Merge remote-tracking branch 'upstream/main'

# Conflicts:
#	web/src/pages/flow/canvas/node/retrieval-node.tsx

conf/mapping.json

@@ -140,13 +140,21 @@
         }
       },
       {
-        "string": {
+        "rank_feature": {
           "match": "*_fea",
           "mapping": {
             "type": "rank_feature"
           }
         }
       },
+      {
+        "rank_features": {
+          "match": "*_feas",
+          "mapping": {
+            "type": "rank_features"
+          }
+        }
+      },
       {
         "dense_vector": {
           "match": "*_512_vec",

docs/references/python_api_reference.md

@@ -1,4 +1,4 @@
----
+from sdk.python.ragflow_sdk import Agentfrom docutils.nodes import titlefrom sdk.python.ragflow_sdk import Agent---
 sidebar_position: 2
 slug: /python_api_reference
 ---
@@ -1513,4 +1513,123 @@ while True:
     for ans in session.ask(question, stream=True):
         print(ans.content[len(cont):], end='', flush=True)
         cont = ans.content
+```
+---
+
+## List agent sessions
+
+```python
+Agent.list_sessions(
+    agent_id,
+    rag
+    page: int = 1, 
+    page_size: int = 30, 
+    orderby: str = "update_time", 
+    desc: bool = True,
+    id: str = None
+) -> List[Session]
+```
+
+Lists sessions associated with the current agent.
+
+### Parameters
+
+#### page: `int`
+
+Specifies the page on which the sessions will be displayed. Defaults to `1`.
+
+#### page_size: `int`
+
+The number of sessions on each page. Defaults to `30`.
+
+#### orderby: `str`
+
+The field by which sessions should be sorted. Available options:
+
+- `"create_time"`
+- `"update_time"`(default)
+
+#### desc: `bool`
+
+Indicates whether the retrieved sessions should be sorted in descending order. Defaults to `True`.
+
+#### id: `str`
+
+The ID of the agent session to retrieve. Defaults to `None`.
+
+
+### Returns
+
+- Success: A list of `Session` objects associated with the current agent.
+- Failure: `Exception`.
+
+### Examples
+
+```python
+from ragflow_sdk import RAGFlow
+
+rag_object = RAGFlow(api_key="<YOUR_API_KEY>", base_url="http://<YOUR_BASE_URL>:9380")
+agent_id = "2710f2269b4611ef8fdf0242ac120006"
+sessions=Agent.list_sessions(agent_id,rag_object)
+for session in sessions:
+    print(session)
+```
+
+---
+## List agents
+
+```python
+RAGFlow.list_agents(
+    page: int = 1, 
+    page_size: int = 30, 
+    orderby: str = "create_time", 
+    desc: bool = True,
+    id: str = None,
+    title: str = None
+) -> List[Agent]
+```
+
+Lists agents.
+
+### Parameters
+
+#### page: `int`
+
+Specifies the page on which the agents will be displayed. Defaults to `1`.
+
+#### page_size: `int`
+
+The number of agents on each page. Defaults to `30`.
+
+#### orderby: `str`
+
+The attribute by which the results are sorted. Available options:
+
+- `"create_time"` (default)
+- `"update_time"`
+
+#### desc: `bool`
+
+Indicates whether the retrieved agents should be sorted in descending order. Defaults to `True`.
+
+#### id: `str`  
+
+The ID of the agent to retrieve. Defaults to `None`.
+
+#### name: `str`  
+
+The name of the agent to retrieve. Defaults to `None`.
+
+### Returns
+
+- Success: A list of `Agent` objects.
+- Failure: `Exception`.
+
+### Examples
+
+```python
+from ragflow_sdk import RAGFlow
+rag_object = RAGFlow(api_key="<YOUR_API_KEY>", base_url="http://<YOUR_BASE_URL>:9380")
+for agent in rag_object.list_agents():
+    print(agent)
 ```

rag/nlp/query.py

@@ -120,7 +120,7 @@ def need_fine_grained_tokenize(tk):
             keywords.append(tt)
             twts = self.tw.weights([tt])
             syns = self.syn.lookup(tt)
-            if syns: keywords.extend(syns)
+            if syns and len(keywords) < 32: keywords.extend(syns)
             logging.debug(json.dumps(twts, ensure_ascii=False))
             tms = []
             for tk, w in sorted(twts, key=lambda x: x[1] * -1):
@@ -140,17 +140,24 @@ def need_fine_grained_tokenize(tk):
                 sm = [FulltextQueryer.subSpecialChar(m) for m in sm if len(m) > 1]
                 sm = [m for m in sm if len(m) > 1]
 
-                keywords.append(re.sub(r"[ \\\"']+", "", tk))
-                keywords.extend(sm)
-                if len(keywords) >= 12:
-                    break
+                if len(keywords) < 32:
+                    keywords.append(re.sub(r"[ \\\"']+", "", tk))
+                    keywords.extend(sm)
 
                 tk_syns = self.syn.lookup(tk)
+                tk_syns = [FulltextQueryer.subSpecialChar(s) for s in tk_syns]
+                if len(keywords) < 32: keywords.extend([s for s in tk_syns if s])
+                tk_syns = [rag_tokenizer.fine_grained_tokenize(s) for s in tk_syns if s]
+                tk_syns = [f"\"{s}\"" if s.find(" ")>0 else s for s in tk_syns]
+
+                if len(keywords) >= 32:
+                    break
+
                 tk = FulltextQueryer.subSpecialChar(tk)
                 if tk.find(" ") > 0:
                     tk = '"%s"' % tk
                 if tk_syns:
-                    tk = f"({tk} %s)" % " ".join(tk_syns)
+                    tk = f"({tk} OR (%s)^0.2)" % " ".join(tk_syns)
                 if sm:
                     tk = f'{tk} OR "%s" OR ("%s"~2)^0.5' % (" ".join(sm), " ".join(sm))
                 if tk.strip():
@@ -159,14 +166,14 @@ def need_fine_grained_tokenize(tk):
             tms = " ".join([f"({t})^{w}" for t, w in tms])
 
             if len(twts) > 1:
-                tms += ' ("%s"~4)^1.5' % (" ".join([t for t, _ in twts]))
+                tms += ' ("%s"~2)^1.5' % rag_tokenizer.tokenize(tt)
             if re.match(r"[0-9a-z ]+$", tt):
                 tms = f'("{tt}" OR "%s")' % rag_tokenizer.tokenize(tt)
 
             syns = " OR ".join(
                 [
-                    '"%s"^0.7'
-                    % FulltextQueryer.subSpecialChar(rag_tokenizer.tokenize(s))
+                    '"%s"'
+                    % rag_tokenizer.tokenize(FulltextQueryer.subSpecialChar(s))
                     for s in syns
                 ]
             )

sdk/python/ragflow_sdk/modules/agent.py

@@ -1,6 +1,7 @@
 from .base import Base
 from .session import Session
 import requests
+from typing import List
 
 class Agent(Base):
     def __init__(self,rag,res_dict):
@@ -57,3 +58,18 @@ def create_session(id,rag) -> Session:
             return Session(rag,res.get("data"))
         raise Exception(res.get("message"))
 
+    @staticmethod
+    def list_sessions(agent_id,rag,page: int = 1, page_size: int = 30, orderby: str = "create_time", desc: bool = True,
+                      id: str = None) -> List[Session]:
+        url = f"{rag.api_url}/agents/{agent_id}/sessions"
+        headers = {"Authorization": f"Bearer {rag.user_key}"}
+        params = {"page": page, "page_size": page_size, "orderby": orderby, "desc": desc, "id": id}
+        res = requests.get(url=url,headers=headers,params=params)
+        res = res.json()
+        if res.get("code") == 0:
+            result_list = []
+            for data in res.get("data"):
+                temp_agent = Session(rag,data)
+                result_list.append(temp_agent)
+            return result_list
+        raise Exception(res.get("message"))

sdk/python/ragflow_sdk/modules/session.py

@@ -8,12 +8,12 @@ def __init__(self, rag, res_dict):
         self.id = None
         self.name = "New session"
         self.messages = [{"role": "assistant", "content": "Hi! I am your assistant，can I help you?"}]
-        self.chat_id = None
-        self.agent_id = None
         for key,value in res_dict.items():
             if key =="chat_id" and value is not None:
+                self.chat_id = None
                 self.__session_type = "chat"
             if key == "agent_id" and value is not None:
+                self.agent_id = None
                 self.__session_type = "agent"
         super().__init__(rag, res_dict)
 

sdk/python/ragflow_sdk/ragflow.py

@@ -18,6 +18,7 @@
 from .modules.chat import Chat
 from .modules.chunk import Chunk
 from .modules.dataset import DataSet
+from .modules.agent import Agent
 
 
 class RAGFlow:
@@ -86,8 +87,10 @@ def list_datasets(self, page: int = 1, page_size: int = 30, orderby: str = "crea
             return result_list
         raise Exception(res["message"])
 
-    def create_chat(self, name: str, avatar: str = "", dataset_ids: list[str] = [],
-                         llm: Chat.LLM | None = None, prompt: Chat.Prompt | None = None) -> Chat:
+    def create_chat(self, name: str, avatar: str = "", dataset_ids=None,
+                    llm: Chat.LLM | None = None, prompt: Chat.Prompt | None = None) -> Chat:
+        if dataset_ids is None:
+            dataset_ids = []
         dataset_list = []
         for id in dataset_ids:
             dataset_list.append(id)
@@ -176,3 +179,15 @@ def retrieve(self, dataset_ids, document_ids=None, question="", page=1, page_siz
                     chunks.append(chunk)
                 return chunks
             raise Exception(res.get("message"))
+
+
+    def list_agents(self, page: int = 1, page_size: int = 30, orderby: str = "update_time", desc: bool = True,
+                      id: str | None = None, title: str | None = None) -> list[Agent]:
+        res = self.get("/agents",{"page": page, "page_size": page_size, "orderby": orderby, "desc": desc, "id": id, "title": title})
+        res = res.json()
+        result_list = []
+        if res.get("code") == 0:
+            for data in res['data']:
+                result_list.append(Agent(self, data))
+            return result_list
+        raise Exception(res["message"])

sdk/python/test/test_sdk_api/t_agent.py

@@ -0,0 +1,9 @@
+from ragflow_sdk import RAGFlow,Agent
+from common import HOST_ADDRESS
+import pytest
+
+@pytest.mark.skip(reason="")
+def test_list_agents_with_success(get_api_key_fixture):
+    API_KEY=get_api_key_fixture
+    rag = RAGFlow(API_KEY,HOST_ADDRESS)
+    rag.list_agents()

sdk/python/test/test_sdk_api/t_dataset.py

@@ -51,4 +51,5 @@ def test_delete_datasets_with_success(get_api_key_fixture):
 def test_list_datasets_with_success(get_api_key_fixture):
     API_KEY = get_api_key_fixture
     rag = RAGFlow(API_KEY, HOST_ADDRESS)
+    rag.create_dataset("test_list_datasets")
     rag.list_datasets()

sdk/python/test/test_sdk_api/t_session.py

@@ -107,4 +107,11 @@ def test_create_agent_conversation_with_success(get_api_key_fixture):
     API_KEY = "ragflow-BkOGNhYjIyN2JiODExZWY5MzVhMDI0Mm"
     rag = RAGFlow(API_KEY,HOST_ADDRESS)
     session = Agent.create_session("2e45b5209c1011efa3e90242ac120006", rag)
-    session.ask("What is this job")
+    session.ask("What is this job")
+
+@pytest.mark.skip(reason="")
+def test_list_agent_sessions_with_success(get_api_key_fixture):
+    API_KEY = "ragflow-BkOGNhYjIyN2JiODExZWY5MzVhMDI0Mm"
+    agent_id = "2710f2269b4611ef8fdf0242ac120006"
+    rag = RAGFlow(API_KEY,HOST_ADDRESS)
+    Agent.list_sessions(agent_id,rag)

web/src/components/knowledge-base-item.tsx

@@ -1,12 +1,12 @@
 import { useTranslate } from '@/hooks/common-hooks';
-import { useNextFetchKnowledgeList } from '@/hooks/knowledge-hooks';
+import { useFetchKnowledgeList } from '@/hooks/knowledge-hooks';
 import { UserOutlined } from '@ant-design/icons';
 import { Avatar, Form, Select, Space } from 'antd';
 
 const KnowledgeBaseItem = () => {
   const { t } = useTranslate('chat');
 
-  const { list: knowledgeList } = useNextFetchKnowledgeList(true);
+  const { list: knowledgeList } = useFetchKnowledgeList(true);
 
   const knowledgeOptions = knowledgeList.map((x) => ({
     label: (

web/src/components/ui/skeleton.tsx

@@ -0,0 +1,39 @@
+import { cn } from '@/lib/utils';
+
+function Skeleton({
+  className,
+  ...props
+}: React.HTMLAttributes<HTMLDivElement>) {
+  return (
+    <div
+      className={cn('animate-pulse rounded-md bg-muted', className)}
+      {...props}
+    />
+  );
+}
+
+function ParagraphSkeleton() {
+  return (
+    <div className="flex items-center space-x-4">
+      <Skeleton className="h-12 w-12 rounded-full" />
+      <div className="space-y-2">
+        <Skeleton className="h-4 w-[250px]" />
+        <Skeleton className="h-4 w-[200px]" />
+      </div>
+    </div>
+  );
+}
+
+function CardSkeleton() {
+  return (
+    <div className="flex flex-col space-y-3">
+      <Skeleton className="h-[125px] w-[250px] rounded-xl" />
+      <div className="space-y-2">
+        <Skeleton className="h-4 w-[250px]" />
+        <Skeleton className="h-4 w-[200px]" />
+      </div>
+    </div>
+  );
+}
+
+export { CardSkeleton, ParagraphSkeleton, Skeleton };

web/src/hooks/knowledge-hooks.ts

@@ -41,7 +41,7 @@ export const useFetchKnowledgeBaseConfiguration = () => {
   return { data, loading };
 };
 
-export const useNextFetchKnowledgeList = (
+export const useFetchKnowledgeList = (
   shouldFilterListWithoutDocument: boolean = false,
 ): {
   list: IKnowledge[];