Creating a langchain vectorstore with chroma and openai embeddings loading pdfs

langchain_chroma_openai_vectorstore.py

from langchain_chroma import Chroma
from langchain_openai import OpenAIEmbeddings
from langchain_community.document_loaders import PDFMinerLoader, PyMuPDFLoader
from langchain_text_splitters import RecursiveCharacterTextSplitter

pdf_path = "https://www.barclaycard.co.uk/content/dam/barclaycard/documents/personal/existing-customers/terms-and-conditions-barclaycard-core-2019.pdf"

loader = PDFMinerLoader(pdf_path) # loads all text into a single document
loader = PyMuPDFLoader(pdf_path) # loads each page as a separate document
documents = loader.load()

text_splitter = RecursiveCharacterTextSplitter(
    chunk_size=1000, 
    chunk_overlap=100,
    separators=["\n\n", "\n", " ", ""],
)
docs = text_splitter.split_documents(documents)

embeddings = OpenAIEmbeddings(model="text-embedding-ada-002")
db = Chroma.from_documents(documents=docs, embedding=embeddings)

query = "Why can't max do this by himself?"
docs = db.similarity_search(query)

print(docs[0].page_content)