Configuration Template

The following template can be used and stored as a .env in the the directory where you're are pointing the --root parameter on your Indexing Pipeline execution.

For details about how to run the Indexing Pipeline, refer to the Index CLI documentation.

.env File Template

Required variables are uncommented. All the optional configuration can be turned on or off as needed.

Minimal Configuration

# Base LLM Settings
GRAPHRAG_API_KEY="your_api_key"
GRAPHRAG_API_BASE="http://<domain>.openai.azure.com" # For Azure OpenAI Users
GRAPHRAG_API_VERSION="api_version" # For Azure OpenAI Users

# Text Generation Settings
GRAPHRAG_LLM_TYPE="azure_openai_chat" # or openai_chat
GRAPHRAG_LLM_DEPLOYMENT_NAME="gpt-4-turbo-preview"
GRAPHRAG_LLM_MODEL_SUPPORTS_JSON=True

# Text Embedding Settings
GRAPHRAG_EMBEDDING_TYPE="azure_openai_embedding" # or openai_embedding
GRAPHRAG_LLM_DEPLOYMENT_NAME="text-embedding-3-small"

# Data Mapping Settings
GRAPHRAG_INPUT_TYPE="text"

Full Configuration


# Required LLM Config

# Input Data Configuration
GRAPHRAG_INPUT_TYPE="file"

# Plaintext Input Data Configuration
# GRAPHRAG_INPUT_FILE_PATTERN=.*\.txt

# Text Input Data Configuration
GRAPHRAG_INPUT_FILE_TYPE="text"
GRAPHRAG_INPUT_FILE_PATTERN=".*\.txt$"
GRAPHRAG_INPUT_SOURCE_COLUMN=source
# GRAPHRAG_INPUT_TIMESTAMP_COLUMN=None
# GRAPHRAG_INPUT_TIMESTAMP_FORMAT=None
# GRAPHRAG_INPUT_TEXT_COLUMN="text"
# GRAPHRAG_INPUT_ATTRIBUTE_COLUMNS=id
# GRAPHRAG_INPUT_TITLE_COLUMN="title"
# GRAPHRAG_INPUT_TYPE="file"
# GRAPHRAG_INPUT_CONNECTION_STRING=None
# GRAPHRAG_INPUT_CONTAINER_NAME=None
# GRAPHRAG_INPUT_BASE_DIR=None

# Base LLM Settings
GRAPHRAG_API_KEY="your_api_key"
GRAPHRAG_API_BASE="http://<domain>.openai.azure.com" # For Azure OpenAI Users
GRAPHRAG_API_VERSION="api_version" # For Azure OpenAI Users
# GRAPHRAG_API_ORGANIZATION=None
# GRAPHRAG_API_PROXY=None

# Text Generation Settings
# GRAPHRAG_LLM_TYPE=openai_chat
GRAPHRAG_LLM_API_KEY="your_api_key" # If GRAPHRAG_API_KEY is not set
GRAPHRAG_LLM_API_BASE="http://<domain>.openai.azure.com" # For Azure OpenAI Users and if GRAPHRAG_API_BASE is not set
GRAPHRAG_LLM_API_VERSION="api_version" # For Azure OpenAI Users and if GRAPHRAG_API_VERSION is not set
GRAPHRAG_LLM_MODEL_SUPPORTS_JSON=True # Suggested by default
# GRAPHRAG_LLM_API_ORGANIZATION=None
# GRAPHRAG_LLM_API_PROXY=None
# GRAPHRAG_LLM_DEPLOYMENT_NAME=None
# GRAPHRAG_LLM_MODEL=gpt-4-turbo-preview
# GRAPHRAG_LLM_MAX_TOKENS=4000
# GRAPHRAG_LLM_REQUEST_TIMEOUT=180
# GRAPHRAG_LLM_THREAD_COUNT=50
# GRAPHRAG_LLM_THREAD_STAGGER=0.3
# GRAPHRAG_LLM_CONCURRENT_REQUESTS=25
# GRAPHRAG_LLM_TPM=0
# GRAPHRAG_LLM_RPM=0
# GRAPHRAG_LLM_MAX_RETRIES=10
# GRAPHRAG_LLM_MAX_RETRY_WAIT=10
# GRAPHRAG_LLM_SLEEP_ON_RATE_LIMIT_RECOMMENDATION=True

# Text Embedding Settings
# GRAPHRAG_EMBEDDING_TYPE=openai_embedding
GRAPHRAG_EMBEDDING_API_KEY="your_api_key" # If GRAPHRAG_API_KEY is not set
GRAPHRAG_EMBEDDING_API_BASE="http://<domain>.openai.azure.com"  # For Azure OpenAI Users and if GRAPHRAG_API_BASE is not set
GRAPHRAG_EMBEDDING_API_VERSION="api_version" # For Azure OpenAI Users and if GRAPHRAG_API_VERSION is not set
# GRAPHRAG_EMBEDDING_API_ORGANIZATION=None
# GRAPHRAG_EMBEDDING_API_PROXY=None
# GRAPHRAG_EMBEDDING_DEPLOYMENT_NAME=None
# GRAPHRAG_EMBEDDING_MODEL=text-embedding-3-small
# GRAPHRAG_EMBEDDING_BATCH_SIZE=16
# GRAPHRAG_EMBEDDING_BATCH_MAX_TOKENS=8191
# GRAPHRAG_EMBEDDING_TARGET=required
# GRAPHRAG_EMBEDDING_SKIP=None
# GRAPHRAG_EMBEDDING_THREAD_COUNT=None
# GRAPHRAG_EMBEDDING_THREAD_STAGGER=50
# GRAPHRAG_EMBEDDING_CONCURRENT_REQUESTS=25
# GRAPHRAG_EMBEDDING_TPM=0
# GRAPHRAG_EMBEDDING_RPM=0
# GRAPHRAG_EMBEDDING_MAX_RETRIES=10
# GRAPHRAG_EMBEDDING_MAX_RETRY_WAIT=10
# GRAPHRAG_EMBEDDING_SLEEP_ON_RATE_LIMIT_RECOMMENDATION=True

# Data Mapping Settings
# GRAPHRAG_INPUT_ENCODING=utf-8

# Data Chunking
# GRAPHRAG_CHUNK_SIZE=1200
# GRAPHRAG_CHUNK_OVERLAP=100
# GRAPHRAG_CHUNK_BY_COLUMNS=id

# Prompting Overrides
# GRAPHRAG_ENTITY_EXTRACTION_PROMPT_FILE=None
# GRAPHRAG_ENTITY_EXTRACTION_MAX_GLEANINGS=1
# GRAPHRAG_ENTITY_EXTRACTION_ENTITY_TYPES=organization,person,event,geo
# GRAPHRAG_SUMMARIZE_DESCRIPTIONS_PROMPT_FILE=None
# GRAPHRAG_SUMMARIZE_DESCRIPTIONS_MAX_LENGTH=500
# GRAPHRAG_CLAIM_EXTRACTION_DESCRIPTION="Any claims or facts that could be relevant to threat analysis."
# GRAPHRAG_CLAIM_EXTRACTION_PROMPT_FILE=None
# GRAPHRAG_CLAIM_EXTRACTION_MAX_GLEANINGS=1
# GRAPHRAG_COMMUNITY_REPORT_PROMPT_FILE=None
# GRAPHRAG_COMMUNITY_REPORT_MAX_LENGTH=1500

# Storage
# GRAPHRAG_STORAGE_TYPE=file
# GRAPHRAG_STORAGE_CONNECTION_STRING=None
# GRAPHRAG_STORAGE_CONTAINER_NAME=None
# GRAPHRAG_STORAGE_BASE_DIR=None

# Cache
# GRAPHRAG_CACHE_TYPE=file
# GRAPHRAG_CACHE_CONNECTION_STRING=None
# GRAPHRAG_CACHE_CONTAINER_NAME=None
# GRAPHRAG_CACHE_BASE_DIR=None

# Reporting
# GRAPHRAG_REPORTING_TYPE=file
# GRAPHRAG_REPORTING_CONNECTION_STRING=None
# GRAPHRAG_REPORTING_CONTAINER_NAME=None
# GRAPHRAG_REPORTING_BASE_DIR=None

# Node2Vec Parameters
# GRAPHRAG_NODE2VEC_ENABLED=False
# GRAPHRAG_NODE2VEC_NUM_WALKS=10
# GRAPHRAG_NODE2VEC_WALK_LENGTH=40
# GRAPHRAG_NODE2VEC_WINDOW_SIZE=2
# GRAPHRAG_NODE2VEC_ITERATIONS=3
# GRAPHRAG_NODE2VEC_RANDOM_SEED=597832

# Data Snapshotting
# GRAPHRAG_SNAPSHOT_GRAPHML=False
# GRAPHRAG_SNAPSHOT_RAW_ENTITIES=False
# GRAPHRAG_SNAPSHOT_TOP_LEVEL_NODES=False

# Miscellaneous Settings
# GRAPHRAG_ASYNC_MODE=asyncio
# GRAPHRAG_ENCODING_MODEL=cl100k_base
# GRAPHRAG_MAX_CLUSTER_SIZE=10
# GRAPHRAG_SKIP_WORKFLOWS=None
# GRAPHRAG_UMAP_ENABLED=False