72 lines
1.8 KiB
Python
72 lines
1.8 KiB
Python
|
import os
|
||
|
|
import json
|
||
|
|
import time
|
||
|
|
import numpy as np
|
||
|
|
|
||
|
|
from lightrag import LightRAG
|
||
|
|
from lightrag.utils import EmbeddingFunc
|
||
|
|
from lightrag.llm import openai_complete_if_cache, openai_embedding
|
||
|
|
|
||
|
|
|
||
|
|
## For Upstage API
|
||
|
|
# please check if embedding_dim=4096 in lightrag.py and llm.py in lightrag direcotry
|
||
|
|
async def llm_model_func(
|
||
|
|
prompt, system_prompt=None, history_messages=[], **kwargs
|
||
|
|
) -> str:
|
||
|
|
return await openai_complete_if_cache(
|
||
|
|
"solar-mini",
|
||
|
|
prompt,
|
||
|
|
system_prompt=system_prompt,
|
||
|
|
history_messages=history_messages,
|
||
|
|
api_key=os.getenv("UPSTAGE_API_KEY"),
|
||
|
|
base_url="https://api.upstage.ai/v1/solar",
|
||
|
|
**kwargs,
|
||
|
|
)
|
||
|
|
|
||
|
|
|
||
|
|
async def embedding_func(texts: list[str]) -> np.ndarray:
|
||
|
|
return await openai_embedding(
|
||
|
|
texts,
|
||
|
|
model="solar-embedding-1-large-query",
|
||
|
|
api_key=os.getenv("UPSTAGE_API_KEY"),
|
||
|
|
base_url="https://api.upstage.ai/v1/solar",
|
||
|
|
)
|
||
|
|
|
||
|
|
|
||
|
|
## /For Upstage API
|
||
|
|
|
||
|
|
|
||
|
|
def insert_text(rag, file_path):
|
||
|
|
with open(file_path, mode="r") as f:
|
||
|
|
unique_contexts = json.load(f)
|
||
|
|
|
||
|
|
retries = 0
|
||
|
|
max_retries = 3
|
||
|
|
while retries < max_retries:
|
||
|
|
try:
|
||
|
|
rag.insert(unique_contexts)
|
||
|
|
break
|
||
|
|
except Exception as e:
|
||
|
|
retries += 1
|
||
|
|
print(f"Insertion failed, retrying ({retries}/{max_retries}), error: {e}")
|
||
|
|
time.sleep(10)
|
||
|
|
if retries == max_retries:
|
||
|
|
print("Insertion failed after exceeding the maximum number of retries")
|
||
|
|
|
||
|
|
|
||
|
|
cls = "mix"
|
||
|
|
WORKING_DIR = f"../{cls}"
|
||
|
|
|
||
|
|
if not os.path.exists(WORKING_DIR):
|
||
|
|
os.mkdir(WORKING_DIR)
|
||
|
|
|
||
|
|
rag = LightRAG(
|
||
|
|
working_dir=WORKING_DIR,
|
||
|
|
llm_model_func=llm_model_func,
|
||
|
|
embedding_func=EmbeddingFunc(
|
||
|
|
embedding_dim=4096, max_token_size=8192, func=embedding_func
|
||
|
|
),
|
||
|
|
)
|
||
|
|
|
||
|
|
insert_text(rag, f"../datasets/unique_contexts/{cls}_unique_contexts.json")
|