Bug描述

当我们在Elasticsearch中使用dense_x时，尤其是在使用70+页时，我们会遇到以下错误：

raise self._make_status_error_from_response(err.response) from None
openai.RateLimitError: Error code: 429 - {'error': {'code': '429', 'message': 'Requests to the ChatCompletions_Create Operation under Azure OpenAI API version 2023-07-01-preview have exceeded token rate limit of your current OpenAI S0 pricing tier. Please retry after 59 seconds. Please go here:
https://aka.ms/oai/quotaincrease
if you would like to further increase the default rate limit.'}}

版本

llama-index==0.10.10

重现步骤

from llama_index.core import SimpleDirectoryReader
from llama_index.core.node_parser import SentenceSplitter
# from dense_base import DenseXRetrievalPack
from dense_pack2.base import DenseXRetrievalPack as dp2
from llama_index.vector_stores.elasticsearch import ElasticsearchStore
def define_rag():
    """
    This function is for defining the RAG
    """
    vector_store = ElasticsearchStore(
        index_name="dense_index_58",
        es_url="http://localhost:9200",
    )
    documents = SimpleDirectoryReader("./docs").load_data()

    llm = llm_query()
    embed_model = embeded_model()

    print("creating denseX")
    retriever_chunk = dp2(
        documents,
        proposition_llm=embed_model,
        query_llm=llm,
        text_splitter=SentenceSplitter(chunk_size=1024),
        vector_store = vector_store
        )
    query_engine_chunk = retriever_chunk.query_engine
    print("denseX creation done")

在dense_x中，我们在base.py中修改了一些代码，并将其导入为dp2,如上代码所示：

import asyncio
import json
from typing import Any, Dict, List, Optional

import yaml
from llama_index.core import Document, ServiceContext, VectorStoreIndex, StorageContext
from llama_index.core.async_utils import run_jobs
from llama_index.core.base.embeddings.base import BaseEmbedding
from llama_index.core.base.response.schema import RESPONSE_TYPE
from llama_index.core.llama_pack.base import BaseLlamaPack
from llama_index.core.node_parser.interface import TextSplitter
from llama_index.core.node_parser.text import SentenceSplitter
from llama_index.core.prompts import PromptTemplate
from llama_index.core.query_engine import RetrieverQueryEngine
from llama_index.core.retrievers import RecursiveRetriever
from llama_index.core.schema import IndexNode, TextNode
from llama_index.embeddings.openai import OpenAIEmbedding
from llama_index.llms.openai import OpenAI

lm = llm_query()
embed_model = embeded_model()
class DenseXRetrievalPack(BaseLlamaPack):
    def __init__(
        self,
        documents: List[Document],
        proposition_llm: Optional[LLM] = None,
        query_llm: Optional[LLM] = None,
        embed_model: Optional[BaseEmbedding] = None,
        text_splitter: TextSplitter = SentenceSplitter(),
        vector_store: Optional[ElasticsearchStore] = None,
        similarity_top_k: int = 4
    ) -> None:
        """Init params."""
        self._proposition_llm = llm
        # self._proposition_llm = proposition_llm or OpenAI(
        #     model="gpt-3.5-turbo",
        #     temperature=0.1,
        #     max_tokens=750,
        # )

        embed_model = embed_model #or OpenAIEmbedding(embed_batch_size=128)

相关日志/回溯

• 无响应*