# We'll need to install the Redis client
!pip install redis

#Install wget to pull zip file
!pip install wget

import openai

from typing import List, Iterator
import pandas as pd
import numpy as np
import os
import wget
from ast import literal_eval

# Redis client library for Python
import redis

# I've set this to our new embeddings model, this can be changed to the embedding model of your choice
EMBEDDING_MODEL = "text-embedding-3-small"

# Ignore unclosed SSL socket warnings - optional in case you get these errors
import warnings

warnings.filterwarnings(action="ignore", message="unclosed", category=ResourceWarning)
warnings.filterwarnings("ignore", category=DeprecationWarning) 

embeddings_url = 'https://cdn.openai.com/API/examples/data/vector_database_wikipedia_articles_embedded.zip'

# The file is ~700 MB so this will take some time
wget.download(embeddings_url)

import zipfile
with zipfile.ZipFile("vector_database_wikipedia_articles_embedded.zip","r") as zip_ref:
    zip_ref.extractall("../data")

article_df = pd.read_csv('../data/vector_database_wikipedia_articles_embedded.csv')

# Read vectors from strings back into a list
article_df['title_vector'] = article_df.title_vector.apply(literal_eval)
article_df['content_vector'] = article_df.content_vector.apply(literal_eval)

# Set vector_id to be a string
article_df['vector_id'] = article_df['vector_id'].apply(str)

# Constants
VECTOR_DIM = len(article_df['title_vector'][0]) # length of the vectors
VECTOR_NUMBER = len(article_df)                 # initial number of vectors
INDEX_NAME = "embeddings-index"                 # name of the search index
PREFIX = "doc"                                  # prefix for the document keys
DISTANCE_METRIC = "COSINE"                      # distance metric for the vectors (ex. COSINE, IP, L2)

# Define RediSearch fields for each of the columns in the dataset
title = TextField(name="title")
url = TextField(name="url")
text = TextField(name="text")
title_embedding = VectorField("title_vector",
    "FLAT", {
        "TYPE": "FLOAT32",
        "DIM": VECTOR_DIM,
        "DISTANCE_METRIC": DISTANCE_METRIC,
        "INITIAL_CAP": VECTOR_NUMBER,
    }
)
text_embedding = VectorField("content_vector",
    "FLAT", {
        "TYPE": "FLOAT32",
        "DIM": VECTOR_DIM,
        "DISTANCE_METRIC": DISTANCE_METRIC,
        "INITIAL_CAP": VECTOR_NUMBER,
    }
)
fields = [title, url, text, title_embedding, text_embedding]

# Check if index exists
try:
    redis_client.ft(INDEX_NAME).info()
    print("Index already exists")
except:
    # Create RediSearch Index
    redis_client.ft(INDEX_NAME).create_index(
        fields = fields,
        definition = IndexDefinition(prefix=[PREFIX], index_type=IndexType.HASH)
    )

def index_documents(client: redis.Redis, prefix: str, documents: pd.DataFrame):
    records = documents.to_dict("records")
    for doc in records:
        key = f"{prefix}:{str(doc['id'])}"

        # create byte vectors for title and content
        title_embedding = np.array(doc["title_vector"], dtype=np.float32).tobytes()
        content_embedding = np.array(doc["content_vector"], dtype=np.float32).tobytes()

        # replace list of floats with byte vectors
        doc["title_vector"] = title_embedding
        doc["content_vector"] = content_embedding

        client.hset(key, mapping = doc)

def search_redis(
    redis_client: redis.Redis,
    user_query: str,
    index_name: str = "embeddings-index",
    vector_field: str = "title_vector",
    return_fields: list = ["title", "url", "text", "vector_score"],
    hybrid_fields = "*",
    k: int = 20,
) -> List[dict]:

    # Creates embedding vector from user query
    embedded_query = openai.Embedding.create(input=user_query,
                                            model=EMBEDDING_MODEL,
                                            )["data"][0]['embedding']

    # Prepare the Query
    base_query = f'{hybrid_fields}=>[KNN {k} @{vector_field} $vector AS vector_score]'
    query = (
        Query(base_query)
         .return_fields(*return_fields)
         .sort_by("vector_score")
         .paging(0, k)
         .dialect(2)
    )
    params_dict = {"vector": np.array(embedded_query).astype(dtype=np.float32).tobytes()}

    # perform vector search
    results = redis_client.ft(index_name).search(query, params_dict)
    for i, article in enumerate(results.docs):
        score = 1 - float(article.vector_score)
        print(f"{i}. {article.title} (Score: {round(score ,3) })")
    return results.docs

def create_hybrid_field(field_name: str, value: str) -> str:
    return f'@{field_name}:"{value}"'