如何利用Kay.ai和LangChain处理SEC文件数据

llzwxh888

于 2024-10-08 04:01:11 发布

阅读量147

点赞数 3

文章标签：人工智能 langchain 数据库 python

本文链接：https://blog.csdn.net/ppoojjj/article/details/142749767

版权

引言

SEC文件是提交给美国证券交易委员会（SEC）的财务报表或其他正式文件。公开公司、某些内部人士以及经纪交易商需要定期进行SEC文件的提交。投资者和金融专业人士依赖这些文件来获取他们评估投资对象公司的信息。

通过Kay.ai和Cybersyn提供的数据，使用Snowflake Marketplace，我们能够更高效地处理和分析这些文件。本文将介绍如何利用Kay.ai和LangChain来检索和分析SEC文件数据。

主要内容

环境设置

首先，你需要安装kay包，并获取一个免费的API密钥，可以在Kay.ai上申请。获取API密钥后，将其设置为环境变量KAY_API_KEY。

# 设置Kay和OpenAI的API密钥
from getpass import getpass

KAY_API_KEY = getpass(prompt="Enter your Kay API Key: ")
OPENAI_API_KEY = getpass(prompt="Enter your OpenAI API Key: ")

import os

os.environ["KAY_API_KEY"] = KAY_API_KEY
os.environ["OPENAI_API_KEY"] = OPENAI_API_KEY

使用KayAiRetriever

在这个例子中，我们将使用KayAiRetriever。更多详细的参数信息可以查看kay notebook。

# 导入相关包
from langchain.chains import ConversationalRetrievalChain
from langchain_community.retrievers import KayAiRetriever
from langchain_openai import ChatOpenAI

# 初始化模型和检索器
model = ChatOpenAI(model="gpt-3.5-turbo")
retriever = KayAiRetriever.create(
    dataset_id="company", data_types=["10-K", "10-Q"], num_contexts=6
)
qa = ConversationalRetrievalChain.from_llm(model, retriever=retriever)

提问和获取答案

我们可以使用该设置来提问并获取答案。以下是一个完整的示例：

# 定义问题
questions = [
    "What are patterns in Nvidia's spend over the past three quarters?",
    # 你可以添加更多问题
]
chat_history = []

# 提问并获取答案
for question in questions:
    result = qa({"question": question, "chat_history": chat_history})
    chat_history.append((question, result["answer"]))
    print(f"-> **Question**: {question} \n")
    print(f"**Answer**: {result['answer']} \n")

示例输出

-> **Question**: What are patterns in Nvidia's spend over the past three quarters? 

**Answer**: Based on the provided information, here are the patterns in NVIDIA's spend over the past three quarters:

1. Research and Development Expenses:
   - Q3 2022: Increased by 34% compared to Q3 2021.
   - Q1 2023: Increased by 40% compared to Q1 2022.
   - Q2 2022: Increased by 25% compared to Q2 2021.
   
   Overall, research and development expenses have been consistently increasing over the past three quarters.

2. Sales, General and Administrative Expenses:
   - Q3 2022: Increased by 8% compared to Q3 2021.
   - Q1 2023: Increased by 14% compared to Q1 2022.
   - Q2 2022: Decreased by 16% compared to Q2 2021.
   
   The pattern for sales, general and administrative expenses is not as consistent, with some quarters showing an increase and others showing a decrease.

3. Total Operating Expenses:
   - Q3 2022: Increased by 25% compared to Q3 2021.
   - Q1 2023: Increased by 113% compared to Q1 2022.
   - Q2 2022: Increased by 9% compared to Q2 2021.
   
   Total operating expenses have generally been increasing over the past three quarters, with a significant increase in Q1 2023.

Overall, the pattern indicates a consistent increase in research and development expenses and total operating expenses, while sales, general and administrative expenses show some fluctuations.