Copyright (c) 2024 Microsoft Corporation.

# Copyright (c) 2024 Microsoft Corporation.
# Licensed under the MIT License.

import os

import pandas as pd
from graphrag.config.enums import ModelType
from graphrag.config.models.drift_search_config import DRIFTSearchConfig
from graphrag.config.models.language_model_config import LanguageModelConfig
from graphrag.language_model.manager import ModelManager
from graphrag.query.indexer_adapters import (
    read_indexer_entities,
    read_indexer_relationships,
    read_indexer_report_embeddings,
    read_indexer_reports,
    read_indexer_text_units,
)
from graphrag.query.structured_search.drift_search.drift_context import (
    DRIFTSearchContextBuilder,
)
from graphrag.query.structured_search.drift_search.search import DRIFTSearch
from graphrag.tokenizer.get_tokenizer import get_tokenizer
from graphrag_vectors.lancedb import LanceDBVectorStore

INPUT_DIR = "./inputs/operation dulce"
LANCEDB_URI = f"{INPUT_DIR}/lancedb"

COMMUNITY_REPORT_TABLE = "community_reports"
COMMUNITY_TABLE = "communities"
ENTITY_TABLE = "entities"
RELATIONSHIP_TABLE = "relationships"
COVARIATE_TABLE = "covariates"
TEXT_UNIT_TABLE = "text_units"
COMMUNITY_LEVEL = 2


# read nodes table to get community and degree data
entity_df = pd.read_parquet(f"{INPUT_DIR}/{ENTITY_TABLE}.parquet")
community_df = pd.read_parquet(f"{INPUT_DIR}/{COMMUNITY_TABLE}.parquet")

print(f"Entity df columns: {entity_df.columns}")

entities = read_indexer_entities(entity_df, community_df, COMMUNITY_LEVEL)

# load description embeddings to an in-memory lancedb vectorstore
# to connect to a remote db, specify url and port values.
description_embedding_store = LanceDBVectorStore(
    db_uri=LANCEDB_URI,
    index_name="entity_description",
)
description_embedding_store.connect()

full_content_embedding_store = LanceDBVectorStore(
    db_uri=LANCEDB_URI,
    index_name="community_full_content",
)
full_content_embedding_store.connect()

print(f"Entity count: {len(entity_df)}")
entity_df.head()

relationship_df = pd.read_parquet(f"{INPUT_DIR}/{RELATIONSHIP_TABLE}.parquet")
relationships = read_indexer_relationships(relationship_df)

print(f"Relationship count: {len(relationship_df)}")
relationship_df.head()

text_unit_df = pd.read_parquet(f"{INPUT_DIR}/{TEXT_UNIT_TABLE}.parquet")
text_units = read_indexer_text_units(text_unit_df)

print(f"Text unit records: {len(text_unit_df)}")
text_unit_df.head()

report_df = pd.read_parquet(f"{INPUT_DIR}/{COMMUNITY_REPORT_TABLE}.parquet")
reports = read_indexer_reports(report_df, community_df, COMMUNITY_LEVEL)
read_indexer_report_embeddings(reports, full_content_embedding_store)

api_key = os.environ["GRAPHRAG_API_KEY"]

chat_config = LanguageModelConfig(
    api_key=api_key,
    type=ModelType.Chat,
    model_provider="openai",
    model="gpt-4.1",
    max_retries=20,
)
chat_model = ModelManager().get_or_create_chat_model(
    name="local_search",
    model_type=ModelType.Chat,
    config=chat_config,
)

tokenizer = get_tokenizer(chat_config)

embedding_config = LanguageModelConfig(
    api_key=api_key,
    type=ModelType.Embedding,
    model_provider="openai",
    model="text-embedding-3-large",
    max_retries=20,
)

text_embedder = ModelManager().get_or_create_embedding_model(
    name="local_search_embedding",
    model_type=ModelType.Embedding,
    config=embedding_config,
)

drift_params = DRIFTSearchConfig(
    primer_folds=1,
    drift_k_followups=3,
    n_depth=3,
)

context_builder = DRIFTSearchContextBuilder(
    model=chat_model,
    text_embedder=text_embedder,
    entities=entities,
    relationships=relationships,
    reports=reports,
    entity_text_embeddings=description_embedding_store,
    text_units=text_units,
    tokenizer=tokenizer,
    config=drift_params,
)

search = DRIFTSearch(
    model=chat_model, context_builder=context_builder, tokenizer=tokenizer
)

resp = await search.search("Who is agent Mercer?")

resp.response

print(resp.context_data)