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

### What problem does this PR solve?

Close #9648

### Type of change

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

api/apps/sdk/session.py

@@ -84,18 +84,10 @@ def create_agent_session(tenant_id, agent_id):
     session_id=get_uuid()
     canvas = Canvas(cvs.dsl, tenant_id, agent_id)
     canvas.reset()
-    conv = {
-        "id": session_id,
-        "dialog_id": cvs.id,
-        "user_id": user_id,
-        "message": [],
-        "source": "agent",
-        "dsl": cvs.dsl
-    }
-    API4ConversationService.save(**conv)
-
+    
     cvs.dsl = json.loads(str(canvas))
     conv = {"id": session_id, "dialog_id": cvs.id, "user_id": user_id, "message": [{"role": "assistant", "content": canvas.get_prologue()}], "source": "agent", "dsl": cvs.dsl}
+    API4ConversationService.save(**conv)
     conv["agent_id"] = conv.pop("dialog_id")
     return get_result(data=conv)
 
@@ -570,6 +562,9 @@ def list_agent_session(tenant_id, agent_id):
                             "chunks" in conv["reference"][chunk_num]):
                         chunks = conv["reference"][chunk_num]["chunks"]
                         for chunk in chunks:
+                            # Ensure chunk is a dictionary before calling get method
+                            if not isinstance(chunk, dict):
+                                continue
                             new_chunk = {
                                 "id": chunk.get("chunk_id", chunk.get("id")),
                                 "content": chunk.get("content_with_weight", chunk.get("content")),

api/db/services/canvas_service.py

@@ -182,7 +182,8 @@ def completion(tenant_id, agent_id, session_id=None, **kwargs):
             "user_id": user_id,
             "message": [],
             "source": "agent",
-            "dsl": cvs.dsl
+            "dsl": cvs.dsl,
+            "reference": []
         }
         API4ConversationService.save(**conv)
         conv = API4Conversation(**conv)

api/db/services/dialog_service.py

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

api/utils/api_utils.py

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

docs/references/http_api_reference.md

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

graphrag/entity_resolution.py

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

graphrag/general/community_reports_extractor.py

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

graphrag/general/index.py

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

graphrag/light/graph_prompt.py

@@ -130,7 +130,36 @@ Output:
 
 PROMPTS[
     "entiti_continue_extraction"
-] = """MANY entities were missed in the last extraction.  Add them below using the same format:
+] = """
+MANY entities and relationships were missed in the last extraction. Please find only the missing entities and relationships from previous text.
+
+---Remember Steps---
+
+1. Identify all entities. For each identified entity, extract the following information:
+- entity_name: Name of the entity, use same language as input text. If English, capitalized the name
+- entity_type: One of the following types: [{entity_types}]
+- entity_description: Provide a comprehensive description of the entity's attributes and activities *based solely on the information present in the input text*. **Do not infer or hallucinate information not explicitly stated.** If the text provides insufficient information to create a comprehensive description, state "Description not available in text."
+Format each entity as ("entity"{tuple_delimiter}<entity_name>{tuple_delimiter}<entity_type>{tuple_delimiter}<entity_description>)
+
+2. From the entities identified in step 1, identify all pairs of (source_entity, target_entity) that are *clearly related* to each other.
+For each pair of related entities, extract the following information:
+- source_entity: name of the source entity, as identified in step 1
+- target_entity: name of the target entity, as identified in step 1
+- relationship_description: explanation as to why you think the source entity and the target entity are related to each other
+- relationship_strength: a numeric score indicating strength of the relationship between the source entity and target entity
+- relationship_keywords: one or more high-level key words that summarize the overarching nature of the relationship, focusing on concepts or themes rather than specific details
+Format each relationship as ("relationship"{tuple_delimiter}<source_entity>{tuple_delimiter}<target_entity>{tuple_delimiter}<relationship_description>{tuple_delimiter}<relationship_keywords>{tuple_delimiter}<relationship_strength>)
+
+3. Identify high-level key words that summarize the main concepts, themes, or topics of the entire text. These should capture the overarching ideas present in the document.
+Format the content-level key words as ("content_keywords"{tuple_delimiter}<high_level_keywords>)
+
+4. Return output in {language} as a single list of all the entities and relationships identified in steps 1 and 2. Use **{record_delimiter}** as the list delimiter.
+
+5. When finished, output {completion_delimiter}
+
+---Output---
+
+Add new entities and relations below using the same format, and do not include entities and relations that have been previously extracted. :
 """
 
 PROMPTS[
@@ -252,4 +281,4 @@ When handling information with timestamps:
 - List up to 5 most important reference sources at the end under "References", clearly indicating whether each source is from Knowledge Graph (KG) or Vector Data (VD)
   Format: [KG/VD] Source content
 
-Add sections and commentary to the response as appropriate for the length and format. If the provided information is insufficient to answer the question, clearly state that you don't know or cannot provide an answer in the same language as the user's question."""
+Add sections and commentary to the response as appropriate for the length and format. If the provided information is insufficient to answer the question, clearly state that you don't know or cannot provide an answer in the same language as the user's question."""

graphrag/utils.py

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

rag/llm/__init__.py

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

rag/llm/chat_model.py

@@ -29,7 +29,6 @@ import json_repair
 import litellm
 import openai
 import requests
-from ollama import Client
 from openai import OpenAI
 from openai.lib.azure import AzureOpenAI
 from strenum import StrEnum
@@ -683,73 +682,6 @@ class ZhipuChat(Base):
         return super().chat_streamly_with_tools(system, history, gen_conf)
 
 
-class OllamaChat(Base):
-    _FACTORY_NAME = "Ollama"
-
-    def __init__(self, key, model_name, base_url=None, **kwargs):
-        super().__init__(key, model_name, base_url=base_url, **kwargs)
-
-        self.client = Client(host=base_url) if not key or key == "x" else Client(host=base_url, headers={"Authorization": f"Bearer {key}"})
-        self.model_name = model_name
-        self.keep_alive = kwargs.get("ollama_keep_alive", int(os.environ.get("OLLAMA_KEEP_ALIVE", -1)))
-
-    def _clean_conf(self, gen_conf):
-        options = {}
-        if "max_tokens" in gen_conf:
-            options["num_predict"] = gen_conf["max_tokens"]
-        for k in ["temperature", "top_p", "presence_penalty", "frequency_penalty"]:
-            if k not in gen_conf:
-                continue
-            options[k] = gen_conf[k]
-        return options
-
-    def _chat(self, history, gen_conf={}, **kwargs):
-        # Calculate context size
-        ctx_size = self._calculate_dynamic_ctx(history)
-
-        gen_conf["num_ctx"] = ctx_size
-        response = self.client.chat(model=self.model_name, messages=history, options=gen_conf, keep_alive=self.keep_alive)
-        ans = response["message"]["content"].strip()
-        token_count = response.get("eval_count", 0) + response.get("prompt_eval_count", 0)
-        return ans, token_count
-
-    def chat_streamly(self, system, history, gen_conf={}, **kwargs):
-        if system:
-            history.insert(0, {"role": "system", "content": system})
-        if "max_tokens" in gen_conf:
-            del gen_conf["max_tokens"]
-        try:
-            # Calculate context size
-            ctx_size = self._calculate_dynamic_ctx(history)
-            options = {"num_ctx": ctx_size}
-            if "temperature" in gen_conf:
-                options["temperature"] = gen_conf["temperature"]
-            if "max_tokens" in gen_conf:
-                options["num_predict"] = gen_conf["max_tokens"]
-            if "top_p" in gen_conf:
-                options["top_p"] = gen_conf["top_p"]
-            if "presence_penalty" in gen_conf:
-                options["presence_penalty"] = gen_conf["presence_penalty"]
-            if "frequency_penalty" in gen_conf:
-                options["frequency_penalty"] = gen_conf["frequency_penalty"]
-
-            ans = ""
-            try:
-                response = self.client.chat(model=self.model_name, messages=history, stream=True, options=options, keep_alive=self.keep_alive)
-                for resp in response:
-                    if resp["done"]:
-                        token_count = resp.get("prompt_eval_count", 0) + resp.get("eval_count", 0)
-                        yield token_count
-                    ans = resp["message"]["content"]
-                    yield ans
-            except Exception as e:
-                yield ans + "\n**ERROR**: " + str(e)
-            yield 0
-        except Exception as e:
-            yield "**ERROR**: " + str(e)
-            yield 0
-
-
 class LocalAIChat(Base):
     _FACTORY_NAME = "LocalAI"
 
@@ -1422,7 +1354,7 @@ class Ai302Chat(Base):
 
 
 class LiteLLMBase(ABC):
-    _FACTORY_NAME = ["Tongyi-Qianwen", "Bedrock", "Moonshot", "xAI", "DeepInfra", "Groq", "Cohere", "Gemini", "DeepSeek", "NVIDIA", "TogetherAI", "Anthropic"]
+    _FACTORY_NAME = ["Tongyi-Qianwen", "Bedrock", "Moonshot", "xAI", "DeepInfra", "Groq", "Cohere", "Gemini", "DeepSeek", "NVIDIA", "TogetherAI", "Anthropic", "Ollama"]
 
     def __init__(self, key, model_name, base_url=None, **kwargs):
         self.timeout = int(os.environ.get("LM_TIMEOUT_SECONDS", 600))

rag/svr/task_executor.py

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

web/src/app.tsx

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

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

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

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

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

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

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

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

@@ -209,10 +209,16 @@ export const MultiSelect = React.forwardRef<
     const [isAnimating, setIsAnimating] = React.useState(false);
 
     React.useEffect(() => {
-      if (selectedValues === undefined) {
+      if (!selectedValues && props.value) {
+        setSelectedValues(props.value as string[]);
+      }
+    }, [props.value, selectedValues]);
+
+    React.useEffect(() => {
+      if (!selectedValues && !props.value && defaultValue) {
         setSelectedValues(defaultValue);
       }
-    }, [defaultValue, selectedValues]);
+    }, [defaultValue, props.value, selectedValues]);
 
     const flatOptions = React.useMemo(() => {
       return options.flatMap((option) =>
@@ -293,15 +299,18 @@ export const MultiSelect = React.forwardRef<
                         variant="secondary"
                         className={cn(
                           isAnimating ? 'animate-bounce' : '',
+                          'px-1',
                           multiSelectVariants({ variant }),
                         )}
                         style={{ animationDuration: `${animation}s` }}
                       >
-                        <div className="flex items-center gap-1">
+                        <div className="flex justify-between items-center gap-1">
                           {IconComponent && (
                             <IconComponent className="h-4 w-4" />
                           )}
-                          <div>{option?.label}</div>
+                          <div className="max-w-28 text-ellipsis overflow-hidden">
+                            {option?.label}
+                          </div>
                           <XCircle
                             className="h-4 w-4 cursor-pointer"
                             onClick={(event) => {

web/src/locales/en.ts

@@ -1,6 +1,7 @@
 export default {
   translation: {
     common: {
+      selectPlaceholder: 'select value',
       delete: 'Delete',
       deleteModalTitle: 'Are you sure to delete this item?',
       ok: 'Yes',
@@ -94,6 +95,16 @@ export default {
       noMoreData: `That's all. Nothing more.`,
     },
     knowledgeDetails: {
+      created: 'Created',
+      learnMore: 'Learn More',
+      general: 'General',
+      chunkMethodTab: 'Chunk Method',
+      testResults: 'Test Results',
+      testSetting: 'Test Setting',
+      retrievalTesting: 'Retrieval Testing',
+      retrievalTestingDescription:
+        'Conduct a retrieval test to check if RAGFlow can recover the intended content for the LLM.',
+      Parse: 'Parse',
       dataset: 'Dataset',
       testing: 'Retrieval testing',
       files: 'files',

web/src/locales/zh.ts

@@ -1,6 +1,7 @@
 export default {
   translation: {
     common: {
+      selectPlaceholder: '请选择',
       delete: '删除',
       deleteModalTitle: '确定删除吗?',
       ok: '是',
@@ -86,6 +87,16 @@ export default {
       noMoreData: '没有更多数据了',
     },
     knowledgeDetails: {
+      created: '创建于',
+      learnMore: '了解更多',
+      general: '通用',
+      chunkMethodTab: '切片方法',
+      testResults: '测试结果',
+      testSetting: '测试设置',
+      retrievalTesting: '知识检索测试',
+      retrievalTestingDescription:
+        '进行检索测试，检查 RAGFlow 是否能够为大语言模型（LLM）恢复预期的内容。',
+      Parse: '解析',
       dataset: '数据集',
       testing: '检索测试',
       configuration: '配置',

web/src/pages/dataset/index.tsx

@@ -30,7 +30,9 @@ export default function DatasetWrapper() {
             </BreadcrumbItem>
             <BreadcrumbSeparator />
             <BreadcrumbItem>
-              <BreadcrumbPage>{data.name}</BreadcrumbPage>
+              <BreadcrumbPage className="w-28 whitespace-nowrap text-ellipsis overflow-hidden">
+                {data.name}
+              </BreadcrumbPage>
             </BreadcrumbItem>
           </BreadcrumbList>
         </Breadcrumb>

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

@@ -1,5 +1,6 @@
 import { Button } from '@/components/ui/button';
 import { cn } from '@/lib/utils';
+import { t } from 'i18next';
 import { X } from 'lucide-react';
 import { useState } from 'react';
 import CategoryPanel from './category-panel';
@@ -26,7 +27,7 @@ export default ({
             setVisible(!visible);
           }}
         >
-          Learn More
+          {t('knowledgeDetails.learnMore')}
         </Button>
       </div>
       <div

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

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

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

@@ -107,7 +107,7 @@ export default function DatasetSettings() {
                 >
                   <div className="flex w-full h-full justify-center	items-center">
                     <span className="h-full group-data-[state=active]:border-b-2 border-foreground	">
-                      General
+                      {t('knowledgeDetails.general')}
                     </span>
                   </div>
                 </TabsTrigger>
@@ -117,7 +117,7 @@ export default function DatasetSettings() {
                 >
                   <div className="flex w-full h-full justify-center	items-center">
                     <span className="h-full group-data-[state=active]:border-b-2 border-foreground	">
-                      Chunk Method
+                      {t('knowledgeDetails.chunkMethodTab')}
                     </span>
                   </div>
                 </TabsTrigger>

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

@@ -67,10 +67,14 @@ export function SideBar({ refreshCount }: PropType) {
             {data.name}
           </h3>
           <div className="flex justify-between">
-            <span>{data.doc_num} files</span>
+            <span>
+              {data.doc_num} {t('knowledgeDetails.files')}
+            </span>
             <span>{formatBytes(data.size)}</span>
           </div>
-          <div>Created {formatPureDate(data.create_time)}</div>
+          <div>
+            {t('knowledgeDetails.created')} {formatPureDate(data.create_time)}
+          </div>
         </div>
       </div>
 

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

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

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

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

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

@@ -39,7 +39,7 @@ export function SeeAllCard() {
   const { navigateToDatasetList } = useNavigatePage();
 
   return (
-    <Card className="w-40 flex-none" onClick={navigateToDatasetList}>
+    <Card className="w-40 flex-none h-full" onClick={navigateToDatasetList}>
       <CardContent className="p-2.5 pt-1 w-full h-full flex items-center justify-center gap-1.5 text-text-secondary">
         See All <ChevronRight className="size-4" />
       </CardContent>

web/src/pages/home/datasets.tsx

@@ -31,16 +31,20 @@ export function Datasets() {
           </div>
         ) : (
           <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}
-                dataset={dataset}
-                showDatasetRenameModal={showDatasetRenameModal}
-              ></DatasetCard>
-            ))}
+            {kbs
+              ?.slice(0, 6)
+              .map((dataset) => (
+                <DatasetCard
+                  key={dataset.id}
+                  dataset={dataset}
+                  showDatasetRenameModal={showDatasetRenameModal}
+                ></DatasetCard>
+              ))}
+            <div className="min-h-24">
+              <SeeAllCard></SeeAllCard>
+            </div>
           </div>
         )}
-        <SeeAllCard></SeeAllCard>
       </div>
       {datasetRenameVisible && (
         <RenameDialog

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

@@ -9,6 +9,7 @@ import {
   setLLMSettingEnabledValues,
 } from '@/utils/form';
 import { zodResolver } from '@hookform/resolvers/zod';
+import { omit } from 'lodash';
 import { X } from 'lucide-react';
 import { useEffect } from 'react';
 import { useForm } from 'react-hook-form';
@@ -69,7 +70,7 @@ export function ChatSettings({ switchSettingVisible }: ChatSettingsProps) {
         ? await transformFile2Base64(icon[0])
         : '';
     setDialog({
-      ...data,
+      ...omit(data, 'operator_permission'),
       ...nextValues,
       icon: avatar,
       dialog_id: id,

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

@@ -48,7 +48,10 @@ export const useRenameChat = () => {
       const nextChat = {
         ...(isEmpty(chat)
           ? InitialData
-          : { ...omit(chat, 'nickname', 'tenant_avatar'), dialog_id: chat.id }),
+          : {
+              ...omit(chat, 'nickname', 'tenant_avatar', 'operator_permission'),
+              dialog_id: chat.id,
+            }),
         name,
       };
       const ret = await setDialog(nextChat);