File size: 2,965 Bytes
d5a6487
 
bcc7923
 
 
 
 
 
 
 
 
 
 
7d71f93
bcc7923
 
5c5bbab
bcc7923
 
 
 
 
 
 
 
 
407ae47
 
 
 
 
 
bcc7923
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0d4f501
bcc7923
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e4bfc79
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
from langchain import PromptTemplate
#from langchain_core.prompts import PromptTemplate
import os 
from langchain_community.embeddings import HuggingFaceBgeEmbeddings
from langchain_community.vectorstores import FAISS
from langchain_community.llms.ctransformers import CTransformers
#from langchain.chains import RetrievalQA
from langchain.chains.retrieval_qa.base import RetrievalQA
import chainlit as cl

DB_FAISS_PATH = 'vectorstores/'

custom_prompt_template = '''
use the following pieces of information to answer the user's questions.
If you don't know the answer, please just say that don't know the answer, don't try to make uo an answer.

Context : {context}
Question : {question}

only return the helpful answer below and nothing else.
'''

def set_custom_prompt():
    """
    Prompt template for QA retrieval for vector stores
    """
    # prompt = PromptTemplate(template = custom_prompt_template,
    #                         input_variables = ['context','question'])
    
    # return prompt
    prompt = PromptTemplate(template=custom_prompt_template,
                            input_variables=['context', 'question'])  # Ensure this matches expected inputs
    
    return prompt

def load_llm():
    llm = CTransformers(
        model = 'TheBloke/Llama-2-7B-Chat-GGML',
        #model = AutoModel.from_pretrained("TheBloke/Llama-2-7B-Chat-GGML"),
        model_type = 'llama',
        max_new_token = 512,
        temperature = 0.5
    )
    return llm

def retrieval_qa_chain(llm,prompt,db):
    qa_chain = RetrievalQA.from_chain_type(
        llm = llm,
        chain_type = 'stuff',
        retriever = db.as_retriever(search_kwargs= {'k': 2}),
        return_source_documents = True,
        chain_type_kwargs = {'prompt': prompt}
    )

    return qa_chain

def qa_bot():
    embeddings = HuggingFaceBgeEmbeddings(model_name = 'sentence-transformers/all-MiniLM-L6-v2',
                                          model_kwargs = {'device':'cpu'})
    
    
    db = FAISS.load_local(DB_FAISS_PATH, embeddings,allow_dangerous_deserialization=True)
    llm = load_llm()
    qa_prompt = set_custom_prompt()
    qa = retrieval_qa_chain(llm,qa_prompt, db)

    return qa

def final_result(query):
    qa_result = qa_bot()
    response = qa_result({'query' : query})

    return response


import streamlit as st

# Initialize the bot
bot = qa_bot()

def process_query(query):
    # Here you would include the logic to process the query and return a response
    response, sources = bot.answer_query(query)  # Modify this according to your bot implementation
    if sources:
        response += f"\nSources: {', '.join(sources)}"
    else:
        response += "\nNo Sources Found"
    return response

# Setting up the Streamlit app
st.title('Medical Chatbot')

user_input = st.text_input("Hi, welcome to the medical Bot. What is your query?")

if user_input:
    output = process_query(user_input)
    st.text_area("Response", output, height=300)