-
Notifications
You must be signed in to change notification settings - Fork 0
/
senttrans_llama3,.1.py
80 lines (63 loc) · 3.08 KB
/
senttrans_llama3,.1.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
69
70
71
72
73
74
75
76
77
78
79
80
import streamlit as st
import os
import time
from langchain_groq import ChatGroq
from langchain_community.embeddings.huggingface import HuggingFaceEmbeddings
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
from langchain_community.vectorstores import FAISS
from langchain_community.document_loaders import PyPDFLoader
from dotenv import load_dotenv
load_dotenv()
# Load the GROQ and OpenAI API keys
groq_api_key = os.getenv('GROQ_API_KEY')
st.title("LLAMA 3.1 AND SENTENCE TRANSFORMER")
llm = ChatGroq(groq_api_key=groq_api_key, model_name="Llama3-8b-8192")
prompt = ChatPromptTemplate.from_template(
"""
നൽകിയിരിക്കുന്ന സന്ദർഭത്തെ അടിസ്ഥാനമാക്കി മാത്രം ചോദ്യങ്ങൾക്ക് ഉത്തരം നൽകുക.
ചോദ്യത്തെ അടിസ്ഥാനമാക്കി ഏറ്റവും കൃത്യമായ മറുപടി നൽകുക. ഉത്തരം മലയാളത്തിൽ പറയുക
<context>
{context}
<context>
Questions:{input}
"""
)
def vector_embedding(docs):
embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
final_documents = text_splitter.split_documents(docs)
vectors = FAISS.from_documents(final_documents, embeddings)
return vectors
# Ensure the temporary directory exists
temp_dir = "./temp"
os.makedirs(temp_dir, exist_ok=True)
uploaded_files = st.file_uploader("Upload your documents", type=["pdf"], accept_multiple_files=True)
if uploaded_files:
docs = []
for uploaded_file in uploaded_files:
file_path = os.path.join(temp_dir, uploaded_file.name)
with open(file_path, "wb") as f:
f.write(uploaded_file.getbuffer())
loader = PyPDFLoader(file_path)
docs.extend(loader.load())
st.session_state.vectors = vector_embedding(docs)
st.write("Vector Store DB is ready")
prompt1 = st.text_input("Enter Your Question From Documents")
if st.button("Generate Response") and prompt1:
if "vectors" in st.session_state:
document_chain = create_stuff_documents_chain(llm, prompt)
retriever = st.session_state.vectors.as_retriever()
retrieval_chain = create_retrieval_chain(retriever, document_chain)
start = time.process_time()
response = retrieval_chain.invoke({'input': prompt1})
st.write(f"Response time: {time.process_time() - start:.2f} seconds")
st.write(response['answer'])
with st.expander("Document Similarity Search"):
for i, doc in enumerate(response["context"]):
st.write(doc.page_content)
st.write("--------------------------------")
else:
st.write("Please upload documents and generate the vector store DB first.")