本地搜索

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.input.loaders.dfs import (
    store_entity_semantic_embeddings,
)
from graphrag.query.llm.oai.chat_openai import ChatOpenAI
from graphrag.query.llm.oai.embedding import OpenAIEmbedding
from graphrag.query.llm.oai.typing import OpenaiApiType
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.input.loaders.dfs import (
    store_entity_semantic_embeddings,
)
from graphrag.query.llm.oai.chat_openai import ChatOpenAI
from graphrag.query.llm.oai.embedding import OpenAIEmbedding
from graphrag.query.llm.oai.typing import OpenaiApiType
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 = "create_final_community_reports"
ENTITY_TABLE = "create_final_nodes"
ENTITY_EMBEDDING_TABLE = "create_final_entities"
RELATIONSHIP_TABLE = "create_final_relationships"
COVARIATE_TABLE = "create_final_covariates"
TEXT_UNIT_TABLE = "create_final_text_units"
COMMUNITY_LEVEL = 2
INPUT_DIR = "./inputs/operation dulce"
LANCEDB_URI = f"{INPUT_DIR}/lancedb"

COMMUNITY_REPORT_TABLE = "create_final_community_reports"
ENTITY_TABLE = "create_final_nodes"
ENTITY_EMBEDDING_TABLE = "create_final_entities"
RELATIONSHIP_TABLE = "create_final_relationships"
COVARIATE_TABLE = "create_final_covariates"
TEXT_UNIT_TABLE = "create_final_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")
entity_embedding_df = pd.read_parquet(f"{INPUT_DIR}/{ENTITY_EMBEDDING_TABLE}.parquet")

entities = read_indexer_entities(entity_df, entity_embedding_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="entity_description_embeddings",
)
description_embedding_store.connect(db_uri=LANCEDB_URI)
entity_description_embeddings = store_entity_semantic_embeddings(
    entities=entities, vectorstore=description_embedding_store
)

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")
entity_embedding_df = pd.read_parquet(f"{INPUT_DIR}/{ENTITY_EMBEDDING_TABLE}.parquet")

entities = read_indexer_entities(entity_df, entity_embedding_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="entity_description_embeddings",
)
description_embedding_store.connect(db_uri=LANCEDB_URI)
entity_description_embeddings = store_entity_semantic_embeddings(
    entities=entities, vectorstore=description_embedding_store
)

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

Entity count: 434

Out[4]:

	title	type	description	source_id	community	degree	human_readable_id	id	size	graph_embedding	entity_type	top_level_node_id
0	ALEX MERCER	PERSON	Alex Mercer is a character with a military bac...	00fafabae48948779fee2afe600f5143,1e433d6b30887...	1	9	0	b45241d70f0e43fca764df95b2b81f77	9	None	None	b45241d70f0e43fca764df95b2b81f77
1	TAYLOR CRUZ	PERSON	Taylor Cruz is a character who plays a pivotal...	00fafabae48948779fee2afe600f5143,1e433d6b30887...	1	12	1	4119fd06010c494caa07f439b333f4c5	12	None	None	4119fd06010c494caa07f439b333f4c5
2	JORDAN HAYES	PERSON	Dr. Jordan Hayes is a key character in a narra...	00fafabae48948779fee2afe600f5143,2cf7a230c367a...	1	9	2	d3835bf3dda84ead99deadbeac5d0d7d	9	None	None	d3835bf3dda84ead99deadbeac5d0d7d
3	SAM RIVERA	PERSON	Sam Rivera is a character renowned for their t...	00fafabae48948779fee2afe600f5143,1e433d6b30887...	1	15	3	077d2820ae1845bcbb1803379a3d1eae	15	None	None	077d2820ae1845bcbb1803379a3d1eae
4	PARANORMAL MILITARY SQUAD	ORGANIZATION	The Paranormal Military Squad is an elite clan...	00fafabae48948779fee2afe600f5143,1e433d6b30887...	1	14	4	3671ea0dd4e84c1a9b02c5ab2c8f4bac	14	None	None	3671ea0dd4e84c1a9b02c5ab2c8f4bac

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: 276

Out[5]:

	source	target	weight	description	text_unit_ids	id	human_readable_id	source_degree	target_degree	rank
0	ALEX MERCER	TAYLOR CRUZ	7.0	Alex Mercer and Taylor Cruz are integral membe...	[00fafabae48948779fee2afe600f5143, 1e433d6b308...	b35c3d1a7daa4924b6bdb58bc69c354d	0	9	12	21
1	ALEX MERCER	TAYLOR CRUZ	7.0	Alex Mercer and Taylor Cruz are integral membe...	[00fafabae48948779fee2afe600f5143, 1e433d6b308...	b35c3d1a7daa4924b6bdb58bc69c354d	0	9	12	21
2	ALEX MERCER	TAYLOR CRUZ	7.0	Alex Mercer and Taylor Cruz are integral membe...	[00fafabae48948779fee2afe600f5143, 1e433d6b308...	b35c3d1a7daa4924b6bdb58bc69c354d	0	9	12	21
3	ALEX MERCER	TAYLOR CRUZ	7.0	Alex Mercer and Taylor Cruz are integral membe...	[00fafabae48948779fee2afe600f5143, 1e433d6b308...	b35c3d1a7daa4924b6bdb58bc69c354d	0	9	12	21
4	ALEX MERCER	JORDAN HAYES	6.0	Alex Mercer and Jordan Hayes are colleagues wh...	[00fafabae48948779fee2afe600f5143, 2cf7a230c36...	a97e2ecd870944cfbe71c79bc0fcc752	1	9	9	18

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: 89

Read community reports¶

In [7]:

Copied!

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

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

Report records: 6

Out[7]:

	community	full_content	level	rank	title	rank_explanation	summary	findings	full_content_json	id
0	4	# Dulce Base and the Paranormal Military Squad...	1	8.5	Dulce Base and the Paranormal Military Squad: ...	The impact severity rating is high due to the ...	The community is centered around Dulce Base, a...	[{'explanation': 'Dulce Base is the primary lo...	{\n "title": "Dulce Base and the Paranormal...	6f8ba6b6-506e-46c1-83ce-982d59622554
1	5	# Sam Rivera and the Paranormal Military Squad...	1	7.5	Sam Rivera and the Paranormal Military Squad a...	The impact severity rating is high due to the ...	The community is centered around Sam Rivera, a...	[{'explanation': 'Sam Rivera is recognized for...	{\n "title": "Sam Rivera and the Paranormal...	418f4536-d673-4212-8a7c-ca1aac547d0f
2	0	# Dulce Base and the Paranormal Military Squad...	0	8.5	Dulce Base and the Paranormal Military Squad Team	The impact severity rating is high due to the ...	Dulce Base serves as the operational hub for t...	[{'explanation': 'The Paranormal Military Squa...	{\n "title": "Dulce Base and the Paranormal...	251df57e-fd49-49a7-b262-ccaff95d7a51
3	1	# Dulce Base and the Paranormal Military Squad...	0	8.5	Dulce Base and the Paranormal Military Squad: ...	The impact severity rating is high due to the ...	The community is centered around Dulce Base, a...	[{'explanation': 'Sam Rivera is recognized for...	{\n "title": "Dulce Base and the Paranormal...	6e536385-8056-4a82-8670-c0ccaf007fb4
4	2	# Dulce Base: Extraterrestrial Research and Co...	0	8.5	Dulce Base: Extraterrestrial Research and Comm...	The impact severity rating is high due to the ...	Dulce Base is a highly classified facility in ...	[{'explanation': 'Dulce Base is the epicenter ...	{\n "title": "Dulce Base: Extraterrestrial ...	660c8fba-b65f-4fcd-9c98-203600cf1981

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: 12

Out[8]:

	id	text	n_tokens	document_ids	entity_ids	relationship_ids	covariate_ids
0	2cf7a230c367a2dfaf0fc3c903eb8948	# Operation: Dulce\n\n## Chapter 1\n\nThe thru...	2500	[958fdd043f17ade63cb13570b59df295]	[b45241d70f0e43fca764df95b2b81f77, 4119fd06010...	[b35c3d1a7daa4924b6bdb58bc69c354d, a97e2ecd870...	[ad5a2020-cdec-4982-acdf-dbe5ee530066, 9d8a0fe...
1	6d1255303acb7c9dc951cb0f5fc3042c	be the same.\n\n\*\n\nThe sense of foreboding...	2500	[958fdd043f17ade63cb13570b59df295]	[b45241d70f0e43fca764df95b2b81f77, 4119fd06010...	[b35c3d1a7daa4924b6bdb58bc69c354d, a97e2ecd870...	[5d1c9126-c48d-4755-9f9c-f739c823f95f, ec64a42...
2	e841f178310356740b2ee9101d12c97f	. "Your take on these signal inconsistencies?"...	2500	[958fdd043f17ade63cb13570b59df295]	[b45241d70f0e43fca764df95b2b81f77, 4119fd06010...	[b35c3d1a7daa4924b6bdb58bc69c354d, a97e2ecd870...	[0b22a34b-32e9-46a4-a0e8-d3d5466eba15, 7e14972...
3	f36d96862b9366d7240b5c7ceb04f12b	, absorbed in the bewilderment of contact, whi...	2500	[958fdd043f17ade63cb13570b59df295]	[b45241d70f0e43fca764df95b2b81f77, 4119fd06010...	[b35c3d1a7daa4924b6bdb58bc69c354d, 09f18f81442...	[9cd6d645-ab97-4b39-b02e-647cea9b5545, 50dc124...
4	f7d43808d2fb452cd953bf50c6de6bd4	were at once coherent and enigmatic: "*Voyage...	2500	[958fdd043f17ade63cb13570b59df295]	[b45241d70f0e43fca764df95b2b81f77, 4119fd06010...	[e02be3e37ca0454883a4c1fd859c24bb, 1dbc51475cb...	[87cf5900-6211-4e04-9115-50f3617c88b4]

In [9]:

Copied!





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

llm = ChatOpenAI(
    api_key=api_key,
    model=llm_model,
    api_type=OpenaiApiType.OpenAI,  # OpenaiApiType.OpenAI or OpenaiApiType.AzureOpenAI
    max_retries=20,
)

token_encoder = tiktoken.get_encoding("cl100k_base")

text_embedder = OpenAIEmbedding(
    api_key=api_key,
    api_base=None,
    api_type=OpenaiApiType.OpenAI,
    model=embedding_model,
    deployment_name=embedding_model,
    max_retries=20,
)
api_key = os.environ["GRAPHRAG_API_KEY"]
llm_model = os.environ["GRAPHRAG_LLM_MODEL"]
embedding_model = os.environ["GRAPHRAG_EMBEDDING_MODEL"]

llm = ChatOpenAI(
    api_key=api_key,
    model=llm_model,
    api_type=OpenaiApiType.OpenAI,  # OpenaiApiType.OpenAI or OpenaiApiType.AzureOpenAI
    max_retries=20,
)

token_encoder = tiktoken.get_encoding("cl100k_base")

text_embedder = OpenAIEmbedding(
    api_key=api_key,
    api_base=None,
    api_type=OpenaiApiType.OpenAI,
    model=embedding_model,
    deployment_name=embedding_model,
    max_retries=20,
)

---------------------------------------------------------------------------
KeyError                                  Traceback (most recent call last)
Cell In[9], line 1
----> 1 api_key = os.environ["GRAPHRAG_API_KEY"]
      2 llm_model = os.environ["GRAPHRAG_LLM_MODEL"]
      3 embedding_model = os.environ["GRAPHRAG_EMBEDDING_MODEL"]

File <frozen os>:679, in __getitem__(self, key)

KeyError: 'GRAPHRAG_API_KEY'

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)
}

llm_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)
}

llm_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(
    llm=llm,
    context_builder=context_builder,
    token_encoder=token_encoder,
    llm_params=llm_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(
    llm=llm,
    context_builder=context_builder,
    token_encoder=token_encoder,
    llm_params=llm_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     llm=llm,
      3     context_builder=context_builder,
      4     token_encoder=token_encoder,
      5     llm_params=llm_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 'llm' is not defined

Run local search on sample queries¶

In [13]:

Copied!

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

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[13], line 1
----> 1 result = await search_engine.asearch("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.asearch(question)
print(result.response)
question = "Tell me about Dr. Jordan Hayes"
result = await search_engine.asearch(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.asearch(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!

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

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[17], line 1
----> 1 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(
    llm=llm,
    context_builder=context_builder,
    token_encoder=token_encoder,
    llm_params=llm_params,
    context_builder_params=local_context_params,
)
question_generator = LocalQuestionGen(
    llm=llm,
    context_builder=context_builder,
    token_encoder=token_encoder,
    llm_params=llm_params,
    context_builder_params=local_context_params,
)

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

NameError: name 'llm' 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