File size: 1,916 Bytes
8746512
f4c9977
8b3b01c
f4c9977
0553d6a
8746512
f4c9977
8b3b01c
f4c9977
 
 
 
 
 
 
 
 
275e33e
 
8b3b01c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f4c9977
8b3b01c
f4c9977
8b3b01c
 
f4c9977
8b3b01c
f4c9977
275e33e
f4c9977
 
 
 
8746512
275e33e
8b3b01c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import inspect
import os
import asyncio
from lightrag import LightRAG
from lightrag.llm import openai_complete, openai_embed
from lightrag.utils import EmbeddingFunc, always_get_an_event_loop
from lightrag import QueryParam
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, "dickens")
if not os.path.exists(WORKING_DIR):
    os.mkdir(WORKING_DIR)
print(f"WorkingDir: {WORKING_DIR}")

api_key = "empty"


async def initialize_rag():
    rag = LightRAG(
        working_dir=WORKING_DIR,
        llm_model_func=openai_complete,
        llm_model_name="qwen2.5-14b-instruct@4bit",
        llm_model_max_async=4,
        llm_model_max_token_size=32768,
        llm_model_kwargs={"base_url": "http://127.0.0.1:1234/v1", "api_key": api_key},
        embedding_func=EmbeddingFunc(
            embedding_dim=1024,
            max_token_size=8192,
            func=lambda texts: openai_embed(
                texts=texts,
                model="text-embedding-bge-m3",
                base_url="http://127.0.0.1:1234/v1",
                api_key=api_key,
            ),
        ),
    )

    await rag.initialize_storages()
    await initialize_pipeline_status()

    return rag


async def print_stream(stream):
    async for chunk in stream:
        if chunk:
            print(chunk, end="", flush=True)


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

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

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

    loop = always_get_an_event_loop()
    if inspect.isasyncgen(resp):
        loop.run_until_complete(print_stream(resp))
    else:
        print(resp)


if __name__ == "__main__":
    main()