File size: 1,578 Bytes
b4bac0d |
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 |
import os
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.vectorstores import Chroma
from langchain.document_loaders import PyPDFium2Loader
from langchain.chains.question_answering import load_qa_chain
# from langchain.llms import OpenAI
from langchain.chat_models import ChatOpenAI
class PDFQuery:
def __init__(self):
os.environ["OPENAI_API_KEY"] = "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"
self.embeddings = OpenAIEmbeddings()
self.text_splitter = RecursiveCharacterTextSplitter(chunk_size=800, chunk_overlap=200)
# self.llm = OpenAI(temperature=0, openai_api_key=openai_api_key)
self.llm = ChatOpenAI(temperature=0)
self.chain = None
self.db = None
def ask(self, question: str) -> str:
if self.chain is None:
response = "Please, add a document."
else:
docs = self.db.get_relevant_documents(question)
response = self.chain.run(input_documents=docs, question=question)
return response
def ingest(self, file_path: os.PathLike) -> None:
loader = PyPDFium2Loader(file_path)
documents = loader.load()
splitted_documents = self.text_splitter.split_documents(documents)
self.db = Chroma.from_documents(splitted_documents, self.embeddings).as_retriever()
# self.chain = load_qa_chain(OpenAI(temperature=0), chain_type="stuff")
self.chain = load_qa_chain(ChatOpenAI(temperature=0), chain_type="stuff")
|