File size: 4,342 Bytes
883904b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
import os
from lightrag import LightRAG, QueryParam
from lightrag.llm.llama_index_impl import (
    llama_index_complete_if_cache,
    llama_index_embed,
)
from lightrag.utils import EmbeddingFunc
from llama_index.llms.litellm import LiteLLM
from llama_index.embeddings.litellm import LiteLLMEmbedding
import asyncio
import nest_asyncio

nest_asyncio.apply()

from lightrag.kg.shared_storage import initialize_pipeline_status

# Configure working directory
WORKING_DIR = "./index_default"
print(f"WORKING_DIR: {WORKING_DIR}")

# Model configuration
LLM_MODEL = os.environ.get("LLM_MODEL", "gemma-3-4b")
print(f"LLM_MODEL: {LLM_MODEL}")
EMBEDDING_MODEL = os.environ.get("EMBEDDING_MODEL", "arctic-embed")
print(f"EMBEDDING_MODEL: {EMBEDDING_MODEL}")
EMBEDDING_MAX_TOKEN_SIZE = int(os.environ.get("EMBEDDING_MAX_TOKEN_SIZE", 8192))
print(f"EMBEDDING_MAX_TOKEN_SIZE: {EMBEDDING_MAX_TOKEN_SIZE}")

# LiteLLM configuration
LITELLM_URL = os.environ.get("LITELLM_URL", "http://localhost:4000")
print(f"LITELLM_URL: {LITELLM_URL}")
LITELLM_KEY = os.environ.get("LITELLM_KEY", "sk-4JdvGFKqSA3S0k_5p0xufw")

if not os.path.exists(WORKING_DIR):
    os.mkdir(WORKING_DIR)


# Initialize LLM function
async def llm_model_func(prompt, system_prompt=None, history_messages=[], **kwargs):
    try:
        # Initialize LiteLLM if not in kwargs
        if "llm_instance" not in kwargs:
            llm_instance = LiteLLM(
                model=f"openai/{LLM_MODEL}",  # Format: "provider/model_name"
                api_base=LITELLM_URL,
                api_key=LITELLM_KEY,
                temperature=0.7,
            )
            kwargs["llm_instance"] = llm_instance

        chat_kwargs = {}
        chat_kwargs["litellm_params"] = {
            "metadata": {
                "opik": {
                    "project_name": "lightrag_llamaindex_litellm_opik_demo",
                    "tags": ["lightrag", "litellm"],
                }
            }
        }

        response = await llama_index_complete_if_cache(
            kwargs["llm_instance"],
            prompt,
            system_prompt=system_prompt,
            history_messages=history_messages,
            chat_kwargs=chat_kwargs,
        )
        return response
    except Exception as e:
        print(f"LLM request failed: {str(e)}")
        raise


# Initialize embedding function
async def embedding_func(texts):
    try:
        embed_model = LiteLLMEmbedding(
            model_name=f"openai/{EMBEDDING_MODEL}",
            api_base=LITELLM_URL,
            api_key=LITELLM_KEY,
        )
        return await llama_index_embed(texts, embed_model=embed_model)
    except Exception as e:
        print(f"Embedding failed: {str(e)}")
        raise


# Get embedding dimension
async def get_embedding_dim():
    test_text = ["This is a test sentence."]
    embedding = await embedding_func(test_text)
    embedding_dim = embedding.shape[1]
    print(f"embedding_dim={embedding_dim}")
    return embedding_dim


async def initialize_rag():
    embedding_dimension = await get_embedding_dim()

    rag = LightRAG(
        working_dir=WORKING_DIR,
        llm_model_func=llm_model_func,
        embedding_func=EmbeddingFunc(
            embedding_dim=embedding_dimension,
            max_token_size=EMBEDDING_MAX_TOKEN_SIZE,
            func=embedding_func,
        ),
    )

    await rag.initialize_storages()
    await initialize_pipeline_status()

    return rag


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

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

    # Test different query modes
    print("\nNaive Search:")
    print(
        rag.query(
            "What are the top themes in this story?", param=QueryParam(mode="naive")
        )
    )

    print("\nLocal Search:")
    print(
        rag.query(
            "What are the top themes in this story?", param=QueryParam(mode="local")
        )
    )

    print("\nGlobal Search:")
    print(
        rag.query(
            "What are the top themes in this story?", param=QueryParam(mode="global")
        )
    )

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


if __name__ == "__main__":
    main()