@ export const useRenameChat = () => {
   } = useSetModalState();
   const { setDialog, loading } = useSetDialog();
   const { t } = useTranslation();
+  const tenantInfo = useFetchTenantInfo();
 
   const InitialData = useMemo(
     () => ({
@@ -32,13 +34,13 @@ export const useRenameChat = () => {
         reasoning: false,
         parameters: [{ key: 'knowledge', optional: false }],
       },
-      llm_id: '',
+      llm_id: tenantInfo.data.llm_id,
       llm_setting: {},
       similarity_threshold: 0.2,
       vector_similarity_weight: 0.30000000000000004,
       top_n: 8,
     }),
-    [t],
+    [t, tenantInfo.data.llm_id],
   );
 
   const onChatRenameOk = useCallback(
@@ -46,7 +48,10 @@ export const useRenameChat = () => {
       const nextChat = {
         ...(isEmpty(chat)
           ? InitialData
-          : { ...omit(chat, 'nickname', 'tenant_avatar'), dialog_id: chat.id }),
+          : {
+              ...omit(chat, 'nickname', 'tenant_avatar', 'operator_permission'),
+              dialog_id: chat.id,
+            }),
         name,
       };
       const ret = await setDialog(nextChat);

web/src/pages/next-chats/hooks/use-send-multiple-message.ts

@@ -1,3 +1,4 @@
+import showMessage from '@/components/ui/message';
 import { MessageType } from '@/constants/chat';
 import {
   useHandleMessageInputChange,
@@ -159,7 +160,7 @@ export function useSendMultipleChatMessage(
       if (res && (res?.response.status !== 200 || res?.data?.code !== 0)) {
         // cancel loading
         setValue(message.content);
-        console.info('removeLatestMessage111');
+        showMessage.error(res.data.message);
         removeLatestMessage(chatBoxId);
       }
     },

web/src/pages/next-search/index.tsx

@@ -128,7 +128,7 @@ export default function SearchPage() {
       </div>
       <div className="absolute right-5 top-4 ">
         <Button
-          className="bg-text-primary  text-bg-base border-b-[#00BEB4] border-b-2"
+          className="bg-text-primary  text-bg-base border-b-accent-primary border-b-2"
           onClick={() => {
             handleOperate().then((res) => {
               console.log(res, 'res');

web/src/pages/next-search/search-home.tsx

@@ -27,7 +27,7 @@ export default function SearchPage({
       <div className="relative z-10 px-8 pt-8 flex  text-transparent flex-col justify-center items-center w-[780px]">
         <h1
           className={cn(
-            'text-4xl font-bold bg-gradient-to-r from-sky-600 from-30% via-sky-500 via-60% to-emerald-500 bg-clip-text',
+            'text-4xl font-bold bg-gradient-to-l from-[#40EBE3] to-[#4A51FF] bg-clip-text',
           )}
         >
           RAGFlow

web/src/pages/next-search/search-setting-aisummery-config.tsx

@@ -21,7 +21,7 @@ import {
 } from '@/constants/knowledge';
 import { useTranslate } from '@/hooks/common-hooks';
 import { useComposeLlmOptionsByModelTypes } from '@/hooks/llm-hooks';
-import { camelCase } from 'lodash';
+import { camelCase, isEqual } from 'lodash';
 import { useCallback } from 'react';
 import { useFormContext } from 'react-hook-form';
 import { z } from 'zod';
@@ -61,20 +61,15 @@ export function LlmSettingFieldItems({
 
   const handleChange = useCallback(
     (parameter: string) => {
-      const currentValues = { ...form.getValues() };
-      console.log('currentValues', currentValues);
       const values =
         settledModelVariableMap[
           parameter as keyof typeof settledModelVariableMap
         ];
       const enabledKeys = Object.keys(LlmSettingEnableSchema);
 
-      // const nextValues = { ...currentValues, ...values };
-
       for (const key in values) {
         if (Object.prototype.hasOwnProperty.call(values, key)) {
-          const element = values[key];
+          const element = values[key as keyof typeof values];
-
           form.setValue(`${prefix}.${key}`, element);
         }
       }
@@ -90,7 +85,11 @@ export function LlmSettingFieldItems({
   const parameterOptions = Object.values(ModelVariableType).map((x) => ({
     label: t(camelCase(x)),
     value: x,
-  }));
+  })) as unknown as { label: string; value: ModelVariableType | 'Custom' }[];
+  parameterOptions.push({
+    label: t(camelCase('Custom')),
+    value: 'Custom',
+  });
 
   const getFieldWithPrefix = useCallback(
     (name: string) => {
@@ -99,6 +98,35 @@ export function LlmSettingFieldItems({
     [prefix],
   );
 
+  const checkParameterIsEquel = () => {
+    const [
+      parameter,
+      topPValue,
+      frequencyPenaltyValue,
+      temperatureValue,
+      presencePenaltyValue,
+    ] = form.getValues([
+      getFieldWithPrefix('parameter'),
+      getFieldWithPrefix('temperature'),
+      getFieldWithPrefix('top_p'),
+      getFieldWithPrefix('frequency_penalty'),
+      getFieldWithPrefix('presence_penalty'),
+    ]);
+    if (parameter && parameter !== 'Custom') {
+      const parameterValue =
+        settledModelVariableMap[parameter as keyof typeof ModelVariableType];
+      const parameterRealValue = {
+        top_p: topPValue,
+        temperature: temperatureValue,
+        frequency_penalty: frequencyPenaltyValue,
+        presence_penalty: presencePenaltyValue,
+      };
+      if (!isEqual(parameterValue, parameterRealValue)) {
+        form.setValue(getFieldWithPrefix('parameter'), 'Custom');
+      }
+    }
+  };
+
   return (
     <div className="space-y-5">
       <FormField
@@ -113,7 +141,7 @@ export function LlmSettingFieldItems({
             <FormControl>
               <SelectWithSearch
                 options={options || modelOptions}
-                triggerClassName="bg-bg-card"
+                triggerClassName="!bg-bg-input"
                 {...field}
               ></SelectWithSearch>
             </FormControl>
@@ -159,6 +187,9 @@ export function LlmSettingFieldItems({
         label="temperature"
         max={1}
         step={0.01}
+        onChange={() => {
+          checkParameterIsEquel();
+        }}
       ></SliderInputSwitchFormField>
       <SliderInputSwitchFormField
         name={getFieldWithPrefix('top_p')}
@@ -166,6 +197,9 @@ export function LlmSettingFieldItems({
         label="topP"
         max={1}
         step={0.01}
+        onChange={() => {
+          checkParameterIsEquel();
+        }}
       ></SliderInputSwitchFormField>
       <SliderInputSwitchFormField
         name={getFieldWithPrefix('presence_penalty')}
@@ -173,6 +207,9 @@ export function LlmSettingFieldItems({
         label="presencePenalty"
         max={1}
         step={0.01}
+        onChange={() => {
+          checkParameterIsEquel();
+        }}
       ></SliderInputSwitchFormField>
       <SliderInputSwitchFormField
         name={getFieldWithPrefix('frequency_penalty')}
@@ -180,6 +217,9 @@ export function LlmSettingFieldItems({
         label="frequencyPenalty"
         max={1}
         step={0.01}
+        onChange={() => {
+          checkParameterIsEquel();
+        }}
       ></SliderInputSwitchFormField>
       {/* <SliderInputSwitchFormField
         name={getFieldWithPrefix('max_tokens')}

web/src/pages/next-search/search-setting.tsx

@@ -114,8 +114,8 @@ const SearchSetting: React.FC<SearchSettingProps> = ({
   const [avatarBase64Str, setAvatarBase64Str] = useState(''); // Avatar Image base64
   const [datasetList, setDatasetList] = useState<MultiSelectOptionType[]>([]);
   const [datasetSelectEmbdId, setDatasetSelectEmbdId] = useState('');
-  const descriptionDefaultValue = 'You are an intelligent assistant.';
   const { t } = useTranslation();
+  const descriptionDefaultValue = t('search.descriptionValue');
   const resetForm = useCallback(() => {
     formMethods.reset({
       search_id: data?.id,
@@ -136,9 +136,9 @@ const SearchSetting: React.FC<SearchSettingProps> = ({
         use_rerank: search_config?.rerank_id ? true : false,
         top_k: search_config?.top_k || 1024,
         summary: search_config?.summary || false,
-        chat_id: '',
+        chat_id: search_config?.chat_id || '',
         llm_setting: {
-          llm_id: llm_setting?.llm_id || '',
+          llm_id: search_config?.chat_id || '',
           parameter: llm_setting?.parameter,
           temperature: llm_setting?.temperature,
           top_p: llm_setting?.top_p,
@@ -159,7 +159,7 @@ const SearchSetting: React.FC<SearchSettingProps> = ({
         meta_data_filter: search_config?.meta_data_filter,
       },
     });
-  }, [data, search_config, llm_setting, formMethods]);
+  }, [data, search_config, llm_setting, formMethods, descriptionDefaultValue]);
 
   useEffect(() => {
     resetForm();
@@ -255,7 +255,7 @@ const SearchSetting: React.FC<SearchSettingProps> = ({
         ...other_config
       } = search_config;
       const llmSetting = {
-        llm_id: llm_setting.llm_id,
+        // llm_id: llm_setting.llm_id,
         parameter: llm_setting.parameter,
         temperature: llm_setting.temperature,
         top_p: llm_setting.top_p,
@@ -263,22 +263,11 @@ const SearchSetting: React.FC<SearchSettingProps> = ({
         presence_penalty: llm_setting.presence_penalty,
       } as IllmSettingProps;
 
-      if (!llm_setting.frequencyPenaltyEnabled) {
-        delete llmSetting.frequency_penalty;
-      }
-      if (!llm_setting.presencePenaltyEnabled) {
-        delete llmSetting.presence_penalty;
-      }
-      if (!llm_setting.temperatureEnabled) {
-        delete llmSetting.temperature;
-      }
-      if (!llm_setting.topPEnabled) {
-        delete llmSetting.top_p;
-      }
       await updateSearch({
         ...other_formdata,
         search_config: {
           ...other_config,
+          chat_id: llm_setting.llm_id,
           vector_similarity_weight: 1 - vector_similarity_weight,
           rerank_id: use_rerank ? rerank_id : '',
           llm_setting: { ...llmSetting },
@@ -415,7 +404,7 @@ const SearchSetting: React.FC<SearchSettingProps> = ({
                   <FormLabel>{t('search.description')}</FormLabel>
                   <FormControl>
                     <Textarea
-                      placeholder="You are an intelligent assistant."
+                      placeholder={descriptionDefaultValue}
                       {...field}
                       onFocus={() => {
                         if (field.value === descriptionDefaultValue) {
@@ -444,7 +433,7 @@ const SearchSetting: React.FC<SearchSettingProps> = ({
                     <span className="text-destructive mr-1"> *</span>
                     {t('search.datasets')}
                   </FormLabel>
-                  <FormControl>
+                  <FormControl className="bg-bg-input">
                     <MultiSelect
                       options={datasetList}
                       onValueChange={(value) => {
@@ -452,7 +441,6 @@ const SearchSetting: React.FC<SearchSettingProps> = ({
                       }}
                       showSelectAll={false}
                       placeholder={t('chat.knowledgeBasesMessage')}
-                      variant="inverted"
                       maxCount={10}
                       defaultValue={field.value}
                       {...field}
@@ -568,6 +556,7 @@ const SearchSetting: React.FC<SearchSettingProps> = ({
                         <RAGFlowSelect
                           {...field}
                           options={rerankModelOptions}
+                          triggerClassName={'bg-bg-input'}
                           // disabled={disabled}
                           placeholder={'model'}
                         />

web/src/pages/next-search/search-view.tsx

@@ -83,7 +83,7 @@ export default function SearchingView({
       >
         <h1
           className={cn(
-            'text-4xl font-bold bg-gradient-to-r from-sky-600 from-30% via-sky-500 via-60% to-emerald-500 bg-clip-text cursor-pointer',
+            'text-4xl font-bold bg-gradient-to-l from-[#40EBE3] to-[#4A51FF] bg-clip-text cursor-pointer',
           )}
           onClick={() => {
             setIsSearching?.(false);