-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathmain.py
72 lines (59 loc) · 2.42 KB
/
main.py
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
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
import os
import streamlit as st
import pickle
import time
from langchain import OpenAI
from langchain.chains import RetrievalQAWithSourcesChain
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.document_loaders import UnstructuredURLLoader
from langchain.embeddings import OpenAIEmbeddings
from langchain.vectorstores import FAISS
from dotenv import load_dotenv
load_dotenv() # take environment variables from .env (especially openai api key)
st.title("RockyBot: News Research Tool 📈")
st.sidebar.title("News Article URLs")
urls = []
for i in range(3):
url = st.sidebar.text_input(f"URL {i+1}")
urls.append(url)
process_url_clicked = st.sidebar.button("Process URLs")
file_path = "faiss_store_openai.pkl"
main_placeholder = st.empty()
llm = OpenAI(temperature=0.9, max_tokens=500)
if process_url_clicked:
# load data
loader = UnstructuredURLLoader(urls=urls)
main_placeholder.text("Data Loading...Started...✅✅✅")
data = loader.load()
# split data
text_splitter = RecursiveCharacterTextSplitter(
separators=['\n\n', '\n', '.', ','],
chunk_size=1000
)
main_placeholder.text("Text Splitter...Started...✅✅✅")
docs = text_splitter.split_documents(data)
# create embeddings and save it to FAISS index
embeddings = OpenAIEmbeddings()
vectorstore_openai = FAISS.from_documents(docs, embeddings)
main_placeholder.text("Embedding Vector Started Building...✅✅✅")
time.sleep(2)
# Save the FAISS index to a pickle file
with open(file_path, "wb") as f:
pickle.dump(vectorstore_openai, f)
query = main_placeholder.text_input("Question: ")
if query:
if os.path.exists(file_path):
with open(file_path, "rb") as f:
vectorstore = pickle.load(f)
chain = RetrievalQAWithSourcesChain.from_llm(llm=llm, retriever=vectorstore.as_retriever())
result = chain({"question": query}, return_only_outputs=True)
# result will be a dictionary of this format --> {"answer": "", "sources": [] }
st.header("Answer")
st.write(result["answer"])
# Display sources, if available
sources = result.get("sources", "")
if sources:
st.subheader("Sources:")
sources_list = sources.split("\n") # Split the sources by newline
for source in sources_list:
st.write(source)