mirror of
https://github.com/hwchase17/langchain
synced 2024-10-31 15:20:26 +00:00
89ef440c14
- **Description**: Adding retrievers for [kay.ai](https://kay.ai) and SEC filings powered by Kay and Cybersyn. Kay provides context as a service: it's an API built for RAG. - **Issue**: N/A - **Dependencies**: Just added a dep to the [kay](https://pypi.org/project/kay/) package - **Tag maintainer**: @baskaryan @hwchase17 Discussed in slack - **Twtter handle:** [@vishalrohra_](https://twitter.com/vishalrohra_) --------- Co-authored-by: Bagatur <baskaryan@gmail.com>
166 lines
5.6 KiB
Plaintext
166 lines
5.6 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "263f914c-9d67-4316-8b3d-03c3b99ba9d8",
|
|
"metadata": {},
|
|
"source": [
|
|
"SEC filings data\n",
|
|
"=\n",
|
|
"\n",
|
|
"SEC filings data powered by [Kay.ai](https://kay.ai) and [Cybersyn](https://www.cybersyn.com/).\n",
|
|
"\n",
|
|
">The SEC filing is a financial statement or other formal document submitted to the U.S. Securities and Exchange Commission (SEC). Public companies, certain insiders, and broker-dealers are required to make regular SEC filings. Investors and financial professionals rely on these filings for information about companies they are evaluating for investment purposes."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "fc507b8e-ea51-417c-93da-42bf998a1195",
|
|
"metadata": {},
|
|
"source": [
|
|
"Setup\n",
|
|
"=\n",
|
|
"\n",
|
|
"First you will need to install the `kay` package. You will also need an API key: you can get one for free at [https://kay.ai](https://kay.ai/). Once you have an API key, you must set it as an environment variable `KAY_API_KEY`.\n",
|
|
"\n",
|
|
"In this example we're going to use the `KayAiRetriever`. Take a look at the [kay notebook](/docs/integrations/retrievers/kay) for more detailed information for the parmeters that it accepts.`"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "c923bea0-585a-4f62-8662-efc167e8d793",
|
|
"metadata": {},
|
|
"source": [
|
|
"Examples\n",
|
|
"=\n",
|
|
"\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"id": "f7b8c99c-0341-4f3c-912f-a11e98f7de71",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdin",
|
|
"output_type": "stream",
|
|
"text": [
|
|
" ········\n",
|
|
" ········\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"# Setup API keys for Kay and OpenAI\n",
|
|
"from getpass import getpass\n",
|
|
"KAY_API_KEY = getpass()\n",
|
|
"OPENAI_API_KEY = getpass()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"id": "04ee2d6b-c2ab-4e15-8a8b-afaf6ef8c0f6",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import os\n",
|
|
"os.environ[\"KAY_API_KEY\"] = KAY_API_KEY\n",
|
|
"os.environ[\"OPENAI_API_KEY\"] = OPENAI_API_KEY"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 7,
|
|
"id": "0c504bcd-f6e0-4028-a797-b31fb4b6d027",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from langchain.chains import ConversationalRetrievalChain\n",
|
|
"from langchain.chat_models import ChatOpenAI\n",
|
|
"from langchain.retrievers import KayAiRetriever\n",
|
|
"\n",
|
|
"model = ChatOpenAI(model_name=\"gpt-3.5-turbo\")\n",
|
|
"retriever = KayAiRetriever.create(dataset_id=\"company\", data_types=[\"10-K\", \"10-Q\"], num_contexts=6)\n",
|
|
"qa = ConversationalRetrievalChain.from_llm(model, retriever=retriever)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 11,
|
|
"id": "977f158b-38d3-4b5f-9379-7cdd09436327",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"-> **Question**: What are patterns in Nvidia's spend over the past three quarters? \n",
|
|
"\n",
|
|
"**Answer**: Based on the provided information, here are the patterns in NVIDIA's spend over the past three quarters:\n",
|
|
"\n",
|
|
"1. Research and Development Expenses:\n",
|
|
" - Q3 2022: Increased by 34% compared to Q3 2021.\n",
|
|
" - Q1 2023: Increased by 40% compared to Q1 2022.\n",
|
|
" - Q2 2022: Increased by 25% compared to Q2 2021.\n",
|
|
" \n",
|
|
" Overall, research and development expenses have been consistently increasing over the past three quarters.\n",
|
|
"\n",
|
|
"2. Sales, General and Administrative Expenses:\n",
|
|
" - Q3 2022: Increased by 8% compared to Q3 2021.\n",
|
|
" - Q1 2023: Increased by 14% compared to Q1 2022.\n",
|
|
" - Q2 2022: Decreased by 16% compared to Q2 2021.\n",
|
|
" \n",
|
|
" The pattern for sales, general and administrative expenses is not as consistent, with some quarters showing an increase and others showing a decrease.\n",
|
|
"\n",
|
|
"3. Total Operating Expenses:\n",
|
|
" - Q3 2022: Increased by 25% compared to Q3 2021.\n",
|
|
" - Q1 2023: Increased by 113% compared to Q1 2022.\n",
|
|
" - Q2 2022: Increased by 9% compared to Q2 2021.\n",
|
|
" \n",
|
|
" Total operating expenses have generally been increasing over the past three quarters, with a significant increase in Q1 2023.\n",
|
|
"\n",
|
|
"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. \n",
|
|
"\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"questions = [\n",
|
|
" \"What are patterns in Nvidia's spend over the past three quarters?\",\n",
|
|
" #\"What are some recent challenges faced by the renewable energy sector?\",\n",
|
|
"]\n",
|
|
"chat_history = []\n",
|
|
"\n",
|
|
"for question in questions:\n",
|
|
" result = qa({\"question\": question, \"chat_history\": chat_history})\n",
|
|
" chat_history.append((question, result[\"answer\"]))\n",
|
|
" print(f\"-> **Question**: {question} \\n\")\n",
|
|
" print(f\"**Answer**: {result['answer']} \\n\")"
|
|
]
|
|
}
|
|
],
|
|
"metadata": {
|
|
"kernelspec": {
|
|
"display_name": "Python 3 (ipykernel)",
|
|
"language": "python",
|
|
"name": "python3"
|
|
},
|
|
"language_info": {
|
|
"codemirror_mode": {
|
|
"name": "ipython",
|
|
"version": 3
|
|
},
|
|
"file_extension": ".py",
|
|
"mimetype": "text/x-python",
|
|
"name": "python",
|
|
"nbconvert_exporter": "python",
|
|
"pygments_lexer": "ipython3",
|
|
"version": "3.9.18"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 5
|
|
}
|