Spaces:
Sleeping
Sleeping
File size: 3,392 Bytes
edbf017 |
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 |
"""
The code in this script subjects to a licence of 96harsh52/LLaMa_2_chatbot (https://github.com/96harsh52/LLaMa_2_chatbot)
Youtube instruction (https://www.youtube.com/watch?v=kXuHxI5ZcG0&list=PLrLEqwuz-mRIdQrfeCjeCyFZ-Pl6ffPIN&index=18)
Llama 2 Model (Quantized one by the Bloke): https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGML/blob/main/llama-2-7b-chat.ggmlv3.q8_0.bin
Llama 2 HF Model (Original One): https://huggingface.co/meta-llama
Chainlit docs: https://github.com/Chainlit/chainlit
"""
from langchain import PromptTemplate
from langchain_community.embeddings import HuggingFaceEmbeddings
from langchain_community.vectorstores import FAISS
from langchain.chains import RetrievalQA
from langchain_community.llms import CTransformers
import chainlit as cl
DB_FAISS_PATH = 'vectorstore/db_faiss'
custom_prompt_template = """Use the following pieces of information to answer the user's question.
If you don't know the answer, just say that you don't know, don't try to make up an answer.
Context: {context}
Question: {question}
Only return the helpful answer below and nothing else.
Helpful answer:
"""
def set_custom_prompt():
"""
Prompt template for QA retrieval for each vectorstore
"""
prompt = PromptTemplate(template=custom_prompt_template,
input_variables=['context', 'question'])
return prompt
def load_llm():
"""
Load the language model
"""
llm = CTransformers(model='TheBloke/Llama-2-7b-Chat-GGUF',
model_file='llama-2-7b-chat.Q8_0.gguf',
model_type='llama',
max_new_tokens=512,
temperature=0.5)
return llm
def retrieval_qa_chain(llm, prompt, db):
"""
Create a retrieval QA chain
"""
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():
"""
Create a QA bot
"""
embeddings = HuggingFaceEmbeddings(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
@cl.on_chat_start
async def start():
chain = qa_bot()
msg = cl.Message(content="Starting the bot...")
await msg.send()
msg.content = "Hi, Welcome to Medical Chatbot. What is your query?"
await msg.update()
cl.user_session.set("chain", chain)
@cl.on_message
async def main(message: cl.Message):
chain = cl.user_session.get("chain")
cb = cl.AsyncLangchainCallbackHandler(
stream_final_answer=True, answer_prefix_tokens=["FINAL", "ANSWER"]
)
cb.answer_reached = True
res = await chain.acall(message.content, callbacks=[cb])
answer = res["result"]
sources = res["source_documents"]
if sources:
answer += f"\nSources:" + str(sources)
else:
answer += "\nNo sources found"
await cl.Message(content=answer).send()
|