[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

@@ -95,7 +95,8 @@ For more advanced env variables and configurations, please refer to [Prepare env
 
 ### 5. Deploy the Service on Intel GPU Using Docker Compose
 
-set Milvus DB and chat history round for inference: 
+set Milvus DB and chat history round for inference:
+
 ```bash
 # EC-RAG support Milvus as persistent database, by default milvus is disabled, you can choose to set MILVUS_ENABLED=1 to enable it
 export MILVUS_ENABLED=0
@@ -123,7 +124,7 @@ docker compose -f docker_compose/intel/gpu/arc/compose_vllm.yaml up -d
 #### option b. Deploy the Service on Arc B60 Using Docker Compose
 
 ```bash
-# Besides MILVUS_ENABLED and CHAT_HISTORY_ROUND, below enviroments are exposed for vLLM config, you can change them to your preference:
+# Besides MILVUS_ENABLED and CHAT_HISTORY_ROUND, below environments are exposed for vLLM config, you can change them to your preference:
 # export VLLM_SERVICE_PORT_B60=8086
 # export DTYPE=float16
 # export TP=1 # for multi GPU, you can change TP value

EdgeCraftRAG/docker_compose/intel/gpu/arc/compose_vllm_b60.yaml

@@ -183,4 +183,4 @@ services:
       -dp=$${DP}"
 networks:
   default:
-    driver: bridge
+    driver: bridge

EdgeCraftRAG/docs/API_Guide.md

@@ -219,4 +219,4 @@ curl -X POST http://${HOST_IP}:16010/v1/retrieval -H "Content-Type: application/
 
 ```bash
 curl -X POST http://${HOST_IP}:16011/v1/chatqna -H "Content-Type: application/json" -d '{"messages":"#REPLACE WITH YOUR QUESTION HERE#", "top_n":5, "max_tokens":512}' | jq '.'
-```
+```

EdgeCraftRAG/docs/Advanced_Setup.md

@@ -208,6 +208,6 @@ Model preparation is the same as vLLM inference section, please refer to [Prepar
 
 This section is the same as default vLLM inference section, please refer to [Prepare env variables and configurations](../docker_compose/intel/gpu/arc/README.md#prepare-env-variables-and-configurations) and [Start Edge Craft RAG Services with Docker Compose](../docker_compose/intel/gpu/arc/README.md#deploy-the-service-on-arc-a770-using-docker-compose)
 
-### 2. Access Kbadmin UI 
+### 2. Access Kbadmin UI
 
 please refer to [ChatQnA with Kbadmin in UI](./Explore_Edge_Craft_RAG.md#chatqna-with-kbadmin-in-ui)

EdgeCraftRAG/docs/Explore_Edge_Craft_RAG.md

@@ -34,7 +34,7 @@ After knowledge base creation, you can upload the documents for retrieval.
 Then, you can submit messages in the chat box in `Chat` page.
 ![chat_with_rag](../assets/img/chatqna.png)
 
-## ChatQnA with Kbadmin in UI 
+## ChatQnA with Kbadmin in UI
 
 ### Kbadmin Pipeline
 
@@ -52,4 +52,4 @@ Please select 'kbadmin' in `Type`and select kb name from the kbs you created in
 ![upload_data](../assets/img/kbadmin_kb.png)
 
 Then, you can submit messages in the chat box in `Chat` page.
-![chat_with_rag](../assets/img/chatqna.png)
+![chat_with_rag](../assets/img/chatqna.png)

EdgeCraftRAG/edgecraftrag/api/v1/chatqna.py

@@ -38,7 +38,7 @@ async def chatqna(request: ChatCompletionRequest):
         active_kb = ctx.knowledgemgr.get_active_knowledge_base()
         request.user = active_kb if active_kb else None
         if experience_kb:
-            request.tool_choice = 'auto' if experience_kb.experience_active else 'none'
+            request.tool_choice = "auto" if experience_kb.experience_active else "none"
         generator = ctx.get_pipeline_mgr().get_active_pipeline().generator
         if generator:
             request.model = generator.model_id
@@ -62,7 +62,7 @@ async def ragqna(request: ChatCompletionRequest):
         active_kb = ctx.knowledgemgr.get_active_knowledge_base()
         request.user = active_kb if active_kb else None
         if experience_kb:
-            request.tool_choice = 'auto' if experience_kb.experience_active else 'none'
+            request.tool_choice = "auto" if experience_kb.experience_active else "none"
         generator = ctx.get_pipeline_mgr().get_active_pipeline().generator
         if generator:
             request.model = generator.model_id

EdgeCraftRAG/edgecraftrag/api/v1/knowledge_base.py

@@ -5,15 +5,15 @@
 import json
 import os
 import re
+from typing import Dict, List, Union
 
-from typing import List, Dict, Union
 from edgecraftrag.api.v1.data import add_data
-from edgecraftrag.api_schema import DataIn, KnowledgeBaseCreateIn, ExperienceIn
+from edgecraftrag.api_schema import DataIn, ExperienceIn, KnowledgeBaseCreateIn
 from edgecraftrag.base import IndexerType
+from edgecraftrag.components.query_preprocess import query_search
+from edgecraftrag.components.retriever import get_kbs_info
 from edgecraftrag.context import ctx
 from edgecraftrag.utils import compare_mappings
-from edgecraftrag.components.retriever import get_kbs_info
-from edgecraftrag.components.query_preprocess import query_search
 from fastapi import FastAPI, HTTPException, status
 from pymilvus.exceptions import MilvusException
 
@@ -23,6 +23,7 @@
 KNOWLEDGE_BASE_ROOT = "/home/user/ui_cache"
 CONFIG_DIR = "/home/user/ui_cache/configs"
 
+
 # Get all knowledge bases
 @kb_app.get(path="/v1/knowledge")
 async def get_all_knowledge_bases():
@@ -52,7 +53,7 @@ async def create_knowledge_base(knowledge: KnowledgeBaseCreateIn):
                 detail="Knowledge base names must begin with a letter or underscore",
             )
 
-        if knowledge.active and knowledge.comp_type =="knowledge" and knowledge.comp_subtype == "origin_kb":
+        if knowledge.active and knowledge.comp_type == "knowledge" and knowledge.comp_subtype == "origin_kb":
             active_pl.indexer.reinitialize_indexer(knowledge.name)
             active_pl.update_indexer_to_retriever()
         elif knowledge.comp_subtype == "kbadmin_kb":
@@ -74,7 +75,10 @@ async def delete_knowledge_base(knowledge_name: str):
         if rm_kb.comp_type == "knowledge" and rm_kb.comp_subtype == "origin_kb":
             if active_kb:
                 if active_kb.name == knowledge_name or active_kb.idx == knowledge_name:
-                    raise HTTPException(status_code=status.HTTP_500_INTERNAL_SERVER_ERROR, detail="Cannot delete a running knowledge base.")
+                    raise HTTPException(
+                        status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
+                        detail="Cannot delete a running knowledge base.",
+                    )
             kb_file_path = rm_kb.get_file_paths()
             if kb_file_path:
                 if active_pl.indexer.comp_subtype == "milvus_vector":
@@ -84,7 +88,10 @@ async def delete_knowledge_base(knowledge_name: str):
                         active_pl.update_indexer_to_retriever()
         if rm_kb.comp_type == "experience":
             if rm_kb.experience_active:
-                raise HTTPException(status_code=status.HTTP_500_INTERNAL_SERVER_ERROR, detail="Cannot delete a running experience knowledge base.")
+                raise HTTPException(
+                    status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
+                    detail="Cannot delete a running experience knowledge base.",
+                )
             else:
                 rm_kb.clear_experiences()
         result = ctx.knowledgemgr.delete_knowledge_base(knowledge_name)
@@ -129,10 +136,15 @@ async def add_file_to_knowledge_base(knowledge_name, file_path: DataIn):
     try:
         active_pl = ctx.get_pipeline_mgr().get_active_pipeline()
         kb = ctx.knowledgemgr.get_knowledge_base_by_name_or_id(knowledge_name)
-        if kb.comp_type =="experience":
-             raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail="The experience type cannot perform file operations.")
+        if kb.comp_type == "experience":
+            raise HTTPException(
+                status_code=status.HTTP_404_NOT_FOUND, detail="The experience type cannot perform file operations."
+            )
         if kb.comp_subtype == "kbadmin_kb" or active_pl.indexer.comp_subtype == "kbadmin_indexer":
-            raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail="Please proceed to the kbadmin interface to perform the operation.")
+            raise HTTPException(
+                status_code=status.HTTP_404_NOT_FOUND,
+                detail="Please proceed to the kbadmin interface to perform the operation.",
+            )
         # Validate and normalize the user-provided path
         user_path = file_path.local_path
         normalized_path = os.path.normpath(os.path.join(KNOWLEDGE_BASE_ROOT, user_path))
@@ -184,10 +196,15 @@ async def remove_file_from_knowledge_base(knowledge_name, file_path: DataIn):
     try:
         active_pl = ctx.get_pipeline_mgr().get_active_pipeline()
         kb = ctx.knowledgemgr.get_knowledge_base_by_name_or_id(knowledge_name)
-        if kb.comp_type =="experience":
-             raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail="The experience type cannot perform file operations.")
+        if kb.comp_type == "experience":
+            raise HTTPException(
+                status_code=status.HTTP_404_NOT_FOUND, detail="The experience type cannot perform file operations."
+            )
         if kb.comp_subtype == "kbadmin_kb" or active_pl.indexer.comp_subtype == "kbadmin_indexer":
-            raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail="Please proceed to the kbadmin interface to perform the operation.")
+            raise HTTPException(
+                status_code=status.HTTP_404_NOT_FOUND,
+                detail="Please proceed to the kbadmin interface to perform the operation.",
+            )
         active_kb = ctx.knowledgemgr.get_active_knowledge_base()
         if file_path.local_path in kb.get_file_paths():
             kb.remove_file_path(file_path.local_path)
@@ -215,9 +232,10 @@ async def remove_file_from_knowledge_base(knowledge_name, file_path: DataIn):
     except ValueError as e:
         raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail=str(e))
 
+
 @kb_app.post("/v1/experience")
 def get_experience_by_question(req: ExperienceIn):
-    kb = ctx.knowledgemgr.get_experience_kb()   
+    kb = ctx.knowledgemgr.get_experience_kb()
     result = kb.get_experience_by_question(req.question)
     if not result:
         raise HTTPException(404, detail="Experience not found")
@@ -238,41 +256,41 @@ def update_experience(experience: ExperienceIn):
     kb = ctx.knowledgemgr.get_experience_kb()
     result = kb.update_experience(experience.question, experience.content)
     if not result:
-        raise HTTPException(404, detail=f"Question not found")
+        raise HTTPException(404, detail="Question not found")
     return result
 
 
 @kb_app.delete("/v1/experiences")
-def delete_experience(req :ExperienceIn):
+def delete_experience(req: ExperienceIn):
     kb = ctx.knowledgemgr.get_experience_kb()
     success = kb.delete_experience(req.question)
     if not success:
         raise HTTPException(404, detail=f"Question {req.question} not found")
-    return {"message": f"Question deleted"}
+    return {"message": "Question deleted"}
 
 
 @kb_app.post("/v1/multiple_experiences/check")
 def check_duplicate_multiple_experiences(experiences: List[Dict[str, Union[str, List[str]]]]):
     kb = ctx.knowledgemgr.get_experience_kb()
     if not kb:
-       raise HTTPException(404, detail=f"No active experience type knowledge base")
+        raise HTTPException(404, detail="No active experience type knowledge base")
     all_existing = kb.get_all_experience()
     existing_questions = {item["question"] for item in all_existing}
     new_questions = [exp["question"] for exp in experiences if "question" in exp]
     duplicate_questions = [q for q in new_questions if q in existing_questions]
     if duplicate_questions:
         return {"code": 2001, "detail": "Duplicate experiences are appended OR overwritten!"}
     else:
-        kb.add_multiple_experiences(experiences=experiences, flag=True)  
-        return {"status": "success","detail": "No duplicate experiences, added successfully"}
+        kb.add_multiple_experiences(experiences=experiences, flag=True)
+        return {"status": "success", "detail": "No duplicate experiences, added successfully"}
 
 
 @kb_app.post("/v1/multiple_experiences/confirm")
-def confirm_multiple_experiences(experiences: List[Dict[str, Union[str, List[str]]]],flag: bool):
+def confirm_multiple_experiences(experiences: List[Dict[str, Union[str, List[str]]]], flag: bool):
     kb = ctx.knowledgemgr.get_experience_kb()
     try:
         if not kb:
-            raise HTTPException(404, detail=f"No active experience type knowledge base")
+            raise HTTPException(404, detail="No active experience type knowledge base")
         kb.add_multiple_experiences(experiences=experiences, flag=flag)
         return {"status": "success", "detail": "Experiences added successfully"}
     except Exception as e:
@@ -291,17 +309,14 @@ def add_experiences_from_file(req: DataIn):
 
 @kb_app.post(path="/v1/view_sub_questions")
 async def view_sub_questions(que: ExperienceIn):
-        active_pl = ctx.get_pipeline_mgr().get_active_pipeline()
-        CONFIG_DIR
-        search_config_path = os.path.join(CONFIG_DIR,"search_config.yaml")
-        search_dir = os.path.join(CONFIG_DIR,"experience_dir/experience.json")
-        top1_issue, sub_questions_result = await query_search(
-            user_input=que.question,
-            search_config_path=search_config_path,
-            search_dir=search_dir,
-            pl=active_pl
-        )
-        return sub_questions_result
+    active_pl = ctx.get_pipeline_mgr().get_active_pipeline()
+    CONFIG_DIR
+    search_config_path = os.path.join(CONFIG_DIR, "search_config.yaml")
+    search_dir = os.path.join(CONFIG_DIR, "experience_dir/experience.json")
+    top1_issue, sub_questions_result = await query_search(
+        user_input=que.question, search_config_path=search_config_path, search_dir=search_dir, pl=active_pl
+    )
+    return sub_questions_result
 
 
 @kb_app.get("/v1/kbadmin/kbs_list")
@@ -310,9 +325,9 @@ def get_kbs_list():
     try:
         if not active_pl or active_pl.indexer.comp_subtype != "kbadmin_indexer":
             return []
-        CONNECTION_ARGS =  {"uri": active_pl.indexer.vector_url}
+        CONNECTION_ARGS = {"uri": active_pl.indexer.vector_url}
         kbs_list = get_kbs_info(CONNECTION_ARGS)
-        kb_names =  [name for name in kbs_list.keys()]
+        kb_names = [name for name in kbs_list.keys()]
         return kb_names
     except Exception as e:
         raise HTTPException(status_code=400, detail=str(e))
@@ -372,7 +387,7 @@ async def load_knowledge_from_file():
             for Knowledgebase_data in all_data:
                 pipeline_req = KnowledgeBaseCreateIn(**Knowledgebase_data)
                 kb = ctx.knowledgemgr.create_knowledge_base(pipeline_req)
-                if  kb.comp_type =="knowledge":
+                if kb.comp_type == "knowledge":
                     if Knowledgebase_data["file_map"]:
                         if active_pl.indexer.comp_subtype != "milvus_vector" and Knowledgebase_data["active"]:
                             for file_path in Knowledgebase_data["file_map"].values():
@@ -401,7 +416,15 @@ async def save_knowledge_to_file():
         kb_base = ctx.knowledgemgr.get_all_knowledge_bases()
         knowledgebases_data = []
         for kb in kb_base:
-            kb_json = {"name": kb.name, "description": kb.description, "active": kb.active, "file_map": kb.file_map, "comp_type": kb.comp_type, "comp_subtype":kb.comp_subtype, "experience_active": kb.experience_active}
+            kb_json = {
+                "name": kb.name,
+                "description": kb.description,
+                "active": kb.active,
+                "file_map": kb.file_map,
+                "comp_type": kb.comp_type,
+                "comp_subtype": kb.comp_subtype,
+                "experience_active": kb.experience_active,
+            }
             knowledgebases_data.append(kb_json)
         json_str = json.dumps(knowledgebases_data, indent=2, ensure_ascii=False)
         with open(KNOWLEDGEBASE_FILE, "w", encoding="utf-8") as f:
@@ -412,6 +435,8 @@ async def save_knowledge_to_file():
 
 all_pipeline_milvus_maps = {"change_pl": []}
 current_pipeline_kb_map = {}
+
+
 async def refresh_milvus_map(milvus_name):
     current_pipeline_kb_map.clear()
     knowledge_bases_list = await get_all_knowledge_bases()
@@ -420,13 +445,13 @@ async def refresh_milvus_map(milvus_name):
             continue
         current_pipeline_kb_map[kb.name] = kb.file_map
     all_pipeline_milvus_maps[milvus_name] = copy.deepcopy(current_pipeline_kb_map)
-    milvus_maps_path = os.path.join(CONFIG_DIR,"milvus_maps.json")
+    milvus_maps_path = os.path.join(CONFIG_DIR, "milvus_maps.json")
     with open(milvus_maps_path, "w", encoding="utf-8") as f:
         json.dump(all_pipeline_milvus_maps, f, ensure_ascii=False, indent=2)
 
 
 def read_milvus_maps():
-    milvus_maps_path = os.path.join(CONFIG_DIR,"milvus_maps.json")
+    milvus_maps_path = os.path.join(CONFIG_DIR, "milvus_maps.json")
     global all_pipeline_milvus_maps
     try:
         with open(milvus_maps_path, "r", encoding="utf-8") as f:
@@ -435,38 +460,45 @@ def read_milvus_maps():
         all_pipeline_milvus_maps = {"change_pl": []}
     return all_pipeline_milvus_maps
 
+
 def save_change_pl(pl_name):
-    if pl_name not in  all_pipeline_milvus_maps["change_pl"]:
+    if pl_name not in all_pipeline_milvus_maps["change_pl"]:
         return all_pipeline_milvus_maps["change_pl"].append(pl_name)
 
+
 async def Synchronizing_vector_data(old_active_pl, new_active_pl, pl_change):
     try:
         if pl_change:
             save_change_pl(new_active_pl.name)
         active_kb = ctx.knowledgemgr.get_active_knowledge_base()
-       # Determine whether it is kbadmin type
+        # Determine whether it is kbadmin type
         if old_active_pl:
-            if old_active_pl.retriever.comp_subtype == "kbadmin_retriever" and new_active_pl.retriever.comp_subtype == "kbadmin_retriever":
+            if (
+                old_active_pl.retriever.comp_subtype == "kbadmin_retriever"
+                and new_active_pl.retriever.comp_subtype == "kbadmin_retriever"
+            ):
                 if active_kb:
                     if active_kb.comp_subtype == "kbadmin_kb":
                         new_active_pl.retriever.config_kbadmin_milvus(active_kb.name)
                 return True
             elif old_active_pl.retriever.comp_subtype == "kbadmin_retriever":
                 return True
-        
-        milvus_name = (old_active_pl.name + str(old_active_pl.indexer.model_extra["d"]) if old_active_pl else "default_kb")
+
+        milvus_name = (
+            old_active_pl.name + str(old_active_pl.indexer.model_extra["d"]) if old_active_pl else "default_kb"
+        )
         if not new_active_pl.status.active:
             if old_active_pl:
                 if old_active_pl.indexer.comp_subtype == "milvus_vector":
                     await refresh_milvus_map(milvus_name)
             return True
         if not active_kb:
             return True
-        if new_active_pl.retriever.comp_subtype=="kbadmin_retriever":
-                if active_kb:
-                    if active_kb.comp_subtype == "kbadmin_kb":
-                        new_active_pl.retriever.config_kbadmin_milvus(active_kb.name)
-                return True
+        if new_active_pl.retriever.comp_subtype == "kbadmin_retriever":
+            if active_kb:
+                if active_kb.comp_subtype == "kbadmin_kb":
+                    new_active_pl.retriever.config_kbadmin_milvus(active_kb.name)
+            return True
         # Perform milvus data synchronization
         if new_active_pl.indexer.comp_subtype == "milvus_vector":
             # Pipeline component state changed