import bm25s
import Stemmer  # optional: for stemming

# Create your corpus here
corpus = [
    "a cat is a feline and likes to purr",
    "a dog is the human's best friend and loves to play",
    "a bird is a beautiful animal that can fly",
    "a fish is a creature that lives in water and swims",
]

# optional: create a stemmer
stemmer = Stemmer.Stemmer("english")

# Tokenize the corpus and only keep the ids (faster and saves memory)
corpus_tokens = bm25s.tokenize(corpus, stopwords="en", stemmer=stemmer)

# Create the BM25 model and index the corpus
retriever = bm25s.BM25()
retriever.index(corpus_tokens)

# Query the corpus
query = "does the fish purr like a cat?"
query_tokens = bm25s.tokenize(query, stemmer=stemmer)

# Get top-k results as a tuple of (doc ids, scores). Both are arrays of shape (n_queries, k)
results, scores = retriever.retrieve(query_tokens, corpus=corpus, k=2)

for i in range(results.shape[1]):
    doc, score = results[0, i], scores[0, i]
    print(f"Rank {i+1} (score: {score:.2f}): {doc}")

# You can save the arrays to a directory...
retriever.save("animal_index_bm25")

# You can save the corpus along with the model
retriever.save("animal_index_bm25", corpus=corpus)

# ...and load them when you need them
import bm25s
reloaded_retriever = bm25s.BM25.load("animal_index_bm25", load_corpus=True)
# set load_corpus=False if you don't need the corpus

# You can provide a list of queries instead of a single query
queries = ["What is a cat?", "is the bird a dog?"]

# Provide your own stopwords list if you don't like the default one
stopwords = ["a", "the"]

# For stemming, use any function that is callable on each word list
stemmer_fn = lambda lst: [word for word in lst]

# Tokenize the queries
query_token_ids = bm25s.tokenize(queries, stopwords=stopwords, stemmer=stemmer_fn)

# If you want the tokenizer to return strings instead of token ids, you can do this
query_token_strs = bm25s.tokenize(queries, return_ids=False)

# You can use a different corpus for retrieval, e.g., titles instead of full docs
titles = ["About Cat", "About Dog", "About Bird", "About Fish"]

# You can also choose to only return the documents and omit the scores
results = retriever.retrieve(query_token_ids, corpus=titles, k=2, return_as="documents")

# The documents are returned as a numpy array of shape (n_queries, k)
for i in range(results.shape[1]):
    print(f"Rank {i+1}: {results[0, i]}")

# Create a BM25 index
# ...

# let's say you have a large corpus
corpus = [
    "a very long document that is very long and has many words",
    "another long document that is long and has many words",
    # ...
]
# Save the BM25 index to a file
retriever.save("bm25s_very_big_index", corpus=corpus)

# Load the BM25 index as a memory-mapped file, which is memory efficient
# and reduce overhead of loading the full index into memory
retriever = bm25s.BM25.load("bm25s_very_big_index", mmap=True)

from bm25s.tokenization import Tokenizer

corpus = [
      "a cat is a feline and likes to purr",
      "a dog is the human's best friend and loves to play",
      "a bird is a beautiful animal that can fly",
      "a fish is a creature that lives in water and swims",
]

# Pick your favorite stemmer, and pass 
stemmer = None
stopwords = ["is"]
splitter = lambda x: x.split() # function or regex pattern
# Create a tokenizer
tokenizer = Tokenizer(
      stemmer=stemmer, stopwords=stopwords, splitter=splitter
)

corpus_tokens = tokenizer.tokenize(corpus)

# let's see what the tokens look like
print("tokens:", corpus_tokens)
print("vocab:", tokenizer.get_vocab_dict())

# note: the vocab dict will either be a dict of `word -> id` if you don't have a stemmer, and a dict of `stemmed word -> stem id` if you do.
# You can save the vocab. it's fine to use the same dir as your index if filename doesn't conflict
tokenizer.save_vocab(save_dir="bm25s_very_big_index")

# loading:
new_tokenizer = Tokenizer(stemmer=stemmer, stopwords=[], splitter=splitter)
new_tokenizer.load_vocab("bm25s_very_big_index")
print("vocab reloaded:", new_tokenizer.get_vocab_dict())

# the same can be done for stopwords
print("stopwords before reload:", new_tokenizer.stopwords)
tokenizer.save_stopwords(save_dir="bm25s_very_big_index")
new_tokenizer.load_stopwords("bm25s_very_big_index")
print("stopwords reloaded:", new_tokenizer.stopwords)

# The IR book recommends default values of k1 between 1.2 and 2.0, and b=0.75
retriever = bm25s.BM25(method="robertson", k1=1.5, b=0.75)

# For BM25+, BM25L, you need a delta parameter (default is 0.5)
retriever = bm25s.BM25(method="bm25+", delta=1.5)

# You can also choose a different "method" for idf, while keeping the default for the rest
# for example, this is equivalent to rank-bm25 when `epsilon=0`
retriever = bm25s.BM25(method="atire", idf_method="robertson")
# and this is equivalent to bm25-pt
retriever = bm25s.BM25(method="atire", idf_method="lucene")

import os
import bm25s
from bm25s.hf import BM25HF

# Create a BM25 index
retriever = BM25HF()
# Create your corpus here
corpus = [
    "a cat is a feline and likes to purr",
    "a dog is the human's best friend and loves to play",
    "a bird is a beautiful animal that can fly",
    "a fish is a creature that lives in water and swims",
]
corpus_tokens = bm25s.tokenize(corpus)
retriever.index(corpus_tokens)

# Set your username and token
user = "your-username"
token = os.environ["HF_TOKEN"]
retriever.save_to_hub(f"{user}/bm25s-animals", token=token, corpus=corpus)
# You can also save it publicly with private=False

import bm25s
from bm25s.hf import BM25HF

# Load a BM25 index from the Hugging Face model hub
user = "your-username"
retriever = BM25HF.load_from_hub(f"{user}/bm25s-animals")

# you can specify revision and load_corpus=True if needed
retriever = BM25HF.load_from_hub(
    f"{user}/bm25s-animals", revision="main", load_corpus=True
)

# if you want a low-memory usage, you can load as memory map with `mmap=True`
retriever = BM25HF.load_from_hub(
    f"{user}/bm25s-animals", load_corpus=True, mmap=True
)

# Query the corpus
query = "does the fish purr like a cat?"

# Tokenize the query
query_tokens = bm25s.tokenize(query)

# Get top-k results as a tuple of (doc ids, scores). Both are arrays of shape (n_queries, k)
results, scores = retriever.retrieve(query_tokens, k=2)