import sklearn
import sqlite3
import numpy as np
from sklearn.metrics.pairwise import cosine_similarity
from openai import OpenAI
import os
import gradio as gr

client = OpenAI(api_key=os.environ["Secret"])

def find_closest_neighbors(vector1, dictionary_of_vectors):
    """Takes a vector and a dictionary of vectors and returns the three closest neighbors"""
    vector = client.embeddings.create(
        input=vector1,
        model="text-embedding-ada-002"
    ).data[0].embedding
    
    vector = np.array(vector)
    cosine_similarities = {}
    for key, value in dictionary_of_vectors.items():
        cosine_similarities[key] = cosine_similarity(vector.reshape(1, -1), value.reshape(1, -1))[0][0]
    sorted_cosine_similarities = sorted(cosine_similarities.items(), key=lambda x: x[1], reverse=True)
    match_list = sorted_cosine_similarities[0:4]
    return match_list

def predict(message, history):
    # Connect to the database
    conn = sqlite3.connect('QRIdatabase7.db')
    cursor = conn.cursor()
    cursor.execute('''SELECT text, embedding FROM chunks''')
    rows = cursor.fetchall()
    dictionary_of_vectors = {}
    for row in rows:
        text = row[0]
        embedding_str = row[1]
        embedding = np.fromstring(embedding_str, sep=' ')
        dictionary_of_vectors[text] = embedding
    conn.close()
    
    # Find the closest neighbors
    match_list = find_closest_neighbors(message, dictionary_of_vectors)
    context = ''
    for match in match_list:
        context += str(match[0])
    context = context[:1500]  # Limit context length
    
    prep = f"This is an OpenAI model tuned to answer questions specific to the Qualia Research institute, a research institute that focuses on consciousness. Here are some question-specific passages selected that may or may not be useful in answering user queries. Here is the user query to answer, potentially related to consciousness, the human experience, and phenomenology: {context}. Here is a question specific to QRI and consciousness in general Q: {message} A: "
    
    messages = []
    # Convert history to the expected format
    for human, assistant in history:
        messages.append({"role": "user", "content": human})
        messages.append({"role": "assistant", "content": assistant})
    messages.append({"role": "user", "content": prep})
    
    stream = client.chat.completions.create(
        model="gpt-3.5-turbo",
        messages=messages,
        temperature=1.0,
        stream=True
    )
    
    partial_message = ""
    for chunk in stream:
        if chunk.choices[0].delta.content is not None:
            partial_message += chunk.choices[0].delta.content
            yield partial_message

with gr.Blocks(title="QRI Research Assistant") as demo:
    chatbot = gr.ChatInterface(
        predict,
        title="QRI Research Assistant",
        description="Ask questions about consciousness, human experience, and phenomenology based on QRI research.",
        examples=[
            "What is consciousness?",
            "How does QRI approach the study of phenomenology?",
            "What are the key theories about qualia?"
        ]
    )

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