Spaces:
Sleeping
Sleeping
File size: 4,363 Bytes
ff4614b 9b3f2e9 d643080 9b3f2e9 d643080 9b3f2e9 ff4614b d643080 9b3f2e9 ff4614b 9b3f2e9 0d20107 ff4614b 9b3f2e9 ff4614b 61170c1 036f779 d643080 30e2f30 d643080 9b3f2e9 30e2f30 9b3f2e9 30e2f30 9b3f2e9 d643080 30e2f30 d643080 9b3f2e9 d643080 9b3f2e9 d643080 9b3f2e9 d643080 9b3f2e9 d643080 9b3f2e9 d643080 9b3f2e9 d643080 9b3f2e9 d643080 30e2f30 d643080 30e2f30 d643080 30e2f30 d643080 9b3f2e9 30e2f30 d643080 61170c1 9b3f2e9 30e2f30 d643080 30e2f30 d643080 9b3f2e9 d643080 9b3f2e9 30e2f30 9b3f2e9 ee4e058 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 |
# from typing import List
# from chainlit.types import AskFileResponse
from aimakerspace.text_utils import CharacterTextSplitter, PDFFileLoader
from aimakerspace.openai_utils.prompts import (
UserRolePrompt,
SystemRolePrompt,
)
from aimakerspace.openai_utils.embedding import EmbeddingModel
from aimakerspace.vectordatabase import VectorDatabase
from aimakerspace.openai_utils.chatmodel import ChatOpenAI
import chainlit as cl
# import asyncio
# from operator import itemgetter
import nest_asyncio
nest_asyncio.apply()
from langchain_community.document_loaders import PyMuPDFLoader
from langchain_text_splitters import RecursiveCharacterTextSplitter
filepath_NIST = "data/NIST.AI.600-1.pdf"
filepath_Blueprint = "data/Blueprint-for-an-AI-Bill-of-Rights.pdf"
text_splitter = RecursiveCharacterTextSplitter(
chunk_size = 500,
chunk_overlap = 50
)
documents_NIST = PyMuPDFLoader(filepath_NIST).load()
documents_Blueprint = PyMuPDFLoader(filepath_Blueprint).load()
split_NIST = text_splitter.split_documents(documents_NIST)
split_Blueprint = text_splitter.split_documents(documents_Blueprint)
# embeddings = OpenAIEmbeddings(model="text-embedding-3-small")
# vectorstore = Qdrant.from_documents(
# documents=rag_documents,
# embedding=embeddings,
# location=":memory:",
# collection_name="Implications of AI"
# )
# retriever = qdrant_vectorstore.as_retriever()
RAG_PROMPT = """\
Given a provided context and question, you must answer the question based only on context.
If you cannot answer the question based on the context - you must say "I don't know".
Context: {context}
Question: {question}
"""
# prompt = ChatPromptTemplate.from_template(RAG_PROMPT)
RAG_PROMPT_TEMPLATE = """ \
Use the provided context to answer the user's query.
You may not answer the user's query unless there is specific context in the following text.
If you do not know the answer, or cannot answer, please respond with "I don't know".
"""
rag_prompt = SystemRolePrompt(RAG_PROMPT_TEMPLATE)
USER_PROMPT_TEMPLATE = """ \
Context:
{context}
User Query:
{user_query}
"""
user_prompt = UserRolePrompt(USER_PROMPT_TEMPLATE)
class RetrievalAugmentedQAPipeline:
def __init__(self, llm: ChatOpenAI(), vector_db_retriever: VectorDatabase) -> None:
self.llm = llm
self.vector_db_retriever = vector_db_retriever
async def arun_pipeline(self, user_query: str):
context_list = self.vector_db_retriever.search_by_text(user_query, k=4)
context_prompt = ""
for context in context_list:
context_prompt += context[0] + "\n"
formatted_system_prompt = rag_prompt.create_message()
formatted_user_prompt = user_prompt.create_message(user_query=user_query, context=context_prompt)
async def generate_response():
async for chunk in self.llm.astream([formatted_system_prompt, formatted_user_prompt]):
yield chunk
return {"response": generate_response(), "context": context_list}
# ------------------------------------------------------------
@cl.on_chat_start # marks a function that will be executed at the start of a user session
async def start_chat():
# settings = {
# "model": "gpt-3.5-turbo",
# "temperature": 0,
# "max_tokens": 500,
# "top_p": 1,
# "frequency_penalty": 0,
# "presence_penalty": 0,
# }
# # Create a dict vector store
vector_db = VectorDatabase()
# vector_db = await vector_db.abuild_from_list(rag_documents)
vector_db = await vector_db.abuild_from_list(split_NIST)
vector_db = await vector_db.abuild_from_list(split_Blueprint)
# # chat_openai = ChatOpenAI()
llm = ChatOpenAI(model="gpt-4o-mini", tags=["base_llm"])
# # Create a chain
rag_chain = RetrievalAugmentedQAPipeline(
vector_db_retriever=vector_db,
llm=llm
)
# cl.user_session.set("settings", settings)
cl.user_session.set("chain", rag_chain)
@cl.on_message # marks a function that should be run each time the chatbot receives a message from a user
async def main(message):
chain = cl.user_session.get("chain")
msg = cl.Message(content="")
result = await chain.arun_pipeline(message.content)
async for stream_resp in result["response"]:
await msg.stream_token(stream_resp)
await msg.send() |