Fix logging message formatting

(cherry picked from commit e0fd31a60d)

env.example

@@ -1,22 +1,5 @@
 ### This is sample file of .env
 
-###############################################################################
-### ⚡️ QUICK START: OpenAI Configuration (Recommended)
-###############################################################################
-### To get started with OpenAI, you only need:
-### 1. Set your OpenAI API key (get from https://platform.openai.com/api-keys)
-###    export OPENAI_API_KEY="sk-your-actual-api-key"
-### 2. Then you can start the server with default OpenAI configuration:
-###    lightrag-server
-### 
-### The default configuration will use:
-###   - LLM: gpt-4o-mini (entity/relation extraction, graph merging, query answering)
-###   - Embedding: text-embedding-3-small (vector embeddings)
-### No additional configuration needed!
-###
-### See LLM and Embedding Configuration sections below to customize models
-###############################################################################
-
 ###########################
 ### Server Configuration
 ###########################
@@ -40,13 +23,13 @@ WEBUI_DESCRIPTION="Simple and Fast Graph Based RAG System"
 # WORKING_DIR=<absolute_path_for_working_dir>
 
 ### Tiktoken cache directory (Store cached files in this folder for offline deployment)
-# TIKTOKEN_CACHE_DIR=./temp/tiktoken
+# TIKTOKEN_CACHE_DIR=/app/data/tiktoken
 
-### Ollama Emulating Model and Tag (used only when EMBEDDING_BINDING=ollama)
+### Ollama Emulating Model and Tag
 # OLLAMA_EMULATING_MODEL_NAME=lightrag
 OLLAMA_EMULATING_MODEL_TAG=latest
 
-### Max nodes return from grap retrieval in webui
+### Max nodes return from graph retrieval in webui
 # MAX_GRAPH_NODES=1000
 
 ### Logging level
@@ -67,44 +50,30 @@ OLLAMA_EMULATING_MODEL_TAG=latest
 # JWT_ALGORITHM=HS256
 
 ### API-Key to access LightRAG Server API
-### Use this key in HTTP requests with the 'X-API-Key' header
-### Example: curl -H "X-API-Key: your-secure-api-key-here" http://localhost:9621/query
 # LIGHTRAG_API_KEY=your-secure-api-key-here
 # WHITELIST_PATHS=/health,/api/*
 
-###############################################################################
-### OpenAI API Key (Required for OpenAI LLM and Embedding)
-### Get your key from: https://platform.openai.com/api-keys
-### This is the PRIMARY way to configure OpenAI (environment variable takes precedence)
-###############################################################################
-# OPENAI_API_KEY=sk-your-actual-openai-api-key-here
-
 ######################################################################################
 ### Query Configuration
 ###
-### How to control the context lenght sent to LLM:
+### How to control the context length sent to LLM:
 ###    MAX_ENTITY_TOKENS + MAX_RELATION_TOKENS < MAX_TOTAL_TOKENS
-###    Chunk_Tokens = MAX_TOTAL_TOKENS - Actual_Entity_Tokens - Actual_Reation_Tokens
+###    Chunk_Tokens = MAX_TOTAL_TOKENS - Actual_Entity_Tokens - Actual_Relation_Tokens
 ######################################################################################
-# LLM responde cache for query (Not valid for streaming response)
+# LLM response cache for query (Not valid for streaming response)
 ENABLE_LLM_CACHE=true
 # COSINE_THRESHOLD=0.2
 ### Number of entities or relations retrieved from KG
 # TOP_K=40
-### Maxmium number or chunks for naive vector search
+### Maximum number or chunks for naive vector search
 # CHUNK_TOP_K=20
-### control the actual enties send to LLM
+### control the actual entities send to LLM
 # MAX_ENTITY_TOKENS=6000
 ### control the actual relations send to LLM
 # MAX_RELATION_TOKENS=8000
-### control the maximum tokens send to LLM (include entities, raltions and chunks)
+### control the maximum tokens send to LLM (include entities, relations and chunks)
 # MAX_TOTAL_TOKENS=30000
 
-### maximum number of related chunks per source entity or relation
-###     The chunk picker uses this value to determine the total number of chunks selected from KG(knowledge graph)
-###     Higher values increase re-ranking time
-# RELATED_CHUNK_NUMBER=5
-
 ### chunk selection strategies
 ###     VECTOR: Pick KG chunks by vector similarity, delivered chunks to the LLM aligning more closely with naive retrieval
 ###     WEIGHT: Pick KG chunks by entity and chunk weight, delivered more solely KG related chunks to the LLM
@@ -119,7 +88,7 @@ ENABLE_LLM_CACHE=true
 RERANK_BINDING=null
 ### Enable rerank by default in query params when RERANK_BINDING is not null
 # RERANK_BY_DEFAULT=True
-### rerank score chunk filter(set to 0.0 to keep all chunks, 0.6 or above if LLM is not strong enought)
+### rerank score chunk filter(set to 0.0 to keep all chunks, 0.6 or above if LLM is not strong enough)
 # MIN_RERANK_SCORE=0.0
 
 ### For local deployment with vLLM
@@ -157,7 +126,7 @@ SUMMARY_LANGUAGE=English
 # CHUNK_SIZE=1200
 # CHUNK_OVERLAP_SIZE=100
 
-### Number of summary semgments or tokens to trigger LLM summary on entity/relation merge (at least 3 is recommented)
+### Number of summary segments or tokens to trigger LLM summary on entity/relation merge (at least 3 is recommended)
 # FORCE_LLM_SUMMARY_ON_MERGE=8
 ### Max description token size to trigger LLM summary
 # SUMMARY_MAX_TOKENS = 1200
@@ -166,6 +135,19 @@ SUMMARY_LANGUAGE=English
 ### Maximum context size sent to LLM for description summary
 # SUMMARY_CONTEXT_SIZE=12000
 
+### control the maximum chunk_ids stored in vector and graph db
+# MAX_SOURCE_IDS_PER_ENTITY=300
+# MAX_SOURCE_IDS_PER_RELATION=300
+### control chunk_ids limitation method: KEEP, FIFO (KEEP: Keep oldest, FIFO: First in first out)
+# SOURCE_IDS_LIMIT_METHOD=KEEP
+### Maximum number of file paths stored in entity/relation file_path field
+# MAX_FILE_PATHS=30
+
+### maximum number of related chunks per source entity or relation
+###     The chunk picker uses this value to determine the total number of chunks selected from KG(knowledge graph)
+###     Higher values increase re-ranking time
+# RELATED_CHUNK_NUMBER=5
+
 ###############################
 ### Concurrency Configuration
 ###############################
@@ -185,17 +167,10 @@ MAX_PARALLEL_INSERT=2
 ### LLM request timeout setting for all llm (0 means no timeout for Ollma)
 # LLM_TIMEOUT=180
 
-# PRIMARY CONFIGURATION: OpenAI (Recommended for production)
 LLM_BINDING=openai
-LLM_MODEL=gpt-4o-mini
+LLM_MODEL=gpt-4o
 LLM_BINDING_HOST=https://api.openai.com/v1
 LLM_BINDING_API_KEY=your_api_key
-# Note: By default, uses OPENAI_API_KEY environment variable
-
-### ALTERNATIVE: Using gpt-4o for higher quality (higher cost)
-# LLM_BINDING=openai
-# LLM_MODEL=gpt-4o
-# LLM_BINDING_HOST=https://api.openai.com/v1
 
 ### Optional for Azure
 # AZURE_OPENAI_API_VERSION=2024-08-01-preview
@@ -212,7 +187,7 @@ LLM_BINDING_API_KEY=your_api_key
 # OPENAI_LLM_TEMPERATURE=0.9
 ### Set the max_tokens to mitigate endless output of some LLM (less than LLM_TIMEOUT * llm_output_tokens/second, i.e. 9000 = 180s * 50 tokens/s)
 ### Typically, max_tokens does not include prompt content, though some models, such as Gemini Models, are exceptions
-### For vLLM/SGLang doployed models, or most of OpenAI compatible API provider
+### For vLLM/SGLang deployed models, or most of OpenAI compatible API provider
 # OPENAI_LLM_MAX_TOKENS=9000
 ### For OpenAI o1-mini or newer modles
 OPENAI_LLM_MAX_COMPLETION_TOKENS=9000
@@ -226,7 +201,7 @@ OPENAI_LLM_MAX_COMPLETION_TOKENS=9000
 # OPENAI_LLM_REASONING_EFFORT=minimal
 ### OpenRouter Specific Parameters
 # OPENAI_LLM_EXTRA_BODY='{"reasoning": {"enabled": false}}'
-### Qwen3 Specific Parameters depoly by vLLM
+### Qwen3 Specific Parameters deploy by vLLM
 # OPENAI_LLM_EXTRA_BODY='{"chat_template_kwargs": {"enable_thinking": false}}'
 
 ### use the following command to see all support options for Ollama LLM
@@ -244,52 +219,44 @@ OLLAMA_LLM_NUM_CTX=32768
 
 ####################################################################################
 ### Embedding Configuration (Should not be changed after the first file processed)
-### EMBEDDING_BINDING: openai, ollama, azure_openai, jina, lollms, aws_bedrock
+### EMBEDDING_BINDING: ollama, openai, azure_openai, jina, lollms, aws_bedrock
-### PRIMARY CONFIGURATION: OpenAI (Recommended)
 ####################################################################################
 # EMBEDDING_TIMEOUT=30
-EMBEDDING_BINDING=openai
+EMBEDDING_BINDING=ollama
-EMBEDDING_MODEL=text-embedding-3-small
+EMBEDDING_MODEL=bge-m3:latest
-EMBEDDING_DIM=1536
+EMBEDDING_DIM=1024
-EMBEDDING_BINDING_HOST=https://api.openai.com/v1
+EMBEDDING_BINDING_API_KEY=your_api_key
-# EMBEDDING_BINDING_API_KEY=your_openai_api_key (uses OPENAI_API_KEY env var by default)
+# If the embedding service is deployed within the same Docker stack, use host.docker.internal instead of localhost
+EMBEDDING_BINDING_HOST=http://localhost:11434
 
-### ALTERNATIVE: Text-embedding-3-large (higher quality, higher cost)
+### OpenAI compatible (VoyageAI embedding openai compatible)
 # EMBEDDING_BINDING=openai
 # EMBEDDING_MODEL=text-embedding-3-large
 # EMBEDDING_DIM=3072
 # EMBEDDING_BINDING_HOST=https://api.openai.com/v1
-
-### ALTERNATIVE: Local Ollama embedding (no API key required, requires Ollama service)
-# EMBEDDING_BINDING=ollama
-# EMBEDDING_MODEL=bge-m3:latest
-# EMBEDDING_DIM=1024
-# EMBEDDING_BINDING_HOST=http://localhost:11434
 # EMBEDDING_BINDING_API_KEY=your_api_key
-# If the embedding service is deployed within the same Docker stack, use host.docker.internal instead of localhost
 
-### ALTERNATIVE: Azure OpenAI embedding
+### Optional for Azure
-# EMBEDDING_BINDING=azure_openai
+# AZURE_EMBEDDING_DEPLOYMENT=text-embedding-3-large
-# AZURE_EMBEDDING_DEPLOYMENT=text-embedding-3-small
 # AZURE_EMBEDDING_API_VERSION=2023-05-15
 # AZURE_EMBEDDING_ENDPOINT=your_endpoint
 # AZURE_EMBEDDING_API_KEY=your_api_key
 
-### ALTERNATIVE: Jina AI Embedding
+### Jina AI Embedding
 # EMBEDDING_BINDING=jina
 # EMBEDDING_BINDING_HOST=https://api.jina.ai/v1/embeddings
 # EMBEDDING_MODEL=jina-embeddings-v4
 # EMBEDDING_DIM=2048
 # EMBEDDING_BINDING_API_KEY=your_api_key
 
-### Ollama embedding options (only used when EMBEDDING_BINDING=ollama)
+### Optional for Ollama embedding
 OLLAMA_EMBEDDING_NUM_CTX=8192
 ### use the following command to see all support options for Ollama embedding
 ### lightrag-server --embedding-binding ollama --help
 
 ####################################################################
-### WORKSPACE setting workspace name for all storage types
+### WORKSPACE sets workspace name for all storage types
-### in the purpose of isolating data from LightRAG instances.
+### for the purpose of isolating data from LightRAG instances.
 ### Valid workspace name constraints: a-z, A-Z, 0-9, and _
 ####################################################################
 # WORKSPACE=space1

lightrag/constants.py

@@ -57,8 +57,24 @@ DEFAULT_HISTORY_TURNS = 0
 DEFAULT_MIN_RERANK_SCORE = 0.0
 DEFAULT_RERANK_BINDING = "null"
 
-# File path configuration for vector and graph database(Should not be changed, used in Milvus Schema)
+# Default source ids limit in meta data for entity and relation
+DEFAULT_MAX_SOURCE_IDS_PER_ENTITY = 3
+DEFAULT_MAX_SOURCE_IDS_PER_RELATION = 3
+SOURCE_IDS_LIMIT_METHOD_KEEP = "KEEP"  # Keep oldest
+SOURCE_IDS_LIMIT_METHOD_FIFO = "FIFO"  # First In First Out (Keep newest)
+DEFAULT_SOURCE_IDS_LIMIT_METHOD = SOURCE_IDS_LIMIT_METHOD_KEEP
+VALID_SOURCE_IDS_LIMIT_METHODS = {
+    SOURCE_IDS_LIMIT_METHOD_KEEP,
+    SOURCE_IDS_LIMIT_METHOD_FIFO,
+}
+# Default file_path limit in meta data for entity and relation (Use same limit method as source_ids)
+DEFAULT_MAX_FILE_PATHS = 2
+
+# Field length of file_path in Milvus Schema for entity and relation (Should not be changed)
+# file_path must store all file paths up to the DEFAULT_MAX_FILE_PATHS limit within the metadata.
 DEFAULT_MAX_FILE_PATH_LENGTH = 32768
+# Placeholder for more file paths in meta data for entity and relation (Should not be changed)
+DEFAULT_FILE_PATH_MORE_PLACEHOLDER = "truncated"
 
 # Default temperature for LLM
 DEFAULT_TEMPERATURE = 1.0