import gradio as gr
from huggingface_hub import InferenceClient
import os
import faiss
from transformers import pipeline
from sentence_transformers import SentenceTransformer

documents = [
    "The capital of France is Paris.",
    "Python is a popular programming language.",
    "The Eiffel Tower is located in Paris.",
    "Llama is a type of animal found in South America.",
    "Paris is known for its art, fashion, and culture.",
    "Gabor Toth is the author of this document."
]

embedding_model = SentenceTransformer('all-MiniLM-L6-v2')
document_embeddings = embedding_model.encode(documents, convert_to_tensor=True)
document_embeddings_np = document_embeddings.cpu().numpy()

index = faiss.IndexFlatL2(document_embeddings_np.shape[1])
index.add(document_embeddings_np)


client = InferenceClient("meta-llama/Llama-3.2-B-Instruct")
COHERE_API_KEY = os.getenv("COHERE_API_KEY")

def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
):
    
    query_embedding = embedding_model.encode([message], convert_to_tensor=True)
    query_embedding_np = query_embedding.cpu().numpy()
    distances, indices = index.search(query_embedding_np, k=1)
    relevant_document = documents[indices[0][0]]
    messages = [{"role": "system", "content": system_message},{{"role": "system", "content": f"context: {relevant_document}"}}]



    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})

    response = ""

    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

demo = gr.ChatInterface(
    respond,
    additional_inputs=[
        gr.Textbox(value="You are a friendly Chatbot.", 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()