|
import os |
|
import openai |
|
from dotenv import load_dotenv |
|
|
|
|
|
API_KEY = os.getenv("open_ai_key") |
|
|
|
|
|
with open(".env", "w") as env_file: |
|
env_file.write(f"openai_api_key={API_KEY}\n") |
|
|
|
|
|
load_dotenv(".env") |
|
|
|
openai.api_key = os.environ.get("openai_api_key") |
|
|
|
os.environ["OPENAI_API_KEY"] = openai.api_key |
|
|
|
with open("sample_awards.csv") as f: |
|
sample_awards = f.read() |
|
|
|
from langchain.text_splitter import CharacterTextSplitter |
|
|
|
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0, separator = "\n") |
|
texts = text_splitter.split_text(sample_awards) |
|
|
|
from langchain.embeddings.openai import OpenAIEmbeddings |
|
|
|
embeddings = OpenAIEmbeddings() |
|
|
|
from langchain.vectorstores import Chroma |
|
|
|
docsearch = Chroma.from_texts(texts, embeddings, metadatas=[{"source": str(i)} for i in range(len(texts))]).as_retriever() |
|
|
|
from langchain.chains.question_answering import load_qa_chain |
|
from langchain.llms import OpenAI |
|
|
|
chain = load_qa_chain(OpenAI(temperature=0), chain_type="stuff") |
|
|
|
def question(text): |
|
query = text |
|
docs = docsearch.get_relevant_documents(query) |
|
return chain.run(input_documents=docs, question=query) |
|
|
|
import gradio as gr |
|
|
|
gr.Interface( |
|
question, |
|
inputs="text", |
|
outputs="text", |
|
title="Awards Question Answering", |
|
).launch() |
|
|
