feat: add persistent tiktoken cache to reduce re-downloads (#171)
Configure tiktoken to cache tokenizer encodings in ./data/tiktoken-cache instead of using system temp directory. This prevents re-downloading encoding files on every container restart and improves startup time. Changes: - Add TIKTOKEN_CACHE_DIR configuration in config.py - Set TIKTOKEN_CACHE_DIR environment variable in token_utils.py - Bump version to 1.0.7
This commit is contained in:
parent
dd79d7a511
commit
aa593c60bd
4 changed files with 23 additions and 12 deletions
|
|
@ -11,3 +11,7 @@ LANGGRAPH_CHECKPOINT_FILE = f"{sqlite_folder}/checkpoints.sqlite"
|
|||
# UPLOADS FOLDER
|
||||
UPLOADS_FOLDER = f"{DATA_FOLDER}/uploads"
|
||||
os.makedirs(UPLOADS_FOLDER, exist_ok=True)
|
||||
|
||||
# TIKTOKEN CACHE FOLDER
|
||||
TIKTOKEN_CACHE_DIR = f"{DATA_FOLDER}/tiktoken-cache"
|
||||
os.makedirs(TIKTOKEN_CACHE_DIR, exist_ok=True)
|
||||
|
|
|
|||
|
|
@ -3,6 +3,13 @@ Token utilities for Open Notebook.
|
|||
Handles token counting and cost calculations for language models.
|
||||
"""
|
||||
|
||||
import os
|
||||
from open_notebook.config import TIKTOKEN_CACHE_DIR
|
||||
|
||||
# Set tiktoken cache directory before importing tiktoken to ensure
|
||||
# tokenizer encodings are cached persistently in the data folder
|
||||
os.environ["TIKTOKEN_CACHE_DIR"] = TIKTOKEN_CACHE_DIR
|
||||
|
||||
|
||||
def token_count(input_string: str) -> int:
|
||||
"""
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
[project]
|
||||
name = "open-notebook"
|
||||
version = "1.0.6"
|
||||
version = "1.0.7"
|
||||
description = "An open source implementation of a research assistant, inspired by Google Notebook LM"
|
||||
authors = [
|
||||
{name = "Luis Novo", email = "lfnovo@gmail.com"}
|
||||
|
|
|
|||
22
uv.lock
22
uv.lock
|
|
@ -2208,7 +2208,7 @@ wheels = [
|
|||
|
||||
[[package]]
|
||||
name = "open-notebook"
|
||||
version = "1.0.6"
|
||||
version = "1.0.7"
|
||||
source = { editable = "." }
|
||||
dependencies = [
|
||||
{ name = "ai-prompter" },
|
||||
|
|
@ -2741,18 +2741,18 @@ wheels = [
|
|||
|
||||
[[package]]
|
||||
name = "psutil"
|
||||
version = "7.1.0"
|
||||
version = "7.1.1"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/b3/31/4723d756b59344b643542936e37a31d1d3204bcdc42a7daa8ee9eb06fb50/psutil-7.1.0.tar.gz", hash = "sha256:655708b3c069387c8b77b072fc429a57d0e214221d01c0a772df7dfedcb3bcd2", size = 497660, upload-time = "2025-09-17T20:14:52.902Z" }
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/89/fc/889242351a932d6183eec5df1fc6539b6f36b6a88444f1e63f18668253aa/psutil-7.1.1.tar.gz", hash = "sha256:092b6350145007389c1cfe5716050f02030a05219d90057ea867d18fe8d372fc", size = 487067, upload-time = "2025-10-19T15:43:59.373Z" }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/46/62/ce4051019ee20ce0ed74432dd73a5bb087a6704284a470bb8adff69a0932/psutil-7.1.0-cp36-abi3-macosx_10_9_x86_64.whl", hash = "sha256:76168cef4397494250e9f4e73eb3752b146de1dd950040b29186d0cce1d5ca13", size = 245242, upload-time = "2025-09-17T20:14:56.126Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/38/61/f76959fba841bf5b61123fbf4b650886dc4094c6858008b5bf73d9057216/psutil-7.1.0-cp36-abi3-macosx_11_0_arm64.whl", hash = "sha256:5d007560c8c372efdff9e4579c2846d71de737e4605f611437255e81efcca2c5", size = 246682, upload-time = "2025-09-17T20:14:58.25Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/88/7a/37c99d2e77ec30d63398ffa6a660450b8a62517cabe44b3e9bae97696e8d/psutil-7.1.0-cp36-abi3-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:22e4454970b32472ce7deaa45d045b34d3648ce478e26a04c7e858a0a6e75ff3", size = 287994, upload-time = "2025-09-17T20:14:59.901Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/9d/de/04c8c61232f7244aa0a4b9a9fbd63a89d5aeaf94b2fc9d1d16e2faa5cbb0/psutil-7.1.0-cp36-abi3-manylinux_2_12_x86_64.manylinux2010_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8c70e113920d51e89f212dd7be06219a9b88014e63a4cec69b684c327bc474e3", size = 291163, upload-time = "2025-09-17T20:15:01.481Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/f4/58/c4f976234bf6d4737bc8c02a81192f045c307b72cf39c9e5c5a2d78927f6/psutil-7.1.0-cp36-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7d4a113425c037300de3ac8b331637293da9be9713855c4fc9d2d97436d7259d", size = 293625, upload-time = "2025-09-17T20:15:04.492Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/79/87/157c8e7959ec39ced1b11cc93c730c4fb7f9d408569a6c59dbd92ceb35db/psutil-7.1.0-cp37-abi3-win32.whl", hash = "sha256:09ad740870c8d219ed8daae0ad3b726d3bf9a028a198e7f3080f6a1888b99bca", size = 244812, upload-time = "2025-09-17T20:15:07.462Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/bf/e9/b44c4f697276a7a95b8e94d0e320a7bf7f3318521b23de69035540b39838/psutil-7.1.0-cp37-abi3-win_amd64.whl", hash = "sha256:57f5e987c36d3146c0dd2528cd42151cf96cd359b9d67cfff836995cc5df9a3d", size = 247965, upload-time = "2025-09-17T20:15:09.673Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/26/65/1070a6e3c036f39142c2820c4b52e9243246fcfc3f96239ac84472ba361e/psutil-7.1.0-cp37-abi3-win_arm64.whl", hash = "sha256:6937cb68133e7c97b6cc9649a570c9a18ba0efebed46d8c5dae4c07fa1b67a07", size = 244971, upload-time = "2025-09-17T20:15:12.262Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/51/30/f97f8fb1f9ecfbeae4b5ca738dcae66ab28323b5cfbc96cb5565f3754056/psutil-7.1.1-cp36-abi3-macosx_10_9_x86_64.whl", hash = "sha256:8fa59d7b1f01f0337f12cd10dbd76e4312a4d3c730a4fedcbdd4e5447a8b8460", size = 244221, upload-time = "2025-10-19T15:44:03.145Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/7b/98/b8d1f61ebf35f4dbdbaabadf9208282d8adc820562f0257e5e6e79e67bf2/psutil-7.1.1-cp36-abi3-macosx_11_0_arm64.whl", hash = "sha256:2a95104eae85d088891716db676f780c1404fc15d47fde48a46a5d61e8f5ad2c", size = 245660, upload-time = "2025-10-19T15:44:05.657Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/f0/4a/b8015d7357fefdfe34bc4a3db48a107bae4bad0b94fb6eb0613f09a08ada/psutil-7.1.1-cp36-abi3-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:98629cd8567acefcc45afe2f4ba1e9290f579eacf490a917967decce4b74ee9b", size = 286963, upload-time = "2025-10-19T15:44:08.877Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/3d/3c/b56076bb35303d0733fc47b110a1c9cce081a05ae2e886575a3587c1ee76/psutil-7.1.1-cp36-abi3-manylinux_2_12_x86_64.manylinux2010_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:92ebc58030fb054fa0f26c3206ef01c31c29d67aee1367e3483c16665c25c8d2", size = 290118, upload-time = "2025-10-19T15:44:11.897Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/dc/af/c13d360c0adc6f6218bf9e2873480393d0f729c8dd0507d171f53061c0d3/psutil-7.1.1-cp36-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:146a704f224fb2ded2be3da5ac67fc32b9ea90c45b51676f9114a6ac45616967", size = 292587, upload-time = "2025-10-19T15:44:14.67Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/90/2d/c933e7071ba60c7862813f2c7108ec4cf8304f1c79660efeefd0de982258/psutil-7.1.1-cp37-abi3-win32.whl", hash = "sha256:295c4025b5cd880f7445e4379e6826f7307e3d488947bf9834e865e7847dc5f7", size = 243772, upload-time = "2025-10-19T15:44:16.938Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/be/f3/11fd213fff15427bc2853552138760c720fd65032d99edfb161910d04127/psutil-7.1.1-cp37-abi3-win_amd64.whl", hash = "sha256:9b4f17c5f65e44f69bd3a3406071a47b79df45cf2236d1f717970afcb526bcd3", size = 246936, upload-time = "2025-10-19T15:44:18.663Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/0a/8d/8a9a45c8b655851f216c1d44f68e3533dc8d2c752ccd0f61f1aa73be4893/psutil-7.1.1-cp37-abi3-win_arm64.whl", hash = "sha256:5457cf741ca13da54624126cd5d333871b454ab133999a9a103fb097a7d7d21a", size = 243944, upload-time = "2025-10-19T15:44:20.666Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
|
|
|
|||
Loading…
Reference in a new issue