hz/ebiz-dify-ai
1
0
Fork 0
mirror of http://112.124.100.131/huang.ze/ebiz-dify-ai.git synced 2025-12-22 09:16:53 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: backend model load balancing support (#4927)

Browse Source
This commit is contained in:
takatost
2024-06-05 00:13:04 +08:00
committed by GitHub
parent 52ec152dd3
commit d1dbbc1e33
47 changed files with 2191 additions and 256 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
api/core/rag/splitter/fixed_text_splitter.py
View File

@@ -1,10 +1,9 @@
"""Functionality for splitting text."""
from __future__ import annotations
from typing import Any, Optional, cast
from typing import Any, Optional
from core.model_manager import ModelInstance
from core.model_runtime.model_providers.__base.text_embedding_model import TextEmbeddingModel
from core.model_runtime.model_providers.__base.tokenizers.gpt2_tokenzier import GPT2Tokenizer
from core.rag.splitter.text_splitter import (
TS,
@@ -35,11 +34,7 @@ class EnhanceRecursiveCharacterTextSplitter(RecursiveCharacterTextSplitter):
return 0
if embedding_model_instance:
embedding_model_type_instance = embedding_model_instance.model_type_instance
embedding_model_type_instance = cast(TextEmbeddingModel, embedding_model_type_instance)
return embedding_model_type_instance.get_num_tokens(
model=embedding_model_instance.model,
credentials=embedding_model_instance.credentials,
return embedding_model_instance.get_text_embedding_num_tokens(
texts=[text]
)
else: