Spaces:
Sleeping
Sleeping
File size: 3,259 Bytes
6e43359 344e3f4 6e43359 |
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 |
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, HuggingFaceEmbeddings
from io import BytesIO
from langchain.document_loaders import PyPDFLoader
import gradio as gr
import chromadb
from dotenv import load_dotenv
from constants import CHROMA_SETTINGS
from io import BytesIO
import gradio as gr
local_llm = "TheBloke/zephyr-7B-beta-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() / 2)
}
llm = CTransformers(
model=local_llm,
model_type="mistral",
lib="avx2", #for CPU use
**config
)
embeddings_model_name = os.environ.get('EMBEDDINGS_MODEL_NAME')
persist_directory = os.environ.get('PERSIST_DIRECTORY')
target_source_chunks = int(os.environ.get('TARGET_SOURCE_CHUNKS',4))
if not load_dotenv():
print("Could not load .env file or it is empty. Please check if it exists and is readable.")
exit(1)
print("Loading embeddings model...")
embeddings = HuggingFaceEmbeddings(model_name=embeddings_model_name)
chroma_client = chromadb.PersistentClient(settings=CHROMA_SETTINGS , path=persist_directory)
db = Chroma(persist_directory=persist_directory, embedding_function=embeddings, client_settings=CHROMA_SETTINGS, client=chroma_client)
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:
"""
prompt = PromptTemplate(template=prompt_template, input_variables=['context', 'question'])
retriever = db.as_retriever(search_kwargs={"k": target_source_chunks})
# activate/deactivate the streaming StdOut callback for LLMs
'''
query="What is state ownership report"
semantic_search_results = retriever.get_relevant_documents(query)
print(semantic_search_results)
query="What is state ownership report"
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=True)
response= qa(query)
print(response)'''
chain_type_kwargs = {"prompt": prompt}
input_gradio= gr.Text(
label="Prompt",
show_label=False,
max_lines=2,
placeholder="Enter your question here",
container=False,
)
def get_response(input_gradio ):
query=input_gradio
qa = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=retriever, return_source_documents= False, chain_type_kwargs=chain_type_kwargs, verbose=True)
response= qa(query)
return response['result']
iface= gr.Interface(
fn=get_response,
inputs=input_gradio,
outputs="text",
title="Stimline Chatbot",
description="A chatbot that uses the LLM to answer anything regarding Stimline",
allow_flagging='never'
)
# Interactive questions and answers
iface.launch()
|