Confirm this is an issue with the Python library and not an underlying OpenAI API

• This is an issue with the Python library

Describe the bug

我用from openai import OpenAI这个库访问时候回复速度很快，但是我在利用llamaindex来结合gpt与模型时候，queryengine.query（）这个语句就会报错openai.APITimeoutError: Request timed，以下是我的报错信息：
03/05/2024 16:42:02 - [INFO] -openai._base_client->>> Retrying request to /chat/completions in 0.859262 seconds
03/05/2024 16:42:23 - [INFO] -openai._base_client->>> Retrying request to /chat/completions in 1.629988 seconds
03/05/2024 16:42:46 - [INFO] -openai._base_client->>> Retrying request to /chat/completions in 3.447563 seconds
Traceback (most recent call last):
File "C:\Users\590\anaconda3\envs\bce\lib\site-packages\httpx_transports\default.py", line 69, in map_httpcore_exceptions
yield
File "C:\Users\590\anaconda3\envs\bce\lib\site-packages\httpx_transports\default.py", line 233, in handle_request
resp = self._pool.handle_request(req)
File "C:\Users\590\anaconda3\envs\bce\lib\site-packages\httpcore_sync\connection_pool.py", line 216, in handle_request
raise exc from None
File "C:\Users\590\anaconda3\envs\bce\lib\site-packages\httpcore_sync\connection_pool.py", line 196, in handle_request
response = connection.handle_request(
File "C:\Users\590\anaconda3\envs\bce\lib\site-packages\httpcore_sync\connection.py", line 99, in handle_request
raise exc
File "C:\Users\590\anaconda3\envs\bce\lib\site-packages\httpcore_sync\connection.py", line 76, in handle_request
stream = self._connect(request)
File "C:\Users\590\anaconda3\envs\bce\lib\site-packages\httpcore_sync\connection.py", line 122, in _connect
stream = self._network_backend.connect_tcp(**kwargs)
File "C:\Users\590\anaconda3\envs\bce\lib\site-packages\httpcore_backends\sync.py", line 205, in connect_tcp
with map_exceptions(exc_map):
File "C:\Users\590\anaconda3\envs\bce\lib\contextlib.py", line 153, in exit
self.gen.throw(typ, value, traceback)
File "C:\Users\590\anaconda3\envs\bce\lib\site-packages\httpcore_exceptions.py", line 14, in map_exceptions
raise to_exc(exc) from exc
httpcore.ConnectTimeout: [WinError 10060] 由于连接方在一段时间后没有正确答复或连接的主机没有反应，连接尝试失败。

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "C:\Users\590\anaconda3\envs\bce\lib\site-packages\openai_base_client.py", line 918, in _request
response = self._client.send(
File "C:\Users\590\anaconda3\envs\bce\lib\site-packages\httpx_client.py", line 914, in send
response = self._send_handling_auth(
File "C:\Users\590\anaconda3\envs\bce\lib\site-packages\httpx_client.py", line 942, in _send_handling_auth
response = self._send_handling_redirects(
File "C:\Users\590\anaconda3\envs\bce\lib\site-packages\httpx_client.py", line 979, in _send_handling_redirects
response = self._send_single_request(request)
File "C:\Users\590\anaconda3\envs\bce\lib\site-packages\httpx_client.py", line 1015, in _send_single_request
response = transport.handle_request(request)
File "C:\Users\590\anaconda3\envs\bce\lib\site-packages\httpx_transports\default.py", line 232, in handle_request
with map_httpcore_exceptions():
File "C:\Users\590\anaconda3\envs\bce\lib\contextlib.py", line 153, in exit
self.gen.throw(typ, value, traceback)
File "C:\Users\590\anaconda3\envs\bce\lib\site-packages\httpx_transports\default.py", line 86, in map_httpcore_exceptions
raise mapped_exc(message) from exc
httpx.ConnectTimeout: [WinError 10060] 由于连接方在一段时间后没有正确答复或连接的主机没有反应，连接尝试失败。

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "D:\BCE\pycharmcode\test2.py", line 51, in
query_response = query_engine.query(query)
File "C:\Users\590\anaconda3\envs\bce\lib\site-packages\llama_index\core\base_query_engine.py", line 40, in query
return self._query(str_or_query_bundle)
File "C:\Users\590\anaconda3\envs\bce\lib\site-packages\llama_index\query_engine\retriever_query_engine.py", line 172, in _query
response = self._response_synthesizer.synthesize(
File "C:\Users\590\anaconda3\envs\bce\lib\site-packages\llama_index\response_synthesizers\base.py", line 168, in synthesize
response_str = self.get_response(
File "C:\Users\590\anaconda3\envs\bce\lib\site-packages\llama_index\response_synthesizers\compact_and_refine.py", line 38, in get_response
return super().get_response(
File "C:\Users\590\anaconda3\envs\bce\lib\site-packages\llama_index\response_synthesizers\refine.py", line 146, in get_response
response = self._give_response_single(
File "C:\Users\590\anaconda3\envs\bce\lib\site-packages\llama_index\response_synthesizers\refine.py", line 202, in _give_response_single
program(
File "C:\Users\590\anaconda3\envs\bce\lib\site-packages\llama_index\response_synthesizers\refine.py", line 64, in call
answer = self._llm.predict(
File "C:\Users\590\anaconda3\envs\bce\lib\site-packages\llama_index\llms\llm.py", line 239, in predict
chat_response = self.chat(messages)
File "C:\Users\590\anaconda3\envs\bce\lib\site-packages\llama_index\llms\base.py", line 100, in wrapped_llm_chat
f_return_val = f(_self, messages, **kwargs)
File "C:\Users\590\anaconda3\envs\bce\lib\site-packages\llama_index\llms\openai.py", line 237, in chat
return chat_fn(messages, **kwargs)
File "C:\Users\590\anaconda3\envs\bce\lib\site-packages\llama_index\llms\openai.py", line 296, in _chat
response = client.chat.completions.create(
File "C:\Users\590\anaconda3\envs\bce\lib\site-packages\openai_utils_utils.py", line 275, in wrapper
return func(*args, **kwargs)
File "C:\Users\590\anaconda3\envs\bce\lib\site-packages\openai\resources\chat\completions.py", line 663, in create
return self._post(
File "C:\Users\590\anaconda3\envs\bce\lib\site-packages\openai_base_client.py", line 1200, in post
return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))
File "C:\Users\590\anaconda3\envs\bce\lib\site-packages\openai_base_client.py", line 889, in request
return self._request(
File "C:\Users\590\anaconda3\envs\bce\lib\site-packages\openai_base_client.py", line 927, in _request
return self._retry_request(
File "C:\Users\590\anaconda3\envs\bce\lib\site-packages\openai_base_client.py", line 1013, in _retry_request
return self._request(
File "C:\Users\590\anaconda3\envs\bce\lib\site-packages\openai_base_client.py", line 927, in _request
return self._retry_request(
File "C:\Users\590\anaconda3\envs\bce\lib\site-packages\openai_base_client.py", line 1013, in _retry_request
return self._request(
File "C:\Users\590\anaconda3\envs\bce\lib\site-packages\openai_base_client.py", line 927, in _request
return self._retry_request(
File "C:\Users\590\anaconda3\envs\bce\lib\site-packages\openai_base_client.py", line 1013, in _retry_request
return self._request(
File "C:\Users\590\anaconda3\envs\bce\lib\site-packages\openai_base_client.py", line 937, in _request
raise APITimeoutError(request=request) from err
openai.APITimeoutError: Request timed out.

To Reproduce

我的代码是这样的：（我删除了apikey和apiurl）

我们在BCEmbedding中提供llama_index直接集成的接口。

from BCEmbedding.tools.llama_index import BCERerank

import os
from llama_index.embeddings import HuggingFaceEmbedding
from llama_index import VectorStoreIndex, ServiceContext, SimpleDirectoryReader
from llama_index.node_parser import SimpleNodeParser
from llama_index.llms import OpenAI
from llama_index.retrievers import VectorIndexRetriever

init embedding model and reranker model

embed_args = {'model_name': 'D:\BCE\model\bce-embedding-base_v1', 'max_length': 512, 'embed_batch_size': 32, 'device': 'cuda:0'}
embed_model = HuggingFaceEmbedding(**embed_args)

reranker_args = {'model': 'D:\BCE\model\bce-reranker-base_v1', 'top_n': 5, 'device': 'cuda:0'}
reranker_model = BCERerank(**reranker_args)

example #1. extract embeddings

query1 = 'apples'
passages = [
'I like apples',
'I like oranges',
'Apples and oranges are fruits'
]
query_embedding = embed_model.get_query_embedding(query1)
passages_embeddings = embed_model.get_text_embedding_batch(passages)
print('passages_em:'+str(passages_embeddings))
print('query_em:'+str(query_embedding))

example #2. rag example

llm = OpenAI(model='gpt-3.5-turbo', api_key=os.environ.get(''),api_base=os.environ.get(''))
service_context = ServiceContext.from_defaults(llm=llm, embed_model=embed_model)

documents = SimpleDirectoryReader(input_files=["D:\BCE\pycharmcode\文章.pdf","D:\BCE\pycharmcode\文章2.pdf","D:\BCE\pycharmcode\文章3.pdf"]).load_data()
node_parser = SimpleNodeParser.from_defaults(chunk_size=512)
nodes = node_parser.get_nodes_from_documents(documents[0:36])
index = VectorStoreIndex(nodes, service_context=service_context)
query = "请你给我介绍一下这个游戏"

example #2.1. retrieval with EmbeddingModel and RerankerModel

vector_retriever = VectorIndexRetriever(index=index, similarity_top_k=5, service_context=service_context)
retrieval_by_embedding = vector_retriever.retrieve(query)
retrieval_by_reranker = reranker_model.postprocess_nodes(retrieval_by_embedding, query_str=query)
print(retrieval_by_embedding)
print(retrieval_by_reranker)

example #2.2. query with EmbeddingModel and RerankerModel

query_engine = index.as_query_engine(node_postprocessors=[reranker_model])
print(query_engine)
query_response = query_engine.query(query)

print(query_response)

Code snippets

No response

OS

windows11

Python version

Python 3.10.13

Library version

1.13.3