Global Search

In [1]:

Copied!

# Copyright (c) 2024 Microsoft Corporation.
# Licensed under the MIT License.
# Copyright (c) 2024 Microsoft Corporation.
# Licensed under the MIT License.

In [2]:

Copied!





import os

import pandas as pd
import tiktoken

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
import os

import pandas as pd
import tiktoken

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

Global Search example¶

Global search method generates answers by searching over all AI-generated community reports in a map-reduce fashion. This is a resource-intensive method, but often gives good responses for questions that require an understanding of the dataset as a whole (e.g. What are the most significant values of the herbs mentioned in this notebook?).

LLM setup¶

In [3]:

Copied!





api_key = os.environ["GRAPHRAG_API_KEY"]
llm_model = os.environ["GRAPHRAG_LLM_MODEL"]

config = LanguageModelConfig(
    api_key=api_key,
    type=ModelType.OpenAIChat,
    model=llm_model,
    max_retries=20,
)
model = ModelManager().get_or_create_chat_model(
    name="global_search",
    model_type=ModelType.OpenAIChat,
    config=config,
)

token_encoder = tiktoken.encoding_for_model(llm_model)
api_key = os.environ["GRAPHRAG_API_KEY"]
llm_model = os.environ["GRAPHRAG_LLM_MODEL"]

config = LanguageModelConfig(
    api_key=api_key,
    type=ModelType.OpenAIChat,
    model=llm_model,
    max_retries=20,
)
model = ModelManager().get_or_create_chat_model(
    name="global_search",
    model_type=ModelType.OpenAIChat,
    config=config,
)

token_encoder = tiktoken.encoding_for_model(llm_model)

---------------------------------------------------------------------------
ValidationError                           Traceback (most recent call last)
Cell In[3], line 4
      1 api_key = os.environ["GRAPHRAG_API_KEY"]
      2 llm_model = os.environ["GRAPHRAG_LLM_MODEL"]
----> 4 config = LanguageModelConfig(
      5     api_key=api_key,
      6     type=ModelType.OpenAIChat,
      7     model=llm_model,
      8     max_retries=20,
      9 )
     10 model = ModelManager().get_or_create_chat_model(
     11     name="global_search",
     12     model_type=ModelType.OpenAIChat,
     13     config=config,
     14 )
     16 token_encoder = tiktoken.encoding_for_model(llm_model)

File ~/.cache/pypoetry/virtualenvs/graphrag-F2jvqev7-py3.11/lib/python3.11/site-packages/pydantic/main.py:253, in BaseModel.__init__(self, **data)
    251 # `__tracebackhide__` tells pytest and some other tools to omit this function from tracebacks
    252 __tracebackhide__ = True
--> 253 validated_self = self.__pydantic_validator__.validate_python(data, self_instance=self)
    254 if self is not validated_self:
    255     warnings.warn(
    256         'A custom validator is returning a value other than `self`.\n'
    257         "Returning anything other than `self` from a top level model validator isn't supported when validating via `__init__`.\n"
    258         'See the `model_validator` docs (https://docs.pydantic.dev/latest/concepts/validators/#model-validators) for more details.',
    259         stacklevel=2,
    260     )

ValidationError: 1 validation error for LanguageModelConfig
  Value error, API Key is required for ModelType.OpenAIChat when using api_key authentication. Please rerun `graphrag init` and set the API_KEY. [type=value_error, input_value={'api_key': '', 'type': "...: '', 'max_retries': 20}, input_type=dict]
    For further information visit https://errors.pydantic.dev/2.11/v/value_error

Load community reports as context for global search¶

Load all community reports in the community_reports table from GraphRAG, to be used as context data for global search.
Load entities from the entities tables from GraphRAG, to be used for calculating community weights for context ranking. Note that this is optional (if no entities are provided, we will not calculate community weights and only use the rank attribute in the community reports table for context ranking)
Load all communities in the communities table from the GraphRAG, to be used to reconstruct the community graph hierarchy for dynamic community selection.

In [4]:

Copied!





# parquet files generated from indexing pipeline
INPUT_DIR = "./inputs/operation dulce"
COMMUNITY_TABLE = "communities"
COMMUNITY_REPORT_TABLE = "community_reports"
ENTITY_TABLE = "entities"

# community level in the Leiden community hierarchy from which we will load the community reports
# higher value means we use reports from more fine-grained communities (at the cost of higher computation cost)
COMMUNITY_LEVEL = 2
# parquet files generated from indexing pipeline
INPUT_DIR = "./inputs/operation dulce"
COMMUNITY_TABLE = "communities"
COMMUNITY_REPORT_TABLE = "community_reports"
ENTITY_TABLE = "entities"

# community level in the Leiden community hierarchy from which we will load the community reports
# higher value means we use reports from more fine-grained communities (at the cost of higher computation cost)
COMMUNITY_LEVEL = 2

In [5]:

Copied!





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")

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 after filtering by community level {COMMUNITY_LEVEL}: {len(reports)}"
)

report_df.head()
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")

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 after filtering by community level {COMMUNITY_LEVEL}: {len(reports)}"
)

report_df.head()

Total report count: 2
Report count after filtering by community level 2: 2

Out[5]:

	id	human_readable_id	community	level	parent	children	title	summary	full_content	rank	rating_explanation	findings	full_content_json	period	size
0	6c3a555680d647ac8be866a129c7b0ea	0	0	0	-1	[]	Operation: Dulce and Dulce Base Exploration	The community revolves around 'Operation: Dulc...	# Operation: Dulce and Dulce Base Exploration\...	8.5	The impact severity rating is high due to the ...	[{'explanation': 'Operation: Dulce is a signif...	{\n "title": "Operation: Dulce and Dulce Ba...	2025-03-04	7
1	0127331a1ea34b8ba19de2c2a4cb3bc9	1	1	0	-1	[]	Paranormal Military Squad and Operation: Dulce	The community centers around the Paranormal Mi...	# Paranormal Military Squad and Operation: Dul...	8.5	The impact severity rating is high due to the ...	[{'explanation': 'Agent Alex Mercer is a key f...	{\n "title": "Paranormal Military Squad and...	2025-03-04	9

Build global context based on community reports¶

In [6]:

Copied!





context_builder = GlobalCommunityContext(
    community_reports=reports,
    communities=communities,
    entities=entities,  # default to None if you don't want to use community weights for ranking
    token_encoder=token_encoder,
)
context_builder = GlobalCommunityContext(
    community_reports=reports,
    communities=communities,
    entities=entities,  # default to None if you don't want to use community weights for ranking
    token_encoder=token_encoder,
)

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[6], line 5
      1 context_builder = GlobalCommunityContext(
      2     community_reports=reports,
      3     communities=communities,
      4     entities=entities,  # default to None if you don't want to use community weights for ranking
----> 5     token_encoder=token_encoder,
      6 )

NameError: name 'token_encoder' is not defined

Perform global search¶

In [7]:

Copied!





context_builder_params = {
    "use_community_summary": False,  # False means using full community reports. True means using community short summaries.
    "shuffle_data": True,
    "include_community_rank": True,
    "min_community_rank": 0,
    "community_rank_name": "rank",
    "include_community_weight": True,
    "community_weight_name": "occurrence weight",
    "normalize_community_weight": True,
    "max_tokens": 12_000,  # change this based on the token limit you have on your model (if you are using a model with 8k limit, a good setting could be 5000)
    "context_name": "Reports",
}

map_llm_params = {
    "max_tokens": 1000,
    "temperature": 0.0,
    "response_format": {"type": "json_object"},
}

reduce_llm_params = {
    "max_tokens": 2000,  # change this based on the token limit you have on your model (if you are using a model with 8k limit, a good setting could be 1000-1500)
    "temperature": 0.0,
}
context_builder_params = {
    "use_community_summary": False,  # False means using full community reports. True means using community short summaries.
    "shuffle_data": True,
    "include_community_rank": True,
    "min_community_rank": 0,
    "community_rank_name": "rank",
    "include_community_weight": True,
    "community_weight_name": "occurrence weight",
    "normalize_community_weight": True,
    "max_tokens": 12_000,  # change this based on the token limit you have on your model (if you are using a model with 8k limit, a good setting could be 5000)
    "context_name": "Reports",
}

map_llm_params = {
    "max_tokens": 1000,
    "temperature": 0.0,
    "response_format": {"type": "json_object"},
}

reduce_llm_params = {
    "max_tokens": 2000,  # change this based on the token limit you have on your model (if you are using a model with 8k limit, a good setting could be 1000-1500)
    "temperature": 0.0,
}

In [8]:

Copied!





search_engine = GlobalSearch(
    model=model,
    context_builder=context_builder,
    token_encoder=token_encoder,
    max_data_tokens=12_000,  # change this based on the token limit you have on your model (if you are using a model with 8k limit, a good setting could be 5000)
    map_llm_params=map_llm_params,
    reduce_llm_params=reduce_llm_params,
    allow_general_knowledge=False,  # set this to True will add instruction to encourage the LLM to incorporate general knowledge in the response, which may increase hallucinations, but could be useful in some use cases.
    json_mode=True,  # set this to False if your LLM model does not support JSON mode.
    context_builder_params=context_builder_params,
    concurrent_coroutines=32,
    response_type="multiple paragraphs",  # free form text describing the response type and format, can be anything, e.g. prioritized list, single paragraph, multiple paragraphs, multiple-page report
)
search_engine = GlobalSearch(
    model=model,
    context_builder=context_builder,
    token_encoder=token_encoder,
    max_data_tokens=12_000,  # change this based on the token limit you have on your model (if you are using a model with 8k limit, a good setting could be 5000)
    map_llm_params=map_llm_params,
    reduce_llm_params=reduce_llm_params,
    allow_general_knowledge=False,  # set this to True will add instruction to encourage the LLM to incorporate general knowledge in the response, which may increase hallucinations, but could be useful in some use cases.
    json_mode=True,  # set this to False if your LLM model does not support JSON mode.
    context_builder_params=context_builder_params,
    concurrent_coroutines=32,
    response_type="multiple paragraphs",  # free form text describing the response type and format, can be anything, e.g. prioritized list, single paragraph, multiple paragraphs, multiple-page report
)

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[8], line 2
      1 search_engine = GlobalSearch(
----> 2     model=model,
      3     context_builder=context_builder,
      4     token_encoder=token_encoder,
      5     max_data_tokens=12_000,  # change this based on the token limit you have on your model (if you are using a model with 8k limit, a good setting could be 5000)
      6     map_llm_params=map_llm_params,
      7     reduce_llm_params=reduce_llm_params,
      8     allow_general_knowledge=False,  # set this to True will add instruction to encourage the LLM to incorporate general knowledge in the response, which may increase hallucinations, but could be useful in some use cases.
      9     json_mode=True,  # set this to False if your LLM model does not support JSON mode.
     10     context_builder_params=context_builder_params,
     11     concurrent_coroutines=32,
     12     response_type="multiple paragraphs",  # free form text describing the response type and format, can be anything, e.g. prioritized list, single paragraph, multiple paragraphs, multiple-page report
     13 )

NameError: name 'model' is not defined

In [9]:

Copied!

result = await search_engine.search("What is operation dulce?")

print(result.response)
result = await search_engine.search("What is operation dulce?")

print(result.response)

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[9], line 1
----> 1 result = await search_engine.search("What is operation dulce?")
      3 print(result.response)

NameError: name 'search_engine' is not defined

In [10]:

Copied!

# inspect the data used to build the context for the LLM responses
result.context_data["reports"]
# inspect the data used to build the context for the LLM responses
result.context_data["reports"]

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[10], line 2
      1 # inspect the data used to build the context for the LLM responses
----> 2 result.context_data["reports"]

NameError: name 'result' is not defined

In [11]:

Copied!





# inspect number of LLM calls and tokens
print(
    f"LLM calls: {result.llm_calls}. Prompt tokens: {result.prompt_tokens}. Output tokens: {result.output_tokens}."
)
# inspect number of LLM calls and tokens
print(
    f"LLM calls: {result.llm_calls}. Prompt tokens: {result.prompt_tokens}. Output tokens: {result.output_tokens}."
)

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[11], line 3
      1 # inspect number of LLM calls and tokens
      2 print(
----> 3     f"LLM calls: {result.llm_calls}. Prompt tokens: {result.prompt_tokens}. Output tokens: {result.output_tokens}."
      4 )

NameError: name 'result' is not defined