import gradio as gr
from huggingface_hub import InferenceClient
import os
from pinecone import Pinecone, ServerlessSpec
from sentence_transformers import SentenceTransformer


pc = Pinecone(api_key=os.getenv("PINECONE_API_KEY"))

index = pc.Index("medicine")

"""
For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
"""
client = InferenceClient("meta-llama/Meta-Llama-3-8B-Instruct")

embedding_model = SentenceTransformer(
    "nomic-ai/nomic-embed-text-v1", trust_remote_code=True
)


def retriever(message, embedding_model):
    print("Encoding query")
    encoded_message = embedding_model.encode(message)
    print("Fetching most similar doc")
    matches = index.query(
        vector=encoded_message.tolist(), top_k=1, include_metadata=True
    )
    print(f"Most similar chunk: {matches['matches'][0]['metadata']['original_text']}")
    retrieved_data = matches["matches"][0]["metadata"]["original_text"]

    return retrieved_data


def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
):
    messages = [{"role": "system", "content": system_message}]

    for val in history:
        if val[0]:
            messages.append({"role": "user", "content": val[0]})
        if val[1]:
            messages.append({"role": "assistant", "content": val[1]})

    messages.append({"role": "user", "content": message})
    print("Retrieving docs")
    retrieved_data = retriever(message, embedding_model)
    # Added as context to LLM
    messages.append({"role": "user", "content": retrieved_data})

    response = ""
    print("Completion request")
    for message in client.chat_completion(
        messages,
        max_tokens=max_tokens,
        stream=True,
        temperature=temperature,
        top_p=top_p,
    ):
        token = message.choices[0].delta.content

        response += token
        yield response


"""
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
"""
with open("prompt.txt") as file:
    prompt = file.read()

demo = gr.ChatInterface(
    respond,
    additional_inputs=[
        gr.Textbox(value=prompt, label="System message"),
        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
        gr.Slider(
            minimum=0.1,
            maximum=1.0,
            value=0.95,
            step=0.05,
            label="Top-p (nucleus sampling)",
        ),
    ],
)


if __name__ == "__main__":
    demo.launch()