[pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

Author: pre-commit-ci[bot]

EdgeCraftRAG/docker_compose/intel/gpu/arc/README.md

@@ -22,19 +22,22 @@ This section describes how to quickly deploy and test the EdgeCraftRAG service m
 
 ### 1. Prerequisites
 
-EC-RAG supports vLLM deployment(default method) and local OpenVINO deployment for Intel Arc GPU and Core Ultra Platform. Prerequisites are shown as below:  
+EC-RAG supports vLLM deployment(default method) and local OpenVINO deployment for Intel Arc GPU and Core Ultra Platform. Prerequisites are shown as below:
 
 #### Core Ultra
+
 **OS**: Ubuntu 24.04 or newer  
 **Driver & libraries**: Please refer to [Installing Client GPUs on Ubuntu Desktop](https://dgpu-docs.intel.com/driver/client/overview.html#installing-client-gpus-on-ubuntu-desktop)  
 **Available Inferencing Framework**: openVINO
 
 #### Intel Arc B60
-**OS**: Ubuntu 25.04 Desktop (for Core Ultra and Xeon-W), Ubuntu 25.04 Server (for Xeon-SP).   
+
+**OS**: Ubuntu 25.04 Desktop (for Core Ultra and Xeon-W), Ubuntu 25.04 Server (for Xeon-SP).  
 **Driver & libraries**: Please refer to [Install Bare Metal Environment](https://github.com/intel/llm-scaler/tree/main/vllm#11-install-bare-metal-environment) for detailed setup  
 **Available Inferencing Framework**: openVINO, vLLM
 
 #### Intel Arc A770
+
 **OS**: Ubuntu Server 22.04.1 or newer (at least 6.2 LTS kernel)  
 **Driver & libraries**: Please refer to [Installing GPUs Drivers](https://dgpu-docs.intel.com/driver/installation-rolling.html#installing-gpu-drivers) for detailed driver & libraries setup  
 **Available Inferencing Framework**: openVINO, vLLM
@@ -50,9 +53,9 @@ cd GenAIExamples/EdgeCraftRAG
 
 > **NOTE**: If you want to checkout a released version, such as v1.5:
 >
->```
->git checkout v1.5
->```
+> ```
+> git checkout v1.5
+> ```
 
 ### 3. Prepare models
 
@@ -75,6 +78,7 @@ optimum-cli export openvino -m BAAI/bge-reranker-large ${MODEL_PATH}/BAAI/bge-re
 #### LLM
 
 ##### openVINO
+
 If you have Core Ultra platform only, please prepare openVINO models:  
 You can also run openVINO models on discrete GPU.
 
@@ -84,6 +88,7 @@ optimum-cli export openvino --model Qwen/Qwen3-8B ${MODEL_PATH}/Qwen/Qwen3-8B/IN
 ```
 
 ##### vLLM
+
 Alternatively, if you have discrete GPU and want to use vLLM, please prepare models for vLLM:
 
 ```bash
@@ -141,20 +146,23 @@ export MILVUS_ENABLED=0
 
 #### Option a. Deploy openVINO LLM based EC-RAG for Core Ultra, Arc B60, Arc A770
 
-Make sure you have prepared [openVINO models](#openvino)  
+Make sure you have prepared [openVINO models](#openvino)
+
 ```bash
 docker compose -f docker_compose/intel/gpu/arc/compose.yaml up -d
 ```
 
 #### Option b.1. Deploy vLLM based EC-RAG for Arc B60
-Make sure you have prepared [vLLM models](#vllm) 
+
+Make sure you have prepared [vLLM models](#vllm)
 
 ```bash
 docker compose --profile b60 -f docker_compose/intel/gpu/arc/compose.yaml up -d
 ```
 
 #### Option b.2. Deploy vLLM based EC-RAG for Arc A770
-Make sure you have prepared [vLLM models](#vllm) 
+
+Make sure you have prepared [vLLM models](#vllm)
 
 ```bash
 docker compose --profile a770 -f docker_compose/intel/gpu/arc/compose.yaml up -d

EdgeCraftRAG/docker_compose/intel/gpu/arc/README_zh.md

@@ -25,16 +25,19 @@
 EC-RAG 支持 vLLM 部署（默认方式）以及面向 Intel Arc GPU 和 Core Ultra 平台的本地 OpenVINO 部署。前置条件如下：
 
 #### Core Ultra
+
 **操作系统**：Ubuntu 24.04 或更高版本  
 **驱动与库**：请参考 [Installing Client GPUs on Ubuntu Desktop](https://dgpu-docs.intel.com/driver/client/overview.html#installing-client-gpus-on-ubuntu-desktop)  
 **可用推理框架**：openVINO
 
 #### Intel Arc B60
+
 **操作系统**：Ubuntu 25.04 Desktop（适用于 Core Ultra 和 Xeon-W），Ubuntu 25.04 Server（适用于 Xeon-SP）。  
 **驱动与库**：详细安装请参考 [Install Bare Metal Environment](https://github.com/intel/llm-scaler/tree/main/vllm#11-install-bare-metal-environment)  
 **可用推理框架**：openVINO、vLLM
 
 #### Intel Arc A770
+
 **操作系统**：Ubuntu Server 22.04.1 或更高版本（至少 6.2 LTS 内核）  
 **驱动与库**：详细驱动与库安装请参考 [Installing GPUs Drivers](https://dgpu-docs.intel.com/driver/installation-rolling.html#installing-gpu-drivers)  
 **可用推理框架**：openVINO、vLLM
@@ -50,9 +53,9 @@ cd GenAIExamples/EdgeCraftRAG
 
 > **注意**：如果你想切换到某个发布版本，例如 v1.5：
 >
->```
->git checkout v1.5
->```
+> ```
+> git checkout v1.5
+> ```
 
 ### 3. 准备模型
 
@@ -75,6 +78,7 @@ optimum-cli export openvino -m BAAI/bge-reranker-large ${MODEL_PATH}/BAAI/bge-re
 #### LLM
 
 ##### openVINO
+
 如果你只有 Core Ultra 平台，请准备 openVINO 模型：
 你也可以在独立 GPU 上运行 openVINO 模型。
 
@@ -84,6 +88,7 @@ optimum-cli export openvino --model Qwen/Qwen3-8B ${MODEL_PATH}/Qwen/Qwen3-8B/IN
 ```
 
 ##### vLLM
+
 另外，如果你有独立显卡，可以为 vLLM 准备模型：
 
 ```bash
@@ -199,11 +204,11 @@ docker compose -f docker_compose/intel/gpu/arc/compose.yaml down
 
 下表全面概述了示例 Docker Compose 文件中各类部署所使用的 EdgeCraftRAG 服务。表中每一行代表一个独立服务，详细说明了可用镜像及其在部署架构中的功能描述。
 
-| 服务名称            | 可选镜像名称                             | 可选 | 描述                                                                                             |
-| ------------------- | ---------------------------------------- | ---- | ------------------------------------------------------------------------------------------------ |
-| etcd                | quay.io/coreos/etcd:v3.5.5               | 否   | 提供分布式键值存储，用于服务发现和配置管理。                                                     |
-| minio               | minio/minio:RELEASE.2023-03-20T20-16-18Z | 否   | 提供对象存储服务，用于存储文档和模型文件。                                                       |
-| milvus-standalone   | milvusdb/milvus:v2.4.6                   | 否   | 提供向量数据库能力，用于管理 embedding 和相似度检索。                                            |
-| edgecraftrag-server | opea/edgecraftrag-server:latest          | 否   | 作为 EdgeCraftRAG 服务后端，具体形态随部署方式不同而变化。                                       |
-| edgecraftrag-ui     | opea/edgecraftrag-ui:latest              | 否   | 提供 EdgeCraftRAG 服务的用户界面。                                                               |
-| ecrag               | opea/edgecraftrag:latest                 | 否   | 作为反向代理，管理 UI 与后端服务之间的流量。                                                     |
+| 服务名称            | 可选镜像名称                             | 可选 | 描述                                                       |
+| ------------------- | ---------------------------------------- | ---- | ---------------------------------------------------------- |
+| etcd                | quay.io/coreos/etcd:v3.5.5               | 否   | 提供分布式键值存储，用于服务发现和配置管理。               |
+| minio               | minio/minio:RELEASE.2023-03-20T20-16-18Z | 否   | 提供对象存储服务，用于存储文档和模型文件。                 |
+| milvus-standalone   | milvusdb/milvus:v2.4.6                   | 否   | 提供向量数据库能力，用于管理 embedding 和相似度检索。      |
+| edgecraftrag-server | opea/edgecraftrag-server:latest          | 否   | 作为 EdgeCraftRAG 服务后端，具体形态随部署方式不同而变化。 |
+| edgecraftrag-ui     | opea/edgecraftrag-ui:latest              | 否   | 提供 EdgeCraftRAG 服务的用户界面。                         |
+| ecrag               | opea/edgecraftrag:latest                 | 否   | 作为反向代理，管理 UI 与后端服务之间的流量。               |

EdgeCraftRAG/edgecraftrag/api/v1/data.py

@@ -5,12 +5,13 @@
 import os
 from typing import List
 
+from edgecraftrag.api.v1.knowledge_base import add_file_to_knowledge_base
 from edgecraftrag.api_schema import DataIn, FilesIn
 from edgecraftrag.config_repository import MilvusConfigRepository
 from edgecraftrag.context import ctx
 from edgecraftrag.env import UI_DIRECTORY
 from fastapi import FastAPI, File, HTTPException, UploadFile, status
-from edgecraftrag.api.v1.knowledge_base import add_file_to_knowledge_base
+
 data_app = FastAPI()
 
 
@@ -24,7 +25,7 @@ async def get_nodes_with_kb(kb_name=None):
         kb = ctx.get_knowledge_mgr().get_active_knowledge_base()
     if kb.indexer.comp_subtype == "faiss_vector":
         return kb.indexer.docstore.docs
-    elif kb.indexer.comp_subtype == "milvus_vector":  
+    elif kb.indexer.comp_subtype == "milvus_vector":
         collection_name = kb.name
         Milvus_node_list = MilvusConfigRepository.create_connection(collection_name, 1, kb.indexer.vector_url)
         results = Milvus_node_list.get_configs(output_fields=["text", "_node_content", "doc_id"])

EdgeCraftRAG/edgecraftrag/api/v1/knowledge_base.py

@@ -8,34 +8,33 @@
 from typing import Dict, List, Union
 
 from edgecraftrag.api_schema import DataIn, ExperienceIn, KnowledgeBaseCreateIn
-from edgecraftrag.components.query_preprocess import query_search
-from edgecraftrag.components.indexer import get_kbs_info
-from edgecraftrag.config_repository import (
-    MilvusConfigRepository,
-    save_knowledge_configurations,
-)
-from edgecraftrag.context import ctx
-from edgecraftrag.env import (
-    KNOWLEDGEBASE_FILE,
-    SEARCH_CONFIG_PATH,
-    SEARCH_DIR,
-    UI_DIRECTORY,
-)
 from edgecraftrag.base import (
     IndexerType,
     ModelType,
     NodeParserType,
 )
 from edgecraftrag.components.benchmark import Benchmark
-from edgecraftrag.components.indexer import KBADMINIndexer, VectorIndexer
+from edgecraftrag.components.indexer import KBADMINIndexer, VectorIndexer, get_kbs_info
 from edgecraftrag.components.node_parser import (
     HierarchyNodeParser,
     KBADMINParser,
     SimpleNodeParser,
     SWindowNodeParser,
     UnstructedNodeParser,
 )
-from fastapi import FastAPI, HTTPException, status, Query
+from edgecraftrag.components.query_preprocess import query_search
+from edgecraftrag.config_repository import (
+    MilvusConfigRepository,
+    save_knowledge_configurations,
+)
+from edgecraftrag.context import ctx
+from edgecraftrag.env import (
+    KNOWLEDGEBASE_FILE,
+    SEARCH_CONFIG_PATH,
+    SEARCH_DIR,
+    UI_DIRECTORY,
+)
+from fastapi import FastAPI, HTTPException, Query, status
 
 kb_app = FastAPI()
 
@@ -51,7 +50,9 @@ async def get_all_knowledge_bases():
 
 # Get knowledge base files in a certain range.
 @kb_app.get("/v1/knowledge/{knowledge_name}/filemap")
-async def get_knowledge_base_filemap(knowledge_name: str, page_num: int = Query(1, ge=1), page_size: int = Query(20, ge=1)):
+async def get_knowledge_base_filemap(
+    knowledge_name: str, page_num: int = Query(1, ge=1), page_size: int = Query(20, ge=1)
+):
     kb = ctx.knowledgemgr.get_knowledge_base_by_name_or_id(knowledge_name)
     if kb and kb.file_map:
         file_map = kb.file_map
@@ -61,7 +62,7 @@ async def get_knowledge_base_filemap(knowledge_name: str, page_num: int = Query(
         if start >= filemap_len:
             return None
         file_map_subset = itertools.islice(file_map.items(), start, end)
-        return {"file_map": dict(file_map_subset),"total": kb.calculate_totals()}
+        return {"file_map": dict(file_map_subset), "total": kb.calculate_totals()}
     else:
         return None
 
@@ -101,7 +102,7 @@ async def create_knowledge_base(knowledge: KnowledgeBaseCreateIn):
                     active_pl.update_retriever_list(ctx.knowledgemgr.get_active_knowledge_base())
             except Exception as e:
                 ctx.knowledgemgr.delete_knowledge_base(knowledge.name)
-                raise HTTPException(status_code=status.HTTP_500_INTERNAL_SERVER_ERROR, detail=str(e))  
+                raise HTTPException(status_code=status.HTTP_500_INTERNAL_SERVER_ERROR, detail=str(e))
         await save_knowledge_configurations("add", kb)
         return "Create knowledge base successfully"
     except Exception as e:
@@ -156,7 +157,7 @@ async def update_knowledge_base(knowledge: KnowledgeBaseCreateIn):
                 raise HTTPException(status_code=status.HTTP_500_INTERNAL_SERVER_ERROR, detail=str(e))
 
             # reload data for knowledge base
-            node_parser_changed = (kb_node_parser != kb.node_parser)
+            node_parser_changed = kb_node_parser != kb.node_parser
             if node_parser_changed or kb_indexer != kb.indexer:
                 await handle_reload_data(kb, node_parser_changed)
         elif kb.comp_subtype == "kbadmin_kb":
@@ -176,10 +177,10 @@ async def update_knowledge_base(knowledge: KnowledgeBaseCreateIn):
 @kb_app.post(path="/v1/knowledge/{knowledge_name}/files")
 async def add_file_to_knowledge_base(knowledge_name, file_path: DataIn):
     """
-        1. Parse file into Llamaindex Document and add file to filemgr
-        2. Add file path to knowledge base
-        3. Update nodes and vector store for knowledge base
-        4. Update pipeline retriever if active knowledge base's indexer changed
+    1. Parse file into Llamaindex Document and add file to filemgr
+    2. Add file path to knowledge base
+    3. Update nodes and vector store for knowledge base
+    4. Update pipeline retriever if active knowledge base's indexer changed
     """
     try:
         kb = ctx.knowledgemgr.get_knowledge_base_by_name_or_id(knowledge_name)
@@ -222,7 +223,7 @@ async def add_file_to_knowledge_base(knowledge_name, file_path: DataIn):
             raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail="Error uploading file.")
 
         # update retriever with indexer since indexer updated
-        if  kb.active:
+        if kb.active:
             active_pl = ctx.get_pipeline_mgr().get_active_pipeline()
             if active_pl:
                 active_pl.update_retriever(kb, prev_indexer)
@@ -258,7 +259,7 @@ async def remove_file_from_knowledge_base(knowledge_name, file_path: DataIn):
             )
         await remove_document_handler(document_list, kb)
         # update retriever with indexer since indexer updated
-        if  kb.active:
+        if kb.active:
             active_pl = ctx.get_pipeline_mgr().get_active_pipeline()
             if active_pl:
                 active_pl.update_retriever(kb, prev_indexer)
@@ -459,6 +460,7 @@ async def handle_reload_data(kb, node_parser_changed: bool = False):
     # update indexer
     await kb.update_nodes_to_indexer()
 
+
 async def update_kb_handler(kb, knowledge):
     if kb.enable_benchmark:
         kb.benchmark = Benchmark(True, "")
@@ -493,7 +495,9 @@ async def update_kb_handler(kb, knowledge):
             ctx.get_node_parser_mgr().add(kb.node_parser)
     if knowledge.indexer is not None:
         ind = knowledge.indexer
-        found_indexer = ctx.get_indexer_mgr().search_indexer(ind) if ind.indexer_type != IndexerType.MILVUS_VECTOR else None
+        found_indexer = (
+            ctx.get_indexer_mgr().search_indexer(ind) if ind.indexer_type != IndexerType.MILVUS_VECTOR else None
+        )
         if found_indexer is not None:
             kb.indexer = found_indexer
         else:

EdgeCraftRAG/edgecraftrag/api/v1/pipeline.py

@@ -17,7 +17,6 @@
 from edgecraftrag.components.benchmark import Benchmark
 from edgecraftrag.components.generator import FreeChatGenerator, QnAGenerator
 from edgecraftrag.components.postprocessor import MetadataReplaceProcessor, RerankProcessor
-
 from edgecraftrag.config_repository import MilvusConfigRepository, save_pipeline_configurations
 from edgecraftrag.context import ctx
 from edgecraftrag.env import PIPELINE_FILE
@@ -217,7 +216,9 @@ async def update_pipeline_handler(pl, req):
                 raise Exception("Inference Type Not Supported")
 
     if pl.status.active != req.active:
-        ctx.get_pipeline_mgr().activate_pipeline(pl.name, req.active, ctx.get_knowledge_mgr().get_active_knowledge_base())
+        ctx.get_pipeline_mgr().activate_pipeline(
+            pl.name, req.active, ctx.get_knowledge_mgr().get_active_knowledge_base()
+        )
     return pl
 
 

EdgeCraftRAG/edgecraftrag/components/indexer.py

@@ -6,14 +6,15 @@
 import faiss
 from edgecraftrag.base import BaseComponent, CompType, IndexerType
 from edgecraftrag.context import ctx
+from langchain_milvus import Milvus
 from langchain_openai import OpenAIEmbeddings
 from llama_index.core import StorageContext, VectorStoreIndex
 from llama_index.vector_stores.faiss import FaissVectorStore
 from llama_index.vector_stores.milvus import MilvusVectorStore
 from pydantic import model_serializer
-from langchain_milvus import Milvus
 from pymilvus import Collection, MilvusException, connections, utility
 
+
 class VectorIndexer(BaseComponent, VectorStoreIndex):
     def __init__(self, embed_model, vector_type, vector_url="http://localhost:19530", kb_name="default_kb"):
         BaseComponent.__init__(

EdgeCraftRAG/edgecraftrag/components/knowledge_base.py

@@ -3,8 +3,8 @@
 
 import json
 import os
-import uuid
 import time
+import uuid
 from typing import Any, Dict, List, Optional, Union
 
 from edgecraftrag.base import BaseComponent, BenchType, CompType
@@ -16,6 +16,7 @@
 from llama_index.core.schema import Document
 from pydantic import Field, model_serializer
 
+
 class Knowledge(BaseComponent):
 
     node_parser: Optional[BaseComponent] = Field(default=None)
@@ -347,7 +348,7 @@ def calculate_totals(self):
         else:
             total = None
         return total
-    
+
     def update_nodes(self, nodes: List[Document]):
         self.nodes = nodes
 
@@ -370,7 +371,7 @@ async def run_node_parser(self, docs: List[Document]) -> Any:
             self.benchmark.update_benchmark_data(benchmark_index, BenchType.CHUNK_NUM, benchmark_data)
         self.add_nodes(nodes)
         return nodes
-        
+
     async def update_nodes_to_indexer(self) -> Any:
         if self.indexer is not None:
             self.indexer.insert_nodes(self.nodes)