Spaces:
Sleeping
Sleeping
File size: 2,774 Bytes
4809e9f b98acaf 4809e9f 87898ec 4809e9f 5593b74 4809e9f 87898ec 4809e9f 87898ec 4809e9f 87898ec 4809e9f 87898ec 80d4056 4809e9f 87898ec 4809e9f 87898ec 4809e9f a80b12d 5704570 4809e9f 87898ec |
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 |
from langchain import PromptTemplate, LLMChain
from langchain.llms import CTransformers
import os
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.vectorstores import Chroma
from langchain.chains import RetrievalQA
from langchain.embeddings import HuggingFaceBgeEmbeddings
from io import BytesIO
from langchain.document_loaders import PyPDFLoader
import gradio as gr
local_llm = "zephyr-7b-beta.Q5_K_S.gguf"
config = {
'max_new_tokens': 1024,
'repetition_penalty': 1.1,
'temperature': 0.1,
'top_k': 50,
'top_p': 0.9,
'stream': True,
'threads': int(os.cpu_count())
}
llm = CTransformers(
model=local_llm,
model_type="mistral",
lib="avx2", #for CPU use
**config
)
print("LLM Initialized...")
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:
"""
model_name = "BAAI/bge-large-en"
model_kwargs = {'device': 'cpu'}
encode_kwargs = {'normalize_embeddings': False}
embeddings = HuggingFaceBgeEmbeddings(
model_name=model_name,
model_kwargs=model_kwargs,
encode_kwargs=encode_kwargs
)
prompt = PromptTemplate(template=prompt_template, input_variables=['context', 'question'])
load_vector_store = Chroma(persist_directory="store/ntrs23_cosine", embedding_function=embeddings)
retriever = load_vector_store.as_retriever(search_kwargs={"k":1})
print("######################################################################")
chain_type_kwargs = {"prompt": prompt}
qa = RetrievalQA.from_chain_type(
llm=llm,
chain_type="stuff",
retriever=retriever,
return_source_documents = False,
chain_type_kwargs= chain_type_kwargs,
verbose=False
)
sample_prompts = ["How many shipping bills filled in 2022?"]
def get_response(input):
query = input
chain_type_kwargs = {"prompt": prompt}
qa = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=retriever, return_source_documents=False, chain_type_kwargs=chain_type_kwargs, verbose=False)
response = qa(query)
return response['result']
input = gr.Text(
label="Prompt",
show_label=False,
max_lines=1,
placeholder="Enter your prompt",
container=False,
)
iface = gr.Interface(fn=get_response,
inputs=input,
outputs="text",
title="NTRS-NCTC Chatbot",
description="Please Enter Your Query.",
examples=sample_prompts,
# allow_screenshot=False,
allow_flagging=False
)
iface.launch() |