File size: 3,131 Bytes
e06a7a0 8b3b01c e06a7a0 8b3b01c e06a7a0 8b3b01c e06a7a0 5b0dc1f e06a7a0 5b0dc1f e06a7a0 5b0dc1f e06a7a0 275e33e 8b3b01c e06a7a0 9bc4562 5b0dc1f e06a7a0 8b3b01c 275e33e 8b3b01c e06a7a0 5b0dc1f |
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 |
import os
import logging
import asyncio
import numpy as np
from dotenv import load_dotenv
from sentence_transformers import SentenceTransformer
from openai import AzureOpenAI
from lightrag import LightRAG, QueryParam
from lightrag.utils import EmbeddingFunc
from lightrag.kg.shared_storage import initialize_pipeline_status
WORKING_DIR = "./dickens"
# Configure Logging
logging.basicConfig(level=logging.INFO)
# Load environment variables from .env file
load_dotenv()
AZURE_OPENAI_API_VERSION = os.getenv("AZURE_OPENAI_API_VERSION")
AZURE_OPENAI_DEPLOYMENT = os.getenv("AZURE_OPENAI_DEPLOYMENT")
AZURE_OPENAI_API_KEY = os.getenv("AZURE_OPENAI_API_KEY")
AZURE_OPENAI_ENDPOINT = os.getenv("AZURE_OPENAI_ENDPOINT")
async def llm_model_func(
prompt, system_prompt=None, history_messages=[], keyword_extraction=False, **kwargs
) -> str:
# Create a client for AzureOpenAI
client = AzureOpenAI(
api_key=AZURE_OPENAI_API_KEY,
api_version=AZURE_OPENAI_API_VERSION,
azure_endpoint=AZURE_OPENAI_ENDPOINT,
)
# Build the messages list for the conversation
messages = []
if system_prompt:
messages.append({"role": "system", "content": system_prompt})
if history_messages:
messages.extend(history_messages)
messages.append({"role": "user", "content": prompt})
# Call the LLM
chat_completion = client.chat.completions.create(
model=AZURE_OPENAI_DEPLOYMENT,
messages=messages,
temperature=kwargs.get("temperature", 0),
top_p=kwargs.get("top_p", 1),
n=kwargs.get("n", 1),
)
return chat_completion.choices[0].message.content
async def embedding_func(texts: list[str]) -> np.ndarray:
model = SentenceTransformer("all-MiniLM-L6-v2")
embeddings = model.encode(texts, convert_to_numpy=True)
return embeddings
async def initialize_rag():
rag = LightRAG(
working_dir=WORKING_DIR,
llm_model_func=llm_model_func,
embedding_func=EmbeddingFunc(
embedding_dim=384,
max_token_size=8192,
func=embedding_func,
),
vector_storage="FaissVectorDBStorage",
vector_db_storage_cls_kwargs={
"cosine_better_than_threshold": 0.2 # Your desired threshold
},
)
await rag.initialize_storages()
await initialize_pipeline_status()
return rag
def main():
# Initialize RAG instance
rag = asyncio.run(initialize_rag())
# Insert the custom chunks into LightRAG
book1 = open("./book_1.txt", encoding="utf-8")
book2 = open("./book_2.txt", encoding="utf-8")
rag.insert([book1.read(), book2.read()])
query_text = "What are the main themes?"
print("Result (Naive):")
print(rag.query(query_text, param=QueryParam(mode="naive")))
print("\nResult (Local):")
print(rag.query(query_text, param=QueryParam(mode="local")))
print("\nResult (Global):")
print(rag.query(query_text, param=QueryParam(mode="global")))
print("\nResult (Hybrid):")
print(rag.query(query_text, param=QueryParam(mode="hybrid")))
if __name__ == "__main__":
main()
|