Fix: Fixed an issue where knowledge base could not be shared #9634 (#9642)

### What problem does this PR solve?

Fix: Fixed an issue where knowledge base could not be shared #9634

### 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))
-        prompt = self.string_format(prompt, args)
+        for p in self._param.prompts:
+            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:

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

@@ -44,9 +44,6 @@ def retrieval(tenant_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)
 
         ranks = settings.retrievaler.retrieval(

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
-                    new_text += working_text[last_end:match.start()] + html_table + "\n\n"
+                    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"
                 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
-            #HTML table extraction - handle possible html/body wrapper tags
+        if "<table>" in working_text.lower():  # for optimize performance
+            # 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,
+        }

graphrag/entity_resolution.py

@@ -169,7 +169,7 @@ 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:
+                with trio.move_on_after(280) 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/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)

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))
-            return [types.TextContent(type="text", text="\n".join(chunks))]
+
+            # Cache document metadata and dataset information
+            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/raptor.py

@@ -42,7 +42,7 @@ 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)
         if response:
@@ -56,7 +56,7 @@ class RecursiveAbstractiveProcessing4TreeOrganizedRetrieval:
         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)
         if response is not None:
@@ -86,7 +86,7 @@ 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]

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

@@ -85,7 +85,7 @@ 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 = {
-  setFiles: Dispatch<SetStateAction<File[]>>;
+function buildUploadFormSchema(t: TFunction) {
+  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;
 };
-
-export function UploaderTabs({ setFiles }: UploaderTabsProps) {
+function UploadForm({ submit, showParseOnCreation }: UploadFormProps) {
   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">
-      <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">
-        <FileUploader
-          maxFileCount={8}
-          maxSize={8 * 1024 * 1024}
-          onValueChange={setFiles}
-          accept={{ '*': [] }}
-        />
-      </TabsContent>
-      <TabsContent value="password">{t('common.comingSoon')}</TabsContent>
-    </Tabs>
+    <Form {...form}>
+      <form
+        onSubmit={form.handleSubmit(submit)}
+        id={UploadFormId}
+        className="space-y-4"
+      >
+        {showParseOnCreation && (
+          <RAGFlowFormItem
+            name="parseOnCreation"
+            label={t('fileManager.parseOnCreation')}
+          >
+            {(field) => (
+              <Switch
+                onCheckedChange={field.onChange}
+                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,
-    maxFileCount = 1,
+    maxSize = 1024 * 1024 * 10000000,
+    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/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/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/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>
-          <FormLabel tooltip={tooltip}>{label}</FormLabel>
+        <FormItem
+          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 (
-    <span className="bg-text-secondary rounded-sm px-1 text-bg-base text-xs">
-      {children}
-    </span>
-  );
+  return <span className="bg-bg-card rounded-sm px-1 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/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': selectedValue === actualValue,
+                'text-bg-base bg-metallic-gradient border-b-[#00BEB4] border-b-2':
+                  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/locales/en.ts

@@ -70,7 +70,7 @@ export default {
       review: 'from 500+ reviews',
     },
     header: {
-      knowledgeBase: 'Knowledge Base',
+      knowledgeBase: 'Dataset',
       chat: 'Chat',
       register: 'Register',
       signin: 'Sign in',
@@ -86,7 +86,7 @@ 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',
@@ -845,6 +845,7 @@ 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 +1442,7 @@ 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/zh.ts

@@ -799,6 +799,7 @@ 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 +1345,7 @@ 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/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/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.DONE]: { label: 'SUCCESS', color: 'blue' },
-  [RunningStatus.FAIL]: { label: 'FAIL', color: 'red' },
+  [RunningStatus.CANCEL]: { label: 'CANCEL', color: 'var(--state-warning)' },
+  [RunningStatus.DONE]: { label: 'SUCCESS', color: 'var(--state-success)' },
+  [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.RUNNING]: <CircleX />,
-  [RunningStatus.CANCEL]: <RefreshCw />,
-  [RunningStatus.DONE]: <RefreshCw />,
-  [RunningStatus.FAIL]: <RefreshCw />,
+  [RunningStatus.UNSTART]: (
+    <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.RUNNING]: <CircleX size={14} color="var(--state-error)" />,
+  [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">
-      <div className="w-28 flex items-center justify-between">
+    <section className="flex gap-8 items-center">
+      <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
-          variant={'ghost'}
-          size={'sm'}
+        <div
+          className="cursor-pointer flex items-center gap-3"
           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>
@@ -35,7 +35,7 @@ export default function DatasetWrapper() {
           </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="overflow-auto max-h-[76vh]">
+    <section className="h-full flex flex-col">
+      <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 +1,5 @@
 import { Button } from '@/components/ui/button';
+import { cn } from '@/lib/utils';
 import { X } from 'lucide-react';
 import { useState } from 'react';
 import CategoryPanel from './category-panel';
@@ -14,20 +15,22 @@ export default ({
 
   return (
     <div
-      style={{
-        display: tab === 'chunkMethodForm' ? 'block' : 'none',
-      }}
+      className={cn('hidden flex-1', {
+        'flex flex-col': tab === 'chunkMethodForm',
+      })}
     >
-      <Button
-        variant="outline"
-        onClick={() => {
-          setVisible(!visible);
-        }}
-      >
-        Learn More
-      </Button>
+      <div>
+        <Button
+          variant="outline"
+          onClick={() => {
+            setVisible(!visible);
+          }}
+        >
+          Learn More
+        </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/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');
-              const { name, description } = form.formState.values;
+              let isValidate = await form.trigger('name');
+              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
@@ -120,10 +122,10 @@ export default function DatasetSettings() {
                   </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

@@ -62,8 +62,8 @@ export function SideBar({ refreshCount }: PropType) {
           name={data.name}
           className="size-16"
         ></RAGFlowAvatar>
-        <div className=" text-text-secondary text-xs space-y-1">
-          <h3 className="text-lg font-semibold line-clamp-1 text-text-primary">
+        <div className=" text-text-secondary text-xs space-y-1 overflow-hidden">
+          <h3 className="text-lg font-semibold line-clamp-1 text-text-primary text-ellipsis overflow-hidden">
             {data.name}
           </h3>
           <div className="flex justify-between">

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

@@ -1,5 +1,6 @@
 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';
@@ -32,6 +33,7 @@ export function DatasetCard({
           <MoreButton></MoreButton>
         </DatasetDropdown>
       }
+      sharedBadge={<SharedBadge>{dataset.nickname}</SharedBadge>}
       onClick={navigateToDataset(dataset.id)}
     />
   );
@@ -41,7 +43,7 @@ export function SeeAllCard() {
   const { navigateToDatasetList } = useNavigatePage();
 
   return (
-    <Card className="w-40" onClick={navigateToDatasetList}>
+    <Card className="w-40 flex-none" 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

@@ -30,7 +30,7 @@ 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) => (
               <DatasetCard
                 key={dataset.id}

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

@@ -35,13 +35,18 @@ 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,
@@ -89,25 +94,28 @@ 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)}>
-          <section className="space-y-6 overflow-auto max-h-[82vh] pr-4">
+        <form
+          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-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

@@ -113,7 +113,7 @@ export function LlmSettingFieldItems({
             <FormControl>
               <SelectWithSearch
                 options={options || modelOptions}
-                triggerClassName="bg-bg-card"
+                triggerClassName="!bg-bg-input"
                 {...field}
               ></SelectWithSearch>
             </FormControl>

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,
@@ -415,7 +415,7 @@ 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 +444,7 @@ 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 +452,6 @@ const SearchSetting: React.FC<SearchSettingProps> = ({
                       }}
                       showSelectAll={false}
                       placeholder={t('chat.knowledgeBasesMessage')}
-                      variant="inverted"
                       maxCount={10}
                       defaultValue={field.value}
                       {...field}
@@ -568,6 +567,7 @@ 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);

web/src/pages/profile-setting/mcp/import-mcp-dialog/import-mcp-form.tsx

@@ -59,8 +59,6 @@ export function ImportMcpForm({ hideModal, onOk }: IModalProps<any>) {
                 <FileUploader
                   value={field.value}
                   onValueChange={field.onChange}
-                  maxFileCount={1}
-                  maxSize={4 * 1024 * 1024}
                   accept={{ '*.json': [FileMimeType.Json] }}
                 />
               </FormControl>

web/src/routes.ts

@@ -70,116 +70,73 @@ const routes = [
     component: `@/pages${Routes.AgentShare}`,
     layout: false,
   },
-  // {
-  //   path: '/',
-  //   component: '@/layouts',
-  //   layout: false,
-  //   wrappers: ['@/wrappers/auth'],
-  //   routes: [
-  //     { path: '/', redirect: '/knowledge' },
-  //     {
-  //       path: '/knowledge',
-  //       component: '@/pages/knowledge',
-  //       // component: '@/pages/knowledge/datasets',
-  //     },
-  //     {
-  //       path: '/knowledge',
-  //       component: '@/pages/add-knowledge',
-  //       routes: [
-  //         {
-  //           path: '/knowledge/dataset',
-  //           component: '@/pages/add-knowledge/components/knowledge-dataset',
-  //           routes: [
-  //             {
-  //               path: '/knowledge/dataset',
-  //               component: '@/pages/add-knowledge/components/knowledge-file',
-  //             },
-  //             {
-  //               path: '/knowledge/dataset/chunk',
-  //               component: '@/pages/add-knowledge/components/knowledge-chunk',
-  //             },
-  //           ],
-  //         },
-  //         {
-  //           path: '/knowledge/configuration',
-  //           component: '@/pages/add-knowledge/components/knowledge-setting',
-  //         },
-  //         {
-  //           path: '/knowledge/testing',
-  //           component: '@/pages/add-knowledge/components/knowledge-testing',
-  //         },
-  //         {
-  //           path: '/knowledge/knowledgeGraph',
-  //           component: '@/pages/add-knowledge/components/knowledge-graph',
-  //         },
-  //       ],
-  //     },
-  //     {
-  //       path: '/chat',
-  //       component: '@/pages/chat',
-  //     },
-  //     {
-  //       path: '/user-setting',
-  //       component: '@/pages/user-setting',
-  //       routes: [
-  //         { path: '/user-setting', redirect: '/user-setting/profile' },
-  //         {
-  //           path: '/user-setting/profile',
-  //           // component: '@/pages/user-setting/setting-profile',
-  //           component: '@/pages/user-setting/setting-profile',
-  //         },
-  //         {
-  //           path: '/user-setting/locale',
-  //           component: '@/pages/user-setting/setting-locale',
-  //         },
-  //         {
-  //           path: '/user-setting/password',
-  //           component: '@/pages/user-setting/setting-password',
-  //         },
-  //         {
-  //           path: '/user-setting/model',
-  //           component: '@/pages/user-setting/setting-model',
-  //         },
-  //         {
-  //           path: '/user-setting/team',
-  //           component: '@/pages/user-setting/setting-team',
-  //         },
-  //         {
-  //           path: '/user-setting/system',
-  //           component: '@/pages/user-setting/setting-system',
-  //         },
-  //         {
-  //           path: '/user-setting/api',
-  //           component: '@/pages/user-setting/setting-api',
-  //         },
-  //         {
-  //           path: `/user-setting${Routes.Mcp}`,
-  //           component: `@/pages${Routes.ProfileMcp}`,
-  //         },
-  //       ],
-  //     },
-  //     {
-  //       path: '/file',
-  //       component: '@/pages/file-manager',
-  //     },
-  //     {
-  //       path: '/flow',
-  //       component: '@/pages/flow/list',
-  //     },
-  //     {
-  //       path: Routes.AgentList,
-  //       component: `@/pages/${Routes.Agents}`,
-  //     },
-  //     {
-  //       path: '/flow/:id',
-  //       component: '@/pages/flow',
-  //     },
-  //     {
-  //       path: '/search',
-  //       component: '@/pages/search',
-  //     },
-  //   ],
-  // },
+  {
+    path: Routes.Home,
+    component: '@/layouts',
+    layout: false,
+    redirect: '/knowledge',
+  },
+  {
+    path: '/knowledge',
+    component: '@/pages/knowledge',
+  },
+  {
+    path: '/knowledge',
+    component: '@/pages/add-knowledge',
+    routes: [
+      {
+        path: 'dataset',
+        component: '@/pages/add-knowledge/components/knowledge-dataset',
+        routes: [
+          {
+            path: '',
+            component: '@/pages/add-knowledge/components/knowledge-file',
+          },
+          {
+            path: 'chunk',
+            component: '@/pages/add-knowledge/components/knowledge-chunk',
+          },
+        ],
+      },
+      {
+        path: 'configuration',
+        component: '@/pages/add-knowledge/components/knowledge-setting',
+      },
+      {
+        path: 'testing',
+        component: '@/pages/add-knowledge/components/knowledge-testing',
+      },
+      {
+        path: 'knowledgeGraph',
+        component: '@/pages/add-knowledge/components/knowledge-graph',
+      },
+    ],
+  },
+
+  {
+    path: '/chat',
+    component: '@/pages/chat',
+  },
+  {
+    path: '/file',
+    component: '@/pages/file-manager',
+  },
+  {
+    path: '/flow',
+    component: '@/pages/flow/list',
+  },
+  {
+    path: Routes.AgentList,
+    component: `@/pages/${Routes.Agents}`,
+  },
+  {
+    path: '/flow/:id',
+    component: '@/pages/flow',
+  },
+  {
+    path: '/search',
+    component: '@/pages/search',
+  },
   {
     path: '/document/:id',
     component: '@/pages/document-viewer',

web/tailwind.config.js

@@ -58,6 +58,8 @@ module.exports = {
 
         'bg-base': 'var(--bg-base)',
         'bg-card': 'var(--bg-card)',
+        'bg-component': 'var(--bg-component)',
+        'bg-input': 'var(--bg-input)',
         'text-primary': 'var(--text-primary)',
         'text-secondary': 'var(--text-secondary)',
         'text-disabled': 'var(--text-disabled)',
@@ -206,6 +208,10 @@ module.exports = {
           ring: 'hsl(var(--sidebar-ring))',
         },
       },
+      backgroundImage: {
+        'metallic-gradient':
+          'linear-gradient(104deg, var(--text-primary) 30%, var(--metallic) 50%, var(--text-primary) 70%)',
+      },
       borderRadius: {
         lg: `var(--radius)`,
         md: `calc(var(--radius) - 2px)`,

web/tailwind.css

@@ -90,11 +90,15 @@
 
     --input-border: rgba(22, 22, 24, 0.2);
 
+    --metallic: #46464a;
     /* design colors */
 
-    --bg-base: #f6f6f7;
+    --bg-base: #ffffff;
     /* card color , dividing line */
     --bg-card: rgba(0, 0, 0, 0.05);
+    --bg-component: #ffffff;
+    --bg-input: rgba(255, 255, 255, 0);
+    --bg-accent: rgba(76, 164, 231, 0.05);
     /* Button ,Body text, Input completed text */
     --text-primary: #161618;
     --text-secondary: #75787a;
@@ -107,7 +111,7 @@
     --border-accent: #000000;
     --border-button: rgba(0, 0, 0, 0.1);
     /* Regulators, parsing, switches, variables */
-    --accent-primary: #4ca4e7;
+    --accent-primary: #00beb4;
     /* Output Variables Box */
     --bg-accent: rgba(76, 164, 231, 0.05);
 
@@ -230,10 +234,13 @@
 
     --input-border: rgba(255, 255, 255, 0.2);
 
+    --metallic: #fafafa;
     /* design colors */
 
     --bg-base: #161618;
     --bg-card: rgba(255, 255, 255, 0.05);
+    --bg-component: #202025;
+    --bg-input: rgba(255, 255, 255, 0.05);
     --text-primary: #f6f6f7;
     --text-secondary: #b2b5b7;
     --text-disabled: #75787a;