File size: 1,314 Bytes
39dfa69 cf15bd9 39dfa69 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 |
import os
import openai
from dotenv import load_dotenv
API_KEY = os.getenv("open_ai_key")
# Write the API key to the .env file
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()
|