File size: 2,919 Bytes
13b2da2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a3783b9
13b2da2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
from langchain.document_loaders.csv_loader import CSVLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.embeddings import HuggingFaceEmbeddings
from langchain.vectorstores import FAISS
from langchain.llms import CTransformers
from langchain.chains import ConversationalRetrievalChain

def add_vertical_space(spaces=1):
    for _ in range(spaces):
        st.sidebar.markdown("---")

def main():
    st.set_page_config(page_title="Llama-2-GGML CSV Chatbot")
    st.title("Llama-2-GGML CSV Chatbot")

    st.sidebar.title("About")
    st.sidebar.markdown('''
        The Llama-2-GGML CSV Chatbot uses the **Llama-2-7B-Chat-GGML** model.
        
        ### 🔄Bot evolving, stay tuned!
        
        ## Useful Links 🔗
        
        - **Model:** [Llama-2-7B-Chat-GGML](https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGML/tree/main) 📚
        - **GitHub:** [iam-baivab/Llama-2-GGML-CSV-Chatbot](https://github.com/iam-baivab/Llama-2-GGML-CSV-Chatbot) 💬
    ''')

    DB_FAISS_PATH = "vectorstore/db_faiss"
    TEMP_DIR = "temp"

    if not os.path.exists(TEMP_DIR):
        os.makedirs(TEMP_DIR)

    uploaded_file = st.sidebar.file_uploader("Upload CSV file", type=['csv'])

    add_vertical_space(1)
    st.sidebar.write('Made by [@ThisIs-Developer](https://huggingface.co/ThisIs-Developer)')

    if uploaded_file is not None:
        file_path = os.path.join(TEMP_DIR, uploaded_file.name)
        with open(file_path, "wb") as f:
            f.write(uploaded_file.getvalue())

        st.write(f"Uploaded file: {uploaded_file.name}")
        st.write("Processing CSV file...")

        loader = CSVLoader(file_path=file_path, encoding="utf-8", csv_args={'delimiter': ','})
        data = loader.load()

        text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=20)
        text_chunks = text_splitter.split_documents(data)

        st.write(f"Total text chunks: {len(text_chunks)}")

        embeddings = HuggingFaceEmbeddings(model_name='sentence-transformers/all-MiniLM-L6-v2')
        docsearch = FAISS.from_documents(text_chunks, embeddings)
        docsearch.save_local(DB_FAISS_PATH)

        llm = CTransformers(model="models/llama-2-7b-chat.ggmlv3.q4_0.bin",
                            model_type="llama",
                            max_new_tokens=512,
                            temperature=0.1)

        qa = ConversationalRetrievalChain.from_llm(llm, retriever=docsearch.as_retriever())

        st.write("Enter your query:")
        query = st.text_input("Input Prompt:")
        if query:
            with st.spinner("Processing your question..."):
                chat_history = []
                result = qa({"question": query, "chat_history": chat_history})
                st.write("Response:", result['answer'])

        os.remove(file_path)

if __name__ == "__main__":
    main()