Я не могу использовать GPT4All со Streamlit.

Question

Я пытаюсь использовать GPT4All с Streamlit в своем коде Python, но кажется, что какой-то параметр получает неправильные значения. Я испробовал все альтернативы. Это выглядит небольшой проблемой, которую я где-то упускаю.

Мой код:

      from langchain import HuggingFaceHub, LLMChain, PromptTemplate
import streamlit as st
from dotenv import load_dotenv
from PyPDF2 import PdfReader
from langchain.text_splitter import CharacterTextSplitter
from langchain.embeddings import OpenAIEmbeddings, HuggingFaceInstructEmbeddings
from langchain.vectorstores import FAISS
from langchain.memory import ConversationBufferMemory
from langchain.chains import ConversationalRetrievalChain
from langchain.chat_models import ChatOpenAI
from htmlTemplates import bot_template, user_template, css
import transformers
from transformers import pipeline
from gpt4all.gpt4all import GPT4All

def get_pdf_text(pdf_files):

    text = ""
    for pdf_file in pdf_files:
        reader = PdfReader(pdf_file)
        for page in reader.pages:
            text += page.extract_text()
    return text


def get_chunk_text(text):

    text_splitter = CharacterTextSplitter(
        separator="\n",
        chunk_size=1000,
        chunk_overlap=200,
        length_function=len
    )

    chunks = text_splitter.split_text(text)

    return chunks


def get_vector_store(text_chunks):

    # For OpenAI Embeddings

    # embeddings = OpenAIEmbeddings()

    # For Huggingface Embeddings

    # model_name = "hkunlp/instructor-xl"
    embeddings = HuggingFaceInstructEmbeddings(
        model_name="sentence-transformers/all-MiniLM-L6-v2")

    vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)

    return vectorstore


def get_conversation_chain(vector_store):

    # OpenAI Model

    # llm = ChatOpenAI()

    # HuggingFace Model

    # llm = HuggingFaceHub(repo_id="google/flan-t5-xxl",
    #                 model_kwargs={"temperature": 0.8, "max_length": 5000})

    # HuggingFace Model (downloaded)
    # model_name = "distilgpt2"  # or choose any models - distilroberta, roberta, bart etc
    # llm = transformers.AutoModelForCausalLM.from_pretrained(model_name)

    # Create GPT4All Model

    gpt4all = GPT4All(model_name="ggml-gpt4all-j-v1.3-groovy.bin", model_path="./")
    
    #prompt = PromptTemplate(template="{question}", input_variables=["question"])

    #llm_chain = LLMChain(prompt=prompt, llm=gpt4all)

    memory = ConversationBufferMemory(
        memory_key='chat_history', return_messages=True)

    conversation_chain = ConversationalRetrievalChain.from_llm(
        llm=gpt4all,
        retriever=vector_store.as_retriever(),
        memory=memory
    )

    return conversation_chain


def handle_user_input(question):

    response = st.session_state.conversation({'question': question})
    st.session_state.chat_history = response['chat_history']

    for i, message in enumerate(st.session_state.chat_history):
        if i % 2 == 0:
            st.write(user_template.replace(
                "{{MSG}}", message.content), unsafe_allow_html=True)
        else:
            st.write(bot_template.replace(
                "{{MSG}}", message.content), unsafe_allow_html=True)


def main():
    load_dotenv()
    st.set_page_config(page_title='Chat with Your own PDFs',
                       page_icon=':books:')

    st.write(css, unsafe_allow_html=True)

    if "conversation" not in st.session_state:
        st.session_state.conversation = None

    if "chat_history" not in st.session_state:
        st.session_state.chat_history = None

    st.header('Chat with Your own PDFs :books:')
    question = st.text_input("Ask anything to your PDF: ")

    if question:
        handle_user_input(question)

    with st.sidebar:
        st.subheader("Upload your Documents Here: ")
        pdf_files = st.file_uploader("Choose your PDF Files and Press OK", type=[
                                     'pdf'], accept_multiple_files=True)

        if st.button("OK"):
            with st.spinner("Processing your PDFs..."):

                # Get PDF Text
                raw_text = get_pdf_text(pdf_files)

                # Get Text Chunks
                text_chunks = get_chunk_text(raw_text)

                # Create Vector Store

                vector_store = get_vector_store(text_chunks)
                st.write("DONE")

                # Create conversation chain

                st.session_state.conversation = get_conversation_chain(
                    vector_store)


if __name__ == '__main__':
    main()

Я получаю следующее исключение:

      2023-08-24 18:41:50.816 Uncaught app exception
Traceback (most recent call last):
  File "C:\Users\MudassarMa\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\streamlit\runtime\scriptrunner\script_runner.py", line 556, in _run_script
    exec(code, module.__dict__)
  File "C:\Users\MudassarMa\Downloads\Misc\DataScience\taxgpt\main.py", line 153, in <module>
    main()
  File "C:\Users\MudassarMa\Downloads\Misc\DataScience\taxgpt\main.py", line 148, in main
    st.session_state.conversation = get_conversation_chain(
                                    ^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\MudassarMa\Downloads\Misc\DataScience\taxgpt\main.py", line 85, in get_conversation_chain
    conversation_chain = ConversationalRetrievalChain.from_llm(
                         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\MudassarMa\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\langchain\chains\conversational_retrieval\base.py", line 213, in from_llm
    doc_chain = load_qa_chain(
                ^^^^^^^^^^^^^^
  File "C:\Users\MudassarMa\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\langchain\chains\question_answering\__init__.py", line 238, in load_qa_chain
    return loader_mapping[chain_type](
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\MudassarMa\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\langchain\chains\question_answering\__init__.py", line 70, in _load_stuff_chain
    llm_chain = LLMChain(
                ^^^^^^^^^
  File "C:\Users\MudassarMa\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\langchain\load\serializable.py", line 61, in __init__
    super().__init__(**kwargs)
  File "pydantic\main.py", line 341, in pydantic.main.BaseModel.__init__
pydantic.error_wrappers.ValidationError: 1 validation error for LLMChain
llm
  value is not a valid dict (type=type_error.dict)