File size: 2,091 Bytes
5098dd6 |
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 |
import os
import asyncio
from lightrag import LightRAG, QueryParam
from lightrag.llm.openai import gpt_4o_mini_complete, openai_embed
from lightrag.utils import EmbeddingFunc
import numpy as np
#########
# Uncomment the below two lines if running in a jupyter notebook to handle the async nature of rag.insert()
# import nest_asyncio
# nest_asyncio.apply()
#########
WORKING_DIR = "./mongodb_test_dir"
if not os.path.exists(WORKING_DIR):
os.mkdir(WORKING_DIR)
os.environ["OPENAI_API_KEY"] = "sk-"
os.environ["MONGO_URI"] = "mongodb://0.0.0.0:27017/?directConnection=true"
os.environ["MONGO_DATABASE"] = "LightRAG"
os.environ["MONGO_KG_COLLECTION"] = "MDB_KG"
# Embedding Configuration and Functions
EMBEDDING_MODEL = os.environ.get("EMBEDDING_MODEL", "text-embedding-3-large")
EMBEDDING_MAX_TOKEN_SIZE = int(os.environ.get("EMBEDDING_MAX_TOKEN_SIZE", 8192))
async def embedding_func(texts: list[str]) -> np.ndarray:
return await openai_embed(
texts,
model=EMBEDDING_MODEL,
)
async def get_embedding_dimension():
test_text = ["This is a test sentence."]
embedding = await embedding_func(test_text)
return embedding.shape[1]
async def create_embedding_function_instance():
# Get embedding dimension
embedding_dimension = await get_embedding_dimension()
# Create embedding function instance
return EmbeddingFunc(
embedding_dim=embedding_dimension,
max_token_size=EMBEDDING_MAX_TOKEN_SIZE,
func=embedding_func,
)
async def initialize_rag():
embedding_func_instance = await create_embedding_function_instance()
return LightRAG(
working_dir=WORKING_DIR,
llm_model_func=gpt_4o_mini_complete,
embedding_func=embedding_func_instance,
graph_storage="MongoGraphStorage",
log_level="DEBUG",
)
# Run the initialization
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"))
)
|