File size: 3,791 Bytes
1e7caaa |
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 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 |
# JB:
# LangChainDeprecationWarning: Importing embeddings from langchain is deprecated.
# Importing from langchain will no longer be supported as of langchain==0.2.0.
# Please import from langchain-community instead:
# `from langchain_community.embeddings import FastEmbedEmbeddings`.
# To install langchain-community run `pip install -U langchain-community`.
from langchain_community.embeddings import FastEmbedEmbeddings
import os
import streamlit as st
from langchain_groq import ChatGroq
from langchain_community.document_loaders import WebBaseLoader
from langchain_community.embeddings import OllamaEmbeddings
# JB:
from langchain.embeddings import FastEmbedEmbeddings
# from langchain_community.vectorstores import FAISS
# from langchain.vectorstores import Chroma
from langchain_community.vectorstores import Chroma
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.chains.combine_documents import create_stuff_documents_chain
from langchain_core.prompts import ChatPromptTemplate
from langchain.chains import create_retrieval_chain
import time
from dotenv import load_dotenv
load_dotenv() #
# groq_api_key = os.environ['GROQ_API_KEY']
groq_api_key = "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" # os.environ['GROQ_API_KEY']
print("groq_api_key: ", groq_api_key)
if "vector" not in st.session_state:
# st.session_state.embeddings = OllamaEmbeddings() # ORIGINAL
st.session_state.embeddings = FastEmbedEmbeddings() # JB
st.session_state.loader = WebBaseLoader("https://paulgraham.com/greatwork.html")
st.session_state.docs = st.session_state.loader.load()
st.session_state.text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
st.session_state.documents = st.session_state.text_splitter.split_documents( st.session_state.docs)
# st.session_state.vector = FAISS.from_documents(st.session_state.documents, st.session_state.embeddings) # ORIGINAL
# ZIE:
# ZIE VOOR EEN APP MET CHROMADB:
# https://github.com/vndee/local-rag-example/blob/main/rag.py
# https://raw.githubusercontent.com/vndee/local-rag-example/main/rag.py
# Chroma.from_documents(documents=chunks, embedding=FastEmbedEmbeddings())
st.session_state.vector = Chroma.from_documents(st.session_state.documents, st.session_state.embeddings) # JB
# st.title("Chat with Docs - Groq Edition :) ")
st.title("Literature Based Research (LBR) - Alexander Unzicker and Jan Bours - Chat with Docs - Groq Edition (Very Fast!) ")
llm = ChatGroq(
groq_api_key=groq_api_key,
model_name='mixtral-8x7b-32768'
)
prompt = ChatPromptTemplate.from_template("""
Answer the following question based only on the provided context.
Think step by step before providing a detailed answer.
I will tip you $200 if the user finds the answer helpful.
<context>
{context}
</context>
Question: {input}""")
document_chain = create_stuff_documents_chain(llm, prompt)
retriever = st.session_state.vector.as_retriever()
retrieval_chain = create_retrieval_chain(retriever, document_chain)
prompt = st.text_input("Input your prompt here")
# If the user hits enter
if prompt:
# Then pass the prompt to the LLM
start = time.process_time()
response = retrieval_chain.invoke({"input": prompt})
print(f"Response time: {time.process_time() - start}")
st.write(response["answer"])
# With a streamlit expander
with st.expander("Document Similarity Search"):
# Find the relevant chunks
for i, doc in enumerate(response["context"]):
# print(doc)
# st.write(f"Source Document # {i+1} : {doc.metadata['source'].split('/')[-1]}")
st.write(doc.page_content)
st.write("--------------------------------") |