Add kibana tool in the docker compose file(#10525) (#10526)

### What problem does this PR solve?

add kibana tool in the docker compose file(#10525)

### Type of change


- [x] New Feature (non-breaking change which adds functionality)

Co-authored-by: virgilwong <hyhvirgil@gmail.com>

api/apps/kb_app.py

@@ -188,6 +188,9 @@ def detail():
             return get_data_error_result(
                 message="Can't find this knowledgebase!")
         kb["size"] = DocumentService.get_total_size_by_kb_id(kb_id=kb["id"],keywords="", run_status=[], types=[])
+        for key in ["graphrag_task_finish_at", "raptor_task_finish_at", "mindmap_task_finish_at"]:
+            if finish_at := kb.get(key):
+                kb[key] = finish_at.strftime("%Y-%m-%d %H:%M:%S")
         return get_json_result(data=kb)
     except Exception as e:
         return server_error_response(e)

conf/llm_factories.json

@@ -803,6 +803,12 @@
                     "tags": "TEXT EMBEDDING",
                     "max_tokens": 512,
                     "model_type": "embedding"
+                },
+                {
+                    "llm_name": "glm-asr",
+                    "tags": "SPEECH2TEXT",
+                    "max_tokens": 4096,
+                    "model_type": "speech2text"
                 }
             ]
         },
@@ -5140,4 +5146,4 @@
             ]
         }
     ]
-}
+}

docker/.env

@@ -37,9 +37,12 @@ OPENSEARCH_PASSWORD=infini_rag_flow_OS_01
 
 # The port used to expose the Kibana service to the host machine,
 # allowing EXTERNAL access to the service running inside the Docker container.
+# To enable kibana, you need to:
+# 1. Ensure that COMPOSE_PROFILES includes kibana, for example: COMPOSE_PROFILES=${DOC_ENGINE},kibana
+# 2. Comment out or delete the following configurations of the es service in docker-compose-base.yml: xpack.security.enabled、xpack.security.http.ssl.enabled、xpack.security.transport.ssl.enabled (for details: https://www.elastic.co/docs/deploy-manage/security/self-auto-setup#stack-existing-settings-detected)
+# 3. Adjust the es.hosts in conf/service_config.yaml or docker/service_conf.yaml.template to 'https://localhost:1200'
+# 4. After the startup is successful, in the es container, execute the command to generate the kibana token: `bin/elasticsearch-create-enrollment-token -s kibana`, then you can use kibana normally
 KIBANA_PORT=6601
-KIBANA_USER=rag_flow
-KIBANA_PASSWORD=infini_rag_flow
 
 # The maximum amount of the memory, in bytes, that a specific Docker container can use while running.
 # Update it according to the available memory in the host machine.

docker/docker-compose-base.yml

@@ -207,6 +207,30 @@ services:
       start_period: 10s    
 
 
+  kibana:
+    container_name: ragflow-kibana
+    profiles:
+      - kibana
+    image: kibana:${STACK_VERSION}
+    ports:
+      - ${KIBANA_PORT-5601}:5601
+    env_file: .env
+    environment:
+      - TZ=${TIMEZONE}
+    volumes:
+      - kibana_data:/usr/share/kibana/data
+    depends_on:
+      es01:
+        condition: service_started
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:5601/api/status"]
+      interval: 10s
+      timeout: 10s
+      retries: 120
+    networks:
+      - ragflow
+    restart: on-failure
+
 
 volumes:
   esdata01:
@@ -221,6 +245,8 @@ volumes:
     driver: local
   redis_data:
     driver: local
+  kibana_data:
+    driver: local
 
 networks:
   ragflow:

docs/references/python_api_reference.md

@@ -698,6 +698,58 @@ print("Async bulk parsing initiated.")
 
 ---
 
+### Parse documents (with document status)
+
+```python
+DataSet.parse_documents(document_ids: list[str]) -> list[tuple[str, str, int, int]]
+```
+
+Parses documents **synchronously** in the current dataset.  
+This method wraps `async_parse_documents()` and automatically waits for all parsing tasks to complete.  
+It returns detailed parsing results, including the status and statistics for each document.  
+If interrupted by the user (e.g. `Ctrl+C`), all pending parsing jobs will be cancelled gracefully.
+
+#### Parameters
+
+##### document_ids: `list[str]`, *Required*
+
+The IDs of the documents to parse.
+
+#### Returns
+
+A list of tuples with detailed parsing results:  
+```python
+[
+  (document_id: str, status: str, chunk_count: int, token_count: int),
+  ...
+]
+```
+- **status** — Final parsing state (`success`, `failed`, `cancelled`, etc.)  
+- **chunk_count** — Number of content chunks created for the document.  
+- **token_count** — Total number of tokens processed.  
+
+---
+
+#### Example
+
+```python
+rag_object = RAGFlow(api_key="<YOUR_API_KEY>", base_url="http://<YOUR_BASE_URL>:9380")
+dataset = rag_object.create_dataset(name="dataset_name")
+documents = dataset.list_documents(keywords="test")
+ids = [doc.id for doc in documents]
+
+try:
+    finished = dataset.parse_documents(ids)
+    for doc_id, status, chunk_count, token_count in finished:
+        print(f"Document {doc_id} parsing finished with status: {status}, chunks: {chunk_count}, tokens: {token_count}")
+except KeyboardInterrupt:
+    print("\nParsing interrupted by user. All pending tasks have been cancelled.")
+except Exception as e:
+    print(f"Parsing failed: {e}")
+```
+
+---
+
 ### Stop parsing documents
 
 ```python

rag/llm/sequence2txt_model.py

@@ -234,8 +234,8 @@ class DeepInfraSeq2txt(Base):
 
         self.client = OpenAI(api_key=key, base_url=base_url)
         self.model_name = model_name
-        
+
-        
+
 class CometAPISeq2txt(Base):
     _FACTORY_NAME = "CometAPI"
 
@@ -244,7 +244,8 @@ class CometAPISeq2txt(Base):
             base_url = "https://api.cometapi.com/v1"
         self.client = OpenAI(api_key=key, base_url=base_url)
         self.model_name = model_name
-        
+
+
 class DeerAPISeq2txt(Base):
     _FACTORY_NAME = "DeerAPI"
 
@@ -253,3 +254,44 @@ class DeerAPISeq2txt(Base):
             base_url = "https://api.deerapi.com/v1"
         self.client = OpenAI(api_key=key, base_url=base_url)
         self.model_name = model_name
+
+
+class ZhipuSeq2txt(Base):
+    _FACTORY_NAME = "ZHIPU-AI"
+
+    def __init__(self, key, model_name="glm-asr", base_url="https://open.bigmodel.cn/api/paas/v4", **kwargs):
+        if not base_url:
+            base_url = "https://open.bigmodel.cn/api/paas/v4"
+        self.base_url = base_url
+        self.api_key = key
+        self.model_name = model_name
+        self.gen_conf = kwargs.get("gen_conf", {})
+        self.stream = kwargs.get("stream", False)
+
+    def transcription(self, audio_path):
+        payload = {
+            "model": self.model_name,
+            "temperature": str(self.gen_conf.get("temperature", 0.75)) or "0.75",
+            "stream": self.stream,
+        }
+
+        headers = {"Authorization": f"Bearer {self.api_key}"}
+        with open(audio_path, "rb") as audio_file:
+            files = {"file": audio_file}
+
+            try:
+                response = requests.post(
+                    url=f"{self.base_url}/audio/transcriptions",
+                    data=payload,
+                    files=files,
+                    headers=headers,
+                )
+                body = response.json()
+                if response.status_code == 200:
+                    full_content = body["text"]
+                    return full_content, num_tokens_from_string(full_content)
+                else:
+                    error = body["error"]
+                    return f"**ERROR**: code: {error['code']}, message: {error['message']}", 0
+            except Exception as e:
+                return "**ERROR**: " + str(e), 0

rag/prompts/generator.py

@@ -124,7 +124,7 @@ def kb_prompt(kbinfos, max_tokens, hash_id=False):
 
     knowledges = []
     for i, ck in enumerate(kbinfos["chunks"][:chunks_num]):
-        cnt = "\nID: {}".format(i if not hash_id else hash_str2int(get_value(ck, "id", "chunk_id"), 100))
+        cnt = "\nID: {}".format(i if not hash_id else hash_str2int(get_value(ck, "id", "chunk_id"), 500))
         cnt += draw_node("Title", get_value(ck, "docnm_kwd", "document_name"))
         cnt += draw_node("URL", ck['url'])  if "url" in ck else ""
         for k, v in docs.get(get_value(ck, "doc_id", "document_id"), {}).items():

sdk/python/ragflow_sdk/modules/dataset.py

@@ -100,12 +100,51 @@ class DataSet(Base):
         res = res.json()
         if res.get("code") != 0:
             raise Exception(res["message"])
-
+        
+    
+    def _get_documents_status(self, document_ids):
+        import time
+        terminal_states = {"DONE", "FAIL", "CANCEL"}
+        interval_sec = 1
+        pending = set(document_ids)
+        finished = []
+        while pending:
+            for doc_id in list(pending):
+                def fetch_doc(doc_id: str) -> Document | None:
+                    try:
+                        docs = self.list_documents(id=doc_id)
+                        return docs[0] if docs else None
+                    except Exception:
+                        return None
+                doc = fetch_doc(doc_id)
+                if doc is None:
+                    continue
+                if isinstance(doc.run, str) and doc.run.upper() in terminal_states:
+                    finished.append((doc_id, doc.run, doc.chunk_count, doc.token_count))
+                    pending.discard(doc_id)
+                elif float(doc.progress or 0.0) >= 1.0:
+                    finished.append((doc_id, "DONE", doc.chunk_count, doc.token_count))
+                    pending.discard(doc_id)
+            if pending:
+                time.sleep(interval_sec)
+        return finished
+    
     def async_parse_documents(self, document_ids):
         res = self.post(f"/datasets/{self.id}/chunks", {"document_ids": document_ids})
         res = res.json()
         if res.get("code") != 0:
             raise Exception(res.get("message"))
+        
+
+    def parse_documents(self, document_ids):
+        try:
+            self.async_parse_documents(document_ids)
+            self._get_documents_status(document_ids)
+        except KeyboardInterrupt:
+            self.async_cancel_parse_documents(document_ids)
+            
+        return self._get_documents_status(document_ids)
+
 
     def async_cancel_parse_documents(self, document_ids):
         res = self.rm(f"/datasets/{self.id}/chunks", {"document_ids": document_ids})