cleaning code for pull

README.md

@@ -155,6 +155,36 @@ rag = LightRAG(
 ```
 </details>
 
+
+<details>
+<summary> Using Neo4J for Storage </summary>
+
+* For production level scenarios you will most likely want to leverage an enterprise solution
+for KG storage. 
+```python
+export NEO4J_URI="neo4j://localhost:7687"
+export NEO4J_USERNAME="neo4j"
+export NEO4J_PASSWORD="password"
+
+When you launch the project be sure to override the default KG: NetworkS
+by specifying kg="Neo4JStorage".
+
+# Note: Default settings use NetworkX
+#Initialize LightRAG with Neo4J implementation. 
+WORKING_DIR = "./local_neo4jWorkDir"
+
+rag = LightRAG(
+    working_dir=WORKING_DIR,
+    llm_model_func=gpt_4o_mini_complete,  # Use gpt_4o_mini_complete LLM model
+    kg="Neo4JStorage", #<-----------override KG default
+    log_level="DEBUG"  #<-----------override log_level default
+)
+```
+see test_neo4j.py for a working example.
+</details>
+
+
+
 <details>
 <summary> Using Ollama Models </summary>
      

lightrag/kg/__init__.py

@@ -1,27 +1,3 @@
-print ("init package vars here. ......")
-# from .neo4j import GraphStorage as Neo4JStorage
+# print ("init package vars here. ......")
 
 
-# import sys
-# import importlib
-# # Specify the path to the directory containing the module
-# # Add the directory to the system path
-# module_dir = '/Users/kenwiltshire/documents/dev/LightRag/lightrag/kg'
-# sys.path.append(module_dir)
-# # Specify the module name
-# module_name = 'neo4j'
-# # Import the module
-# spec = importlib.util.spec_from_file_location(module_name, f'{module_dir}/{module_name}.py')
-
-# Neo4JStorage = importlib.util.module_from_spec(spec)
-# spec.loader.exec_module(Neo4JStorage)
-
-
-
-# Relative imports are still possible by adding a leading period to the module name when using the from ... import form:
-
-# # Import names from pkg.string
-# from .string import name1, name2
-# # Import pkg.string
-# from . import string
-

lightrag/lightrag.py

@@ -120,9 +120,6 @@ class LightRAG:
     addon_params: dict = field(default_factory=dict)
     convert_response_to_json_func: callable = convert_response_to_json
 
-    # def get_configured_KG(self):
-    #     return self.kg
-
     def __post_init__(self):
         log_file = os.path.join(self.working_dir, "lightrag.log")
         set_logger(log_file)
@@ -133,7 +130,7 @@ class LightRAG:
         _print_config = ",\n  ".join([f"{k} = {v}" for k, v in asdict(self).items()])
         logger.debug(f"LightRAG init with param:\n  {_print_config}\n")
 
-        #should move all storage setup here to leverage initial start params attached to self.
+        #@TODO: should move all storage setup here to leverage initial start params attached to self.
         self.graph_storage_cls: Type[BaseGraphStorage] = self._get_storage_class()[self.kg]
 
         if not os.path.exists(self.working_dir):

lightrag/llm.py

@@ -72,9 +72,7 @@ async def openai_complete_if_cache(
 
 @retry(
     stop=stop_after_attempt(3),
-    #kw_
-    wait=wait_exponential(multiplier=1, min=10, max=60),
-    # wait=wait_exponential(multiplier=1, min=4, max=10),
+    wait=wait_exponential(multiplier=1, min=4, max=10),
     retry=retry_if_exception_type((RateLimitError, APIConnectionError, Timeout)),
 )
 async def azure_openai_complete_if_cache(model,

lightrag/operate.py

@@ -908,7 +908,6 @@ async def hybrid_query(
                 .strip()
             )
             result = "{" + result.split("{")[1].split("}")[0] + "}"
-
             keywords_data = json.loads(result)
             hl_keywords = keywords_data.get("high_level_keywords", [])
             ll_keywords = keywords_data.get("low_level_keywords", [])

lightrag/storage.py

@@ -95,7 +95,6 @@ class NanoVectorDBStorage(BaseVectorStorage):
         embeddings = np.concatenate(embeddings_list)
         for i, d in enumerate(list_data):
             d["__vector__"] = embeddings[i]
-        print (f"Upserting to vector:  {list_data}")
         results = self._client.upsert(datas=list_data)
         return results
 
@@ -110,7 +109,6 @@ class NanoVectorDBStorage(BaseVectorStorage):
         results = [
             {**dp, "id": dp["__id__"], "distance": dp["__metrics__"]} for dp in results
         ]
-        print (f"vector db results {results} for query {query}")
         return results
 
     async def index_done_callback(self):
@@ -235,9 +233,11 @@ class NetworkXStorage(BaseGraphStorage):
             raise ValueError(f"Node embedding algorithm {algorithm} not supported")
         return await self._node_embed_algorithms[algorithm]()
 
+    
+    #@TODO: NOT USED 
     async def _node2vec_embed(self):
         from graspologic import embed
-        print ("is this ever called?")
+
         embeddings, nodes = embed.node2vec_embed(
             self._graph,
             **self.global_config["node2vec_params"],

testkg.py → test_neo4j.py

@@ -17,12 +17,12 @@ rag = LightRAG(
     working_dir=WORKING_DIR,
     llm_model_func=gpt_4o_mini_complete,  # Use gpt_4o_mini_complete LLM model
     kg="Neo4JStorage",
-    log_level="INFO"
+    log_level="DEBUG"
     # llm_model_func=gpt_4o_complete  # Optionally, use a stronger model
 )
 
-# with open("./book.txt") as f:
-#     rag.insert(f.read())
+with open("./book.txt") as f:
+    rag.insert(f.read())
 
 # Perform naive search
 print(rag.query("What are the top themes in this story?", param=QueryParam(mode="naive")))