File size: 2,846 Bytes
75922df
8b3b01c
75922df
0553d6a
75922df
8b3b01c
75922df
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4e9e345
 
75922df
 
 
 
 
 
 
 
 
 
 
275e33e
 
8b3b01c
 
 
 
 
 
 
 
 
 
 
 
 
75922df
8b3b01c
 
 
 
 
 
 
 
 
 
 
 
75922df
8b3b01c
 
275e33e
 
 
8b3b01c
 
 
 
275e33e
 
 
8b3b01c
75922df
8b3b01c
 
275e33e
 
 
8b3b01c
 
 
 
275e33e
 
 
8b3b01c
390c21a
275e33e
8b3b01c
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
import os
import asyncio
from lightrag import LightRAG, QueryParam
from lightrag.llm.ollama import ollama_embed, openai_complete_if_cache
from lightrag.utils import EmbeddingFunc
from lightrag.kg.shared_storage import initialize_pipeline_status

# 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}")

# redis
os.environ["REDIS_URI"] = "redis://localhost:6379"

# neo4j
BATCH_SIZE_NODES = 500
BATCH_SIZE_EDGES = 100
os.environ["NEO4J_URI"] = "bolt://117.50.173.35:7687"
os.environ["NEO4J_USERNAME"] = "neo4j"
os.environ["NEO4J_PASSWORD"] = "12345678"

# milvus
os.environ["MILVUS_URI"] = "http://117.50.173.35:19530"
os.environ["MILVUS_USER"] = "root"
os.environ["MILVUS_PASSWORD"] = "Milvus"
os.environ["MILVUS_DB_NAME"] = "lightrag"


async def llm_model_func(
    prompt, system_prompt=None, history_messages=[], keyword_extraction=False, **kwargs
) -> str:
    return await openai_complete_if_cache(
        "deepseek-chat",
        prompt,
        system_prompt=system_prompt,
        history_messages=history_messages,
        api_key="",
        base_url="",
        **kwargs,
    )


embedding_func = EmbeddingFunc(
    embedding_dim=768,
    max_token_size=512,
    func=lambda texts: ollama_embed(
        texts, embed_model="shaw/dmeta-embedding-zh", host="http://117.50.173.35:11434"
    ),
)


async def initialize_rag():
    rag = LightRAG(
        working_dir=WORKING_DIR,
        llm_model_func=llm_model_func,
        llm_model_max_token_size=32768,
        embedding_func=embedding_func,
        chunk_token_size=512,
        chunk_overlap_token_size=256,
        kv_storage="RedisKVStorage",
        graph_storage="Neo4JStorage",
        vector_storage="MilvusVectorDBStorage",
        doc_status_storage="RedisKVStorage",
    )

    await rag.initialize_storages()
    await initialize_pipeline_status()

    return rag


def main():
    # Initialize RAG instance
    rag = asyncio.run(initialize_rag())

    with open("./book.txt", "r", encoding="utf-8") as f:
        rag.insert(f.read())

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

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

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

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


if __name__ == "__main__":
    main()