This commit is contained in:
Timothy J. Baek
2024-10-25 21:46:14 -07:00
parent 50dcad0f73
commit 780591e991
3 changed files with 13 additions and 11 deletions

View File

@@ -14,6 +14,7 @@ from typing import Iterator, Optional, Sequence, Union
from fastapi import Depends, FastAPI, File, Form, HTTPException, UploadFile, status
from fastapi.middleware.cors import CORSMiddleware
from pydantic import BaseModel
import tiktoken
from open_webui.storage.provider import Storage
@@ -50,7 +51,7 @@ from open_webui.apps.retrieval.utils import (
from open_webui.apps.webui.models.files import Files
from open_webui.config import (
BRAVE_SEARCH_API_KEY,
TIKTOKEN_ENCODING_MODEL_NAME,
TIKTOKEN_ENCODING_NAME,
RAG_TEXT_SPLITTER,
CHUNK_OVERLAP,
CHUNK_SIZE,
@@ -135,7 +136,7 @@ app.state.config.CONTENT_EXTRACTION_ENGINE = CONTENT_EXTRACTION_ENGINE
app.state.config.TIKA_SERVER_URL = TIKA_SERVER_URL
app.state.config.TEXT_SPLITTER = RAG_TEXT_SPLITTER
app.state.config.TIKTOKEN_ENCODING_MODEL_NAME = TIKTOKEN_ENCODING_MODEL_NAME
app.state.config.TIKTOKEN_ENCODING_NAME = TIKTOKEN_ENCODING_NAME
app.state.config.CHUNK_SIZE = CHUNK_SIZE
app.state.config.CHUNK_OVERLAP = CHUNK_OVERLAP
@@ -666,8 +667,9 @@ def save_docs_to_vector_db(
add_start_index=True,
)
elif app.state.config.TEXT_SPLITTER == "token":
text_splitter = TokenTextSplitter(
model_name=app.state.config.TIKTOKEN_ENCODING_MODEL_NAME,
encoding_name=app.state.config.TIKTOKEN_ENCODING_NAME,
chunk_size=app.state.config.CHUNK_SIZE,
chunk_overlap=app.state.config.CHUNK_OVERLAP,
add_start_index=True,