File size: 7,311 Bytes
046051b
 
77d8960
 
 
046051b
77d8960
 
 
8b3b01c
046051b
15ee612
 
 
 
046051b
df22b26
77d8960
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
046051b
 
 
df22b26
046051b
94cd4d3
046051b
 
15ee612
046051b
 
 
15ee612
 
df22b26
046051b
 
df22b26
77d8960
 
 
 
 
 
8b3b01c
 
 
 
 
15ee612
 
 
 
 
 
 
8b3b01c
 
 
 
 
9590c46
8b3b01c
275e33e
 
7441782
 
15ee612
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8b3b01c
9f4950c
046051b
15ee612
 
 
 
 
 
 
 
 
 
7441782
4ea4897
046051b
7441782
77d8960
 
 
 
 
 
7441782
77d8960
 
 
 
046051b
7441782
77d8960
 
 
 
 
 
7441782
77d8960
 
 
 
046051b
7441782
77d8960
 
 
 
 
 
7441782
77d8960
 
 
 
046051b
7441782
77d8960
 
 
 
 
 
7441782
77d8960
 
 
 
 
7441782
 
77d8960
 
 
046051b
9590c46
7441782
77d8960
 
9590c46
77d8960
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
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
import os
import asyncio
import inspect
import logging
import logging.config
from lightrag import LightRAG, QueryParam
from lightrag.llm.openai import openai_complete_if_cache
from lightrag.llm.ollama import ollama_embed
from lightrag.utils import EmbeddingFunc, logger, set_verbose_debug
from lightrag.kg.shared_storage import initialize_pipeline_status

from dotenv import load_dotenv

load_dotenv(dotenv_path=".env", override=False)

WORKING_DIR = "./dickens"


def configure_logging():
    """Configure logging for the application"""

    # Reset any existing handlers to ensure clean configuration
    for logger_name in ["uvicorn", "uvicorn.access", "uvicorn.error", "lightrag"]:
        logger_instance = logging.getLogger(logger_name)
        logger_instance.handlers = []
        logger_instance.filters = []

    # Get log directory path from environment variable or use current directory
    log_dir = os.getenv("LOG_DIR", os.getcwd())
    log_file_path = os.path.abspath(
        os.path.join(log_dir, "lightrag_compatible_demo.log")
    )

    print(f"\nLightRAG compatible demo log file: {log_file_path}\n")
    os.makedirs(os.path.dirname(log_dir), exist_ok=True)

    # Get log file max size and backup count from environment variables
    log_max_bytes = int(os.getenv("LOG_MAX_BYTES", 10485760))  # Default 10MB
    log_backup_count = int(os.getenv("LOG_BACKUP_COUNT", 5))  # Default 5 backups

    logging.config.dictConfig(
        {
            "version": 1,
            "disable_existing_loggers": False,
            "formatters": {
                "default": {
                    "format": "%(levelname)s: %(message)s",
                },
                "detailed": {
                    "format": "%(asctime)s - %(name)s - %(levelname)s - %(message)s",
                },
            },
            "handlers": {
                "console": {
                    "formatter": "default",
                    "class": "logging.StreamHandler",
                    "stream": "ext://sys.stderr",
                },
                "file": {
                    "formatter": "detailed",
                    "class": "logging.handlers.RotatingFileHandler",
                    "filename": log_file_path,
                    "maxBytes": log_max_bytes,
                    "backupCount": log_backup_count,
                    "encoding": "utf-8",
                },
            },
            "loggers": {
                "lightrag": {
                    "handlers": ["console", "file"],
                    "level": "INFO",
                    "propagate": False,
                },
            },
        }
    )

    # Set the logger level to INFO
    logger.setLevel(logging.INFO)
    # Enable verbose debug if needed
    set_verbose_debug(os.getenv("VERBOSE_DEBUG", "false").lower() == "true")


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


async def llm_model_func(
    prompt, system_prompt=None, history_messages=[], keyword_extraction=False, **kwargs
) -> str:
    return await openai_complete_if_cache(
        os.getenv("LLM_MODEL", "deepseek-chat"),
        prompt,
        system_prompt=system_prompt,
        history_messages=history_messages,
        api_key=os.getenv("LLM_BINDING_API_KEY") or os.getenv("OPENAI_API_KEY"),
        base_url=os.getenv("LLM_BINDING_HOST", "https://api.deepseek.com"),
        **kwargs,
    )


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


async def initialize_rag():
    rag = LightRAG(
        working_dir=WORKING_DIR,
        llm_model_func=llm_model_func,
        embedding_func=EmbeddingFunc(
            embedding_dim=int(os.getenv("EMBEDDING_DIM", "1024")),
            max_token_size=int(os.getenv("MAX_EMBED_TOKENS", "8192")),
            func=lambda texts: ollama_embed(
                texts,
                embed_model=os.getenv("EMBEDDING_MODEL", "bge-m3:latest"),
                host=os.getenv("EMBEDDING_BINDING_HOST", "http://localhost:11434"),
            ),
        ),
    )

    await rag.initialize_storages()
    await initialize_pipeline_status()

    return rag


async def main():
    try:
        # Clear old data files
        files_to_delete = [
            "graph_chunk_entity_relation.graphml",
            "kv_store_doc_status.json",
            "kv_store_full_docs.json",
            "kv_store_text_chunks.json",
            "vdb_chunks.json",
            "vdb_entities.json",
            "vdb_relationships.json",
        ]

        for file in files_to_delete:
            file_path = os.path.join(WORKING_DIR, file)
            if os.path.exists(file_path):
                os.remove(file_path)
                print(f"Deleting old file:: {file_path}")

        # Initialize RAG instance
        rag = await initialize_rag()

        # Test embedding function
        test_text = ["This is a test string for embedding."]
        embedding = await rag.embedding_func(test_text)
        embedding_dim = embedding.shape[1]
        print("\n=======================")
        print("Test embedding function")
        print("========================")
        print(f"Test dict: {test_text}")
        print(f"Detected embedding dimension: {embedding_dim}\n\n")

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

        # Perform naive search
        print("\n=====================")
        print("Query mode: naive")
        print("=====================")
        resp = await rag.aquery(
            "What are the top themes in this story?",
            param=QueryParam(mode="naive", stream=True),
        )
        if inspect.isasyncgen(resp):
            await print_stream(resp)
        else:
            print(resp)

        # Perform local search
        print("\n=====================")
        print("Query mode: local")
        print("=====================")
        resp = await rag.aquery(
            "What are the top themes in this story?",
            param=QueryParam(mode="local", stream=True),
        )
        if inspect.isasyncgen(resp):
            await print_stream(resp)
        else:
            print(resp)

        # Perform global search
        print("\n=====================")
        print("Query mode: global")
        print("=====================")
        resp = await rag.aquery(
            "What are the top themes in this story?",
            param=QueryParam(mode="global", stream=True),
        )
        if inspect.isasyncgen(resp):
            await print_stream(resp)
        else:
            print(resp)

        # Perform hybrid search
        print("\n=====================")
        print("Query mode: hybrid")
        print("=====================")
        resp = await rag.aquery(
            "What are the top themes in this story?",
            param=QueryParam(mode="hybrid", stream=True),
        )
        if inspect.isasyncgen(resp):
            await print_stream(resp)
        else:
            print(resp)

    except Exception as e:
        print(f"An error occurred: {e}")
    finally:
        if rag:
            await rag.finalize_storages()


if __name__ == "__main__":
    # Configure logging before running the main function
    configure_logging()
    asyncio.run(main())
    print("\nDone!")