Function main

pdf_bot.py:54–111

()

def main():
    st.header("📄Chat with your pdf file")

    # upload a your pdf file
    pdf = st.file_uploader("Upload your PDF", type="pdf")

    if pdf is not None:
        pdf_reader = PdfReader(pdf)

        text = ""
        for page in pdf_reader.pages:
            text += page.extract_text()

        # langchain_textspliter
        text_splitter = RecursiveCharacterTextSplitter(
            chunk_size=1000, chunk_overlap=200, length_function=len
        )

        chunks = text_splitter.split_text(text=text)
        qa_prompt = ChatPromptTemplate.from_messages(
            [
                (
                    "human",
                    "Based on the provided summary: {summaries} \n Answer the following question:{question}",
                )
            ]
        )

        # Store the chunks part in db (vector)
        vectorstore = Neo4jVector.from_texts(
            chunks,
            url=url,
            username=username,
            password=password,
            embedding=embeddings,
            index_name="pdf_bot",
            node_label="PdfBotChunk",
            pre_delete_collection=True,  # Delete existing PDF data
        )
        qa = (
            RunnableParallel(
                {
                    "summaries": vectorstore.as_retriever(search_kwargs={"k": 2})
                    | format_docs,
                    "question": RunnablePassthrough(),
                }
            )
            | qa_prompt
            | llm
            | StrOutputParser()
        )

        # Accept user questions/query
        query = st.text_input("Ask questions about your PDF file")

        if query:
            stream_handler = StreamHandler(st.empty())
            qa.invoke(query, {"callbacks": [stream_handler]})