File size: 4,286 Bytes
887b79e
 
4ca555a
887b79e
4ca555a
887b79e
 
 
 
4ca555a
887b79e
 
 
 
8bc6aeb
 
 
 
 
 
4ca555a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8bc6aeb
887b79e
 
4ca555a
 
 
887b79e
 
4ca555a
 
887b79e
 
 
 
4ca555a
 
887b79e
 
 
 
4ca555a
 
887b79e
 
 
 
 
 
 
 
 
4ca555a
887b79e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4ca555a
887b79e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
import streamlit as st
from dotenv import load_dotenv
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.embeddings import OpenAIEmbeddings, HuggingFaceInstructEmbeddings
from langchain.vectorstores import FAISS
from langchain.chat_models import ChatOpenAI
from langchain.memory import ConversationBufferMemory
from langchain.chains import ConversationalRetrievalChain
from langchain.document_loaders import PyPDFLoader, TextLoader, JSONLoader, CSVLoader
import tempfile
import os


def get_pdf_text(pdf_docs):
    temp_dir = tempfile.TemporaryDirectory()
    temp_filepath = os.path.join(temp_dir.name, pdf_docs.name)
    with open(temp_filepath, "wb") as f:
        f.write(pdf_docs.getvalue())
    pdf_loader = PyPDFLoader(temp_filepath)
    pdf_doc = pdf_loader.load()
    return pdf_doc


def get_text_file(docs):
    text_loader = TextLoader(docs.name)
    text = text_loader.load()
    return [text]


def get_csv_file(docs):
    csv_loader = CSVLoader(docs.name)
    csv_text = csv_loader.load()
    return csv_text.values.tolist()


def get_json_file(docs):
    json_loader = JSONLoader(docs.name)
    json_text = json_loader.load()
    return [json_text]


def get_text_chunks(documents):
    text_splitter = RecursiveCharacterTextSplitter(
        chunk_size=1000,
        chunk_overlap=200,
        length_function=len
    )

    documents = text_splitter.split_documents(documents)
    return documents


def get_vectorstore(text_chunks):
    embeddings = OpenAIEmbeddings()
    vectorstore = FAISS.from_documents(text_chunks, embeddings)
    return vectorstore


def get_conversation_chain(vectorstore):
    gpt_model_name = 'gpt-3.5-turbo'
    llm = ChatOpenAI(model_name=gpt_model_name)

    memory = ConversationBufferMemory(
        memory_key='chat_history', return_messages=True)
    conversation_chain = ConversationalRetrievalChain.from_llm(
        llm=llm,
        retriever=vectorstore.as_retriever(),
        memory=memory
    )
    return conversation_chain


def handle_userinput(user_question):
    response = st.session_state.conversation({'question': user_question})
    st.session_state.chat_history = response['chat_history']

    for i, message in enumerate(st.session_state.chat_history):
        if i % 2 == 0:
            st.write(user_template.replace(
                "{{MSG}}", message.content), unsafe_allow_html=True)
        else:
            st.write(bot_template.replace(
                "{{MSG}}", message.content), unsafe_allow_html=True)


def main():
    load_dotenv()
    st.set_page_config(page_title="Chat with multiple Files",
                       page_icon=":books:")
    st.write(css, unsafe_allow_html=True)

    if "conversation" not in st.session_state:
        st.session_state.conversation = None
    if "chat_history" not in st.session_state:
        st.session_state.chat_history = None

    st.header("Chat with multiple Files :")
    user_question = st.text_input("Ask a question about your documents:")
    if user_question:
        handle_userinput(user_question)

    with st.sidebar:
        openai_key = st.text_input("Paste your OpenAI API key (sk-...)")
        if openai_key:
            os.environ["OPENAI_API_KEY"] = openai_key

        st.subheader("Your documents")
        docs = st.file_uploader(
            "Upload your files here and click on 'Process'", accept_multiple_files=True)
        if st.button("Process"):
            with st.spinner("Processing"):
                doc_list = []

                for file in docs:
                    if file.type == 'text/plain':
                        doc_list.extend(get_text_file(file))
                    elif file.type in ['application/octet-stream', 'application/pdf']:
                        doc_list.extend(get_pdf_text(file))
                    elif file.type == 'text/csv':
                        doc_list.extend(get_csv_file(file))
                    elif file.type == 'application/json':
                        doc_list.extend(get_json_file(file))

                text_chunks = get_text_chunks(doc_list)
                vectorstore = get_vectorstore(text_chunks)
                st.session_state.conversation = get_conversation_chain(
                    vectorstore)


if __name__ == '__main__':
    main()