Remove manual initialize_pipeline_status() calls across codebase

- Auto-init pipeline status in storages
- Remove redundant import statements
- Simplify initialization pattern
- Update docs and examples

README-zh.md

@@ -222,6 +222,10 @@ python examples/lightrag_openai_demo.py
 
 > ⚠️ **如果您希望将LightRAG集成到您的项目中，建议您使用LightRAG Server提供的REST API**。LightRAG Core通常用于嵌入式应用，或供希望进行研究与评估的学者使用。
 
+### ⚠️ 重要：初始化要求
+
+LightRAG 在使用前需要显式初始化。 创建 LightRAG 实例后，您必须调用 await rag.initialize_storages()，否则将出现错误。
+
 ### 一个简单程序
 
 以下Python代码片段演示了如何初始化LightRAG、插入文本并进行查询：
@@ -231,7 +235,6 @@ import os
 import asyncio
 from lightrag import LightRAG, QueryParam
 from lightrag.llm.openai import gpt_4o_mini_complete, gpt_4o_complete, openai_embed
-from lightrag.kg.shared_storage import initialize_pipeline_status
 from lightrag.utils import setup_logger
 
 setup_logger("lightrag", level="INFO")
@@ -246,9 +249,7 @@ async def initialize_rag():
         embedding_func=openai_embed,
         llm_model_func=gpt_4o_mini_complete,
     )
-    await rag.initialize_storages()
+    await rag.initialize_storages()    return rag
-    await initialize_pipeline_status()
-    return rag
 
 async def main():
     try:
@@ -442,8 +443,6 @@ async def initialize_rag():
     )
 
     await rag.initialize_storages()
-    await initialize_pipeline_status()
-
     return rag
 ```
 
@@ -572,7 +571,6 @@ from lightrag import LightRAG
 from lightrag.llm.llama_index_impl import llama_index_complete_if_cache, llama_index_embed
 from llama_index.embeddings.openai import OpenAIEmbedding
 from llama_index.llms.openai import OpenAI
-from lightrag.kg.shared_storage import initialize_pipeline_status
 from lightrag.utils import setup_logger
 
 # 为LightRAG设置日志处理程序
@@ -589,8 +587,6 @@ async def initialize_rag():
     )
 
     await rag.initialize_storages()
-    await initialize_pipeline_status()
-
     return rag
 
 def main():
@@ -840,8 +836,6 @@ async def initialize_rag():
     # 初始化数据库连接
     await rag.initialize_storages()
     # 初始化文档处理的管道状态
-    await initialize_pipeline_status()
-
     return rag
 ```
 

README.md

@@ -224,10 +224,7 @@ For a streaming response implementation example, please see `examples/lightrag_o
 
 ### ⚠️ Important: Initialization Requirements
 
-**LightRAG requires explicit initialization before use.** You must call both `await rag.initialize_storages()` and `await initialize_pipeline_status()` after creating a LightRAG instance, otherwise you will encounter errors like:
+**LightRAG requires explicit initialization before use.** You must call `await rag.initialize_storages()` after creating a LightRAG instance, otherwise you will encounter errors.
-
-- `AttributeError: __aenter__` - if storages are not initialized
-- `KeyError: 'history_messages'` - if pipeline status is not initialized
 
 ### A Simple Program
 
@@ -238,7 +235,6 @@ import os
 import asyncio
 from lightrag import LightRAG, QueryParam
 from lightrag.llm.openai import gpt_4o_mini_complete, gpt_4o_complete, openai_embed
-from lightrag.kg.shared_storage import initialize_pipeline_status
 from lightrag.utils import setup_logger
 
 setup_logger("lightrag", level="INFO")
@@ -254,9 +250,7 @@ async def initialize_rag():
         llm_model_func=gpt_4o_mini_complete,
     )
     # IMPORTANT: Both initialization calls are required!
-    await rag.initialize_storages()  # Initialize storage backends
+    await rag.initialize_storages()  # Initialize storage backends    return rag
-    await initialize_pipeline_status()  # Initialize processing pipeline
-    return rag
 
 async def main():
     try:
@@ -445,8 +439,6 @@ async def initialize_rag():
     )
 
     await rag.initialize_storages()
-    await initialize_pipeline_status()
-
     return rag
 ```
 
@@ -577,7 +569,6 @@ from lightrag import LightRAG
 from lightrag.llm.llama_index_impl import llama_index_complete_if_cache, llama_index_embed
 from llama_index.embeddings.openai import OpenAIEmbedding
 from llama_index.llms.openai import OpenAI
-from lightrag.kg.shared_storage import initialize_pipeline_status
 from lightrag.utils import setup_logger
 
 # Setup log handler for LightRAG
@@ -594,8 +585,6 @@ async def initialize_rag():
     )
 
     await rag.initialize_storages()
-    await initialize_pipeline_status()
-
     return rag
 
 def main():
@@ -847,8 +836,6 @@ async def initialize_rag():
     # Initialize database connections
     await rag.initialize_storages()
     # Initialize pipeline status for document processing
-    await initialize_pipeline_status()
-
     return rag
 ```
 
@@ -933,8 +920,6 @@ async def initialize_rag():
     # Initialize database connections
     await rag.initialize_storages()
     # Initialize pipeline status for document processing
-    await initialize_pipeline_status()
-
     return rag
 ```
 
@@ -1542,16 +1527,13 @@ If you encounter these errors when using LightRAG:
 
 2. **`KeyError: 'history_messages'`**
    - **Cause**: Pipeline status not initialized
-   - **Solution**: Call `await initialize_pipeline_status()` after initializing storages
+   - **Solution**: Call `
-
 3. **Both errors in sequence**
    - **Cause**: Neither initialization method was called
    - **Solution**: Always follow this pattern:
    ```python
    rag = LightRAG(...)
-   await rag.initialize_storages()
+   await rag.initialize_storages()   ```
-   await initialize_pipeline_status()
-   ```
 
 ### Model Switching Issues
 

examples/lightrag_azure_openai_demo.py

@@ -6,7 +6,6 @@ import numpy as np
 from dotenv import load_dotenv
 import logging
 from openai import AzureOpenAI
-from lightrag.kg.shared_storage import initialize_pipeline_status
 
 logging.basicConfig(level=logging.INFO)
 
@@ -93,9 +92,7 @@ async def initialize_rag():
         ),
     )
 
-    await rag.initialize_storages()
+    await rag.initialize_storages()  # Auto-initializes pipeline_status
-    await initialize_pipeline_status()
-
     return rag
 
 

examples/lightrag_ollama_demo.py

@@ -6,7 +6,6 @@ import logging.config
 from lightrag import LightRAG, QueryParam
 from lightrag.llm.ollama import ollama_model_complete, ollama_embed
 from lightrag.utils import EmbeddingFunc, logger, set_verbose_debug
-from lightrag.kg.shared_storage import initialize_pipeline_status
 
 from dotenv import load_dotenv
 
@@ -104,9 +103,7 @@ async def initialize_rag():
         ),
     )
 
-    await rag.initialize_storages()
+    await rag.initialize_storages()  # Auto-initializes pipeline_status
-    await initialize_pipeline_status()
-
     return rag
 
 

examples/lightrag_openai_compatible_demo.py

@@ -7,7 +7,6 @@ from lightrag import LightRAG, QueryParam
 from lightrag.llm.openai import openai_complete_if_cache
 from lightrag.llm.ollama import ollama_embed
 from lightrag.utils import EmbeddingFunc, logger, set_verbose_debug
-from lightrag.kg.shared_storage import initialize_pipeline_status
 
 from dotenv import load_dotenv
 
@@ -120,9 +119,7 @@ async def initialize_rag():
         ),
     )
 
-    await rag.initialize_storages()
+    await rag.initialize_storages()  # Auto-initializes pipeline_status
-    await initialize_pipeline_status()
-
     return rag
 
 

examples/lightrag_openai_demo.py

@@ -4,7 +4,6 @@ import logging
 import logging.config
 from lightrag import LightRAG, QueryParam
 from lightrag.llm.openai import gpt_4o_mini_complete, openai_embed
-from lightrag.kg.shared_storage import initialize_pipeline_status
 from lightrag.utils import logger, set_verbose_debug
 
 WORKING_DIR = "./dickens"
@@ -84,8 +83,7 @@ async def initialize_rag():
         llm_model_func=gpt_4o_mini_complete,
     )
 
-    await rag.initialize_storages()
+    await rag.initialize_storages()  # Auto-initializes pipeline_status
-    await initialize_pipeline_status()
 
     return rag
 

examples/lightrag_openai_mongodb_graph_demo.py

@@ -4,7 +4,6 @@ from lightrag import LightRAG, QueryParam
 from lightrag.llm.openai import gpt_4o_mini_complete, openai_embed
 from lightrag.utils import EmbeddingFunc
 import numpy as np
-from lightrag.kg.shared_storage import initialize_pipeline_status
 
 #########
 # Uncomment the below two lines if running in a jupyter notebook to handle the async nature of rag.insert()
@@ -61,9 +60,7 @@ async def initialize_rag():
         log_level="DEBUG",
     )
 
-    await rag.initialize_storages()
+    await rag.initialize_storages()  # Auto-initializes pipeline_status
-    await initialize_pipeline_status()
-
     return rag
 
 

examples/modalprocessors_example.py

@@ -7,7 +7,6 @@ This example demonstrates how to use LightRAG's modal processors directly withou
 import asyncio
 import argparse
 from lightrag.llm.openai import openai_complete_if_cache, openai_embed
-from lightrag.kg.shared_storage import initialize_pipeline_status
 from lightrag import LightRAG
 from lightrag.utils import EmbeddingFunc
 from raganything.modalprocessors import (
@@ -190,9 +189,7 @@ async def initialize_rag(api_key: str, base_url: str = None):
         ),
     )
 
-    await rag.initialize_storages()
+    await rag.initialize_storages()  # Auto-initializes pipeline_status
-    await initialize_pipeline_status()
-
     return rag
 
 

examples/rerank_example.py

@@ -29,7 +29,6 @@ import numpy as np
 from lightrag import LightRAG, QueryParam
 from lightrag.llm.openai import openai_complete_if_cache, openai_embed
 from lightrag.utils import EmbeddingFunc, setup_logger
-from lightrag.kg.shared_storage import initialize_pipeline_status
 
 from functools import partial
 from lightrag.rerank import cohere_rerank
@@ -94,9 +93,7 @@ async def create_rag_with_rerank():
         rerank_model_func=rerank_model_func,
     )
 
-    await rag.initialize_storages()
+    await rag.initialize_storages()  # Auto-initializes pipeline_status
-    await initialize_pipeline_status()
-
     return rag
 
 

examples/unofficial-sample/lightrag_bedrock_demo.py

@@ -8,7 +8,6 @@ import logging
 from lightrag import LightRAG, QueryParam
 from lightrag.llm.bedrock import bedrock_complete, bedrock_embed
 from lightrag.utils import EmbeddingFunc
-from lightrag.kg.shared_storage import initialize_pipeline_status
 
 import asyncio
 import nest_asyncio
@@ -32,9 +31,7 @@ async def initialize_rag():
         ),
     )
 
-    await rag.initialize_storages()
+    await rag.initialize_storages()  # Auto-initializes pipeline_status
-    await initialize_pipeline_status()
-
     return rag
 
 

examples/unofficial-sample/lightrag_cloudflare_demo.py

@@ -5,7 +5,6 @@ import logging
 import logging.config
 from lightrag import LightRAG, QueryParam
 from lightrag.utils import EmbeddingFunc, logger, set_verbose_debug
-from lightrag.kg.shared_storage import initialize_pipeline_status
 
 import requests
 import numpy as np
@@ -221,9 +220,7 @@ async def initialize_rag():
         ),
     )
 
-    await rag.initialize_storages()
+    await rag.initialize_storages()  # Auto-initializes pipeline_status
-    await initialize_pipeline_status()
-
     return rag
 
 

examples/unofficial-sample/lightrag_hf_demo.py

@@ -4,7 +4,6 @@ from lightrag import LightRAG, QueryParam
 from lightrag.llm.hf import hf_model_complete, hf_embed
 from lightrag.utils import EmbeddingFunc
 from transformers import AutoModel, AutoTokenizer
-from lightrag.kg.shared_storage import initialize_pipeline_status
 
 import asyncio
 import nest_asyncio
@@ -37,9 +36,7 @@ async def initialize_rag():
         ),
     )
 
-    await rag.initialize_storages()
+    await rag.initialize_storages()  # Auto-initializes pipeline_status
-    await initialize_pipeline_status()
-
     return rag
 
 

examples/unofficial-sample/lightrag_llamaindex_direct_demo.py

@@ -12,7 +12,6 @@ import nest_asyncio
 
 nest_asyncio.apply()
 
-from lightrag.kg.shared_storage import initialize_pipeline_status
 
 # Configure working directory
 WORKING_DIR = "./index_default"
@@ -94,9 +93,7 @@ async def initialize_rag():
         ),
     )
 
-    await rag.initialize_storages()
+    await rag.initialize_storages()  # Auto-initializes pipeline_status
-    await initialize_pipeline_status()
-
     return rag
 
 

examples/unofficial-sample/lightrag_llamaindex_litellm_demo.py

@@ -12,7 +12,6 @@ import nest_asyncio
 
 nest_asyncio.apply()
 
-from lightrag.kg.shared_storage import initialize_pipeline_status
 
 # Configure working directory
 WORKING_DIR = "./index_default"
@@ -96,9 +95,7 @@ async def initialize_rag():
         ),
     )
 
-    await rag.initialize_storages()
+    await rag.initialize_storages()  # Auto-initializes pipeline_status
-    await initialize_pipeline_status()
-
     return rag
 
 

examples/unofficial-sample/lightrag_llamaindex_litellm_opik_demo.py

@@ -12,7 +12,6 @@ import nest_asyncio
 
 nest_asyncio.apply()
 
-from lightrag.kg.shared_storage import initialize_pipeline_status
 
 # Configure working directory
 WORKING_DIR = "./index_default"
@@ -107,9 +106,7 @@ async def initialize_rag():
         ),
     )
 
-    await rag.initialize_storages()
+    await rag.initialize_storages()  # Auto-initializes pipeline_status
-    await initialize_pipeline_status()
-
     return rag
 
 

examples/unofficial-sample/lightrag_lmdeploy_demo.py

@@ -5,7 +5,6 @@ from lightrag.llm.lmdeploy import lmdeploy_model_if_cache
 from lightrag.llm.hf import hf_embed
 from lightrag.utils import EmbeddingFunc
 from transformers import AutoModel, AutoTokenizer
-from lightrag.kg.shared_storage import initialize_pipeline_status
 
 import asyncio
 import nest_asyncio
@@ -62,9 +61,7 @@ async def initialize_rag():
         ),
     )
 
-    await rag.initialize_storages()
+    await rag.initialize_storages()  # Auto-initializes pipeline_status
-    await initialize_pipeline_status()
-
     return rag
 
 

examples/unofficial-sample/lightrag_nvidia_demo.py

@@ -9,7 +9,6 @@ from lightrag.llm import (
 )
 from lightrag.utils import EmbeddingFunc
 import numpy as np
-from lightrag.kg.shared_storage import initialize_pipeline_status
 
 # for custom llm_model_func
 from lightrag.utils import locate_json_string_body_from_string
@@ -115,9 +114,7 @@ async def initialize_rag():
         ),
     )
 
-    await rag.initialize_storages()
+    await rag.initialize_storages()  # Auto-initializes pipeline_status
-    await initialize_pipeline_status()
-
     return rag
 
 

examples/unofficial-sample/lightrag_openai_neo4j_milvus_redis_demo.py

@@ -3,7 +3,6 @@ import asyncio
 from lightrag import LightRAG, QueryParam
 from lightrag.llm.ollama import ollama_embed, openai_complete_if_cache
 from lightrag.utils import EmbeddingFunc
-from lightrag.kg.shared_storage import initialize_pipeline_status
 
 # WorkingDir
 ROOT_DIR = os.path.dirname(os.path.abspath(__file__))
@@ -66,9 +65,7 @@ async def initialize_rag():
         doc_status_storage="RedisKVStorage",
     )
 
-    await rag.initialize_storages()
+    await rag.initialize_storages()  # Auto-initializes pipeline_status
-    await initialize_pipeline_status()
-
     return rag
 
 

lightrag/tools/check_initialization.py

@@ -102,7 +102,6 @@ async def check_lightrag_setup(rag_instance: LightRAG, verbose: bool = False) ->
         print("\n📝 To fix, run this initialization sequence:\n")
         print("  await rag.initialize_storages()")
         print("  from lightrag.kg.shared_storage import initialize_pipeline_status")
-        print("  await initialize_pipeline_status()")
         print(
             "\n📚 Documentation: https://github.com/HKUDS/LightRAG#important-initialization-requirements"
         )
@@ -127,7 +126,6 @@ async def check_lightrag_setup(rag_instance: LightRAG, verbose: bool = False) ->
 async def demo():
     """Demonstrate the diagnostic tool with a test instance."""
     from lightrag.llm.openai import openai_embed, gpt_4o_mini_complete
-    from lightrag.kg.shared_storage import initialize_pipeline_status
 
     print("=" * 50)
     print("LightRAG Initialization Diagnostic Tool")
@@ -145,9 +143,7 @@ async def demo():
 
     print("\n" + "=" * 50)
     print("\n🔄 Initializing...\n")
-    await rag.initialize_storages()
+    await rag.initialize_storages()  # Auto-initializes pipeline_status
-    await initialize_pipeline_status()
-
     print("\n🟢 AFTER initialization:\n")
     await check_lightrag_setup(rag, verbose=True)
 

reproduce/Step_1.py

@@ -4,7 +4,6 @@ import time
 import asyncio
 
 from lightrag import LightRAG
-from lightrag.kg.shared_storage import initialize_pipeline_status
 
 
 def insert_text(rag, file_path):
@@ -35,9 +34,7 @@ if not os.path.exists(WORKING_DIR):
 async def initialize_rag():
     rag = LightRAG(working_dir=WORKING_DIR)
 
-    await rag.initialize_storages()
+    await rag.initialize_storages()  # Auto-initializes pipeline_status
-    await initialize_pipeline_status()
-
     return rag
 
 

reproduce/Step_1_openai_compatible.py

@@ -7,7 +7,6 @@ import numpy as np
 from lightrag import LightRAG
 from lightrag.utils import EmbeddingFunc
 from lightrag.llm.openai import openai_complete_if_cache, openai_embed
-from lightrag.kg.shared_storage import initialize_pipeline_status
 
 
 ## For Upstage API
@@ -70,9 +69,7 @@ async def initialize_rag():
         embedding_func=EmbeddingFunc(embedding_dim=4096, func=embedding_func),
     )
 
-    await rag.initialize_storages()
+    await rag.initialize_storages()  # Auto-initializes pipeline_status
-    await initialize_pipeline_status()
-
     return rag