Spaces:
Sleeping
Sleeping
File size: 4,796 Bytes
50d8518 d09fcc1 e1b6f9e 50d8518 c0682fb 3e096bc 50d8518 c0682fb ab572f0 1d1c48c c0682fb 50d8518 f40c605 50d8518 |
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 |
import os
import gradio as gr
from langchain_groq import ChatGroq
from langchain.prompts import ChatPromptTemplate
from langchain.chains import RetrievalQA, ConversationalRetrievalChain
from langchain.memory import ConversationBufferMemory
from langchain_huggingface.embeddings import HuggingFaceEmbeddings
from langchain_community.vectorstores import Chroma
def rag_retriever(message, history, system_prompt, num_sources=4, temperature=0):
chat = ChatGroq(temperature=temperature, model_name="llama3-70b-8192", api_key=os.getenv("GROQ_API_KEY"))
embeddings = HuggingFaceEmbeddings(model_name="avsolatorio/GIST-large-Embedding-v0")
base_dir = os.path.dirname(os.path.abspath(__file__))
db_path = os.path.join(base_dir, 'chroma.sqlite3')
store = Chroma(persist_directory='/home/user/app', embedding_function=embeddings, collection_name='ai_act')
prompt_template = ChatPromptTemplate.from_messages([
("system", system_prompt+"""
Use the following pieces of context to answer the user's question.
----------------
{context}"""),
("human", "{question}")
])
memory = ConversationBufferMemory(memory_key="chat_history", output_key="answer", return_messages=True)
retriever = store.as_retriever(search_type="similarity", search_kwargs={'k': num_sources})
chain = ConversationalRetrievalChain.from_llm(llm=chat,
retriever=retriever,
return_source_documents=True,
memory=memory,
combine_docs_chain_kwargs={"prompt": prompt_template})
output = chain.invoke({"question": message})
sources = ""
for doc in output['source_documents']:
source_content = doc.page_content.strip().replace("\r\n", " ").replace("\r", " ").replace("\n", " ")
sources += f'<span style="color:green">Страница: {doc.metadata["page"]+1}</span><br><span style="color:gray">{source_content}</span><br><br>'
response = f"""<h5>Отговор:</h5>{output['answer']}<br><h5>Източници:</h5>{sources}"""
return response
rag = gr.ChatInterface(rag_retriever,
examples=[["Каква е целта на настоящия регламент", "You are an expert assistant in Bulgarian regulations. Provide precise and clear answers. Provide a detailed and comprehensive answer, incorporating as much relevant information as possible. Always respond in Bulgarian, regardless of the language used in the question."],
["Какво са Системите с ИИ", "You are an expert assistant in Bulgarian regulations. Provide precise and clear answers. Always respond in Bulgarian, regardless of the language used in the question."],
["Какво е равнище на технологично развитие", "You are an expert assistant in Bulgarian regulations. Provide precise and clear answers. Always respond in Bulgarian, regardless of the language used in the question."]],
title="Чатене с документа AI Act",
description="Питайте каквото пожелаете, но пишете на български.",
chatbot=gr.Chatbot(placeholder="<strong>Вашият личен AI Act помощник</strong><br>Питайте каквото пожелаете, но пишете на български."),
textbox=gr.Textbox(default="Enter your text here", placeholder="Задайте своя въпрос...", container=False, scale=7),
retry_btn="Отново",
undo_btn="Назад",
clear_btn="Изчистете",
submit_btn="Изпрати",
additional_inputs=[gr.components.Textbox("You are an expert assistant in Bulgarian regulations. Provide precise and clear answers. Always respond in Bulgarian, regardless of the language used in the question.", label="System Prompt"),
gr.components.Slider(minimum=1, maximum=10, value=4, step=1, label="Брой препратки"),
gr.components.Slider(minimum=0, maximum=2, value=0, label="Креативност на модела", info="Ако е много високо моделът си измисля, но може да напише интересни неща."),],
additional_inputs_accordion=gr.Accordion("Допълнителни настройки", open=False),
)
rag.launch() |