autogen/python/samples/agentchat_graphrag/settings.yaml

### This config file contains required core defaults that must be set, along with a handful of common optional settings.
### For a full list of available settings, see https://microsoft.github.io/graphrag/config/yaml/

### LLM settings ###
## There are a number of settings to tune the threading and token limits for LLM calls - check the docs.

encoding_model: cl100k_base # this needs to be matched to your model!

llm:
  api_key: null
  type: openai_chat # or azure_openai_chat
  model: gpt-4o
  model_supports_json: true # recommended if this is available for your model.
  # audience: "https://cognitiveservices.azure.com/.default"
  # api_base: https://<resource-name>.openai.azure.com
  # api_version: 2024-08-01-preview
  # deployment_name: gpt-4o

parallelization:
  stagger: 0.3
  # num_threads: 50

async_mode: threaded # or asyncio

embeddings:
  async_mode: threaded # or asyncio
  vector_store:
    type: lancedb
    db_uri: 'data/output/lancedb'
    container_name: default
    overwrite: true
  llm:
    api_key: null
    type: openai_embedding # or azure_openai_embedding
    model: text-embedding-3-small
    # api_base: https://<resource-name>.openai.azure.com
    # api_version: "2023-05-15"
    # audience: "https://cognitiveservices.azure.com/.default"
    # deployment_name: text-embedding-3-small

### Input settings ###

input:
  type: file # or blob
  file_type: text # or csv
  base_dir: "data/input"
  file_encoding: utf-8
  file_pattern: ".*\\.txt$"

chunks:
  size: 1200
  overlap: 100
  group_by_columns: [id]

### Storage settings ###
## If blob storage is specified in the following four sections,
## connection_string and container_name must be provided

cache:
  type: file # or blob
  base_dir: "cache"

reporting:
  type: file # or console, blob
  base_dir: "logs"

storage:
  type: file # or blob
  base_dir: "data/output"

## only turn this on if running `graphrag index` with custom settings
## we normally use `graphrag update` with the defaults
update_index_storage:
  # type: file # or blob
  # base_dir: "update_output"

### Workflow settings ###

skip_workflows: []

entity_extraction:
  prompt: "prompts/entity_extraction.txt"
  entity_types: [organization,person,geo,event]
  max_gleanings: 1

summarize_descriptions:
  prompt: "prompts/summarize_descriptions.txt"
  max_length: 500

claim_extraction:
  enabled: false
  prompt: "prompts/claim_extraction.txt"
  description: "Any claims or facts that could be relevant to information discovery."
  max_gleanings: 1

community_reports:
  prompt: "prompts/community_report.txt"
  max_length: 2000
  max_input_length: 8000

cluster_graph:
  max_cluster_size: 10

embed_graph:
  enabled: false # if true, will generate node2vec embeddings for nodes

umap:
  enabled: false # if true, will generate UMAP embeddings for nodes

snapshots:
  graphml: false
  raw_entities: false
  top_level_nodes: false
  embeddings: false
  transient: false

### Query settings ###
## The prompt locations are required here, but each search method has a number of optional knobs that can be tuned.
## See the config docs: https://microsoft.github.io/graphrag/config/yaml/#query

local_search:
  prompt: "prompts/local_search_system_prompt.txt"

global_search:
  map_prompt: "prompts/global_search_map_system_prompt.txt"
  reduce_prompt: "prompts/global_search_reduce_system_prompt.txt"
  knowledge_prompt: "prompts/global_search_knowledge_system_prompt.txt"

drift_search:
  prompt: "prompts/drift_search_system_prompt.txt"