app.py

import streamlit as st
import os
import getpass
from langchain import PromptTemplate
from langchain import hub
from langchain.docstore.document import Document
from langchain.document_loaders import WebBaseLoader
from langchain.schema import StrOutputParser
from langchain.schema.prompt_template import format_document
from langchain.schema.runnable import RunnablePassthrough
from langchain.vectorstores import Chroma
import google.generativeai as genai
from langchain_google_genai import GoogleGenerativeAIEmbeddings
from langchain_google_genai import ChatGoogleGenerativeAI
from langchain.chains.llm import LLMChain
from langchain.chains import StuffDocumentsChain

GOOGLE_API_KEY=os.environ['GOOGLE_API_KEY']


url_user = st.text_input("Enter Url","https://www.moneycontrol.com/stocksmarketsindia/")

loader = WebBaseLoader(url_user)
docs = loader.load()

gemini_embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")

llm = ChatGoogleGenerativeAI(model="gemini-pro",google_api_key = GOOGLE_API_KEY)


# user_prompt = st.text_input("Enter Prompt","What is the best stocks for the next few weeks")


llm_prompt_template = """You are an expert Stock Market Trader for stock market insights.
Based on the context below
{context}, Suggest some stocks recommendations"""

st.write(llm_prompt_template)
llm_prompt = PromptTemplate.from_template(llm_prompt_template)

llm_chain = LLMChain(llm=llm,prompt=llm_prompt)
stuff_chain = StuffDocumentsChain(llm_chain=llm_chain,document_variable_name="context")


res = stuff_chain.invoke(docs)
st.write(res.output_text)

# If there is no environment variable set for the API key, you can pass the API
# key to the parameter `google_api_key` of the `GoogleGenerativeAIEmbeddings`
# function: `google_api_key = "key"`.

# gemini_embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")

# # Save to disk
# vectorstore = Chroma.from_documents(
#                      documents=docs,                 # Data
#                      embedding=gemini_embeddings,    # Embedding model
#                      persist_directory="./chroma_db" # Directory to save data
#                      )

# vectorstore_disk = Chroma(
#                         persist_directory="./chroma_db",       # Directory of db
#                         embedding_function=gemini_embeddings   # Embedding model