import streamlit as st
from llama_cpp import Llama


repo_ir = "Qwen/Qwen2.5-Coder-1.5B-Instruct-GGUF"
llm = Llama.from_pretrained(
    repo_id=repo_ir,
    filename="qwen2.5-coder-1.5b-instruct-q8_0.gguf",
    verbose=True,
    use_mmap=True,
    use_mlock=True,
    n_threads=4,
    n_threads_batch=4,
    n_ctx=8000,
)
print(f"{repo_ir} loaded successfully. ✅")


# Streamed response emulator
def response_generator(messages):
    completion = llm.create_chat_completion(
        messages, max_tokens=2048, stream=True, temperature=0.7, top_p=0.95
    )

    for message in completion:
        delta = message["choices"][0]["delta"]
        if "content" in delta:
            yield delta["content"]


st.title("CSV TO SQL")

# Initialize chat history
if "messages" not in st.session_state:
    st.session_state.messages = []

# Display chat messages from history on app rerun
for message in st.session_state.messages:
    with st.chat_message(message["role"]):
        st.markdown(message["content"])

# Accept user input
if prompt := st.chat_input("What is up?"):
    # Add user message to chat history
    st.session_state.messages.append({"role": "user", "content": prompt})
    # Display user message in chat message container
    with st.chat_message("user"):
        st.markdown(prompt)

    messages = [{"role": "system", "content": "You are a helpful assistant"}]

    for val in st.session_state.messages:
        messages.append(val)

    messages.append({"role": "user", "content": prompt})
    # Display assistant response in chat message container
    with st.chat_message("assistant"):
        response = st.write_stream(response_generator(messages=messages))
    # Add assistant response to chat history
    st.session_state.messages.append({"role": "assistant", "content": response})