Hi all,

I am new to Pinecone and learning through out the way. I am creating a PDF reader application with LangChain and Pinecone. In one section of my code where I want to split the PDFs user upload into chunks and store them into Pinecone. But I only want to create a new embedding where user upload a new PDF. And I keep getting this error: AttributeError: ‘Index’ object has no attribute ‘exists’.

Can someone please help me. Thank you!

Here is the section of my code where handles this:

read PDF

if pdf is not None: 
    pdf_reader = PdfReader(pdf)
    
    # split document into chunks
    # also can use text split: good for PDFs that do not contains charts and visuals
    sections = []
    for page in pdf_reader.pages:
        # Split the page text by paragraphs (assuming two newlines indicate a new paragraph)
        page_sections = page.extract_text().split('\n\n')
        sections.extend(page_sections)

    chunks = sections
    # st.write(chunks)

    ## embeddings
    # Set up Pinecone
    pinecone.init(api_key=pinecone_api_key, environment='gcp-starter')
    index_name = 'langchainresearch'
    if index_name not in pinecone.list_indexes():
        pinecone.create_index(index_name, dimension=1536, metric="cosine")  # Adjust the dimension as per your embeddings
    index = pinecone.Index(index_name)

    file_name = pdf.name[:-4]
    
    # Check if embeddings are already stored in Pinecone
    file_id = hash(file_name)
    if index.exists(id=file_id):
        # Fetch embeddings from Pinecone
        VectorStore = index.fetch(ids=[file_id])[file_id]
        st.write('Embeddings Loaded from Pinecone')
    else:
        # Compute embeddings
        embeddings = OpenAIEmbeddings(model="text-embedding-ada-002")
        VectorStore = FAISS.from_texts(chunks, embedding=embeddings)

        # Store embeddings in Pinecone
        vectors = VectorStore.get_all_vectors()
        index.upsert(vectors={(file_id, vectors)})
        st.write('Embeddings Computation Completed and Stored in Pinecone')
    
    # Create chat history
    # Pinecone Setup for Chat History
    chat_history_index_name = 'chat_history'
    if chat_history_index_name not in pinecone.list_indexes():
        pinecone.create_index(chat_history_index_name, dimension=1)  # Dimension is 1 as we're not storing vectors here
    chat_history_index = pinecone.Index(chat_history_index_name)

    # Create or Load Chat History from Pinecone
    if pdf:
        # Check if chat history exists in Pinecone
        if chat_history_index.exists(id=pdf.name):
            # Fetch chat history from Pinecone
            chat_history = chat_history_index.fetch(ids=[pdf.name])[pdf.name]
            st.write('Chat History Loaded from Pinecone')
    else:
        # Initialize empty chat history
        chat_history = []

10 posts - 3 participants

Read full topic