%pip install --upgrade --quiet  lark clickhouse-connect

import getpass
import os

if "OPENAI_API_KEY" not in os.environ:
    os.environ["OPENAI_API_KEY"] = getpass.getpass("OpenAI API Key:")
if "MYSCALE_HOST" not in os.environ:
    os.environ["MYSCALE_HOST"] = getpass.getpass("MyScale URL:")
if "MYSCALE_PORT" not in os.environ:
    os.environ["MYSCALE_PORT"] = getpass.getpass("MyScale Port:")
if "MYSCALE_USERNAME" not in os.environ:
    os.environ["MYSCALE_USERNAME"] = getpass.getpass("MyScale Username:")
if "MYSCALE_PASSWORD" not in os.environ:
    os.environ["MYSCALE_PASSWORD"] = getpass.getpass("MyScale Password:")

from langchain_community.vectorstores import MyScale
from langchain_core.documents import Document
from langchain_openai import OpenAIEmbeddings

embeddings = OpenAIEmbeddings()

docs = [
    Document(
        page_content="A bunch of scientists bring back dinosaurs and mayhem breaks loose",
        metadata={"date": "1993-07-02", "rating": 7.7, "genre": ["science fiction"]},
    ),
    Document(
        page_content="Leo DiCaprio gets lost in a dream within a dream within a dream within a ...",
        metadata={"date": "2010-12-30", "director": "Christopher Nolan", "rating": 8.2},
    ),
    Document(
        page_content="A psychologist / detective gets lost in a series of dreams within dreams within dreams and Inception reused the idea",
        metadata={"date": "2006-04-23", "director": "Satoshi Kon", "rating": 8.6},
    ),
    Document(
        page_content="A bunch of normal-sized women are supremely wholesome and some men pine after them",
        metadata={"date": "2019-08-22", "director": "Greta Gerwig", "rating": 8.3},
    ),
    Document(
        page_content="Toys come alive and have a blast doing so",
        metadata={"date": "1995-02-11", "genre": ["animated"]},
    ),
    Document(
        page_content="Three men walk into the Zone, three men walk out of the Zone",
        metadata={
            "date": "1979-09-10",
            "director": "Andrei Tarkovsky",
            "genre": ["science fiction", "adventure"],
            "rating": 9.9,
        },
    ),
]
vectorstore = MyScale.from_documents(
    docs,
    embeddings,
)

from langchain.chains.query_constructor.schema import AttributeInfo
from langchain.retrievers.self_query.base import SelfQueryRetriever
from langchain_openai import ChatOpenAI

metadata_field_info = [
    AttributeInfo(
        name="genre",
        description="The genres of the movie. "
        "It only supports equal and contain comparisons. "
        "Here are some examples: genre = [' A '], genre = [' A ', 'B'], contain (genre, 'A')",
        type="list[string]",
    ),
    # If you want to include length of a list, just define it as a new column
    # This will teach the LLM to use it as a column when constructing filter.
    AttributeInfo(
        name="length(genre)",
        description="The length of genres of the movie",
        type="integer",
    ),
    # Now you can define a column as timestamp. By simply set the type to timestamp.
    AttributeInfo(
        name="date",
        description="The date the movie was released",
        type="timestamp",
    ),
    AttributeInfo(
        name="director",
        description="The name of the movie director",
        type="string",
    ),
    AttributeInfo(
        name="rating", description="A 1-10 rating for the movie", type="float"
    ),
]
document_content_description = "Brief summary of a movie"
llm = ChatOpenAI(temperature=0, model_name="gpt-4o")
retriever = SelfQueryRetriever.from_llm(
    llm, vectorstore, document_content_description, metadata_field_info, verbose=True
)

# This example only specifies a relevant query
retriever.invoke("What are some movies about dinosaurs")

# This example only specifies a filter
retriever.invoke("I want to watch a movie rated higher than 8.5")

# This example specifies a query and a filter
retriever.invoke("Has Greta Gerwig directed any movies about women")

# This example specifies a composite filter
retriever.invoke("What's a highly rated (above 8.5) science fiction film?")

# This example specifies a query and composite filter
retriever.invoke(
    "What's a movie after 1990 but before 2005 that's all about toys, and preferably is animated"
)

# You can use length(genres) to do anything you want
retriever.invoke("What's a movie that have more than 1 genres?")

# Fine-grained datetime? You got it already.
retriever.invoke("What's a movie that release after feb 1995?")

# Don't know what your exact filter should be? Use string pattern match!
retriever.invoke("What's a movie whose name is like Andrei?")

# Contain works for lists: so you can match a list with contain comparator!
retriever.invoke("What's a movie who has genres science fiction and adventure?")

retriever = SelfQueryRetriever.from_llm(
    llm,
    vectorstore,
    document_content_description,
    metadata_field_info,
    enable_limit=True,
    verbose=True,
)

# This example only specifies a relevant query
retriever.invoke("what are two movies about dinosaurs")