Refactor LightRAG Server documentation for clarity and structure.

env.example

@@ -30,11 +30,6 @@
 # LOG_MAX_BYTES=10485760          # Log file max size in bytes, defaults to 10MB
 # LOG_BACKUP_COUNT=5              # Number of backup files to keep, defaults to 5
 
-### Max async calls for LLM
-# MAX_ASYNC=4
-### Optional Timeout for LLM
-# TIMEOUT=150  # Time out in seconds, None for infinite timeout
-
 ### Settings for RAG query
 # HISTORY_TURNS=3
 # COSINE_THRESHOLD=0.2
@@ -44,16 +39,21 @@
 # MAX_TOKEN_ENTITY_DESC=4000
 
 ### Settings for document indexing
+# SUMMARY_LANGUAGE=English
 # CHUNK_SIZE=1200
 # CHUNK_OVERLAP_SIZE=100
-# MAX_TOKENS=32768             # Max tokens send to LLM for summarization
-# MAX_TOKEN_SUMMARY=500        # Max tokens for entity or relations summary
-# SUMMARY_LANGUAGE=English
+# MAX_TOKEN_SUMMARY=500                # Max tokens for entity or relations summary
+# MAX_PARALLEL_INSERT=2                # Number of parallel processing documents in one patch
+# MAX_ASYNC=4                          # Max concurrency requests of LLM
+# ENABLE_LLM_CACHE_FOR_EXTRACT=true    # Enable LLM cache for entity extraction
+
+# EMBEDDING_BATCH_NUM=32               # num of chunks send to Embedding in one request
+# EMBEDDING_FUNC_MAX_ASYNC=16          # Max concurrency requests for Embedding
 # MAX_EMBED_TOKENS=8192
-# ENABLE_LLM_CACHE_FOR_EXTRACT=true  # Enable LLM cache for entity extraction
-# MAX_PARALLEL_INSERT=2        # Maximum number of parallel processing documents in pipeline
 
 ### LLM Configuration (Use valid host. For local services installed with docker, you can use host.docker.internal)
+# MAX_TOKENS=32768             # Max tokens send to LLM (less than context size of the model)
+# TIMEOUT=150                  # Time out in seconds for LLM, None for infinite timeout
 LLM_BINDING=ollama
 LLM_MODEL=mistral-nemo:latest
 LLM_BINDING_API_KEY=your_api_key
@@ -73,8 +73,6 @@ LLM_BINDING_HOST=http://localhost:11434
 ### Embedding Configuration (Use valid host. For local services installed with docker, you can use host.docker.internal)
 EMBEDDING_MODEL=bge-m3:latest
 EMBEDDING_DIM=1024
-EMBEDDING_BATCH_NUM=32
-EMBEDDING_FUNC_MAX_ASYNC=16
 # EMBEDDING_BINDING_API_KEY=your_api_key
 ### ollama example
 EMBEDDING_BINDING=ollama