Global search generates answers by analyzing all AI-generated community reports in a map-reduce fashion. This method is ideal for questions that require understanding of the dataset as a whole.
When to use global search Global search is best suited for:
High-level questions - “What are the main themes?”Dataset-wide insights - “What are the most significant trends?”Comparative analysis - “How do different communities relate?”Summarization tasks - “What is this dataset about?”
How global search works
Community report retrieval
Global search loads all community reports generated during indexing. These reports summarize clusters of related entities and relationships.
Map phase
Each community report is sent to the LLM with your question, generating intermediate answers from different parts of the knowledge graph.
Reduce phase
Intermediate answers are aggregated and synthesized into a final, comprehensive response.
Setting up the notebook Import required libraries import os import pandas as pd from graphrag.config.enums import ModelType from graphrag.config.models.language_model_config import LanguageModelConfig from graphrag.language_model.manager import ModelManager from graphrag.query.indexer_adapters import ( read_indexer_communities, read_indexer_entities, read_indexer_reports, ) from graphrag.query.structured_search.global_search.community_context import ( GlobalCommunityContext, ) from graphrag.query.structured_search.global_search.search import GlobalSearch from graphrag.tokenizer.get_tokenizer import get_tokenizer
api_key = os.environ[ "GRAPHRAG_API_KEY" ] config = LanguageModelConfig( api_key = api_key, type = ModelType.Chat, model_provider = "openai" , model = "gpt-4.1" , max_retries = 20 , ) model = ModelManager().get_or_create_chat_model( name = "global_search" , model_type = ModelType.Chat, config = config, ) tokenizer = get_tokenizer(config)
# Path to indexing outputs INPUT_DIR = "./inputs/operation dulce" COMMUNITY_TABLE = "communities" COMMUNITY_REPORT_TABLE = "community_reports" ENTITY_TABLE = "entities" # Community level to use (higher = more fine-grained, more expensive) COMMUNITY_LEVEL = 2 # Load parquet files community_df = pd.read_parquet( f " { INPUT_DIR } / { COMMUNITY_TABLE } .parquet" ) entity_df = pd.read_parquet( f " { INPUT_DIR } / { ENTITY_TABLE } .parquet" ) report_df = pd.read_parquet( f " { INPUT_DIR } / { COMMUNITY_REPORT_TABLE } .parquet" ) # Convert to GraphRAG data structures communities = read_indexer_communities(community_df, report_df) reports = read_indexer_reports(report_df, community_df, COMMUNITY_LEVEL ) entities = read_indexer_entities(entity_df, community_df, COMMUNITY_LEVEL ) print ( f "Total report count: { len (report_df) } " ) print ( f "Report count at level { COMMUNITY_LEVEL } : { len (reports) } " )
The COMMUNITY_LEVEL parameter controls granularity. Higher values use more detailed community reports but increase computational cost.
Build global context context_builder = GlobalCommunityContext( community_reports = reports, communities = communities, entities = entities, # Optional: enables community weight calculation tokenizer = tokenizer, )
Context builder
Map LLM
Reduce LLM
context_builder_params = { "use_community_summary" : False , # True = summaries, False = full reports "shuffle_data" : True , # Randomize report order "include_community_rank" : True , # Include rank for prioritization "min_community_rank" : 0 , # Minimum rank threshold "community_rank_name" : "rank" , "include_community_weight" : True , # Weight by entity count "community_weight_name" : "occurrence weight" , "normalize_community_weight" : True , "max_tokens" : 12_000 , # Context window size "context_name" : "Reports" , }
map_llm_params = { "max_tokens" : 1000 , # Tokens per intermediate answer "temperature" : 0.0 , # Deterministic for consistency "response_format" : { "type" : "json_object" }, # Structured output }
reduce_llm_params = { "max_tokens" : 2000 , # Tokens for final answer "temperature" : 0.0 , # Deterministic }
Create search engine search_engine = GlobalSearch( model = model, context_builder = context_builder, tokenizer = tokenizer, max_data_tokens = 12_000 , map_llm_params = map_llm_params, reduce_llm_params = reduce_llm_params, allow_general_knowledge = False , # Strictly use indexed data only json_mode = True , # Requires model support context_builder_params = context_builder_params, concurrent_coroutines = 32 , # Parallel map operations response_type = "multiple paragraphs" , # Output format guidance )
result = await search_engine.search( "What is operation dulce?" ) print (result.response)
Inspect context data # View which reports were used result.context_data[ "reports" ]
Analyze token usage print ( f "LLM calls: { result.llm_calls } " ) print ( f "Prompt tokens: { result.prompt_tokens } " ) print ( f "Output tokens: { result.output_tokens } " ) print ( f "Total cost estimate: $ { (result.prompt_tokens * 0.00001 + result.output_tokens * 0.00003 ) :.4f} " )
Example queries
result = await search_engine.search( "What are the top 5 themes in this dataset?" ) print (result.response)
result = await search_engine.search( "How do different organizations interact in this narrative?" ) print (result.response)
result = await search_engine.search( "What are the most significant events and their outcomes?" ) print (result.response)
# Change response type for different output formats search_engine.response_type = "executive summary" result = await search_engine.search( "Provide a comprehensive summary of this dataset" ) print (result.response)
Tuning parameters Level 0 (coarsest)
Level 1-2 (balanced)
Level 3+ (finest)
Fewest communities
Broadest summaries
Lowest cost
Best for very high-level questions
Moderate granularity
Good cost/quality tradeoff
Recommended starting point
Most detailed communities
Highest quality answers
Significantly higher cost
Best for complex analysis
Response type options # Customize output format response_types = [ "single paragraph" , "multiple paragraphs" , "executive summary" , "prioritized list" , "bullet points" , "detailed report" , ] search_engine.response_type = "bullet points"
Parallel processing Increase concurrent_coroutines for faster map phase
Token management Adjust max_tokens based on your model limits max_data_tokens = 8000 # For 8k models
Community filtering Set minimum rank to skip low-importance communities
Summary mode Use summaries instead of full reports to reduce tokens use_community_summary = True
Comparison with local search Aspect Global Search Local Search Question Type High-level, broad Specific, detailed Data Source Community reports Entities + text chunks Cost Higher (map-reduce) Lower (single query) Response Time Slower Faster Best For Themes, trends, summaries Entity details, relationships
Next steps
Local search Learn about local search for specific queries
DRIFT search Explore hybrid search methods
Search comparison Compare all search methods
Query guide Complete global search documentation