Local 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.query.context_builder.entity_extraction import EntityVectorStoreKey
from graphrag.query.indexer_adapters import (
    read_indexer_covariates,
    read_indexer_entities,
    read_indexer_relationships,
    read_indexer_reports,
    read_indexer_text_units,
)
from graphrag.query.question_gen.local_gen import LocalQuestionGen
from graphrag.query.structured_search.local_search.mixed_context import (
    LocalSearchMixedContext,
)
from graphrag.query.structured_search.local_search.search import LocalSearch
from graphrag.vector_stores.lancedb import LanceDBVectorStore
import os

import pandas as pd
import tiktoken

from graphrag.query.context_builder.entity_extraction import EntityVectorStoreKey
from graphrag.query.indexer_adapters import (
    read_indexer_covariates,
    read_indexer_entities,
    read_indexer_relationships,
    read_indexer_reports,
    read_indexer_text_units,
)
from graphrag.query.question_gen.local_gen import LocalQuestionGen
from graphrag.query.structured_search.local_search.mixed_context import (
    LocalSearchMixedContext,
)
from graphrag.query.structured_search.local_search.search import LocalSearch
from graphrag.vector_stores.lancedb import LanceDBVectorStore

Local Search Example¶

Local search method generates answers by combining relevant data from the AI-extracted knowledge-graph with text chunks of the raw documents. This method is suitable for questions that require an understanding of specific entities mentioned in the documents (e.g. What are the healing properties of chamomile?).

Load text units and graph data tables as context for local search¶

In this test we first load indexing outputs from parquet files to dataframes, then convert these dataframes into collections of data objects aligning with the knowledge model.

Load tables to dataframes¶

In [3]:

Copied!





INPUT_DIR = "./inputs/operation dulce"
LANCEDB_URI = f"{INPUT_DIR}/lancedb"

COMMUNITY_REPORT_TABLE = "community_reports"
ENTITY_TABLE = "entities"
COMMUNITY_TABLE = "communities"
RELATIONSHIP_TABLE = "relationships"
COVARIATE_TABLE = "covariates"
TEXT_UNIT_TABLE = "text_units"
COMMUNITY_LEVEL = 2
INPUT_DIR = "./inputs/operation dulce"
LANCEDB_URI = f"{INPUT_DIR}/lancedb"

COMMUNITY_REPORT_TABLE = "community_reports"
ENTITY_TABLE = "entities"
COMMUNITY_TABLE = "communities"
RELATIONSHIP_TABLE = "relationships"
COVARIATE_TABLE = "covariates"
TEXT_UNIT_TABLE = "text_units"
COMMUNITY_LEVEL = 2

Read entities¶

In [4]:

Copied!





# read nodes table to get community and degree data
entity_df = pd.read_parquet(f"{INPUT_DIR}/{ENTITY_TABLE}.parquet")
community_df = pd.read_parquet(f"{INPUT_DIR}/{COMMUNITY_TABLE}.parquet")

entities = read_indexer_entities(entity_df, community_df, COMMUNITY_LEVEL)

# load description embeddings to an in-memory lancedb vectorstore
# to connect to a remote db, specify url and port values.
description_embedding_store = LanceDBVectorStore(
    collection_name="default-entity-description",
)
description_embedding_store.connect(db_uri=LANCEDB_URI)

print(f"Entity count: {len(entity_df)}")
entity_df.head()
# read nodes table to get community and degree data
entity_df = pd.read_parquet(f"{INPUT_DIR}/{ENTITY_TABLE}.parquet")
community_df = pd.read_parquet(f"{INPUT_DIR}/{COMMUNITY_TABLE}.parquet")

entities = read_indexer_entities(entity_df, community_df, COMMUNITY_LEVEL)

# load description embeddings to an in-memory lancedb vectorstore
# to connect to a remote db, specify url and port values.
description_embedding_store = LanceDBVectorStore(
    collection_name="default-entity-description",
)
description_embedding_store.connect(db_uri=LANCEDB_URI)

print(f"Entity count: {len(entity_df)}")
entity_df.head()

Entity count: 18

Out[4]:

	id	human_readable_id	title	type	description	text_unit_ids	frequency	degree
0	425a7862-0aef-4f69-a4c8-8bd42151c9d4	0	ALEX MERCER	PERSON	Agent Alex Mercer is a determined individual w...	[8e938693af886bfd081acbbe8384c3671446bff84a134...	4	9
1	bcdbf1fc-0dc1-460f-bc71-2781729c96ba	1	TAYLOR CRUZ	PERSON	Agent Taylor Cruz is a commanding and authorit...	[8e938693af886bfd081acbbe8384c3671446bff84a134...	4	8
2	ef02ef24-5762-46ce-93ce-7dea6fc86595	2	JORDAN HAYES	PERSON	Dr. Jordan Hayes is a scientist and a member o...	[8e938693af886bfd081acbbe8384c3671446bff84a134...	4	9
3	8b163d27-e43a-4a2c-a26f-866778d8720e	3	SAM RIVERA	PERSON	Sam Rivera is a cybersecurity expert and a tal...	[8e938693af886bfd081acbbe8384c3671446bff84a134...	4	8
4	542aa5bd-ba2d-400a-8488-c52d50bc300d	4	PARANORMAL MILITARY SQUAD	ORGANIZATION	The PARANORMAL MILITARY SQUAD is an elite grou...	[8e938693af886bfd081acbbe8384c3671446bff84a134...	2	6

Read relationships¶

In [5]:

Copied!

relationship_df = pd.read_parquet(f"{INPUT_DIR}/{RELATIONSHIP_TABLE}.parquet")
relationships = read_indexer_relationships(relationship_df)

print(f"Relationship count: {len(relationship_df)}")
relationship_df.head()
relationship_df = pd.read_parquet(f"{INPUT_DIR}/{RELATIONSHIP_TABLE}.parquet")
relationships = read_indexer_relationships(relationship_df)

print(f"Relationship count: {len(relationship_df)}")
relationship_df.head()

Relationship count: 54

Out[5]:

	id	human_readable_id	source	target	description	weight	combined_degree	text_unit_ids
0	2bfad9f4-5abd-48d0-8db3-a9cad9120413	0	ALEX MERCER	TAYLOR CRUZ	Alex Mercer and Taylor Cruz are both agents wo...	37.0	17	[8e938693af886bfd081acbbe8384c3671446bff84a134...
1	6cbb838f-9e83-4086-a684-15c8ed709e52	1	ALEX MERCER	JORDAN HAYES	Alex Mercer and Jordan Hayes are both agents w...	42.0	18	[8e938693af886bfd081acbbe8384c3671446bff84a134...
2	bfdc25f1-80ca-477b-a304-94465b69e680	2	ALEX MERCER	SAM RIVERA	Alex Mercer and Sam Rivera are both agents and...	26.0	17	[8e938693af886bfd081acbbe8384c3671446bff84a134...
3	7a7e943d-a4f5-487b-9625-5d0907c4c26d	3	ALEX MERCER	PARANORMAL MILITARY SQUAD	Alex Mercer is a member of the Paranormal Mili...	17.0	15	[8e938693af886bfd081acbbe8384c3671446bff84a134...
4	5e00bcb9-a17e-4c27-8241-6ebb286a7fc6	4	ALEX MERCER	DULCE	Alex Mercer is preparing to lead the team into...	15.0	14	[8e938693af886bfd081acbbe8384c3671446bff84a134...

In [6]:

Copied!





# NOTE: covariates are turned off by default, because they generally need prompt tuning to be valuable
# Please see the GRAPHRAG_CLAIM_* settings
covariate_df = pd.read_parquet(f"{INPUT_DIR}/{COVARIATE_TABLE}.parquet")

claims = read_indexer_covariates(covariate_df)

print(f"Claim records: {len(claims)}")
covariates = {"claims": claims}
# NOTE: covariates are turned off by default, because they generally need prompt tuning to be valuable
# Please see the GRAPHRAG_CLAIM_* settings
covariate_df = pd.read_parquet(f"{INPUT_DIR}/{COVARIATE_TABLE}.parquet")

claims = read_indexer_covariates(covariate_df)

print(f"Claim records: {len(claims)}")
covariates = {"claims": claims}

Claim records: 17

Read community reports¶

In [7]:

Copied!

report_df = pd.read_parquet(f"{INPUT_DIR}/{COMMUNITY_REPORT_TABLE}.parquet")
reports = read_indexer_reports(report_df, community_df, COMMUNITY_LEVEL)

print(f"Report records: {len(report_df)}")
report_df.head()
report_df = pd.read_parquet(f"{INPUT_DIR}/{COMMUNITY_REPORT_TABLE}.parquet")
reports = read_indexer_reports(report_df, community_df, COMMUNITY_LEVEL)

print(f"Report records: {len(report_df)}")
report_df.head()

Report records: 2

Out[7]:

	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

Read text units¶

In [8]:

Copied!

text_unit_df = pd.read_parquet(f"{INPUT_DIR}/{TEXT_UNIT_TABLE}.parquet")
text_units = read_indexer_text_units(text_unit_df)

print(f"Text unit records: {len(text_unit_df)}")
text_unit_df.head()
text_unit_df = pd.read_parquet(f"{INPUT_DIR}/{TEXT_UNIT_TABLE}.parquet")
text_units = read_indexer_text_units(text_unit_df)

print(f"Text unit records: {len(text_unit_df)}")
text_unit_df.head()

Text unit records: 5

Out[8]:

	id	human_readable_id	text	n_tokens	document_ids	entity_ids	relationship_ids	covariate_ids
0	8e938693af886bfd081acbbe8384c3671446bff84a134a...	1	# Operation: Dulce\n\n## Chapter 1\n\nThe thru...	1200	[6e81f882f89dd5596e1925dd3ae8a4f0a0edcb55b35a8...	[425a7862-0aef-4f69-a4c8-8bd42151c9d4, bcdbf1f...	[2bfad9f4-5abd-48d0-8db3-a9cad9120413, 6cbb838...	[745d28dd-be20-411b-85ff-1c69ca70e7b3, 9cba185...
1	fd1f46d32e1df6cd429542aeda3d64ddf3745ccb80f443...	2	, the hollow echo of the bay a stark reminder ...	1200	[6e81f882f89dd5596e1925dd3ae8a4f0a0edcb55b35a8...	[425a7862-0aef-4f69-a4c8-8bd42151c9d4, bcdbf1f...	[2bfad9f4-5abd-48d0-8db3-a9cad9120413, 6cbb838...	[4f9b461f-5e8f-465d-9586-e2fc81787062, 0f74618...
2	7296d9a1f046854d59079dc183de8a054c27c4843d2979...	3	differently than praise from others. This was...	1200	[6e81f882f89dd5596e1925dd3ae8a4f0a0edcb55b35a8...	[425a7862-0aef-4f69-a4c8-8bd42151c9d4, bcdbf1f...	[2bfad9f4-5abd-48d0-8db3-a9cad9120413, 6cbb838...	[3ef1be9c-4080-4fac-99bd-c4a636248904, 8730b20...
3	ac72722a02ac71242a2a91fca323198d04197daf60515d...	4	contrast to the rigid silence enveloping the ...	1200	[6e81f882f89dd5596e1925dd3ae8a4f0a0edcb55b35a8...	[425a7862-0aef-4f69-a4c8-8bd42151c9d4, bcdbf1f...	[2bfad9f4-5abd-48d0-8db3-a9cad9120413, 6cbb838...	[2c292047-b79a-4958-ab57-7bf7d7a22c92, 3cbd18a...
4	4c277337d461a16aaf8f9760ddb8b44ef220e948a2341d...	5	a mask of duty.\n\nIn the midst of the descen...	35	[6e81f882f89dd5596e1925dd3ae8a4f0a0edcb55b35a8...	[d084d615-3584-4ec8-9931-90aa6075c764, 4b84859...	[6efdc42e-69a2-47c0-97ec-4b296cd16d5e]	[db8da02f-f889-4bb5-8e81-ab2a72e380bb]

In [9]:

Copied!





from graphrag.config.enums import ModelType
from graphrag.config.models.language_model_config import LanguageModelConfig
from graphrag.language_model.manager import ModelManager

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

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

token_encoder = tiktoken.encoding_for_model(llm_model)

embedding_config = LanguageModelConfig(
    api_key=api_key,
    type=ModelType.OpenAIEmbedding,
    model=embedding_model,
    max_retries=20,
)

text_embedder = ModelManager().get_or_create_embedding_model(
    name="local_search_embedding",
    model_type=ModelType.OpenAIEmbedding,
    config=embedding_config,
)
from graphrag.config.enums import ModelType
from graphrag.config.models.language_model_config import LanguageModelConfig
from graphrag.language_model.manager import ModelManager

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

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

token_encoder = tiktoken.encoding_for_model(llm_model)

embedding_config = LanguageModelConfig(
    api_key=api_key,
    type=ModelType.OpenAIEmbedding,
    model=embedding_model,
    max_retries=20,
)

text_embedder = ModelManager().get_or_create_embedding_model(
    name="local_search_embedding",
    model_type=ModelType.OpenAIEmbedding,
    config=embedding_config,
)

---------------------------------------------------------------------------
ValidationError                           Traceback (most recent call last)
Cell In[9], line 9
      6 llm_model = os.environ["GRAPHRAG_LLM_MODEL"]
      7 embedding_model = os.environ["GRAPHRAG_EMBEDDING_MODEL"]
----> 9 chat_config = LanguageModelConfig(
     10     api_key=api_key,
     11     type=ModelType.OpenAIChat,
     12     model=llm_model,
     13     max_retries=20,
     14 )
     15 chat_model = ModelManager().get_or_create_chat_model(
     16     name="local_search",
     17     model_type=ModelType.OpenAIChat,
     18     config=chat_config,
     19 )
     21 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

Create local search context builder¶

In [10]:

Copied!





context_builder = LocalSearchMixedContext(
    community_reports=reports,
    text_units=text_units,
    entities=entities,
    relationships=relationships,
    # if you did not run covariates during indexing, set this to None
    covariates=covariates,
    entity_text_embeddings=description_embedding_store,
    embedding_vectorstore_key=EntityVectorStoreKey.ID,  # if the vectorstore uses entity title as ids, set this to EntityVectorStoreKey.TITLE
    text_embedder=text_embedder,
    token_encoder=token_encoder,
)
context_builder = LocalSearchMixedContext(
    community_reports=reports,
    text_units=text_units,
    entities=entities,
    relationships=relationships,
    # if you did not run covariates during indexing, set this to None
    covariates=covariates,
    entity_text_embeddings=description_embedding_store,
    embedding_vectorstore_key=EntityVectorStoreKey.ID,  # if the vectorstore uses entity title as ids, set this to EntityVectorStoreKey.TITLE
    text_embedder=text_embedder,
    token_encoder=token_encoder,
)

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[10], line 10
      1 context_builder = LocalSearchMixedContext(
      2     community_reports=reports,
      3     text_units=text_units,
      4     entities=entities,
      5     relationships=relationships,
      6     # if you did not run covariates during indexing, set this to None
      7     covariates=covariates,
      8     entity_text_embeddings=description_embedding_store,
      9     embedding_vectorstore_key=EntityVectorStoreKey.ID,  # if the vectorstore uses entity title as ids, set this to EntityVectorStoreKey.TITLE
---> 10     text_embedder=text_embedder,
     11     token_encoder=token_encoder,
     12 )

NameError: name 'text_embedder' is not defined

Create local search engine¶

In [11]:

Copied!





# text_unit_prop: proportion of context window dedicated to related text units
# community_prop: proportion of context window dedicated to community reports.
# The remaining proportion is dedicated to entities and relationships. Sum of text_unit_prop and community_prop should be <= 1
# conversation_history_max_turns: maximum number of turns to include in the conversation history.
# conversation_history_user_turns_only: if True, only include user queries in the conversation history.
# top_k_mapped_entities: number of related entities to retrieve from the entity description embedding store.
# top_k_relationships: control the number of out-of-network relationships to pull into the context window.
# include_entity_rank: if True, include the entity rank in the entity table in the context window. Default entity rank = node degree.
# include_relationship_weight: if True, include the relationship weight in the context window.
# include_community_rank: if True, include the community rank in the context window.
# return_candidate_context: if True, return a set of dataframes containing all candidate entity/relationship/covariate records that
# could be relevant. Note that not all of these records will be included in the context window. The "in_context" column in these
# dataframes indicates whether the record is included in the context window.
# max_tokens: maximum number of tokens to use for the context window.


local_context_params = {
    "text_unit_prop": 0.5,
    "community_prop": 0.1,
    "conversation_history_max_turns": 5,
    "conversation_history_user_turns_only": True,
    "top_k_mapped_entities": 10,
    "top_k_relationships": 10,
    "include_entity_rank": True,
    "include_relationship_weight": True,
    "include_community_rank": False,
    "return_candidate_context": False,
    "embedding_vectorstore_key": EntityVectorStoreKey.ID,  # set this to EntityVectorStoreKey.TITLE if the vectorstore uses entity title as ids
    "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)
}

model_params = {
    "max_tokens": 2_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 1000=1500)
    "temperature": 0.0,
}
# text_unit_prop: proportion of context window dedicated to related text units
# community_prop: proportion of context window dedicated to community reports.
# The remaining proportion is dedicated to entities and relationships. Sum of text_unit_prop and community_prop should be <= 1
# conversation_history_max_turns: maximum number of turns to include in the conversation history.
# conversation_history_user_turns_only: if True, only include user queries in the conversation history.
# top_k_mapped_entities: number of related entities to retrieve from the entity description embedding store.
# top_k_relationships: control the number of out-of-network relationships to pull into the context window.
# include_entity_rank: if True, include the entity rank in the entity table in the context window. Default entity rank = node degree.
# include_relationship_weight: if True, include the relationship weight in the context window.
# include_community_rank: if True, include the community rank in the context window.
# return_candidate_context: if True, return a set of dataframes containing all candidate entity/relationship/covariate records that
# could be relevant. Note that not all of these records will be included in the context window. The "in_context" column in these
# dataframes indicates whether the record is included in the context window.
# max_tokens: maximum number of tokens to use for the context window.


local_context_params = {
    "text_unit_prop": 0.5,
    "community_prop": 0.1,
    "conversation_history_max_turns": 5,
    "conversation_history_user_turns_only": True,
    "top_k_mapped_entities": 10,
    "top_k_relationships": 10,
    "include_entity_rank": True,
    "include_relationship_weight": True,
    "include_community_rank": False,
    "return_candidate_context": False,
    "embedding_vectorstore_key": EntityVectorStoreKey.ID,  # set this to EntityVectorStoreKey.TITLE if the vectorstore uses entity title as ids
    "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)
}

model_params = {
    "max_tokens": 2_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 1000=1500)
    "temperature": 0.0,
}

In [12]:

Copied!





search_engine = LocalSearch(
    model=chat_model,
    context_builder=context_builder,
    token_encoder=token_encoder,
    model_params=model_params,
    context_builder_params=local_context_params,
    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 = LocalSearch(
    model=chat_model,
    context_builder=context_builder,
    token_encoder=token_encoder,
    model_params=model_params,
    context_builder_params=local_context_params,
    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[12], line 2
      1 search_engine = LocalSearch(
----> 2     model=chat_model,
      3     context_builder=context_builder,
      4     token_encoder=token_encoder,
      5     model_params=model_params,
      6     context_builder_params=local_context_params,
      7     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
      8 )

NameError: name 'chat_model' is not defined

Run local search on sample queries¶

In [13]:

Copied!

result = await search_engine.search("Tell me about Agent Mercer")
print(result.response)
result = await search_engine.search("Tell me about Agent Mercer")
print(result.response)

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[13], line 1
----> 1 result = await search_engine.search("Tell me about Agent Mercer")
      2 print(result.response)

NameError: name 'search_engine' is not defined

In [14]:

Copied!

question = "Tell me about Dr. Jordan Hayes"
result = await search_engine.search(question)
print(result.response)
question = "Tell me about Dr. Jordan Hayes"
result = await search_engine.search(question)
print(result.response)

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[14], line 2
      1 question = "Tell me about Dr. Jordan Hayes"
----> 2 result = await search_engine.search(question)
      3 print(result.response)

NameError: name 'search_engine' is not defined

Inspecting the context data used to generate the response¶

In [15]:

Copied!

result.context_data["entities"].head()
result.context_data["entities"].head()

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[15], line 1
----> 1 result.context_data["entities"].head()

NameError: name 'result' is not defined

In [16]:

Copied!

result.context_data["relationships"].head()
result.context_data["relationships"].head()

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[16], line 1
----> 1 result.context_data["relationships"].head()

NameError: name 'result' is not defined

In [17]:

Copied!

if "reports" in result.context_data:
    result.context_data["reports"].head()
if "reports" in result.context_data:
    result.context_data["reports"].head()

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[17], line 1
----> 1 if "reports" in result.context_data:
      2     result.context_data["reports"].head()

NameError: name 'result' is not defined

In [18]:

Copied!

result.context_data["sources"].head()
result.context_data["sources"].head()

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[18], line 1
----> 1 result.context_data["sources"].head()

NameError: name 'result' is not defined

In [19]:

Copied!

if "claims" in result.context_data:
    print(result.context_data["claims"].head())
if "claims" in result.context_data:
    print(result.context_data["claims"].head())

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[19], line 1
----> 1 if "claims" in result.context_data:
      2     print(result.context_data["claims"].head())

NameError: name 'result' is not defined

Question Generation¶

This function takes a list of user queries and generates the next candidate questions.

In [20]:

Copied!





question_generator = LocalQuestionGen(
    model=chat_model,
    context_builder=context_builder,
    token_encoder=token_encoder,
    model_params=model_params,
    context_builder_params=local_context_params,
)
question_generator = LocalQuestionGen(
    model=chat_model,
    context_builder=context_builder,
    token_encoder=token_encoder,
    model_params=model_params,
    context_builder_params=local_context_params,
)

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[20], line 2
      1 question_generator = LocalQuestionGen(
----> 2     model=chat_model,
      3     context_builder=context_builder,
      4     token_encoder=token_encoder,
      5     model_params=model_params,
      6     context_builder_params=local_context_params,
      7 )

NameError: name 'chat_model' is not defined

In [21]:

Copied!





question_history = [
    "Tell me about Agent Mercer",
    "What happens in Dulce military base?",
]
candidate_questions = await question_generator.agenerate(
    question_history=question_history, context_data=None, question_count=5
)
print(candidate_questions.response)
question_history = [
    "Tell me about Agent Mercer",
    "What happens in Dulce military base?",
]
candidate_questions = await question_generator.agenerate(
    question_history=question_history, context_data=None, question_count=5
)
print(candidate_questions.response)

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[21], line 5
      1 question_history = [
      2     "Tell me about Agent Mercer",
      3     "What happens in Dulce military base?",
      4 ]
----> 5 candidate_questions = await question_generator.agenerate(
      6     question_history=question_history, context_data=None, question_count=5
      7 )
      8 print(candidate_questions.response)

NameError: name 'question_generator' is not defined