# Install required dependencies
%pip install --upgrade --quiet  clarifai langchain-community

# Please login and get your API key from  https://clarifai.com/settings/security
from getpass import getpass

CLARIFAI_PAT = getpass()

# Import the required modules
from langchain_community.document_loaders import TextLoader
from langchain_community.vectorstores import Clarifai
from langchain_text_splitters import CharacterTextSplitter

USER_ID = "USERNAME_ID"
APP_ID = "APPLICATION_ID"
NUMBER_OF_DOCS = 2

texts = [
    "I really enjoy spending time with you",
    "I hate spending time with my dog",
    "I want to go for a run",
    "I went to the movies yesterday",
    "I love playing soccer with my friends",
]

metadatas = [
    {"id": i, "text": text, "source": "book 1", "category": ["books", "modern"]}
    for i, text in enumerate(texts)
]

idlist = ["text1", "text2", "text3", "text4", "text5"]
metadatas = [
    {"id": idlist[i], "text": text, "source": "book 1", "category": ["books", "modern"]}
    for i, text in enumerate(texts)
]

# There is an option to initialize clarifai vector store with pat as argument!
clarifai_vector_db = Clarifai(
    user_id=USER_ID,
    app_id=APP_ID,
    number_of_docs=NUMBER_OF_DOCS,
)

# upload with metadata and custom input ids.
response = clarifai_vector_db.add_texts(texts=texts, ids=idlist, metadatas=metadatas)

# upload without metadata (Not recommended)- Since you will not be able to perform Search operation with respect to metadata.
# custom input_id (optional)
response = clarifai_vector_db.add_texts(texts=texts)

clarifai_vector_db = Clarifai.from_texts(
    user_id=USER_ID,
    app_id=APP_ID,
    texts=texts,
    metadatas=metadatas,
)

docs = clarifai_vector_db.similarity_search("I would like to see you")
docs

# There is lots powerful filtering you can do within an app by leveraging metadata filters.
# This one will limit the similarity query to only the texts that have key of "source" matching value of "book 1"
book1_similar_docs = clarifai_vector_db.similarity_search(
    "I would love to see you", filter={"source": "book 1"}
)

# you can also use lists in the input's metadata and then select things that match an item in the list. This is useful for categories like below:
book_category_similar_docs = clarifai_vector_db.similarity_search(
    "I would love to see you", filter={"category": ["books"]}
)

loader = TextLoader("your_local_file_path.txt")
documents = loader.load()
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
docs = text_splitter.split_documents(documents)

USER_ID = "USERNAME_ID"
APP_ID = "APPLICATION_ID"
NUMBER_OF_DOCS = 4

clarifai_vector_db = Clarifai.from_documents(
    user_id=USER_ID,
    app_id=APP_ID,
    documents=docs,
    number_of_docs=NUMBER_OF_DOCS,
)

docs = clarifai_vector_db.similarity_search("Texts related to population")
docs

USER_ID = "USERNAME_ID"
APP_ID = "APPLICATION_ID"
NUMBER_OF_DOCS = 4

clarifai_vector_db = Clarifai(
    user_id=USER_ID,
    app_id=APP_ID,
    number_of_docs=NUMBER_OF_DOCS,
)

docs = clarifai_vector_db.similarity_search(
    "Texts related to ammuniction and president wilson"
)

docs[0].page_content