lightrag-cn-git/env.example

### All configurable environment variable must show up in this sample file in active or comment out status
### Setup tool `make env-*` uses this file to generate final .env file

### Target environment of this env file: host/compose (compose is for Dokcer or Kubernetes)
# LIGHTRAG_RUNTIME_TARGET=host

###########################
### Server Configuration
###########################
HOST=0.0.0.0
PORT=9621
WEBUI_TITLE='My Graph KB'
WEBUI_DESCRIPTION='Simple and Fast Graph Based RAG System'
# WORKERS=2
### gunicorn worker timeout(as default LLM request timeout if LLM_TIMEOUT is not set)
# TIMEOUT=150
# CORS_ORIGINS=http://localhost:3000,http://localhost:8080

### Path Prefix Configuration (Optional)
### Used to host multiple LightRAG instances on one host behind a reverse
### proxy that routes by site prefix. Leave unset (or empty) for a
### single-instance deployment.
###
### - LIGHTRAG_API_PREFIX  : reverse-proxy prefix the upstream proxy strips
###                          before forwarding (passed to FastAPI as root_path).
###
### See docs/MultiSiteDeployment.md for end-to-end examples.
# LIGHTRAG_API_PREFIX=/site01

### Optional SSL Configuration
### Docker note: generated compose files mount staged certs at /app/data/certs/ inside the container
# SSL=true
# SSL_CERTFILE=/path/to/cert.pem
# SSL_KEYFILE=/path/to/key.pem

### Directory Configuration (defaults to current working directory)
### Default value is: ./inputs ./rag_storage
# INPUT_DIR=<absolute_path_for_doc_input_dir>
# WORKING_DIR=<absolute_path_for_working_dir>

### Tiktoken cache directory (Store cached files in this folder for offline deployment)
# TIKTOKEN_CACHE_DIR=/app/data/tiktoken

### Ollama Emulating Model and Tag
# OLLAMA_EMULATING_MODEL_NAME=lightrag
OLLAMA_EMULATING_MODEL_TAG=latest

### Max nodes for graph retrieval (Ensure WebUI local settings are also updated, which is limited to this value)
# MAX_GRAPH_NODES=1000

### Logging level
# LOG_LEVEL=INFO
# VERBOSE=False
# LOG_MAX_BYTES=10485760
# LOG_BACKUP_COUNT=5
### Logfile location (defaults to current working directory)
# LOG_DIR=/path/to/log/directory
# LIGHTRAG_PERFORMANCE_TIMING_LOGS=false

#####################################
### Login and API-Key Configuration
#####################################
# AUTH_ACCOUNTS='admin:admin123,user1:{bcrypt}$2b$12$S8Yu.gCbuAbNTJFB.231gegTwr5pgrFxc8H9kXQ4/sduFBHkhM8Ka'
# TOKEN_SECRET=lightrag-jwt-default-secret-key!
# JWT_ALGORITHM=HS256
# TOKEN_EXPIRE_HOURS=48
# GUEST_TOKEN_EXPIRE_HOURS=24

### Token Auto-Renewal Configuration (Sliding Window Expiration)
### Enable automatic token renewal to prevent active users from being logged out
### When enabled, tokens will be automatically renewed when remaining time < threshold
# TOKEN_AUTO_RENEW=true
### Token renewal threshold (0.0 - 1.0)
### Renew token when remaining time < (total time * threshold)
### Default: 0.5 (renew when 50% time remaining)
### Examples:
###   0.5 = renew when 24h token has 12h left
###   0.25 = renew when 24h token has 6h left
# TOKEN_RENEW_THRESHOLD=0.5
### Note: Token renewal is automatically skipped for certain endpoints:
###   - /health: Health check endpoint (no authentication required)
###   - /documents/paginated: Frequently polled by client (5-30s interval)
###   - /documents/pipeline_status: Very frequently polled by client (2s interval)
###   - Rate limit: Minimum 60 seconds between renewals for same user

### 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/*

######################################################################################
### Query Configuration
###
### 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_Relation_Tokens
######################################################################################
# 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
### Maximum number or chunks for naive vector search
# CHUNK_TOP_K=20
### 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, relations and chunks)
# MAX_TOTAL_TOKENS=30000

### 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
###     If reranking is enabled, the impact of chunk selection strategies will be diminished.
# KG_CHUNK_PICK_METHOD=VECTOR

### 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

#########################################################
### Reranking configuration
### RERANK_BINDING type: null, cohere, jina, aliyun
### For rerank model deployed by vLLM use cohere binding
### If LightRAG deployed in Docker:
###    uses host.docker.internal instead of localhost in RERANK_BINDING_HOST
#########################################################
RERANK_BINDING=null
# RERANK_MODEL=BAAI/bge-reranker-v2-m3
# RERANK_BINDING_HOST=http://localhost:8000/rerank
# RERANK_BINDING_API_KEY=your_rerank_api_key_here

### 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
### Enable rerank by default in query params when RERANK_BINDING is not null
# RERANK_BY_DEFAULT=True

### Rerank concurrency and timeout (independent from base LLM settings)
### MAX_ASYNC_RERANK falls back to MAX_ASYNC when unset.
### RERANK_TIMEOUT has its own default (30s) since reranker calls are
### typically much shorter than full LLM generation.
# MAX_ASYNC_RERANK=4
# RERANK_TIMEOUT=30

### 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
### 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

### 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

### For local deployment Embedding and Reranker with vLLM (OpenAI-compatible API)
### Wizard metadata used to preserve the chosen deployment provider across setup reruns
# LIGHTRAG_SETUP_EMBEDDING_PROVIDER=vllm
# LIGHTRAG_SETUP_RERANK_PROVIDER=vllm
# VLLM_EMBED_MODEL=BAAI/bge-m3
# VLLM_EMBED_PORT=8001
# VLLM_EMBED_DEVICE=cpu
### VLLM_EMBED_API_KEY is passed as --api-key to vLLM; synced to EMBEDDING_BINDING_API_KEY; auto-generated if blank
# VLLM_EMBED_API_KEY=
# VLLM_EMBED_EXTRA_ARGS=
# VLLM_RERANK_MODEL=BAAI/bge-reranker-v2-m3
# VLLM_RERANK_PORT=8000
# VLLM_RERANK_DEVICE=cuda
### VLLM_RERANK_API_KEY is passed as --api-key to vLLM; synced to RERANK_BINDING_API_KEY; auto-generated if blank
# VLLM_RERANK_API_KEY=
### Use float16 for GPU mode. CPU mode uses the official vLLM CPU image.
# VLLM_USE_CPU=1
### Set to 1 for CPU mode, unset for GPU mode
# CUDA_VISIBLE_DEVICES=-1
### Set to -1 to disable CUDA (CPU mode), or specific GPU IDs for GPU mode
# NVIDIA_VISIBLE_DEVICES=0
### Optional Docker runtime equivalent; generated GPU compose honors either variable.
# VLLM_RERANK_EXTRA_ARGS=

########################################
### Document processing configuration
########################################
### Document processing output language: English, Chinese, French, German ...
SUMMARY_LANGUAGE=English

### Enable JSON-structured output for entity extraction
### Default behavior: JSON output is disabled when ENTITY_EXTRACTION_USE_JSON is unset
### JSON output incurs higher latency but delivers improved reliability
ENTITY_EXTRACTION_USE_JSON=true

### Optional external YAML profile for entity type guidance and extraction examples
### Profiles are loaded from PROMPT_DIR/entity_type (PROMPT_DIR defaults to ./prompts).
### A reference template is shipped at prompts/samples/entity_type_prompt.sample.yml;
# ENTITY_TYPE_PROMPT_FILE=entity_type_prompt.yml
# PROMPT_DIR=<absolute_path_for_prompt_dir>

### Multimodal parsing/analyze integration
### Optional parser routing rules. Example for VLM & MinerU enabled configuration:
###     LIGHTRAG_PARSER=*:native-iteP,*:mineru-iteP,*:legacy-R
### Rules may be separated with commas or semicolons. Rules match file suffixes
### (pdf), not full names (*.pdf), and are checked left-to-right.
### If mineru/docling appears in LIGHTRAG_PARSER, the corresponding endpoint
### below must be configured before server startup.
### See docs/FileProcessingPipeline.md for detail
LIGHTRAG_PARSER=*:native-teP,*:legacy-R

### Async parser service protocol (optional)
### Configure these when using remote MinerU/Docling async services

### ---- MinerU shared parameters (both local and official modes) ----
### MinerU API protocol. Choose one active mode.
### - official: MinerU precision API v4. Requires MINERU_API_TOKEN.
### - local: self-hosted mineru-api / mineru-router base URL.
MINERU_API_MODE=local
# MINERU_POLL_INTERVAL_SECONDS=2
# MINERU_MAX_POLLS=180
# MINERU_LANGUAGE=ch
# MINERU_ENABLE_TABLE=true
# MINERU_ENABLE_FORMULA=true
# MINERU_PAGE_RANGES=
### MINERU_PAGE_RANGES semantics differ by mode:
### - official: forwarded verbatim, supports e.g. "1-3,5,7-9".
### - local:    only a single page ("3") or simple range ("1-10"); comma
###             lists are rejected at startup.
### When switching modes, double-check this constraint.

### ---- MinerU local-only (MINERU_API_MODE=local) ----
MINERU_LOCAL_ENDPOINT=http://127.0.0.1:8000
### MINERU_LOCAL_BACKEND: which mineru-api backend handles the parse.
###   Accepted values (per mineru-api POST /tasks form parameter `backend`):
###     hybrid-auto-engine - pipeline + VLM combo with auto-selected local
###                          engine (mineru-api's default). GPU required.
###     pipeline           - CPU-friendly traditional pipeline; no VLM step.
###     vlm-auto-engine    - VLM with auto-selected local inference engine
###                          (sglang-engine / vllm-engine if GPU is available);
###                          requires the matching engine extra preinstalled
###                          on the mineru-api side, plus model weights.
###   We ship `hybrid-auto-engine` -- requires the target mineru-api
###   deployment to have a GPU plus the matching inference engine
###   (sglang / vllm) and model weights installed. Switch to `pipeline`
###   for CPU-only deployments without those dependencies.
MINERU_LOCAL_BACKEND=hybrid-auto-engine
### MINERU_LOCAL_PARSE_METHOD: parsing strategy for the pipeline component.
###   Accepted values:
###     auto - auto-detect embedded text-layer vs OCR per page (default).
###     txt  - extract text from the embedded text layer only; fastest,
###            but yields empty output on scanned PDFs without a text layer.
###     ocr  - force OCR on every page regardless of text-layer quality;
###            slowest, reliable on scanned or low-quality PDFs.
###   Only consumed when MINERU_LOCAL_BACKEND is `pipeline` or
###   `hybrid-auto-engine` (the pipeline arm of the hybrid pipeline).
###   Pure VLM backends (`vlm-auto-engine`, `vlm-http-client`) ignore this
###   parameter -- the VLM model handles layout/OCR natively.
MINERU_LOCAL_PARSE_METHOD=auto
### MINERU_LOCAL_IMAGE_ANALYSIS: enable VLM image/chart analysis pass for
###   better caption an footnote recognition.
###   Only consumed by `vlm-auto-engine`, `vlm-http-client`,
###   `hybrid-auto-engine`, `hybrid-http-client`. The `pipeline` backend
###   silently drops this flag -- its `_process_pipeline` does not accept
###   the kwarg, so setting `false` under pipeline does NOT speed parsing
###   up; pipeline never invokes the VLM image pass to begin with.
###   Disable (`false`) on VLM / hybrid backends to skip the extra VLM
###   round, trading image / chart semantic descriptions for faster parsing
###   and lower GPU cost.
MINERU_LOCAL_IMAGE_ANALYSIS=true
# MINERU_LOCAL_START_PAGE_ID=0
# MINERU_LOCAL_END_PAGE_ID=99999

### ---- MinerU official-only (MINERU_API_MODE=official) ----
# MINERU_API_TOKEN=your-api-key
# MINERU_OFFICIAL_ENDPOINT=https://mineru.net
# MINERU_MODEL_VERSION=vlm
# MINERU_IS_OCR=false

### Force re-upload of file to MinerU on every retry after failure
### Disables caching of result outcomes
# LIGHTRAG_FORCE_REPARSE_MINERU=false

### Docling parser (docling-serve v1 / async API).
###
### Endpoint: base URL only — the client appends /v1/convert/file/async,
###     /v1/status/poll/{task_id}?wait=<DOCLING_POLL_INTERVAL_SECONDS>,
###     /v1/result/{task_id} itself.
### Pipeline shape (pipeline=standard, target_type=zip,
###     to_formats=[json,md], image_export_mode=referenced) is fixed in
###     code so the sidecar flow stays self-consistent — flipping any of
###     these would break the adapter and is therefore not exposed as env.
###
### OCR tunables:
### - DOCLING_DO_OCR: master switch; when false the engine relies only on
###     text-layer extraction.
### - DOCLING_FORCE_OCR: when true, OCR every page regardless of text-layer
###     quality (slower, useful for scanned PDFs with bad text layers).
### - DOCLING_OCR_ENGINE: explicit engine selection (DEPRECATED in the
###     docling-serve OpenAPI but still honored for older deployments).
### - DOCLING_OCR_PRESET: recommended replacement for DOCLING_OCR_ENGINE.
### - DOCLING_OCR_LANG: JSON array (e.g. ["en","zh"]) or comma-separated
###     list. Empty (default) lets the OCR engine pick its default.
### - DOCLING_DO_FORMULA_ENRICHMENT: when true, the code-formula model runs
###     and `texts[*].label="formula"` items carry LaTeX in `text`. Default
###     false because the model may not be present on every deployment;
###     adapter falls back to plain-text formulas when disabled.
###
### Polling budget (server-side long-poll; client does NOT add extra sleep):
### - DOCLING_POLL_INTERVAL_SECONDS: ``?wait=N`` value sent to
###     /v1/status/poll/{task_id}. Larger N = fewer round trips per parse;
###     bound by your reverse-proxy idle timeout. Default 5.
### - DOCLING_MAX_POLLS: max polling rounds before raising TimeoutError.
###     Worst-case wall-clock budget ≈
###     DOCLING_POLL_INTERVAL_SECONDS × DOCLING_MAX_POLLS. Default 240
###     (≈ 20 minutes at wait=5s); raise for very large PDFs.
###
### Bundle cache controls:
### - DOCLING_ENGINE_VERSION: recorded in <base>.docling_raw/_manifest.json.
###     Mismatch with the recorded value forces a cache miss → re-download.
###     Leave empty to skip this check.
### - LIGHTRAG_FORCE_REPARSE_DOCLING: when truthy ("1"/"true"), bypass the
###     docling raw cache and re-upload on every parse_docling call.
### - DOCLING_BBOX_ATTRIBUTES: override the doc-level bbox_attributes
###     written into <base>.blocks.jsonl meta. Default
###     {"origin":"LEFTBOTTOM"} matches docling's default coordinate system.
DOCLING_ENDPOINT=http://localhost:5001
DOCLING_DO_OCR=true
DOCLING_FORCE_OCR=true
DOCLING_DO_FORMULA_ENRICHMENT=false
# DOCLING_OCR_ENGINE=auto
# DOCLING_OCR_PRESET=auto
# DOCLING_OCR_LANG=
# DOCLING_POLL_INTERVAL_SECONDS=5
# DOCLING_MAX_POLLS=240
# DOCLING_BBOX_ATTRIBUTES={"origin":"LEFTBOTTOM"}
### Force re-upload of file to Docling on every retry after failure
### Disables caching of result outcomes
# LIGHTRAG_FORCE_REPARSE_DOCLING=false

### File upload size limit (in bytes)
### Default: 104857600 (100MB)
### Set to 0 or None for unlimited upload size
### Examples:
###   52428800  = 50MB
###   104857600 = 100MB (default)
###   209715200 = 200MB
### Note: If using Nginx as reverse proxy, also configure client_max_body_size
# MAX_UPLOAD_SIZE=104857600

### Global chunk size, 500~1500 is recommended.
### Chunker inherits the global value here only when its own var is unset.
### Exception: P never inherits CHUNK_SIZE — it uses CHUNK_P_SIZE (default 2000).
# CHUNK_SIZE=1200
# CHUNK_OVERLAP_SIZE=100

### Fixed-token chunker (process_options=F, default) settings
###     CHUNK_F_SIZE: per-strategy chunk_token_size override; falls back to CHUNK_SIZE when unset
###     CHUNK_F_OVERLAP_SIZE: token overlap; falls back to CHUNK_OVERLAP_SIZE when unset
###     CHUNK_F_SPLIT_BY_CHARACTER: optional separator string; pre-segment before token windowing
###     CHUNK_F_SPLIT_BY_CHARACTER_ONLY: when true, raise on oversize segment instead of token re-split
# CHUNK_F_SIZE=1200
# CHUNK_F_OVERLAP_SIZE=100
# CHUNK_F_SPLIT_BY_CHARACTER=
# CHUNK_F_SPLIT_BY_CHARACTER_ONLY=false

### Recursive character chunker (process_options=R) settings
###     CHUNK_R_SIZE: per-strategy chunk_token_size override; falls back to CHUNK_SIZE when unset
###     CHUNK_R_OVERLAP_SIZE: token overlap between adjacent chunks; falls back to CHUNK_OVERLAP_SIZE when unset
###     CHUNK_R_SEPARATORS: JSON array of cascaded separators tried by RecursiveCharacterTextSplitter.
###       Default includes CJK sentence-ending punctuation so Chinese / mixed-language
###       documents split at semantic boundaries.  Order: paragraph (\n\n) > line (\n) >
###       Chinese sentence-end (。！？) > Chinese semi-clause (；，) > space > char.
###       English ".?!" are intentionally omitted (literal match would split "0.95" /
###       "e.g."); the English path falls through space / char as before.
# CHUNK_R_SIZE=1200
# CHUNK_R_OVERLAP_SIZE=100
# CHUNK_R_SEPARATORS=["\n\n","\n","。","！","？","；","，"," ",""]

### Semantic vector chunker (process_options=V) settings
###     CHUNK_V_SIZE: per-strategy chunk_token_size hard cap (oversized pieces are
###       re-split via R before being emitted); falls back to CHUNK_SIZE when unset
###     CHUNK_V_BREAKPOINT_THRESHOLD_TYPE: percentile | standard_deviation | interquartile | gradient
###     CHUNK_V_BREAKPOINT_THRESHOLD_AMOUNT: leave empty to use the LangChain per-type default (e.g. 95 for percentile)
###     CHUNK_V_BUFFER_SIZE: number of adjacent sentences combined when computing distances
###     CHUNK_V_SENTENCE_SPLIT_REGEX: regex fed to LangChain SemanticChunker for the
###       initial sentence split.  Default extends the upstream English-only pattern
###       with CJK sentence-end punctuation (。？！).  Override if you need a
###       different language mix.  Note: env value is the raw regex string, no JSON
###       quoting.
# CHUNK_V_SIZE=1200
# CHUNK_V_BREAKPOINT_THRESHOLD_TYPE=percentile
# CHUNK_V_BREAKPOINT_THRESHOLD_AMOUNT=
# CHUNK_V_BUFFER_SIZE=1
# CHUNK_V_SENTENCE_SPLIT_REGEX=(?<=[.?!])\s+|(?<=[。？！])

### Paragraph semantic chunker (process_options=P) settings
###     CHUNK_P_SIZE: per-strategy chunk_token_size override; defaults to 2000 when unset
###       (does NOT fall back to CHUNK_SIZE — paragraph-semantic merging needs more
###       headroom than the global default to keep related paragraphs together).
###     CHUNK_P_OVERLAP_SIZE: overlap for prose fallback and table-bridge context;
###                           falls back to CHUNK_OVERLAP_SIZE when unset
# CHUNK_P_SIZE=2000
# CHUNK_P_OVERLAP_SIZE=100

### 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
### Recommended LLM summary output length in tokens
# SUMMARY_LENGTH_RECOMMENDED=600
### Maximum context size sent to LLM for description summary
# SUMMARY_CONTEXT_SIZE=12000
### Maximum token size allowed for entity extraction input context
# MAX_EXTRACT_INPUT_TOKENS=20480

### Multimodal surrounding-context budget (per-half token cap for the
### `leading` / `trailing` text injected into VLM and extract prompts).
### Computed at analyze_multimodal entry; the two halves are independent
### so deployments can bias context forward or backward as needed.
# SURROUNDING_LEADING_MAX_TOKENS=2000
# SURROUNDING_TRAILING_MAX_TOKENS=2000

### Per-response cap on total entity+relationship rows/records emitted by the LLM
# MAX_EXTRACTION_RECORDS=100
### Per-response cap on entity rows/objects emitted by the LLM
# MAX_EXTRACTION_ENTITIES=40

### 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: FIFO, KEEP
###    FIFO: First in first out
###    KEEP: Keep oldest (less merge action and faster)
# SOURCE_IDS_LIMIT_METHOD=FIFO

### Maximum number of file paths stored in entity/relation file_path field
### For displayed only, does not affect query performance
# MAX_FILE_PATHS=100

### PDF decryption password for protected PDF files
# PDF_DECRYPT_PASSWORD=your_pdf_password_here

### LLM cache for entity/relation extract is enable by default
### Disabling it will prevent graph reconstruction after document deletion
# ENABLE_LLM_CACHE_FOR_EXTRACT=true

########################################
### Pipeline Concurrency Configuration
########################################
### Number of parallel processing documents(between 2~10, MAX_ASYNC/3 is recommended)
MAX_PARALLEL_INSERT=2
### Optional per-stage document pipeline concurrency
# MAX_PARALLEL_PARSE_NATIVE=5
# MAX_PARALLEL_PARSE_MINERU=1
# MAX_PARALLEL_PARSE_DOCLING=1
# MAX_PARALLEL_ANALYZE=5
### Optional queue sizes for staged pipeline workers
# QUEUE_SIZE_DEFAULT=100
# QUEUE_SIZE_INSERT=4
### Max concurrency requests for Embedding
# EMBEDDING_FUNC_MAX_ASYNC=8
### Num of chunks send to Embedding in single request (default is 10)
EMBEDDING_BATCH_NUM=32

###########################################################################
### Gloabal LLM Configuration
###   LLM_BINDING type: openai, ollama, lollms, azure_openai, bedrock, gemini
###   LLM_BINDING_HOST: Service endpoint (left empty if using the provider SDK default endpoint)
###   LLM_BINDING_API_KEY: api key
### If LightRAG deployed in Docker:
###    uses host.docker.internal instead of localhost in LLM_BINDING_HOST
###########################################################################
### LLM request timeout setting for all llm (0 means no timeout for Ollma)
# LLM_TIMEOUT=180

LLM_BINDING=openai
LLM_BINDING_HOST=https://api.openai.com/v1
LLM_BINDING_API_KEY=your_api_key
LLM_MODEL=gpt-5.4-mini

### Max concurrency requests of LLM
MAX_ASYNC=4

###########################################################################
### Role-specific LLM/VLM overrides
### Available roles: EXTRACT, KEYWORD, QUERY, VLM
### If unset, each role falls back to gloabal LLM configuration above.
### For detail information, refer to:
###   docs/RoleSpecificLLMConfiguration.md
###   docs/RoleSpecificLLMConfiguration-zh.md
###########################################################################
# KEYWORD_LLM_MODEL=gpt-5.4-nano
# KEYWORD_MAX_ASYNC_LLM
# KEYWORD_LLM_TIMEOUT=180
# KEYWORD_LLM_BINDING=openai
# KEYWORD_LLM_BINDING_HOST=https://api.openai.com/v1
# KEYWORD_LLM_BINDING_API_KEY=your_api_key

# QUERY_LLM_MODEL=gpt-5.4
# QUERY_MAX_ASYNC_LLM
# QUERY_LLM_TIMEOUT=180
# QUERY_LLM_BINDING=openai
# QUERY_LLM_BINDING_HOST=https://api.openai.com/v1
# QUERY_LLM_BINDING_API_KEY=your_api_key

# VLM_LLM_MODEL=gpt-5.4-mini
# VLM_MAX_ASYNC_LLM=4
# VLM_LLM_TIMEOUT=180
# VLM_LLM_BINDING=openai
# VLM_LLM_BINDING_HOST=https://api.example.com/v1
# VLM_LLM_BINDING_API_KEY=your_vlm_api_key

### Master switch for VLM multimodal analysis (i/t/e items).
### When false, multimodal item is skipped regardless of document process_options
### When true, VLM_LLM_BINDING (or the base LLM_BINDING) must be vision-capable
### lollms is rejected at startup
VLM_PROCESS_ENABLE=false
### Maximum image bytes sent to VLM (5242880=5MB)
VLM_MAX_IMAGE_BYTES=5242880

###########################################################################
### Provider sepecific LLM options
### Increasing the temperature setting may help mitigate infinite inference
###   loops during entity/elation extraction, particularly when using
###   models with more limited capabilities, such as Qwen3-30B
### Set a max output token limit to prevent endless output from certain LLMs,
###   which may trigger timeout errors during entity and relation extraction.
###        max_output_token < LLM_TIMEOUT * llm_tokens_per_second
###   i.e. max_output_token = 9000 = 180s * 50 tokens/s
### Sample commands to list all supported options specific LLM_BINDING:
###   lightrag-server --llm-binding openai  --help
###   lightrag-server --llm-binding bedrock --help
###   lightrag-server --llm-binding gemini  --help
###########################################################################
### OpenAI Specific Parameters (Openrouter of other OpenAI compatible API):
###     LLM_BINDING=openai
###     LLM_BINDING_HOST=https://openrouter.ai/api/v1
###     LLM_MODEL=google/gemini-2.5-flash
# OPENAI_LLM_TEMPERATURE=0.9
### For vLLM/SGLang and most of OpenAI compatible API provider
# OPENAI_LLM_MAX_TOKENS=9000
### For OpenAI o1-mini or newer modles utilizes max_completion_tokens instead of max_tokens
# OPENAI_LLM_MAX_COMPLETION_TOKENS=9000
### For OpenAI reason control
# OPENAI_LLM_REASONING_EFFORT=minimal
### For OpenRouter reasoning control
# OPENAI_LLM_EXTRA_BODY='{"reasoning": {"enabled": false}}'
### For Qwen3 reasoning control deploy by vLLM
# OPENAI_LLM_EXTRA_BODY='{"chat_template_kwargs": {"enable_thinking": false}}'

### Azure OpenAI Specific Parameters:
###     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
### You may use deployment name for LLM_MODEL or set AZURE_OPENAI_DEPLOYMENT instead
# AZURE_OPENAI_DEPLOYMEN=my—deplyment-name
# AZURE_OPENAI_API_VERSION=2024-08-01-preview

### Google AI Studio Gemini Specific Parameters:
### DEFAULT_GEMINI_ENDPOINT means selecting endpoit by SDK automatically
###     LLM_BINDING=gemini
###     LLM_BINDING_HOST=DEFAULT_GEMINI_ENDPOINT
###     LLM_BINDING_API_KEY=your_gemini_api_key
###     LLM_MODEL=gemini-flash-latest
# GEMINI_LLM_TEMPERATURE=0.7
# GEMINI_LLM_MAX_OUTPUT_TOKENS=9000
### Enable or disable thinking
###     GEMINI_LLM_THINKING_CONFIG='{"thinking_budget": -1, "include_thoughts": true}'
###     GEMINI_LLM_THINKING_CONFIG='{"thinking_budget": 0, "include_thoughts": false}'
# GEMINI_LLM_THINKING_CONFIG='{"thinking_budget": 0, "include_thoughts": false}'

### Google Vertex AI Gemini Specific Parameters:
### Vertex AI use GOOGLE_APPLICATION_CREDENTIALS instead of API-KEY for authentication
# 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'

### Bedrock Specific Parameters:
###     LLM_BINDING=bedrock
###     LLM_BINDING_HOST=DEFAULT_BEDROCK_ENDPOINT
###     LLM_MODEL=us.amazon.nova-lite-v1:0
### Region is required for all three modes (Bedrock endpoints are regional).
# AWS_REGION=us-west-1
### Bedrock Authentication (choose ONE of the following three approaches):
### Bedrock API key (bearer token). Bedrock ignores LLM_BINDING_API_KEY;
### set AWS_BEARER_TOKEN_BEDROCK directly before startup. This is a
### process-level AWS SDK setting and cannot be overridden per role.
# AWS_BEARER_TOKEN_BEDROCK=your_bedrock_api_key
### SigV4 credentials (classic IAM user / STS / instance profile).
# 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
### Ambient credentials (AWS SDK default credential chain).
### To use this mode, leave AWS_BEARER_TOKEN_BEDROCK, AWS_ACCESS_KEY_ID,
### AWS_SECRET_ACCESS_KEY, and AWS_SESSION_TOKEN above commented out — the
### AWS SDK will then resolve credentials from ~/.aws/credentials, IAM role,
### instance profile, SSO, or environment variables outside .env.
### Activating any of the lines above forces that explicit mode and bypasses
### the credential chain.
# BEDROCK_LLM_TEMPERATURE=1.0
# BEDROCK_LLM_MAX_TOKENS=9000
# BEDROCK_LLM_TOP_P=1.0
# BEDROCK_LLM_STOP_SEQUENCES='["</s>"]'
### Bedrock model reasoning control
# BEDROCK_LLM_EXTRA_FIELDS='{"reasoningConfig": {"type": "enabled", "maxReasoningEffort": "low"}}'

### Ollama Specific Parameters:
###     LLM_BINDING=ollama
###     LLM_BINDING_HOST=http://localhost:11434
###     LLM_MODEL=qwen3.5:9b
### OLLAMA_LLM_NUM_CTX must be provided, and should at least larger than MAX_TOTAL_TOKENS + 2000
OLLAMA_LLM_NUM_CTX=32768
# OLLAMA_LLM_NUM_PREDICT=9000
# OLLAMA_LLM_TEMPERATURE=0.85
# OLLAMA_LLM_STOP='["</s>", "<|EOT|>"]'

#######################################################################################
### Embedding Configuration (Should not be changed after the first file processed)
### EMBEDDING_BINDING: ollama, openai, azure_openai, jina, lollms, bedrock
### EMBEDDING_BINDING_HOST: Service endpoint (left empty if using default endpoint provided by openai or gemini SDK)
### EMBEDDING_BINDING_API_KEY: api key
### If LightRAG deployed in Docker:
###    uses host.docker.internal instead of localhost in EMBEDDING_BINDING_HOST
### Control whether to send embedding_dim parameter to embedding API
###    For OpenAI: Set EMBEDDING_SEND_DIM=true to enable dynamic dimension adjustment
###    For OpenAI: Set EMBEDDING_SEND_DIM=false (default) to disable sending dimension parameter
###    For Gemini: Allways set EMBEDDING_SEND_DIM=true
### Control whether to use base64 encoding format for embeddings (improves performance for OpenAI)
###    For OpenAI: Set EMBEDDING_USE_BASE64=true (default) to use base64 encoding
###    For Yandex Cloud and other providers that don't support it: Set EMBEDDING_USE_BASE64=false
#######################################################################################
# EMBEDDING_TIMEOUT=30

### OpenAI compatible embedding
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_USE_BASE64=true

### Optional: asymmetric embeddings (query/document behavior split)
### Leave EMBEDDING_ASYMMETRIC unset or set false to keep symmetric behavior.
### Set true only when the selected embedding backend supports asymmetric mode.
# EMBEDDING_ASYMMETRIC=true
### Provider-task bindings such as Jina/Gemini/VoyageAI use provider parameters
### and should not configure the prefix variables below.
### Prefix-based models such as BGE/E5/GTE require both prefix variables.
### Wrap non-empty values with quotes if there are trailing spaces.
# EMBEDDING_DOCUMENT_PREFIX="search_document: "
### Use NO_PREFIX for a side that should intentionally have no prefix.
###     EMBEDDING_DOCUMENT_PREFIX=NO_PREFIX
# EMBEDDING_QUERY_PREFIX="search_query: "

###########################################################################
### Provider sepecific Embedding options
### Increasing the temperature setting may help mitigate infinite inference
###   loops during entity/elation extraction, particularly when using
###   models with more limited capabilities, such as Qwen3-30B
### Set a max output token limit to prevent endless output from certain LLMs,
###   which may trigger timeout errors during entity and relation extraction.
###        max_output_token < LLM_TIMEOUT * llm_tokens_per_second
###   i.e. max_output_token = 9000 = 180s * 50 tokens/s
### Sample commands to list all supported options specific EMBEDDING_BINDING:
###   lightrag-server --embedding-binding openai --help
###   lightrag-server --embedding-binding ollama --help
###   lightrag-server --embedding-binding bedrock --help
###########################################################################
### Azure Embedding Specific Parameters:
### 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

### Ollama Embedding Specific Parameters:
###     EMBEDDING_BINDING=ollama
###     EMBEDDING_BINDING_HOST=http://localhost:11434
###     EMBEDDING_BINDING_API_KEY=your_api_key
###     EMBEDDING_MODEL=qwen3-embedding:4b
###     EMBEDDING_DIM=2560
### Ollama should set num_ctx option inaddition to EMBEDDING_TOKEN_LIMIT
OLLAMA_EMBEDDING_NUM_CTX=8192

### Gemini Embedding Specific Parameters:
### DEFAULT_GEMINI_ENDPOINT means selecting endpoit by SDK automatically
### Gemini embedding requires sending dimension to server
###     EMBEDDING_BINDING=gemini
###     EMBEDDING_BINDING_HOST=DEFAULT_GEMINI_ENDPOINT
###     EMBEDDING_BINDING_API_KEY=your_api_key
###     EMBEDDING_MODEL=gemini-embedding-001
###     EMBEDDING_DIM=1536
###     EMBEDDING_TOKEN_LIMIT=2048
###     EMBEDDING_SEND_DIM=true

### Bedrock Embedding Specific Parameters:
###     EMBEDDING_BINDING=bedrock
###     EMBEDDING_BINDING_HOST=DEFAULT_BEDROCK_ENDPOINT
###     EMBEDDING_MODEL=amazon.titan-embed-text-v2:0
###     EMBEDDING_DIM=1024
### Share the same region and authentication settings as LLMs, no reconfiguration here
###     AWS_REGION=us-west-1
###     AWS_BEARER_TOKEN_BEDROCK=your_bedrock_api_key
###     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

### Jina AI Embedding Specific Parameters:
###     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
### for the purpose of isolating data from LightRAG instances.
### Valid workspace name constraints: a-z, A-Z, 0-9, and _
####################################################################
# WORKSPACE=

############################
### Data storage selection
############################
### Default storage: JSON/Nano/NetworkX (Recommended for test deployment)
LIGHTRAG_KV_STORAGE=JsonKVStorage
LIGHTRAG_DOC_STATUS_STORAGE=JsonDocStatusStorage
LIGHTRAG_GRAPH_STORAGE=NetworkXStorage
LIGHTRAG_VECTOR_STORAGE=NanoVectorDBStorage

### Wizard metadata used to preserve env-storage Docker deployment defaults across setup reruns
# LIGHTRAG_SETUP_POSTGRES_DEPLOYMENT=docker
# LIGHTRAG_SETUP_NEO4J_DEPLOYMENT=docker
# LIGHTRAG_SETUP_MONGODB_DEPLOYMENT=docker
# LIGHTRAG_SETUP_MONGODB_DEPLOYMENT=atlas-capable
# LIGHTRAG_SETUP_REDIS_DEPLOYMENT=docker
# LIGHTRAG_SETUP_MILVUS_DEPLOYMENT=docker
# LIGHTRAG_SETUP_QDRANT_DEPLOYMENT=docker
# LIGHTRAG_SETUP_MEMGRAPH_DEPLOYMENT=docker
# LIGHTRAG_SETUP_OPENSEARCH_DEPLOYMENT=docker

### PostgreSQL Configuration
POSTGRES_HOST=localhost
POSTGRES_PORT=5432
POSTGRES_USER=your_username
POSTGRES_PASSWORD='your_password'
POSTGRES_DATABASE=rag
POSTGRES_MAX_CONNECTIONS=25
### DB specific workspace should not be set, keep for compatible only
# POSTGRES_WORKSPACE=forced_workspace_name

### Use HNSW_HALFVEC for large embeddings (2000+ dim).
### Requires pgvector extension >= 0.7.0.
### Vector storage type: HNSW, HNSW_HALFVEC, IVFFlat, VCHORDRQ
POSTGRES_VECTOR_INDEX_TYPE=HNSW
POSTGRES_HNSW_M=16
POSTGRES_HNSW_EF=200
POSTGRES_IVFFLAT_LISTS=100
POSTGRES_VCHORDRQ_BUILD_OPTIONS=
POSTGRES_VCHORDRQ_PROBES=
POSTGRES_VCHORDRQ_EPSILON=1.9

### PostgreSQL Connection Retry Configuration (Network Robustness)
### NEW DEFAULTS (v1.4.10+): Optimized for HA deployments with ~30s switchover time
### These defaults provide out-of-the-box support for PostgreSQL High Availability setups
###
### Number of retry attempts (1-100, default: 10)
###   - Default 10 attempts allows ~225s total retry time (sufficient for most HA scenarios)
###   - For extreme cases: increase up to 20-50
### Initial retry backoff in seconds (0.1-300.0, default: 3.0)
###   - Default 3.0s provides reasonable initial delay for switchover detection
###   - For faster recovery: decrease to 1.0-2.0
### Maximum retry backoff in seconds (must be >= backoff, max: 600.0, default: 30.0)
###   - Default 30.0s matches typical switchover completion time
###   - For longer switchovers: increase to 60-90
### Connection pool close timeout in seconds (1.0-30.0, default: 5.0)
# POSTGRES_CONNECTION_RETRIES=10
# POSTGRES_CONNECTION_RETRY_BACKOFF=3.0
# POSTGRES_CONNECTION_RETRY_BACKOFF_MAX=30.0
# POSTGRES_POOL_CLOSE_TIMEOUT=5.0

### PostgreSQL SSL Configuration (Optional)
# POSTGRES_SSL_MODE=require
# POSTGRES_SSL_CERT=/path/to/client-cert.pem
# POSTGRES_SSL_KEY=/path/to/client-key.pem
# POSTGRES_SSL_ROOT_CERT=/path/to/ca-cert.pem
# POSTGRES_SSL_CRL=/path/to/crl.pem

### PostgreSQL Server Settings (for Supabase Supavisor)
# Use this to pass extra options to the PostgreSQL connection string.
# For Supabase, you might need to set it like this:
# POSTGRES_SERVER_SETTINGS='options=reference%3D[project-ref]'

# Default is 100 set to 0 to disable
# POSTGRES_STATEMENT_CACHE_SIZE=100

### Neo4j Configuration
NEO4J_URI=neo4j+s://xxxxxxxx.databases.neo4j.io
NEO4J_USERNAME=neo4j
NEO4J_PASSWORD='your_password'
NEO4J_DATABASE=neo4j
NEO4J_MAX_CONNECTION_POOL_SIZE=100
NEO4J_CONNECTION_TIMEOUT=30
NEO4J_CONNECTION_ACQUISITION_TIMEOUT=30
NEO4J_MAX_TRANSACTION_RETRY_TIME=30
NEO4J_MAX_CONNECTION_LIFETIME=300
NEO4J_LIVENESS_CHECK_TIMEOUT=30
NEO4J_KEEP_ALIVE=true
### DB specific workspace should not be set, keep for compatible only
# NEO4J_WORKSPACE=forced_workspace_name

### MongoDB Configuration
# For MongoVectorDBStorage, MONGO_URI must point to a MongoDB endpoint with
# Atlas Search / Vector Search support, such as MongoDB Atlas or Atlas local.
MONGO_URI=mongodb://localhost:27017/
MONGO_DATABASE=LightRAG
### DB specific workspace should not be set, keep for compatible only
# MONGODB_WORKSPACE=forced_workspace_name

# Community/local Docker MongoDB example for KV, graph, or doc-status storage only:
# MONGO_URI=mongodb://localhost:27017/

### OpenSearch Configuration
### OpenSearch can be used for all storage types: KV, Vector, Graph, DocStatus
### Connection settings (comma-separated host:port entries; do not include http:// or https://)
### This setup wizard supports authenticated OpenSearch clusters only.
### OPENSEARCH_USE_SSL controls whether those hosts are reached over TLS.
OPENSEARCH_HOSTS=localhost:9200
OPENSEARCH_USER=admin
OPENSEARCH_PASSWORD=LightRAG2026_!@
OPENSEARCH_USE_SSL=true
OPENSEARCH_VERIFY_CERTS=false
# OPENSEARCH_TIMEOUT=30
# OPENSEARCH_MAX_RETRIES=3
### Index Settings (for 3-AZ Amazon OpenSearch Service, set replicas to 2)
# OPENSEARCH_NUMBER_OF_SHARDS=1
# OPENSEARCH_NUMBER_OF_REPLICAS=0
### k-NN Settings for Vector Storage (HNSW algorithm)
# OPENSEARCH_KNN_EF_CONSTRUCTION=200
# OPENSEARCH_KNN_M=16
# OPENSEARCH_KNN_EF_SEARCH=100
### PPL graphlookup for server-side graph traversal (auto-detected if not set)
# OPENSEARCH_USE_PPL_GRAPHLOOKUP=true
### DB specific workspace should not be set, keep for compatible only
# OPENSEARCH_WORKSPACE=forced_workspace_name

### Milvus Configuration
MILVUS_URI=http://localhost:19530
MILVUS_DB_NAME=lightrag
# MILVUS_DEVICE=cpu
# MILVUS_USER=root
# MILVUS_PASSWORD=your_password
# MILVUS_TOKEN=your_token
# Required for the bundled Docker Milvus stack; may come from .env or exported shell variables.
# MINIO_ACCESS_KEY_ID=minioadmin
# MINIO_SECRET_ACCESS_KEY=minioadmin
### DB specific workspace should not be set, keep for compatible only
# MILVUS_WORKSPACE=forced_workspace_name

### Milvus Vector Index Configuration
### Index type: AUTOINDEX (default), HNSW, HNSW_SQ, HNSW_PQ, IVF_FLAT, IVF_SQ8, DISKANN
# MILVUS_INDEX_TYPE=AUTOINDEX

### Metric type: COSINE (default), L2, IP
# MILVUS_METRIC_TYPE=COSINE

### HNSW / HNSW_SQ / HNSW_PQ Parameters (aligned with Milvus 2.4+ defaults)
### M: Maximum number of connections per node [2-2048], default 16
# MILVUS_HNSW_M=16
### efConstruction: Size of dynamic candidate list during build [8-512], default 360
# MILVUS_HNSW_EF_CONSTRUCTION=360
### ef: Size of dynamic candidate list during search, default 200
# MILVUS_HNSW_EF=200

### HNSW_SQ Specific Parameters (requires Milvus 2.6.8+)
### sq_type: Scalar quantization type - SQ4U, SQ6, SQ8 (default), BF16, FP16
# MILVUS_HNSW_SQ_TYPE=SQ8
### refine: Enable refinement step for higher precision, default false
# MILVUS_HNSW_SQ_REFINE=false
### refine_type: Refinement precision (must be higher than sq_type) - SQ6, SQ8, BF16, FP16, FP32
# MILVUS_HNSW_SQ_REFINE_TYPE=FP32
### refine_k: Refinement expansion factor, default 10
# MILVUS_HNSW_SQ_REFINE_K=10

### IVF_FLAT / IVF_SQ8 Parameters
### nlist: Number of cluster units [1-65536], recommended sqrt(n) for n>1M, default 1024
# MILVUS_IVF_NLIST=1024
### nprobe: Number of units to query [1-nlist], default 16
# MILVUS_IVF_NPROBE=16

### Qdrant
QDRANT_URL=http://localhost:6333
# QDRANT_DEVICE=cpu
# QDRANT_API_KEY=your-api-key
### Qdrant upsert batching (enabled by default)
### Split large upserts by estimated JSON payload size and point count
### Default 16MB keeps safe headroom below common 32MB gateway/request limits
# QDRANT_UPSERT_MAX_PAYLOAD_BYTES=16777216
# QDRANT_UPSERT_MAX_POINTS_PER_BATCH=128
### DB specific workspace should not be set, keep for compatible only
# QDRANT_WORKSPACE=forced_workspace_name

### Redis
REDIS_URI=redis://localhost:6379
REDIS_SOCKET_TIMEOUT=30
REDIS_CONNECT_TIMEOUT=10
REDIS_MAX_CONNECTIONS=100
REDIS_RETRY_ATTEMPTS=3
### DB specific workspace should not be set, keep for compatible only
# REDIS_WORKSPACE=forced_workspace_name

### Memgraph Configuration
MEMGRAPH_URI=bolt://localhost:7687
MEMGRAPH_USERNAME=
MEMGRAPH_PASSWORD=
MEMGRAPH_DATABASE=memgraph
### DB specific workspace should not be set, keep for compatible only
# MEMGRAPH_WORKSPACE=forced_workspace_name

###########################################################
### Langfuse Observability Configuration
### Only works with LLM provided by OpenAI compatible API
### Install with: pip install lightrag-hku[observability]
### Sign up at: https://cloud.langfuse.com or self-host
###########################################################
# LANGFUSE_SECRET_KEY=''
# LANGFUSE_PUBLIC_KEY=''
# LANGFUSE_HOST='https://cloud.langfuse.com'
# LANGFUSE_ENABLE_TRACE=true

############################
### Evaluation Configuration
############################
### RAGAS evaluation models (used for RAG quality assessment)
### ⚠️ IMPORTANT: Both LLM and Embedding endpoints MUST be OpenAI-compatible
### Default uses OpenAI models for evaluation

### LLM Configuration for Evaluation
# EVAL_LLM_MODEL=gpt-4o-mini
### API key for LLM evaluation (fallback to OPENAI_API_KEY if not set)
# EVAL_LLM_BINDING_API_KEY=your_api_key
### Custom OpenAI-compatible endpoint for LLM evaluation (optional)
# EVAL_LLM_BINDING_HOST=https://api.openai.com/v1

### Embedding Configuration for Evaluation
# EVAL_EMBEDDING_MODEL=text-embedding-3-large
### API key for embeddings (fallback: EVAL_LLM_BINDING_API_KEY -> OPENAI_API_KEY)
# EVAL_EMBEDDING_BINDING_API_KEY=your_embedding_api_key
### Custom OpenAI-compatible endpoint for embeddings (fallback: EVAL_LLM_BINDING_HOST)
# EVAL_EMBEDDING_BINDING_HOST=https://api.openai.com/v1

### Performance Tuning
### Number of concurrent test case evaluations
### Lower values reduce API rate limit issues but increase evaluation time
# EVAL_MAX_CONCURRENT=2
### TOP_K query parameter of LightRAG (default: 10)
### Number of entities or relations retrieved from KG
# EVAL_QUERY_TOP_K=10
### LLM request retry and timeout settings for evaluation
# EVAL_LLM_MAX_RETRIES=5
# EVAL_LLM_TIMEOUT=180

##########################################################################
### ----- Preserved custom environment variables from previous .env  -----
### ----- Comments in this session will persist across regenerations -----
### (This must be the final session; ensure the preceding lines unchanged)
##########################################################################
### The "make env*" wizard will leave the following lines unchanged
### You may add additional env vars or commnets here for your own purpose
##########################################################################

### AWS Bedrock
# LLM_BINDING=bedrock
# LLM_BINDING_HOST=DEFAULT_BEDROCK_ENDPOINT
# LLM_MODEL=us.anthropic.claude-haiku-4-5-20251001-v1:0

### ----- Extra setting from previous .env -----