import os
from lightrag import LightRAG, QueryParam
from lightrag.llm.ollama import ollama_model_complete, ollama_embed
from lightrag.utils import EmbeddingFunc

# WorkingDir
ROOT_DIR = os.path.dirname(os.path.abspath(__file__))
WORKING_DIR = os.path.join(ROOT_DIR, "myKG")
if not os.path.exists(WORKING_DIR):
    os.mkdir(WORKING_DIR)
print(f"WorkingDir: {WORKING_DIR}")

# mongo
os.environ["MONGO_URI"] = "mongodb://root:root@localhost:27017/"
os.environ["MONGO_DATABASE"] = "LightRAG"

# neo4j
BATCH_SIZE_NODES = 500
BATCH_SIZE_EDGES = 100
os.environ["NEO4J_URI"] = "bolt://localhost:7687"
os.environ["NEO4J_USERNAME"] = "neo4j"
os.environ["NEO4J_PASSWORD"] = "neo4j"

# milvus
os.environ["MILVUS_URI"] = "http://localhost:19530"
os.environ["MILVUS_USER"] = "root"
os.environ["MILVUS_PASSWORD"] = "root"
os.environ["MILVUS_DB_NAME"] = "lightrag"


rag = LightRAG(
    working_dir=WORKING_DIR,
    llm_model_func=ollama_model_complete,
    llm_model_name="qwen2.5:14b",
    llm_model_max_async=4,
    llm_model_max_token_size=32768,
    llm_model_kwargs={"host": "http://127.0.0.1:11434", "options": {"num_ctx": 32768}},
    embedding_func=EmbeddingFunc(
        embedding_dim=1024,
        max_token_size=8192,
        func=lambda texts: ollama_embed(
            texts=texts, embed_model="bge-m3:latest", host="http://127.0.0.1:11434"
        ),
    ),
    kv_storage="MongoKVStorage",
    graph_storage="Neo4JStorage",
    vector_storage="MilvusVectorDBStorge",
)

file = "./book.txt"
with open(file, "r") as f:
    rag.insert(f.read())

print(
    rag.query("What are the top themes in this story?", param=QueryParam(mode="hybrid"))
)