add LightRAG init parameters in readme

README.md

@@ -511,6 +511,35 @@ if __name__ == "__main__":
 
 </details>
 
+### LightRAG init parameters
+
+| **Parameter** | **Type** | **Explanation** | **Default** |
+| --- | --- | --- | --- |
+| **working\_dir** | `str` | Directory where the cache will be stored | `lightrag_cache+timestamp` |
+| **kv\_storage** | `str` | Storage type for documents and text chunks. Supported types: `JsonKVStorage`, `OracleKVStorage` | `JsonKVStorage` |
+| **vector\_storage** | `str` | Storage type for embedding vectors. Supported types: `NanoVectorDBStorage`, `OracleVectorDBStorage` | `NanoVectorDBStorage` |
+| **graph\_storage** | `str` | Storage type for graph edges and nodes. Supported types: `NetworkXStorage`, `Neo4JStorage`, `OracleGraphStorage` | `NetworkXStorage` |
+| **log\_level** |     | Log level for application runtime | `logging.DEBUG` |
+| **chunk\_token\_size** | `int` | Maximum token size per chunk when splitting documents | `1200` |
+| **chunk\_overlap\_token\_size** | `int` | Overlap token size between two chunks when splitting documents | `100` |
+| **tiktoken\_model\_name** | `str` | Model name for the Tiktoken encoder used to calculate token numbers | `gpt-4o-mini` |
+| **entity\_extract\_max\_gleaning** | `int` | Number of loops in the entity extraction process, appending history messages | `1` |
+| **entity\_summary\_to\_max\_tokens** | `int` | Maximum token size for each entity summary | `500` |
+| **node\_embedding\_algorithm** | `str` | Algorithm for node embedding (currently not used) | `node2vec` |
+| **node2vec\_params** | `dict` | Parameters for node embedding | `{"dimensions": 1536,"num_walks": 10,"walk_length": 40,"window_size": 2,"iterations": 3,"random_seed": 3,}` |
+| **embedding\_func** | `EmbeddingFunc` | Function to generate embedding vectors from text | `openai_embedding` |
+| **embedding\_batch\_num** | `int` | Maximum batch size for embedding processes (multiple texts sent per batch) | `32` |
+| **embedding\_func\_max\_async** | `int` | Maximum number of concurrent asynchronous embedding processes | `16` |
+| **llm\_model\_func** | `callable` | Function for LLM generation | `gpt_4o_mini_complete` |
+| **llm\_model\_name** | `str` | LLM model name for generation | `meta-llama/Llama-3.2-1B-Instruct` |
+| **llm\_model\_max\_token\_size** | `int` | Maximum token size for LLM generation (affects entity relation summaries) | `32768` |
+| **llm\_model\_max\_async** | `int` | Maximum number of concurrent asynchronous LLM processes | `16` |
+| **llm\_model\_kwargs** | `dict` | Additional parameters for LLM generation |     |
+| **vector\_db\_storage\_cls\_kwargs** | `dict` | Additional parameters for vector database (currently not used) |     |
+| **enable\_llm\_cache** | `bool` | If `TRUE`, stores LLM results in cache; repeated prompts return cached responses | `TRUE` |
+| **addon\_params** | `dict` | Additional parameters, e.g., `{"example_number": 1, "language": "Simplified Chinese"}`: sets example limit and output language | `example_number: all examples, language: English` |
+| **convert\_response\_to\_json\_func** | `callable` | Not used | `convert_response_to_json` |
+
 ## API Server Implementation
 
 LightRAG also provides a FastAPI-based server implementation for RESTful API access to RAG operations. This allows you to run LightRAG as a service and interact with it through HTTP requests.

examples/lightrag_api_oracle_demo..py

@@ -81,7 +81,7 @@ async def get_embedding_dim():
 
 async def init():
     # Detect embedding dimension
-    embedding_dimension = 1024  # await get_embedding_dim()
+    embedding_dimension = await get_embedding_dim()
     print(f"Detected embedding dimension: {embedding_dimension}")
     # Create Oracle DB connection
     # The `config` parameter is the connection configuration of Oracle DB
@@ -105,6 +105,7 @@ async def init():
     await oracle_db.check_tables()
     # Initialize LightRAG
     # We use Oracle DB as the KV/vector/graph storage
+    # You can add `addon_params={"example_number": 1, "language": "Simplfied Chinese"}` to control the prompt
     rag = LightRAG(
         enable_llm_cache=False,
         working_dir=WORKING_DIR,

examples/lightrag_oracle_demo.py

@@ -84,6 +84,7 @@ async def main():
 
         # Initialize LightRAG
         # We use Oracle DB as the KV/vector/graph storage
+        # You can add `addon_params={"example_number": 1, "language": "Simplfied Chinese"}` to control the prompt
         rag = LightRAG(
             enable_llm_cache=False,
             working_dir=WORKING_DIR,
@@ -96,8 +97,7 @@ async def main():
             ),
             graph_storage="OracleGraphStorage",
             kv_storage="OracleKVStorage",
-            vector_storage="OracleVectorDBStorage",
-            addon_params={"example_number": 1, "language": "Simplfied Chinese"},
+            vector_storage="OracleVectorDBStorage"            
         )
 
         # Setthe KV/vector/graph storage's `db` property, so all operation will use same connection pool

lightrag/llm.py

@@ -72,7 +72,7 @@ async def openai_complete_if_cache(
     content = response.choices[0].message.content
     if r"\u" in content:
         content = content.encode("utf-8").decode("unicode_escape")
-    print(content)
+    # print(content)
     if hashing_kv is not None:
         await hashing_kv.upsert(
             {args_hash: {"return": response.choices[0].message.content, "model": model}}

lightrag/operate.py

@@ -571,19 +571,19 @@ async def _build_query_context(
             hl_text_units_context,
         )
     return f"""
-# -----Entities-----
-# ```csv
-# {entities_context}
-# ```
-# -----Relationships-----
-# ```csv
-# {relations_context}
-# ```
-# -----Sources-----
-# ```csv
-# {text_units_context}
-# ```
-# """
+-----Entities-----
+```csv
+{entities_context}
+```
+-----Relationships-----
+```csv
+{relations_context}
+```
+-----Sources-----
+```csv
+{text_units_context}
+```
+"""
 
 
 async def _get_node_data(
@@ -593,18 +593,18 @@ async def _get_node_data(
     text_chunks_db: BaseKVStorage[TextChunkSchema],
     query_param: QueryParam,
 ):
-    # 获取相似的实体
+    # get similar entities
     results = await entities_vdb.query(query, top_k=query_param.top_k)
     if not len(results):
         return None
-    # 获取实体信息
+    # get entity information
     node_datas = await asyncio.gather(
         *[knowledge_graph_inst.get_node(r["entity_name"]) for r in results]
     )
     if not all([n is not None for n in node_datas]):
         logger.warning("Some nodes are missing, maybe the storage is damaged")
 
-    # 获取实体的度
+    # get entity degree
     node_degrees = await asyncio.gather(
         *[knowledge_graph_inst.node_degree(r["entity_name"]) for r in results]
     )
@@ -613,11 +613,11 @@ async def _get_node_data(
         for k, n, d in zip(results, node_datas, node_degrees)
         if n is not None
     ]  # what is this text_chunks_db doing.  dont remember it in airvx.  check the diagram.
-    # 根据实体获取文本片段
+    # get entitytext chunk 
     use_text_units = await _find_most_related_text_unit_from_entities(
         node_datas, query_param, text_chunks_db, knowledge_graph_inst
     )
-    # 获取关联的边
+    # get relate edges
     use_relations = await _find_most_related_edges_from_entities(
         node_datas, query_param, knowledge_graph_inst
     )
@@ -625,7 +625,7 @@ async def _get_node_data(
         f"Local query uses {len(node_datas)} entites, {len(use_relations)} relations, {len(use_text_units)} text units"
     )
 
-    # 构建提示词
+    # build prompt
     entites_section_list = [["id", "entity", "type", "description", "rank"]]
     for i, n in enumerate(node_datas):
         entites_section_list.append(