Standardize env.example with setup tool conventions and double-hash syntax

- Add setup tool documentation header
- Convert examples to # # double-hash format
- Enable OpenAI embedding by default
- Update Ollama embedding model reference

Author: danielaskdd

env.example

@@ -1,3 +1,8 @@
+### All configurable environment variable must show up in this sample file in active or comment out status
+### Setup tool `make setup*` uses this file to generate finnal .env file
+### Lines starting with `# #` represent repeated environment variables;
+### These are placeholders and setup tool should not be substituted with actual values in this lines.
+
 ###########################
 ### Server Configuration
 ###########################
@@ -122,22 +127,22 @@ RERANK_BINDING=null
 # RERANK_BY_DEFAULT=True
 
 ### Cohere AI
-# RERANK_MODEL=rerank-v3.5
-# RERANK_BINDING_HOST=https://api.cohere.com/v2/rerank
-# RERANK_BINDING_API_KEY=your_rerank_api_key_here
+# # RERANK_MODEL=rerank-v3.5
+# # RERANK_BINDING_HOST=https://api.cohere.com/v2/rerank
+# # RERANK_BINDING_API_KEY=your_rerank_api_key_here
 ### Cohere rerank chunking configuration (useful for models with token limits like ColBERT)
 # RERANK_ENABLE_CHUNKING=true
 # RERANK_MAX_TOKENS_PER_DOC=480
 
 ### Aliyun Dashscope
-# RERANK_MODEL=gte-rerank-v2
-# RERANK_BINDING_HOST=https://dashscope.aliyuncs.com/api/v1/services/rerank/text-rerank/text-rerank
-# RERANK_BINDING_API_KEY=your_rerank_api_key_here
+# # RERANK_MODEL=gte-rerank-v2
+# # RERANK_BINDING_HOST=https://dashscope.aliyuncs.com/api/v1/services/rerank/text-rerank/text-rerank
+# # RERANK_BINDING_API_KEY=your_rerank_api_key_here
 
 ### Jina AI
-# RERANK_MODEL=jina-reranker-v2-base-multilingual
-# RERANK_BINDING_HOST=https://api.jina.ai/v1/rerank
-# RERANK_BINDING_API_KEY=your_rerank_api_key_here
+# # RERANK_MODEL=jina-reranker-v2-base-multilingual
+# # RERANK_BINDING_HOST=https://api.jina.ai/v1/rerank
+# # RERANK_BINDING_API_KEY=your_rerank_api_key_here
 
 ### For local deployment Embedding and Reranker with vLLM (OpenAI-compatible API)
 ### Wizard metadata used to preserve the chosen rerank provider across setup reruns
@@ -165,7 +170,6 @@ RERANK_BINDING=null
 # NVIDIA_VISIBLE_DEVICES=0
 ### Optional Docker runtime equivalent; generated GPU compose honors either variable.
 # VLLM_RERANK_EXTRA_ARGS=
-# Docker note: generated compose files rewrite localhost to host.docker.internal for the container only.
 
 ########################################
 ### Document processing configuration
@@ -267,46 +271,50 @@ LLM_MODEL=gpt-5-mini
 ### Azure OpenAI example
 ### Use deployment name as model name or set AZURE_OPENAI_DEPLOYMENT instead
 # AZURE_OPENAI_API_VERSION=2024-08-01-preview
-# LLM_BINDING=azure_openai
-# LLM_BINDING_HOST=https://xxxx.openai.azure.com/
-# LLM_BINDING_API_KEY=your_api_key
-# LLM_MODEL=my-gpt-mini-deployment
+# # LLM_BINDING=azure_openai
+# # LLM_BINDING_HOST=https://xxxx.openai.azure.com/
+# # LLM_BINDING_API_KEY=your_api_key
+# # LLM_MODEL=my-gpt-mini-deployment
 
 ### Openrouter example
-# LLM_BINDING=openai
-# LLM_BINDING_HOST=https://openrouter.ai/api/v1
-# LLM_BINDING_API_KEY=your_api_key
-# LLM_MODEL=google/gemini-2.5-flash
+# # LLM_BINDING=openai
+# # LLM_BINDING_HOST=https://openrouter.ai/api/v1
+# # LLM_BINDING_API_KEY=your_api_key
+# # LLM_MODEL=google/gemini-2.5-flash
 
 ### Google Gemini example (AI Studio)
-# LLM_BINDING=gemini
-# LLM_BINDING_API_KEY=your_gemini_api_key
-# LLM_BINDING_HOST=https://generativelanguage.googleapis.com
-# LLM_MODEL=gemini-flash-latest
+# # LLM_BINDING=gemini
+# # LLM_BINDING_API_KEY=your_gemini_api_key
+# # LLM_BINDING_HOST=https://generativelanguage.googleapis.com
+# # LLM_MODEL=gemini-flash-latest
 
 ### use the following command to see all support options for OpenAI, azure_openai or OpenRouter
 ### lightrag-server --llm-binding gemini --help
 ### Gemini Specific Parameters
 # GEMINI_LLM_MAX_OUTPUT_TOKENS=9000
 # GEMINI_LLM_TEMPERATURE=0.7
-### Enable Thinking
+### Enable or disable thinking
 # GEMINI_LLM_THINKING_CONFIG='{"thinking_budget": -1, "include_thoughts": true}'
-### Disable Thinking
-# GEMINI_LLM_THINKING_CONFIG='{"thinking_budget": 0, "include_thoughts": false}'
+# # GEMINI_LLM_THINKING_CONFIG='{"thinking_budget": 0, "include_thoughts": false}'
 
 ### Google Vertex AI example
 ### Vertex AI use GOOGLE_APPLICATION_CREDENTIALS instead of API-KEY for authentication
 ### LLM_BINDING_HOST=DEFAULT_GEMINI_ENDPOINT means select endpoit based on project and location automatically
-# LLM_BINDING=gemini
-# LLM_BINDING_HOST=https://aiplatform.googleapis.com
+# # LLM_BINDING=gemini
+# # LM_BINDING_HOST=https://aiplatform.googleapis.com
 ### or use DEFAULT_GEMINI_ENDPOINT to select endpoint based on project and location automatically
-# LLM_BINDING_HOST=DEFAULT_GEMINI_ENDPOINT
-# LLM_MODEL=gemini-2.5-flash
+# # LLM_BINDING_HOST=DEFAULT_GEMINI_ENDPOINT
+# # LLM_MODEL=gemini-2.5-flash
 # GOOGLE_GENAI_USE_VERTEXAI=true
 # GOOGLE_CLOUD_PROJECT='your-project-id'
 # GOOGLE_CLOUD_LOCATION='us-central1'
 # GOOGLE_APPLICATION_CREDENTIALS='/Users/xxxxx/your-service-account-credentials-file.json'
 
+### Ollama example
+# # LLM_BINDING=ollama
+# # LLM_BINDING_HOST=http://localhost:11434
+# # LLM_MODEL=qwen3.5:9b
+
 ### use the following command to see all support options for Ollama LLM
 ### lightrag-server --llm-binding ollama --help
 ### Ollama Server Specific Parameters
@@ -321,8 +329,8 @@ OLLAMA_LLM_NUM_CTX=32768
 ### Bedrock Specific Parameters
 ### Bedrock uses AWS credentials from the environment / AWS credential chain.
 ### It does not use LLM_BINDING_API_KEY.
-# LLM_BINDING=aws_bedrock
-# LLM_MODEL=anthropic.claude-3-5-sonnet-20241022-v2:0
+# # LLM_BINDING=aws_bedrock
+# # LLM_MODEL=anthropic.claude-3-5-sonnet-20241022-v2:0
 # AWS_ACCESS_KEY_ID=your_aws_access_key_id
 # AWS_SECRET_ACCESS_KEY=your_aws_secret_access_key
 # AWS_SESSION_TOKEN=your_optional_aws_session_token
@@ -344,40 +352,39 @@ OLLAMA_LLM_NUM_CTX=32768
 # EMBEDDING_TIMEOUT=30
 
 ### OpenAI compatible embedding
-### For local vLLM: set EMBEDDING_BINDING_API_KEY=EMPTY (any non-empty placeholder)
-# EMBEDDING_BINDING=openai
-# EMBEDDING_BINDING_HOST=https://api.openai.com/v1
-# EMBEDDING_BINDING_API_KEY=your_api_key
-# EMBEDDING_MODEL=text-embedding-3-large
-# EMBEDDING_DIM=3072
-# EMBEDDING_TOKEN_LIMIT=8192
-# EMBEDDING_SEND_DIM=false
+EMBEDDING_BINDING=openai
+EMBEDDING_BINDING_HOST=https://api.openai.com/v1
+EMBEDDING_BINDING_API_KEY=your_api_key
+EMBEDDING_MODEL=text-embedding-3-large
+EMBEDDING_DIM=3072
+EMBEDDING_TOKEN_LIMIT=8192
+EMBEDDING_SEND_DIM=false
 
 ### Optional for Azure Embedding
 ### Use deployment name as model name or set AZURE_EMBEDDING_DEPLOYMENT instead
+# # EMBEDDING_BINDING=azure_openai
+# # EMBEDDING_BINDING_HOST=https://xxxx.openai.azure.com/
+# # EMBEDDING_API_KEY=your_api_key
+# # EMBEDDING_MODEL==my-text-embedding-3-large-deployment
+# # EMBEDDING_DIM=3072
 # AZURE_EMBEDDING_API_VERSION=2024-08-01-preview
-# EMBEDDING_BINDING=azure_openai
-# EMBEDDING_BINDING_HOST=https://xxxx.openai.azure.com/
-# EMBEDDING_API_KEY=your_api_key
-# EMBEDDING_MODEL==my-text-embedding-3-large-deployment
-# EMBEDDING_DIM=3072
 
 ### Gemini embedding
-# EMBEDDING_BINDING=gemini
-# EMBEDDING_MODEL=gemini-embedding-001
-# EMBEDDING_DIM=1536
-# EMBEDDING_TOKEN_LIMIT=2048
-# EMBEDDING_BINDING_HOST=https://generativelanguage.googleapis.com
-# EMBEDDING_BINDING_API_KEY=your_api_key
+# # EMBEDDING_BINDING=gemini
+# # EMBEDDING_MODEL=gemini-embedding-001
+# # EMBEDDING_DIM=1536
+# # EMBEDDING_TOKEN_LIMIT=2048
+# # EMBEDDING_BINDING_HOST=https://generativelanguage.googleapis.com
+# # EMBEDDING_BINDING_API_KEY=your_api_key
 ### Gemini embedding requires sending dimension to server
-# EMBEDDING_SEND_DIM=true
+# # EMBEDDING_SEND_DIM=true
 
 ### Ollama embedding
-# EMBEDDING_BINDING=ollama
-# EMBEDDING_BINDING_HOST=http://localhost:11434
-# EMBEDDING_BINDING_API_KEY=your_api_key
-# EMBEDDING_MODEL=bge-m3:latest
-# EMBEDDING_DIM=1024
+# # EMBEDDING_BINDING=ollama
+# # EMBEDDING_BINDING_HOST=http://localhost:11434
+# # EMBEDDING_BINDING_API_KEY=your_api_key
+# # EMBEDDING_MODEL=qwen3-embedding:4b
+# # EMBEDDING_DIM=2560
 ### Optional for Ollama embedding
 OLLAMA_EMBEDDING_NUM_CTX=8192
 ### use the following command to see all support options for Ollama embedding
@@ -386,20 +393,20 @@ OLLAMA_EMBEDDING_NUM_CTX=8192
 ### Bedrock embedding
 ### Bedrock uses AWS credentials from the environment / AWS credential chain.
 ### It does not use EMBEDDING_BINDING_API_KEY.
-# EMBEDDING_BINDING=aws_bedrock
-# EMBEDDING_MODEL=amazon.titan-embed-text-v2:0
-# EMBEDDING_DIM=1024
+# # EMBEDDING_BINDING=aws_bedrock
+# # EMBEDDING_MODEL=amazon.titan-embed-text-v2:0
+# # EMBEDDING_DIM=1024
 # AWS_ACCESS_KEY_ID=your_aws_access_key_id
 # AWS_SECRET_ACCESS_KEY=your_aws_secret_access_key
 # AWS_SESSION_TOKEN=your_optional_aws_session_token
 # AWS_REGION=us-east-1
 
 ### 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
+# # 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
 
 ####################################################################
 ### WORKSPACE sets workspace name for all storage types
@@ -418,29 +425,29 @@ OLLAMA_EMBEDDING_NUM_CTX=8192
 # LIGHTRAG_VECTOR_STORAGE=NanoVectorDBStorage
 
 ### Redis Storage (Recommended for production deployment)
-# LIGHTRAG_KV_STORAGE=RedisKVStorage
-# LIGHTRAG_DOC_STATUS_STORAGE=RedisDocStatusStorage
+# # LIGHTRAG_KV_STORAGE=RedisKVStorage
+# # LIGHTRAG_DOC_STATUS_STORAGE=RedisDocStatusStorage
 
 ### Vector Storage (Recommended for production deployment)
-# LIGHTRAG_VECTOR_STORAGE=MilvusVectorDBStorage
-# LIGHTRAG_VECTOR_STORAGE=QdrantVectorDBStorage
-# LIGHTRAG_VECTOR_STORAGE=FaissVectorDBStorage
+# # LIGHTRAG_VECTOR_STORAGE=MilvusVectorDBStorage
+# # LIGHTRAG_VECTOR_STORAGE=QdrantVectorDBStorage
+# # LIGHTRAG_VECTOR_STORAGE=FaissVectorDBStorage
 
 ### Graph Storage (Recommended for production deployment)
-# LIGHTRAG_GRAPH_STORAGE=Neo4JStorage
-# LIGHTRAG_GRAPH_STORAGE=MemgraphStorage
+# # LIGHTRAG_GRAPH_STORAGE=Neo4JStorage
+# # LIGHTRAG_GRAPH_STORAGE=MemgraphStorage
 
 ### PostgreSQL
-# LIGHTRAG_KV_STORAGE=PGKVStorage
-# LIGHTRAG_DOC_STATUS_STORAGE=PGDocStatusStorage
-# LIGHTRAG_GRAPH_STORAGE=PGGraphStorage
-# LIGHTRAG_VECTOR_STORAGE=PGVectorStorage
+# # LIGHTRAG_KV_STORAGE=PGKVStorage
+# # LIGHTRAG_DOC_STATUS_STORAGE=PGDocStatusStorage
+# # LIGHTRAG_GRAPH_STORAGE=PGGraphStorage
+# # LIGHTRAG_VECTOR_STORAGE=PGVectorStorage
 
 ### MongoDB (Vector storage only available on Atlas Cloud)
-# LIGHTRAG_KV_STORAGE=MongoKVStorage
-# LIGHTRAG_DOC_STATUS_STORAGE=MongoDocStatusStorage
-# LIGHTRAG_GRAPH_STORAGE=MongoGraphStorage
-# LIGHTRAG_VECTOR_STORAGE=MongoVectorDBStorage
+# # LIGHTRAG_KV_STORAGE=MongoKVStorage
+# # LIGHTRAG_DOC_STATUS_STORAGE=MongoDocStatusStorage
+# # LIGHTRAG_GRAPH_STORAGE=MongoGraphStorage
+# # LIGHTRAG_VECTOR_STORAGE=MongoVectorDBStorage
 
 ### PostgreSQL Configuration
 POSTGRES_HOST=localhost