Spaces:
Runtime error
Runtime error
File size: 3,218 Bytes
ddcdb82 |
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 |
import chainlit as cl
import tiktoken
import os
from dotenv import load_dotenv
# from langchain.document_loaders import PyMuPDFLoader
from langchain_community.document_loaders import PyMuPDFLoader
from langchain_openai import OpenAIEmbeddings
# from langchain_community.chat_models import OpenAIEmbeddings
from langchain_core.prompts import ChatPromptTemplate
from langchain.text_splitter import RecursiveCharacterTextSplitter
# from langchain.vectorstores import Pinecone
from langchain_community.vectorstores import Pinecone
from operator import itemgetter
from langchain.schema.runnable import RunnablePassthrough
from langchain_openai import ChatOpenAI
from langchain.schema.runnable.config import RunnableConfig
from langchain_core.output_parsers import StrOutputParser
load_dotenv()
RAG_PROMPT = """
CONTEXT:
{context}
QUERY:
{question}
You are a car specialist and can only provide your answers from the context.
Don't tell in your response that you are getting it from the context.
"""
init_settings = {
"model": "gpt-3.5-turbo",
"temperature": 0,
"max_tokens": 500,
"top_p": 1,
"frequency_penalty": 0,
"presence_penalty": 0,
}
# embeddings = OpenAIEmbeddings(model="text-embedding-3-small")
def tiktoken_len(text):
tokens = tiktoken.encoding_for_model("gpt-3.5-turbo").encode(
text,
)
return len(tokens)
car_manual = PyMuPDFLoader(os.environ.get('pdfurl'))
car_manual_data = car_manual.load()
text_splitter = RecursiveCharacterTextSplitter(
chunk_size = 400,
chunk_overlap = 50,
length_function = tiktoken_len)
car_manual_chunks = text_splitter.split_documents(car_manual_data)
embedding_model = OpenAIEmbeddings(model="text-embedding-3-small")
vector_store = Pinecone.from_documents(car_manual_chunks, embedding_model, index_name=os.environ.get('index'))
retriever = vector_store.as_retriever()
rag_prompt = ChatPromptTemplate.from_template(RAG_PROMPT)
model = ChatOpenAI(model="gpt-3.5-turbo")
@cl.on_chat_start
async def main():
# text_splitter = RecursiveCharacterTextSplitter(
# chunk_size = 400,
# chunk_overlap = 50,
# length_function = tiktoken_len)
# car_manual_chunks = text_splitter.split_documents(car_manual_data)
# embedding_model = OpenAIEmbeddings(model="text-embedding-3-small")
# vector_store = Pinecone.from_documents(car_manual_chunks, embedding_model, index_name=os.environ.get('index'))
# retriever = vector_store.as_retriever()
# rag_prompt = ChatPromptTemplate.from_template(RAG_PROMPT)
# model = ChatOpenAI(model="gpt-3.5-turbo")
mecanic_qa_chain = (
{"context": itemgetter("question") | retriever, "question": itemgetter("question")}
| RunnablePassthrough.assign(context=itemgetter("context"))
| rag_prompt | model | StrOutputParser()
)
cl.user_session.set("runnable", mecanic_qa_chain)
@cl.on_message
async def on_message(message: cl.Message):
runnable = cl.user_session.get("runnable")
msg = cl.Message(content="")
async for chunk in runnable.astream(
{"question":message.content},
config=RunnableConfig(callbacks=[cl.LangchainCallbackHandler()]),
):
await msg.stream_token(chunk)
|