DRIFT Search

In [1]:

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

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

In [2]:

import os
from pathlib import Path

import pandas as pd
import tiktoken

from graphrag.config.models.drift_search_config import DRIFTSearchConfig
from graphrag.query.indexer_adapters import (
    read_indexer_entities,
    read_indexer_relationships,
    read_indexer_report_embeddings,
    read_indexer_reports,
    read_indexer_text_units,
)
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.structured_search.drift_search.drift_context import (
    DRIFTSearchContextBuilder,
)
from graphrag.query.structured_search.drift_search.search import DRIFTSearch
from graphrag.vector_stores.lancedb import LanceDBVectorStore

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 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")

print(f"Entity df columns: {entity_df.columns}")

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="default-entity-description",
)
description_embedding_store.connect(db_uri=LANCEDB_URI)

full_content_embedding_store = LanceDBVectorStore(
    collection_name="default-community-full_content",
)
full_content_embedding_store.connect(db_uri=LANCEDB_URI)

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

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()

import os from pathlib import Path import pandas as pd import tiktoken from graphrag.config.models.drift_search_config import DRIFTSearchConfig from graphrag.query.indexer_adapters import ( read_indexer_entities, read_indexer_relationships, read_indexer_report_embeddings, read_indexer_reports, read_indexer_text_units, ) 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.structured_search.drift_search.drift_context import ( DRIFTSearchContextBuilder, ) from graphrag.query.structured_search.drift_search.search import DRIFTSearch from graphrag.vector_stores.lancedb import LanceDBVectorStore 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 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") print(f"Entity df columns: {entity_df.columns}") 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="default-entity-description", ) description_embedding_store.connect(db_uri=LANCEDB_URI) full_content_embedding_store = LanceDBVectorStore( collection_name="default-community-full_content", ) full_content_embedding_store.connect(db_uri=LANCEDB_URI) print(f"Entity count: {len(entity_df)}") entity_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() 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()

Entity df columns: Index(['id', 'human_readable_id', 'title', 'community', 'level', 'degree', 'x',
       'y'],
      dtype='object')
Entity count: 888
Relationship count: 812
Text unit records: 38

Out[2]:

	id	human_readable_id	text	n_tokens	document_ids	entity_ids	relationship_ids	covariate_ids
0	aa55265004ced76e9050ed4b7a45c0496e10faa0eddb8a...	1	../\nJACOB COLLIER: Honestly, I think mastery...	1200	[1e0886ae010728d10b2972f66b88608dc82b8645d3085...	[9a062709-56dd-4bf2-8b41-926124b7a6f7, f8c54a6...	[9af066c8-031b-4c52-b93b-b37763f6f0f7, 5b15580...	[f91209d1-0939-452e-b51b-be1763e2a27d, f2274c3...
1	7f0fb1d3bf517dc76dffa984eec7a25e851e44ead0df82...	2	OMBERG: I grew up and started getting into al...	1200	[1e0886ae010728d10b2972f66b88608dc82b8645d3085...	[9a062709-56dd-4bf2-8b41-926124b7a6f7, f8c54a6...	[c2ac3612-3aaf-440c-babd-e21f474e0366, 9aab0b4...	[13c74c18-439b-4419-8427-4ba826503055, 7120179...
2	27b739ceeddfa100f7be3cf002fd3a27aea2228f1a02c4...	3	, you know, and it’s a very linear pathway too...	1200	[1e0886ae010728d10b2972f66b88608dc82b8645d3085...	[9a062709-56dd-4bf2-8b41-926124b7a6f7, f8c54a6...	[9af066c8-031b-4c52-b93b-b37763f6f0f7, 5456bcb...	[a67f1c21-32ab-4eaa-b063-c815e7f3ea9d]
3	d97017305e234cc51554d653447d73b58441e1ff0f99e4...	4	you know, we started taking a lot of parts an...	1200	[1e0886ae010728d10b2972f66b88608dc82b8645d3085...	[9a062709-56dd-4bf2-8b41-926124b7a6f7, f8c54a6...	[bac3dd9b-f5c8-4966-9dc3-87f1f5976e36, 4f41be8...	[695ac017-7c10-44ad-a681-3b4c1ae86a87]
4	2b6d29f8a74b16ea9a70423bce803a08a5b9ed4e6a946b...	5	only so much processing that my mind can do i...	1200	[1e0886ae010728d10b2972f66b88608dc82b8645d3085...	[9a062709-56dd-4bf2-8b41-926124b7a6f7, f8c54a6...	[d225ff7b-ca47-4fab-8d9a-4f86111526f8, 3fddb40...	[d8a7ad5c-a170-430e-9f9d-902047371ee2]

In [3]:

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

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

token_encoder = tiktoken.encoding_for_model(llm_model)

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"] chat_llm = ChatOpenAI( api_key=api_key, model=llm_model, api_type=OpenaiApiType.OpenAI, # OpenaiApiType.OpenAI or OpenaiApiType.AzureOpenAI max_retries=20, ) token_encoder = tiktoken.encoding_for_model(llm_model) text_embedder = OpenAIEmbedding( api_key=api_key, api_base=None, api_type=OpenaiApiType.OpenAI, model=embedding_model, deployment_name=embedding_model, max_retries=20, )

In [4]:

def read_community_reports(
    input_dir: str,
    community_report_table: str = COMMUNITY_REPORT_TABLE,
):
    """Embeds the full content of the community reports and saves the DataFrame with embeddings to the output path."""
    input_path = Path(input_dir) / f"{community_report_table}.parquet"
    return pd.read_parquet(input_path)


report_df = read_community_reports(INPUT_DIR)
reports = read_indexer_reports(
    report_df,
    entity_df,
    COMMUNITY_LEVEL,
    content_embedding_col="full_content_embeddings",
)
read_indexer_report_embeddings(reports, full_content_embedding_store)

def read_community_reports( input_dir: str, community_report_table: str = COMMUNITY_REPORT_TABLE, ): """Embeds the full content of the community reports and saves the DataFrame with embeddings to the output path.""" input_path = Path(input_dir) / f"{community_report_table}.parquet" return pd.read_parquet(input_path) report_df = read_community_reports(INPUT_DIR) reports = read_indexer_reports( report_df, entity_df, COMMUNITY_LEVEL, content_embedding_col="full_content_embeddings", ) read_indexer_report_embeddings(reports, full_content_embedding_store)

In [5]:

drift_params = DRIFTSearchConfig(
    temperature=0,
    max_tokens=12_000,
    primer_folds=1,
    drift_k_followups=3,
    n_depth=3,
    n=1,
)

context_builder = DRIFTSearchContextBuilder(
    chat_llm=chat_llm,
    text_embedder=text_embedder,
    entities=entities,
    relationships=relationships,
    reports=reports,
    entity_text_embeddings=description_embedding_store,
    text_units=text_units,
    token_encoder=token_encoder,
    config=drift_params,
)

search = DRIFTSearch(
    llm=chat_llm, context_builder=context_builder, token_encoder=token_encoder
)

drift_params = DRIFTSearchConfig( temperature=0, max_tokens=12_000, primer_folds=1, drift_k_followups=3, n_depth=3, n=1, ) context_builder = DRIFTSearchContextBuilder( chat_llm=chat_llm, text_embedder=text_embedder, entities=entities, relationships=relationships, reports=reports, entity_text_embeddings=description_embedding_store, text_units=text_units, token_encoder=token_encoder, config=drift_params, ) search = DRIFTSearch( llm=chat_llm, context_builder=context_builder, token_encoder=token_encoder )

In [6]:

resp = await search.asearch("Who is agent Mercer?")

resp = await search.asearch("Who is agent Mercer?")

---------------------------------------------------------------------------
RateLimitError                            Traceback (most recent call last)
Cell In[6], line 1
----> 1 resp = await search.asearch("Who is agent Mercer?")

File ~/work/graphrag/graphrag/graphrag/query/structured_search/drift_search/search.py:203, in DRIFTSearch.asearch(self, query, conversation_history, reduce, **kwargs)
    200 # Check if query state is empty
    201 if not self.query_state.graph:
    202     # Prime the search with the primer
--> 203     primer_context, token_ct = self.context_builder.build_context(query)
    204     llm_calls["build_context"] = token_ct["llm_calls"]
    205     prompt_tokens["build_context"] = token_ct["prompt_tokens"]

File ~/work/graphrag/graphrag/graphrag/query/structured_search/drift_search/drift_context.py:200, in DRIFTSearchContextBuilder.build_context(self, query, **kwargs)
    191     raise ValueError(missing_reports_error)
    193 query_processor = PrimerQueryProcessor(
    194     chat_llm=self.chat_llm,
    195     text_embedder=self.text_embedder,
    196     token_encoder=self.token_encoder,
    197     reports=self.reports,
    198 )
--> 200 query_embedding, token_ct = query_processor(query)
    202 report_df = self.convert_reports_to_df(self.reports)
    204 # Check compatibility between query embedding and document embeddings

File ~/work/graphrag/graphrag/graphrag/query/structured_search/drift_search/primer.py:97, in PrimerQueryProcessor.__call__(self, query)
     86 def __call__(self, query: str) -> tuple[list[float], dict[str, int]]:
     87     """
     88     Call method to process the query, expand it, and embed the result.
     89 
   (...)
     95     tuple[list[float], int]: List of embeddings for the expanded query and the token count.
     96     """
---> 97     hyde_query, token_ct = self.expand_query(query)
     98     log.info("Expanded query: %s", hyde_query)
     99     return self.text_embedder.embed(hyde_query), token_ct

File ~/work/graphrag/graphrag/graphrag/query/structured_search/drift_search/primer.py:73, in PrimerQueryProcessor.expand_query(self, query)
     66 prompt = f"""Create a hypothetical answer to the following query: {query}\n\n
     67           Format it to follow the structure of the template below:\n\n
     68           {template}\n"
     69           Ensure that the hypothetical answer does not reference new named entities that are not present in the original query."""
     71 messages = [{"role": "user", "content": prompt}]
---> 73 text = self.chat_llm.generate(messages)
     74 prompt_tokens = num_tokens(prompt, self.token_encoder)
     75 output_tokens = num_tokens(text, self.token_encoder)

File ~/work/graphrag/graphrag/graphrag/query/llm/oai/chat_openai.py:78, in ChatOpenAI.generate(self, messages, streaming, callbacks, **kwargs)
     71 try:
     72     retryer = Retrying(
     73         stop=stop_after_attempt(self.max_retries),
     74         wait=wait_exponential_jitter(max=10),
     75         reraise=True,
     76         retry=retry_if_exception_type(self.retry_error_types),
     77     )
---> 78     for attempt in retryer:
     79         with attempt:
     80             return self._generate(
     81                 messages=messages,
     82                 streaming=streaming,
     83                 callbacks=callbacks,
     84                 **kwargs,
     85             )

File ~/.cache/pypoetry/virtualenvs/graphrag-F2jvqev7-py3.11/lib/python3.11/site-packages/tenacity/__init__.py:443, in BaseRetrying.__iter__(self)
    441 retry_state = RetryCallState(self, fn=None, args=(), kwargs={})
    442 while True:
--> 443     do = self.iter(retry_state=retry_state)
    444     if isinstance(do, DoAttempt):
    445         yield AttemptManager(retry_state=retry_state)

File ~/.cache/pypoetry/virtualenvs/graphrag-F2jvqev7-py3.11/lib/python3.11/site-packages/tenacity/__init__.py:376, in BaseRetrying.iter(self, retry_state)
    374 result = None
    375 for action in self.iter_state.actions:
--> 376     result = action(retry_state)
    377 return result

File ~/.cache/pypoetry/virtualenvs/graphrag-F2jvqev7-py3.11/lib/python3.11/site-packages/tenacity/__init__.py:418, in BaseRetrying._post_stop_check_actions.<locals>.exc_check(rs)
    416 retry_exc = self.retry_error_cls(fut)
    417 if self.reraise:
--> 418     raise retry_exc.reraise()
    419 raise retry_exc from fut.exception()

File ~/.cache/pypoetry/virtualenvs/graphrag-F2jvqev7-py3.11/lib/python3.11/site-packages/tenacity/__init__.py:185, in RetryError.reraise(self)
    183 def reraise(self) -> t.NoReturn:
    184     if self.last_attempt.failed:
--> 185         raise self.last_attempt.result()
    186     raise self

File /opt/hostedtoolcache/Python/3.11.11/x64/lib/python3.11/concurrent/futures/_base.py:449, in Future.result(self, timeout)
    447     raise CancelledError()
    448 elif self._state == FINISHED:
--> 449     return self.__get_result()
    451 self._condition.wait(timeout)
    453 if self._state in [CANCELLED, CANCELLED_AND_NOTIFIED]:

File /opt/hostedtoolcache/Python/3.11.11/x64/lib/python3.11/concurrent/futures/_base.py:401, in Future.__get_result(self)
    399 if self._exception:
    400     try:
--> 401         raise self._exception
    402     finally:
    403         # Break a reference cycle with the exception in self._exception
    404         self = None

File ~/work/graphrag/graphrag/graphrag/query/llm/oai/chat_openai.py:80, in ChatOpenAI.generate(self, messages, streaming, callbacks, **kwargs)
     78     for attempt in retryer:
     79         with attempt:
---> 80             return self._generate(
     81                 messages=messages,
     82                 streaming=streaming,
     83                 callbacks=callbacks,
     84                 **kwargs,
     85             )
     86 except RetryError as e:
     87     self._reporter.error(
     88         message="Error at generate()", details={self.__class__.__name__: str(e)}
     89     )

File ~/work/graphrag/graphrag/graphrag/query/llm/oai/chat_openai.py:196, in ChatOpenAI._generate(self, messages, streaming, callbacks, **kwargs)
    194 if not model:
    195     raise ValueError(_MODEL_REQUIRED_MSG)
--> 196 response = self.sync_client.chat.completions.create(  # type: ignore
    197     model=model,
    198     messages=messages,  # type: ignore
    199     stream=streaming,
    200     **kwargs,
    201 )  # type: ignore
    202 if streaming:
    203     full_response = ""

File ~/.cache/pypoetry/virtualenvs/graphrag-F2jvqev7-py3.11/lib/python3.11/site-packages/openai/_utils/_utils.py:279, in required_args.<locals>.inner.<locals>.wrapper(*args, **kwargs)
    277             msg = f"Missing required argument: {quote(missing[0])}"
    278     raise TypeError(msg)
--> 279 return func(*args, **kwargs)

File ~/.cache/pypoetry/virtualenvs/graphrag-F2jvqev7-py3.11/lib/python3.11/site-packages/openai/resources/chat/completions.py:859, in Completions.create(self, messages, model, audio, frequency_penalty, function_call, functions, logit_bias, logprobs, max_completion_tokens, max_tokens, metadata, modalities, n, parallel_tool_calls, prediction, presence_penalty, reasoning_effort, response_format, seed, service_tier, stop, store, stream, stream_options, temperature, tool_choice, tools, top_logprobs, top_p, user, extra_headers, extra_query, extra_body, timeout)
    817 @required_args(["messages", "model"], ["messages", "model", "stream"])
    818 def create(
    819     self,
   (...)
    856     timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
    857 ) -> ChatCompletion | Stream[ChatCompletionChunk]:
    858     validate_response_format(response_format)
--> 859     return self._post(
    860         "/chat/completions",
    861         body=maybe_transform(
    862             {
    863                 "messages": messages,
    864                 "model": model,
    865                 "audio": audio,
    866                 "frequency_penalty": frequency_penalty,
    867                 "function_call": function_call,
    868                 "functions": functions,
    869                 "logit_bias": logit_bias,
    870                 "logprobs": logprobs,
    871                 "max_completion_tokens": max_completion_tokens,
    872                 "max_tokens": max_tokens,
    873                 "metadata": metadata,
    874                 "modalities": modalities,
    875                 "n": n,
    876                 "parallel_tool_calls": parallel_tool_calls,
    877                 "prediction": prediction,
    878                 "presence_penalty": presence_penalty,
    879                 "reasoning_effort": reasoning_effort,
    880                 "response_format": response_format,
    881                 "seed": seed,
    882                 "service_tier": service_tier,
    883                 "stop": stop,
    884                 "store": store,
    885                 "stream": stream,
    886                 "stream_options": stream_options,
    887                 "temperature": temperature,
    888                 "tool_choice": tool_choice,
    889                 "tools": tools,
    890                 "top_logprobs": top_logprobs,
    891                 "top_p": top_p,
    892                 "user": user,
    893             },
    894             completion_create_params.CompletionCreateParams,
    895         ),
    896         options=make_request_options(
    897             extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
    898         ),
    899         cast_to=ChatCompletion,
    900         stream=stream or False,
    901         stream_cls=Stream[ChatCompletionChunk],
    902     )

File ~/.cache/pypoetry/virtualenvs/graphrag-F2jvqev7-py3.11/lib/python3.11/site-packages/openai/_base_client.py:1283, in SyncAPIClient.post(self, path, cast_to, body, options, files, stream, stream_cls)
   1269 def post(
   1270     self,
   1271     path: str,
   (...)
   1278     stream_cls: type[_StreamT] | None = None,
   1279 ) -> ResponseT | _StreamT:
   1280     opts = FinalRequestOptions.construct(
   1281         method="post", url=path, json_data=body, files=to_httpx_files(files), **options
   1282     )
-> 1283     return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))

File ~/.cache/pypoetry/virtualenvs/graphrag-F2jvqev7-py3.11/lib/python3.11/site-packages/openai/_base_client.py:960, in SyncAPIClient.request(self, cast_to, options, remaining_retries, stream, stream_cls)
    957 else:
    958     retries_taken = 0
--> 960 return self._request(
    961     cast_to=cast_to,
    962     options=options,
    963     stream=stream,
    964     stream_cls=stream_cls,
    965     retries_taken=retries_taken,
    966 )

File ~/.cache/pypoetry/virtualenvs/graphrag-F2jvqev7-py3.11/lib/python3.11/site-packages/openai/_base_client.py:1049, in SyncAPIClient._request(self, cast_to, options, retries_taken, stream, stream_cls)
   1047 if remaining_retries > 0 and self._should_retry(err.response):
   1048     err.response.close()
-> 1049     return self._retry_request(
   1050         input_options,
   1051         cast_to,
   1052         retries_taken=retries_taken,
   1053         response_headers=err.response.headers,
   1054         stream=stream,
   1055         stream_cls=stream_cls,
   1056     )
   1058 # If the response is streamed then we need to explicitly read the response
   1059 # to completion before attempting to access the response text.
   1060 if not err.response.is_closed:

File ~/.cache/pypoetry/virtualenvs/graphrag-F2jvqev7-py3.11/lib/python3.11/site-packages/openai/_base_client.py:1098, in SyncAPIClient._retry_request(self, options, cast_to, retries_taken, response_headers, stream, stream_cls)
   1094 # In a synchronous context we are blocking the entire thread. Up to the library user to run the client in a
   1095 # different thread if necessary.
   1096 time.sleep(timeout)
-> 1098 return self._request(
   1099     options=options,
   1100     cast_to=cast_to,
   1101     retries_taken=retries_taken + 1,
   1102     stream=stream,
   1103     stream_cls=stream_cls,
   1104 )

File ~/.cache/pypoetry/virtualenvs/graphrag-F2jvqev7-py3.11/lib/python3.11/site-packages/openai/_base_client.py:1049, in SyncAPIClient._request(self, cast_to, options, retries_taken, stream, stream_cls)
   1047 if remaining_retries > 0 and self._should_retry(err.response):
   1048     err.response.close()
-> 1049     return self._retry_request(
   1050         input_options,
   1051         cast_to,
   1052         retries_taken=retries_taken,
   1053         response_headers=err.response.headers,
   1054         stream=stream,
   1055         stream_cls=stream_cls,
   1056     )
   1058 # If the response is streamed then we need to explicitly read the response
   1059 # to completion before attempting to access the response text.
   1060 if not err.response.is_closed:

File ~/.cache/pypoetry/virtualenvs/graphrag-F2jvqev7-py3.11/lib/python3.11/site-packages/openai/_base_client.py:1098, in SyncAPIClient._retry_request(self, options, cast_to, retries_taken, response_headers, stream, stream_cls)
   1094 # In a synchronous context we are blocking the entire thread. Up to the library user to run the client in a
   1095 # different thread if necessary.
   1096 time.sleep(timeout)
-> 1098 return self._request(
   1099     options=options,
   1100     cast_to=cast_to,
   1101     retries_taken=retries_taken + 1,
   1102     stream=stream,
   1103     stream_cls=stream_cls,
   1104 )

    [... skipping similar frames: SyncAPIClient._request at line 1049 (17 times), SyncAPIClient._retry_request at line 1098 (17 times)]

File ~/.cache/pypoetry/virtualenvs/graphrag-F2jvqev7-py3.11/lib/python3.11/site-packages/openai/_base_client.py:1049, in SyncAPIClient._request(self, cast_to, options, retries_taken, stream, stream_cls)
   1047 if remaining_retries > 0 and self._should_retry(err.response):
   1048     err.response.close()
-> 1049     return self._retry_request(
   1050         input_options,
   1051         cast_to,
   1052         retries_taken=retries_taken,
   1053         response_headers=err.response.headers,
   1054         stream=stream,
   1055         stream_cls=stream_cls,
   1056     )
   1058 # If the response is streamed then we need to explicitly read the response
   1059 # to completion before attempting to access the response text.
   1060 if not err.response.is_closed:

File ~/.cache/pypoetry/virtualenvs/graphrag-F2jvqev7-py3.11/lib/python3.11/site-packages/openai/_base_client.py:1098, in SyncAPIClient._retry_request(self, options, cast_to, retries_taken, response_headers, stream, stream_cls)
   1094 # In a synchronous context we are blocking the entire thread. Up to the library user to run the client in a
   1095 # different thread if necessary.
   1096 time.sleep(timeout)
-> 1098 return self._request(
   1099     options=options,
   1100     cast_to=cast_to,
   1101     retries_taken=retries_taken + 1,
   1102     stream=stream,
   1103     stream_cls=stream_cls,
   1104 )

File ~/.cache/pypoetry/virtualenvs/graphrag-F2jvqev7-py3.11/lib/python3.11/site-packages/openai/_base_client.py:1064, in SyncAPIClient._request(self, cast_to, options, retries_taken, stream, stream_cls)
   1061         err.response.read()
   1063     log.debug("Re-raising status error")
-> 1064     raise self._make_status_error_from_response(err.response) from None
   1066 return self._process_response(
   1067     cast_to=cast_to,
   1068     options=options,
   (...)
   1072     retries_taken=retries_taken,
   1073 )

RateLimitError: Error code: 429 - {'error': {'message': 'You exceeded your current quota, please check your plan and billing details. For more information on this error, read the docs: https://platform.openai.com/docs/guides/error-codes/api-errors.', 'type': 'insufficient_quota', 'param': None, 'code': 'insufficient_quota'}}

In [7]:

resp.response

resp.response

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[7], line 1
----> 1 resp.response

NameError: name 'resp' is not defined

In [8]:

resp.response["nodes"][0]["answer"]

resp.response["nodes"][0]["answer"]

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[8], line 1
----> 1 resp.response["nodes"][0]["answer"]

NameError: name 'resp' is not defined