Added PyPDF Loader and Splitter [Ready for Review] (#958)

Per discussion on Discord. This adds a PDF reader that uses `PyPDF` - a
simple PDF reader. It also tracks page numbers in a per split metadata.
Here's an example:

```python
from langchain.document_loaders import PagedPDFSplitter
from langchain.vectorstores import FAISS
from langchain.embeddings.openai import OpenAIEmbeddings

loader = PagedPDFSplitter(chunk_size=250)
splits, metadatas = loader.load_and_split("examples/example_data/layout-parser-paper.pdf")

faiss_index = FAISS.from_texts(splits, OpenAIEmbeddings(), metadatas=metadatas)
docs = faiss_index.similarity_search("How will the community be engaged?", k=2)
for doc in docs:
    print(doc.metadata["pages"] + ":", doc.page_content)
```

## TODO

- [x] Learn where to add `pypdf` as dependency for building docs
- [x] Add unit test?

---------

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
This commit is contained in:
Andrew White 2023-02-10 02:33:18 -05:00 committed by GitHub
parent ba54d36787
commit 9011f690c6
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
9 changed files with 408 additions and 182 deletions

View File

@ -0,0 +1,87 @@
{
"cells": [
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"# Paged PDF Splitter\n",
"\n",
"This notebook shows how to load a PDF file with the `PagedPDFSplitter`, which \n",
"uses the [pypdf](https://github.com/mstamy2/PyPDF2) library to read a \n",
"PDF file. **Note this reads & splits.** \n",
"\n",
"## Compared with other PDF Reader\n",
"Compared with the `unstructured` PDF reader, this one is local\n",
"and does not require an model - it just extracts text. This means it will\n",
"not work for scanned documents or PDFs containing images of text."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from langchain.document_loaders import PagedPDFSplitter\n",
"\n",
"loader = PagedPDFSplitter(chunk_size=250)\n",
"splits, metadatas = loader.load_and_split(\n",
" \"examples/example_data/layout-parser-paper.pdf\"\n",
")"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"## Using with document retrieval\n",
"\n",
"An advantage of this approach is that documents can be retrieved with page numbers."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from langchain.vectorstores import FAISS\n",
"from langchain.embeddings.openai import OpenAIEmbeddings\n",
"\n",
"faiss_index = FAISS.from_texts(splits, OpenAIEmbeddings(), metadatas=metadatas)\n",
"docs = faiss_index.similarity_search(\"How will the community be engaged?\", k=2)\n",
"for doc in docs:\n",
" print(doc.metadata[\"pages\"] + \":\", doc.page_content)"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.0"
},
"orig_nbformat": 4,
"vscode": {
"interpreter": {
"hash": "5c7b89af1651d0b8571dde13640ecdccf7d5a6204171d6ab33e7c296e100e08a"
}
}
},
"nbformat": 4,
"nbformat_minor": 2
}

View File

@ -15,6 +15,8 @@ There are a lot of different document loaders that LangChain supports. Below are
`PDF <./examples/pdf.html>`_: A walkthrough of how to load data from a PDF file. `PDF <./examples/pdf.html>`_: A walkthrough of how to load data from a PDF file.
`Paged PDF <./examples/paged_pdf_splitter.html>`_: A walkthrough of how to load data from a PDF file with a text reader while tracking page numbers.
`PowerPoint <./examples/powerpoint.html>`_: A walkthrough of how to load data from a powerpoint file. `PowerPoint <./examples/powerpoint.html>`_: A walkthrough of how to load data from a powerpoint file.
`Email <./examples/email.html>`_: A walkthrough of how to load data from an email (`.eml`) file. `Email <./examples/email.html>`_: A walkthrough of how to load data from an email (`.eml`) file.

View File

@ -13,6 +13,7 @@ from langchain.document_loaders.html import UnstructuredHTMLLoader
from langchain.document_loaders.imsdb import IMSDbLoader from langchain.document_loaders.imsdb import IMSDbLoader
from langchain.document_loaders.notion import NotionDirectoryLoader from langchain.document_loaders.notion import NotionDirectoryLoader
from langchain.document_loaders.obsidian import ObsidianLoader from langchain.document_loaders.obsidian import ObsidianLoader
from langchain.document_loaders.paged_pdf import PagedPDFSplitter
from langchain.document_loaders.pdf import UnstructuredPDFLoader from langchain.document_loaders.pdf import UnstructuredPDFLoader
from langchain.document_loaders.powerpoint import UnstructuredPowerPointLoader from langchain.document_loaders.powerpoint import UnstructuredPowerPointLoader
from langchain.document_loaders.readthedocs import ReadTheDocsLoader from langchain.document_loaders.readthedocs import ReadTheDocsLoader
@ -46,4 +47,5 @@ __all__ = [
"AZLyricsLoader", "AZLyricsLoader",
"CollegeConfidentialLoader", "CollegeConfidentialLoader",
"GutenbergLoader", "GutenbergLoader",
"PagedPDFSplitter",
] ]

View File

@ -0,0 +1,56 @@
"""Loads a PDF with pypdf and chunks at character level."""
from typing import Dict, List, Optional, Tuple
class PagedPDFSplitter:
"""Loads a PDF with pypdf and chunks at character level.
Loader also stores page numbers in metadatas.
"""
def __init__(self, chunk_size: int = 4000, chunk_overlap: int = 200):
"""Initialize with file path."""
try:
import pypdf # noqa:F401
except ImportError:
raise ValueError(
"pypdf package not found, please install it with " "`pip install pypdf`"
)
self.chunk_size = chunk_size
self.chunk_overlap = chunk_overlap
def load_and_split(
self, file_path: str, metadata: Optional[Dict] = None
) -> Tuple[List[str], List[Dict]]:
"""Load given path and split into texts and metadatas.
If given, the metadata given will
be duplicated and attached to each split along with page number.
If key is present in metadata, it also has page number
included (e.g., Foo2012 Pages 3-4).
"""
import pypdf
pdfFileObj = open(file_path, "rb")
pdfReader = pypdf.PdfReader(pdfFileObj)
splits = []
split = ""
pages = []
metadatas = []
key = (
metadata["key"] if metadata is not None and "key" in metadata else file_path
)
for i, page in enumerate(pdfReader.pages):
split += page.extract_text()
pages.append(str(i + 1))
if len(split) > self.chunk_size or i == len(pdfReader.pages) - 1:
splits.append(split[: self.chunk_size])
# pretty formatting of pages (e.g. 1-3, 4, 5-7)
pg = "-".join([pages[0], pages[-1]])
metadatas.append(dict(key=f"{key} pages {pg}", pages=pg))
if metadata is not None:
metadatas[-1].update(metadata)
split = str(splits[self.chunk_size: self.chunk_overlap])
pages = [str(i + 1)]
pdfFileObj.close()
return splits, metadatas

418
poetry.lock generated
View File

@ -384,14 +384,14 @@ files = [
[[package]] [[package]]
name = "beautifulsoup4" name = "beautifulsoup4"
version = "4.11.1" version = "4.11.2"
description = "Screen-scraping library" description = "Screen-scraping library"
category = "main" category = "main"
optional = false optional = false
python-versions = ">=3.6.0" python-versions = ">=3.6.0"
files = [ files = [
{file = "beautifulsoup4-4.11.1-py3-none-any.whl", hash = "sha256:58d5c3d29f5a36ffeb94f02f0d786cd53014cf9b3b3951d42e0080d8a9498d30"}, {file = "beautifulsoup4-4.11.2-py3-none-any.whl", hash = "sha256:0e79446b10b3ecb499c1556f7e228a53e64a2bfcebd455f370d8927cb5b59e39"},
{file = "beautifulsoup4-4.11.1.tar.gz", hash = "sha256:ad9aa55b65ef2808eb405f46cf74df7fcb7044d5cbc26487f96eb2ef2e436693"}, {file = "beautifulsoup4-4.11.2.tar.gz", hash = "sha256:bc4bdda6717de5a2987436fb8d72f45dc90dd856bdfd512a1314ce90349a0106"},
] ]
[package.dependencies] [package.dependencies]
@ -403,32 +403,46 @@ lxml = ["lxml"]
[[package]] [[package]]
name = "black" name = "black"
version = "22.12.0" version = "23.1.0"
description = "The uncompromising code formatter." description = "The uncompromising code formatter."
category = "dev" category = "main"
optional = false optional = false
python-versions = ">=3.7" python-versions = ">=3.7"
files = [ files = [
{file = "black-22.12.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9eedd20838bd5d75b80c9f5487dbcb06836a43833a37846cf1d8c1cc01cef59d"}, {file = "black-23.1.0-cp310-cp310-macosx_10_16_arm64.whl", hash = "sha256:b6a92a41ee34b883b359998f0c8e6eb8e99803aa8bf3123bf2b2e6fec505a221"},
{file = "black-22.12.0-cp310-cp310-win_amd64.whl", hash = "sha256:159a46a4947f73387b4d83e87ea006dbb2337eab6c879620a3ba52699b1f4351"}, {file = "black-23.1.0-cp310-cp310-macosx_10_16_universal2.whl", hash = "sha256:57c18c5165c1dbe291d5306e53fb3988122890e57bd9b3dcb75f967f13411a26"},
{file = "black-22.12.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d30b212bffeb1e252b31dd269dfae69dd17e06d92b87ad26e23890f3efea366f"}, {file = "black-23.1.0-cp310-cp310-macosx_10_16_x86_64.whl", hash = "sha256:9880d7d419bb7e709b37e28deb5e68a49227713b623c72b2b931028ea65f619b"},
{file = "black-22.12.0-cp311-cp311-win_amd64.whl", hash = "sha256:7412e75863aa5c5411886804678b7d083c7c28421210180d67dfd8cf1221e1f4"}, {file = "black-23.1.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e6663f91b6feca5d06f2ccd49a10f254f9298cc1f7f49c46e498a0771b507104"},
{file = "black-22.12.0-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c116eed0efb9ff870ded8b62fe9f28dd61ef6e9ddd28d83d7d264a38417dcee2"}, {file = "black-23.1.0-cp310-cp310-win_amd64.whl", hash = "sha256:9afd3f493666a0cd8f8df9a0200c6359ac53940cbde049dcb1a7eb6ee2dd7074"},
{file = "black-22.12.0-cp37-cp37m-win_amd64.whl", hash = "sha256:1f58cbe16dfe8c12b7434e50ff889fa479072096d79f0a7f25e4ab8e94cd8350"}, {file = "black-23.1.0-cp311-cp311-macosx_10_16_arm64.whl", hash = "sha256:bfffba28dc52a58f04492181392ee380e95262af14ee01d4bc7bb1b1c6ca8d27"},
{file = "black-22.12.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:77d86c9f3db9b1bf6761244bc0b3572a546f5fe37917a044e02f3166d5aafa7d"}, {file = "black-23.1.0-cp311-cp311-macosx_10_16_universal2.whl", hash = "sha256:c1c476bc7b7d021321e7d93dc2cbd78ce103b84d5a4cf97ed535fbc0d6660648"},
{file = "black-22.12.0-cp38-cp38-win_amd64.whl", hash = "sha256:82d9fe8fee3401e02e79767016b4907820a7dc28d70d137eb397b92ef3cc5bfc"}, {file = "black-23.1.0-cp311-cp311-macosx_10_16_x86_64.whl", hash = "sha256:382998821f58e5c8238d3166c492139573325287820963d2f7de4d518bd76958"},
{file = "black-22.12.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:101c69b23df9b44247bd88e1d7e90154336ac4992502d4197bdac35dd7ee3320"}, {file = "black-23.1.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2bf649fda611c8550ca9d7592b69f0637218c2369b7744694c5e4902873b2f3a"},
{file = "black-22.12.0-cp39-cp39-win_amd64.whl", hash = "sha256:559c7a1ba9a006226f09e4916060982fd27334ae1998e7a38b3f33a37f7a2148"}, {file = "black-23.1.0-cp311-cp311-win_amd64.whl", hash = "sha256:121ca7f10b4a01fd99951234abdbd97728e1240be89fde18480ffac16503d481"},
{file = "black-22.12.0-py3-none-any.whl", hash = "sha256:436cc9167dd28040ad90d3b404aec22cedf24a6e4d7de221bec2730ec0c97bcf"}, {file = "black-23.1.0-cp37-cp37m-macosx_10_16_x86_64.whl", hash = "sha256:a8471939da5e824b891b25751955be52ee7f8a30a916d570a5ba8e0f2eb2ecad"},
{file = "black-22.12.0.tar.gz", hash = "sha256:229351e5a18ca30f447bf724d007f890f97e13af070bb6ad4c0a441cd7596a2f"}, {file = "black-23.1.0-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8178318cb74f98bc571eef19068f6ab5613b3e59d4f47771582f04e175570ed8"},
{file = "black-23.1.0-cp37-cp37m-win_amd64.whl", hash = "sha256:a436e7881d33acaf2536c46a454bb964a50eff59b21b51c6ccf5a40601fbef24"},
{file = "black-23.1.0-cp38-cp38-macosx_10_16_arm64.whl", hash = "sha256:a59db0a2094d2259c554676403fa2fac3473ccf1354c1c63eccf7ae65aac8ab6"},
{file = "black-23.1.0-cp38-cp38-macosx_10_16_universal2.whl", hash = "sha256:0052dba51dec07ed029ed61b18183942043e00008ec65d5028814afaab9a22fd"},
{file = "black-23.1.0-cp38-cp38-macosx_10_16_x86_64.whl", hash = "sha256:49f7b39e30f326a34b5c9a4213213a6b221d7ae9d58ec70df1c4a307cf2a1580"},
{file = "black-23.1.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:162e37d49e93bd6eb6f1afc3e17a3d23a823042530c37c3c42eeeaf026f38468"},
{file = "black-23.1.0-cp38-cp38-win_amd64.whl", hash = "sha256:8b70eb40a78dfac24842458476135f9b99ab952dd3f2dab738c1881a9b38b753"},
{file = "black-23.1.0-cp39-cp39-macosx_10_16_arm64.whl", hash = "sha256:a29650759a6a0944e7cca036674655c2f0f63806ddecc45ed40b7b8aa314b651"},
{file = "black-23.1.0-cp39-cp39-macosx_10_16_universal2.whl", hash = "sha256:bb460c8561c8c1bec7824ecbc3ce085eb50005883a6203dcfb0122e95797ee06"},
{file = "black-23.1.0-cp39-cp39-macosx_10_16_x86_64.whl", hash = "sha256:c91dfc2c2a4e50df0026f88d2215e166616e0c80e86004d0003ece0488db2739"},
{file = "black-23.1.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2a951cc83ab535d248c89f300eccbd625e80ab880fbcfb5ac8afb5f01a258ac9"},
{file = "black-23.1.0-cp39-cp39-win_amd64.whl", hash = "sha256:0680d4380db3719ebcfb2613f34e86c8e6d15ffeabcf8ec59355c5e7b85bb555"},
{file = "black-23.1.0-py3-none-any.whl", hash = "sha256:7a0f701d314cfa0896b9001df70a530eb2472babb76086344e688829efd97d32"},
{file = "black-23.1.0.tar.gz", hash = "sha256:b0bd97bea8903f5a2ba7219257a44e3f1f9d00073d6cc1add68f0beec69692ac"},
] ]
[package.dependencies] [package.dependencies]
click = ">=8.0.0" click = ">=8.0.0"
mypy-extensions = ">=0.4.3" mypy-extensions = ">=0.4.3"
packaging = ">=22.0"
pathspec = ">=0.9.0" pathspec = ">=0.9.0"
platformdirs = ">=2" platformdirs = ">=2"
tomli = {version = ">=1.1.0", markers = "python_full_version < \"3.11.0a7\""} tomli = {version = ">=1.1.0", markers = "python_version < \"3.11\""}
typing-extensions = {version = ">=3.10.0.0", markers = "python_version < \"3.10\""} typing-extensions = {version = ">=3.10.0.0", markers = "python_version < \"3.10\""}
[package.extras] [package.extras]
@ -787,47 +801,49 @@ toml = ["tomli"]
[[package]] [[package]]
name = "cryptography" name = "cryptography"
version = "39.0.0" version = "39.0.1"
description = "cryptography is a package which provides cryptographic recipes and primitives to Python developers." description = "cryptography is a package which provides cryptographic recipes and primitives to Python developers."
category = "main" category = "main"
optional = false optional = false
python-versions = ">=3.6" python-versions = ">=3.6"
files = [ files = [
{file = "cryptography-39.0.0-cp36-abi3-macosx_10_12_universal2.whl", hash = "sha256:c52a1a6f81e738d07f43dab57831c29e57d21c81a942f4602fac7ee21b27f288"}, {file = "cryptography-39.0.1-cp36-abi3-macosx_10_12_universal2.whl", hash = "sha256:6687ef6d0a6497e2b58e7c5b852b53f62142cfa7cd1555795758934da363a965"},
{file = "cryptography-39.0.0-cp36-abi3-macosx_10_12_x86_64.whl", hash = "sha256:80ee674c08aaef194bc4627b7f2956e5ba7ef29c3cc3ca488cf15854838a8f72"}, {file = "cryptography-39.0.1-cp36-abi3-macosx_10_12_x86_64.whl", hash = "sha256:706843b48f9a3f9b9911979761c91541e3d90db1ca905fd63fee540a217698bc"},
{file = "cryptography-39.0.0-cp36-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.manylinux_2_24_aarch64.whl", hash = "sha256:887cbc1ea60786e534b00ba8b04d1095f4272d380ebd5f7a7eb4cc274710fad9"}, {file = "cryptography-39.0.1-cp36-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.manylinux_2_24_aarch64.whl", hash = "sha256:5d2d8b87a490bfcd407ed9d49093793d0f75198a35e6eb1a923ce1ee86c62b41"},
{file = "cryptography-39.0.0-cp36-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6f97109336df5c178ee7c9c711b264c502b905c2d2a29ace99ed761533a3460f"}, {file = "cryptography-39.0.1-cp36-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:83e17b26de248c33f3acffb922748151d71827d6021d98c70e6c1a25ddd78505"},
{file = "cryptography-39.0.0-cp36-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1a6915075c6d3a5e1215eab5d99bcec0da26036ff2102a1038401d6ef5bef25b"}, {file = "cryptography-39.0.1-cp36-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e124352fd3db36a9d4a21c1aa27fd5d051e621845cb87fb851c08f4f75ce8be6"},
{file = "cryptography-39.0.0-cp36-abi3-manylinux_2_24_x86_64.whl", hash = "sha256:76c24dd4fd196a80f9f2f5405a778a8ca132f16b10af113474005635fe7e066c"}, {file = "cryptography-39.0.1-cp36-abi3-manylinux_2_24_x86_64.whl", hash = "sha256:5aa67414fcdfa22cf052e640cb5ddc461924a045cacf325cd164e65312d99502"},
{file = "cryptography-39.0.0-cp36-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:bae6c7f4a36a25291b619ad064a30a07110a805d08dc89984f4f441f6c1f3f96"}, {file = "cryptography-39.0.1-cp36-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:35f7c7d015d474f4011e859e93e789c87d21f6f4880ebdc29896a60403328f1f"},
{file = "cryptography-39.0.0-cp36-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:875aea1039d78557c7c6b4db2fe0e9d2413439f4676310a5f269dd342ca7a717"}, {file = "cryptography-39.0.1-cp36-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:f24077a3b5298a5a06a8e0536e3ea9ec60e4c7ac486755e5fb6e6ea9b3500106"},
{file = "cryptography-39.0.0-cp36-abi3-musllinux_1_1_aarch64.whl", hash = "sha256:f6c0db08d81ead9576c4d94bbb27aed8d7a430fa27890f39084c2d0e2ec6b0df"}, {file = "cryptography-39.0.1-cp36-abi3-musllinux_1_1_aarch64.whl", hash = "sha256:f0c64d1bd842ca2633e74a1a28033d139368ad959872533b1bab8c80e8240a0c"},
{file = "cryptography-39.0.0-cp36-abi3-musllinux_1_1_x86_64.whl", hash = "sha256:f3ed2d864a2fa1666e749fe52fb8e23d8e06b8012e8bd8147c73797c506e86f1"}, {file = "cryptography-39.0.1-cp36-abi3-musllinux_1_1_x86_64.whl", hash = "sha256:0f8da300b5c8af9f98111ffd512910bc792b4c77392a9523624680f7956a99d4"},
{file = "cryptography-39.0.0-cp36-abi3-win32.whl", hash = "sha256:f671c1bb0d6088e94d61d80c606d65baacc0d374e67bf895148883461cd848de"}, {file = "cryptography-39.0.1-cp36-abi3-win32.whl", hash = "sha256:fe913f20024eb2cb2f323e42a64bdf2911bb9738a15dba7d3cce48151034e3a8"},
{file = "cryptography-39.0.0-cp36-abi3-win_amd64.whl", hash = "sha256:e324de6972b151f99dc078defe8fb1b0a82c6498e37bff335f5bc6b1e3ab5a1e"}, {file = "cryptography-39.0.1-cp36-abi3-win_amd64.whl", hash = "sha256:ced4e447ae29ca194449a3f1ce132ded8fcab06971ef5f618605aacaa612beac"},
{file = "cryptography-39.0.0-pp38-pypy38_pp73-macosx_10_12_x86_64.whl", hash = "sha256:754978da4d0457e7ca176f58c57b1f9de6556591c19b25b8bcce3c77d314f5eb"}, {file = "cryptography-39.0.1-pp38-pypy38_pp73-macosx_10_12_x86_64.whl", hash = "sha256:807ce09d4434881ca3a7594733669bd834f5b2c6d5c7e36f8c00f691887042ad"},
{file = "cryptography-39.0.0-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1ee1fd0de9851ff32dbbb9362a4d833b579b4a6cc96883e8e6d2ff2a6bc7104f"}, {file = "cryptography-39.0.1-pp38-pypy38_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:c5caeb8188c24888c90b5108a441c106f7faa4c4c075a2bcae438c6e8ca73cef"},
{file = "cryptography-39.0.0-pp38-pypy38_pp73-manylinux_2_24_x86_64.whl", hash = "sha256:fec8b932f51ae245121c4671b4bbc030880f363354b2f0e0bd1366017d891458"}, {file = "cryptography-39.0.1-pp38-pypy38_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:4789d1e3e257965e960232345002262ede4d094d1a19f4d3b52e48d4d8f3b885"},
{file = "cryptography-39.0.0-pp38-pypy38_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:407cec680e811b4fc829de966f88a7c62a596faa250fc1a4b520a0355b9bc190"}, {file = "cryptography-39.0.1-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:96f1157a7c08b5b189b16b47bc9db2332269d6680a196341bf30046330d15388"},
{file = "cryptography-39.0.0-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:7dacfdeee048814563eaaec7c4743c8aea529fe3dd53127313a792f0dadc1773"}, {file = "cryptography-39.0.1-pp39-pypy39_pp73-macosx_10_12_x86_64.whl", hash = "sha256:e422abdec8b5fa8462aa016786680720d78bdce7a30c652b7fadf83a4ba35336"},
{file = "cryptography-39.0.0-pp39-pypy39_pp73-macosx_10_12_x86_64.whl", hash = "sha256:ad04f413436b0781f20c52a661660f1e23bcd89a0e9bb1d6d20822d048cf2856"}, {file = "cryptography-39.0.1-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.manylinux_2_24_aarch64.whl", hash = "sha256:b0afd054cd42f3d213bf82c629efb1ee5f22eba35bf0eec88ea9ea7304f511a2"},
{file = "cryptography-39.0.0-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:50386acb40fbabbceeb2986332f0287f50f29ccf1497bae31cf5c3e7b4f4b34f"}, {file = "cryptography-39.0.1-pp39-pypy39_pp73-manylinux_2_24_x86_64.whl", hash = "sha256:6f8ba7f0328b79f08bdacc3e4e66fb4d7aab0c3584e0bd41328dce5262e26b2e"},
{file = "cryptography-39.0.0-pp39-pypy39_pp73-manylinux_2_24_x86_64.whl", hash = "sha256:e5d71c5d5bd5b5c3eebcf7c5c2bb332d62ec68921a8c593bea8c394911a005ce"}, {file = "cryptography-39.0.1-pp39-pypy39_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:ef8b72fa70b348724ff1218267e7f7375b8de4e8194d1636ee60510aae104cd0"},
{file = "cryptography-39.0.0-pp39-pypy39_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:844ad4d7c3850081dffba91cdd91950038ee4ac525c575509a42d3fc806b83c8"}, {file = "cryptography-39.0.1-pp39-pypy39_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:aec5a6c9864be7df2240c382740fcf3b96928c46604eaa7f3091f58b878c0bb6"},
{file = "cryptography-39.0.0-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:e0a05aee6a82d944f9b4edd6a001178787d1546ec7c6223ee9a848a7ade92e39"}, {file = "cryptography-39.0.1-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:fdd188c8a6ef8769f148f88f859884507b954cc64db6b52f66ef199bb9ad660a"},
{file = "cryptography-39.0.0.tar.gz", hash = "sha256:f964c7dcf7802d133e8dbd1565914fa0194f9d683d82411989889ecd701e8adf"}, {file = "cryptography-39.0.1.tar.gz", hash = "sha256:d1f6198ee6d9148405e49887803907fe8962a23e6c6f83ea7d98f1c0de375695"},
] ]
[package.dependencies] [package.dependencies]
cffi = ">=1.12" cffi = ">=1.12"
[package.extras] [package.extras]
docs = ["sphinx (>=1.6.5,!=1.8.0,!=3.1.0,!=3.1.1,!=5.2.0,!=5.2.0.post0)", "sphinx-rtd-theme"] docs = ["sphinx (>=5.3.0)", "sphinx-rtd-theme (>=1.1.1)"]
docstest = ["pyenchant (>=1.6.11)", "sphinxcontrib-spelling (>=4.0.1)", "twine (>=1.12.0)"] docstest = ["pyenchant (>=1.6.11)", "sphinxcontrib-spelling (>=4.0.1)", "twine (>=1.12.0)"]
pep8test = ["black", "ruff"] pep8test = ["black", "check-manifest", "mypy", "ruff", "types-pytz", "types-requests"]
sdist = ["setuptools-rust (>=0.11.4)"] sdist = ["setuptools-rust (>=0.11.4)"]
ssh = ["bcrypt (>=3.1.5)"] ssh = ["bcrypt (>=3.1.5)"]
test = ["hypothesis (>=1.11.4,!=3.79.2)", "iso8601", "pretend", "pytest (>=6.2.0)", "pytest-benchmark", "pytest-cov", "pytest-subtests", "pytest-xdist", "pytz"] test = ["hypothesis (>=1.11.4,!=3.79.2)", "iso8601", "pretend", "pytest (>=6.2.0)", "pytest-benchmark", "pytest-cov", "pytest-shard (>=0.1.2)", "pytest-subtests", "pytest-xdist", "pytz"]
test-randomorder = ["pytest-randomly"]
tox = ["tox"]
[[package]] [[package]]
name = "cymem" name = "cymem"
@ -1969,22 +1985,23 @@ files = [
[[package]] [[package]]
name = "ipykernel" name = "ipykernel"
version = "6.20.2" version = "6.21.1"
description = "IPython Kernel for Jupyter" description = "IPython Kernel for Jupyter"
category = "dev" category = "dev"
optional = false optional = false
python-versions = ">=3.8" python-versions = ">=3.8"
files = [ files = [
{file = "ipykernel-6.20.2-py3-none-any.whl", hash = "sha256:5d0675d5f48bf6a95fd517d7b70bcb3b2c5631b2069949b5c2d6e1d7477fb5a0"}, {file = "ipykernel-6.21.1-py3-none-any.whl", hash = "sha256:1a04bb359212e23e46adc0116ec82ea128c1e5bd532fde4fbe679787ff36f0cf"},
{file = "ipykernel-6.20.2.tar.gz", hash = "sha256:1893c5b847033cd7a58f6843b04a9349ffb1031bc6588401cadc9adb58da428e"}, {file = "ipykernel-6.21.1.tar.gz", hash = "sha256:a0f8eece39cab1ee352c9b59ec67bbe44d8299f8238e4c16ff7f4cf0052d3378"},
] ]
[package.dependencies] [package.dependencies]
appnope = {version = "*", markers = "platform_system == \"Darwin\""} appnope = {version = "*", markers = "platform_system == \"Darwin\""}
comm = ">=0.1.1" comm = ">=0.1.1"
debugpy = ">=1.0" debugpy = ">=1.6.5"
ipython = ">=7.23.1" ipython = ">=7.23.1"
jupyter-client = ">=6.1.12" jupyter-client = ">=6.1.12"
jupyter-core = ">=4.12,<5.0.0 || >=5.1.0"
matplotlib-inline = ">=0.1" matplotlib-inline = ">=0.1"
nest-asyncio = "*" nest-asyncio = "*"
packaging = "*" packaging = "*"
@ -2265,14 +2282,14 @@ testing = ["coverage", "ipykernel", "jupytext", "matplotlib", "nbdime", "nbforma
[[package]] [[package]]
name = "jupyter-client" name = "jupyter-client"
version = "8.0.1" version = "8.0.2"
description = "Jupyter protocol implementation and client libraries" description = "Jupyter protocol implementation and client libraries"
category = "dev" category = "dev"
optional = false optional = false
python-versions = ">=3.8" python-versions = ">=3.8"
files = [ files = [
{file = "jupyter_client-8.0.1-py3-none-any.whl", hash = "sha256:6016b874fd1111d721bc5bee30624399e876e79e6f395d1a559e6dce9fb2e1ba"}, {file = "jupyter_client-8.0.2-py3-none-any.whl", hash = "sha256:c53731eb590b68839b0ce04bf46ff8c4f03278f5d9fe5c3b0f268a57cc2bd97e"},
{file = "jupyter_client-8.0.1.tar.gz", hash = "sha256:3f67b1c8b7687e6db09bef10ff97669932b5e6ef6f5a8ee56d444b89022c5007"}, {file = "jupyter_client-8.0.2.tar.gz", hash = "sha256:47ac9f586dbcff4d79387ec264faf0fdeb5f14845fa7345fd7d1e378f8096011"},
] ]
[package.dependencies] [package.dependencies]
@ -2289,36 +2306,39 @@ test = ["codecov", "coverage", "ipykernel (>=6.14)", "mypy", "paramiko", "pre-co
[[package]] [[package]]
name = "jupyter-console" name = "jupyter-console"
version = "6.4.4" version = "6.5.0"
description = "Jupyter terminal console" description = "Jupyter terminal console"
category = "dev" category = "dev"
optional = false optional = false
python-versions = ">=3.7" python-versions = ">=3.7"
files = [ files = [
{file = "jupyter_console-6.4.4-py3-none-any.whl", hash = "sha256:756df7f4f60c986e7bc0172e4493d3830a7e6e75c08750bbe59c0a5403ad6dee"}, {file = "jupyter_console-6.5.0-py3-none-any.whl", hash = "sha256:87826ab6c8c418731fd78f14ec504df735e79554e35784d0a6379018bb3ef9d7"},
{file = "jupyter_console-6.4.4.tar.gz", hash = "sha256:172f5335e31d600df61613a97b7f0352f2c8250bbd1092ef2d658f77249f89fb"}, {file = "jupyter_console-6.5.0.tar.gz", hash = "sha256:67e68f1da16bc3f6f78ed846dd5543ec0679369f8504734f10bfd206faae39ea"},
] ]
[package.dependencies] [package.dependencies]
ipykernel = "*" ipykernel = ">=6.14"
ipython = "*" ipython = "*"
jupyter-client = ">=7.0.0" jupyter-client = ">=7.0.0"
prompt-toolkit = ">=2.0.0,<3.0.0 || >3.0.0,<3.0.1 || >3.0.1,<3.1.0" jupyter-core = ">=4.12,<5.0.0 || >=5.1.0"
prompt-toolkit = ">=3.0.30"
pygments = "*" pygments = "*"
pyzmq = ">=17"
traitlets = ">=5.4"
[package.extras] [package.extras]
test = ["pexpect"] test = ["pexpect", "pytest"]
[[package]] [[package]]
name = "jupyter-core" name = "jupyter-core"
version = "5.1.5" version = "5.2.0"
description = "Jupyter core package. A base package on which Jupyter projects rely." description = "Jupyter core package. A base package on which Jupyter projects rely."
category = "dev" category = "dev"
optional = false optional = false
python-versions = ">=3.8" python-versions = ">=3.8"
files = [ files = [
{file = "jupyter_core-5.1.5-py3-none-any.whl", hash = "sha256:83064d61bb2a9bc874e8184331c117b3778c2a7e1851f60cb00d273ceb3285ae"}, {file = "jupyter_core-5.2.0-py3-none-any.whl", hash = "sha256:4bdc2928c37f6917130c667d8b8708f20aee539d8283c6be72aabd2a4b4c83b0"},
{file = "jupyter_core-5.1.5.tar.gz", hash = "sha256:8e54c48cde1e0c8345f64bcf9658b78044ddf02b273726cea9d9f59be4b02130"}, {file = "jupyter_core-5.2.0.tar.gz", hash = "sha256:1407cdb4c79ee467696c04b76633fc1884015fa109323365a6372c8e890cc83f"},
] ]
[package.dependencies] [package.dependencies]
@ -2357,18 +2377,18 @@ test = ["click", "coverage", "pre-commit", "pytest (>=7.0)", "pytest-asyncio (>=
[[package]] [[package]]
name = "jupyter-server" name = "jupyter-server"
version = "2.1.0" version = "2.2.1"
description = "The backend—i.e. core services, APIs, and REST endpoints—to Jupyter web applications." description = "The backend—i.e. core services, APIs, and REST endpoints—to Jupyter web applications."
category = "dev" category = "dev"
optional = false optional = false
python-versions = ">=3.8" python-versions = ">=3.8"
files = [ files = [
{file = "jupyter_server-2.1.0-py3-none-any.whl", hash = "sha256:90cd6f2bd0581ddd9b2dbe82026a0f4c228a1d95c86e22460efbfdfc931fcf56"}, {file = "jupyter_server-2.2.1-py3-none-any.whl", hash = "sha256:854fb7d49f6b7f545d4f8354172b004dcda887ba0699def7112daf785ba3c9ce"},
{file = "jupyter_server-2.1.0.tar.gz", hash = "sha256:efaae5e4f0d5f22c7f2f2dc848635036ee74a2df02abed52d30d9d95121ad382"}, {file = "jupyter_server-2.2.1.tar.gz", hash = "sha256:5afb8a0cdfee37d02d69bdf470ae9cbb1dee5d4788f9bc6cc8e54bd8c83fb096"},
] ]
[package.dependencies] [package.dependencies]
anyio = ">=3.1.0,<4" anyio = ">=3.1.0"
argon2-cffi = "*" argon2-cffi = "*"
jinja2 = "*" jinja2 = "*"
jupyter-client = ">=7.4.4" jupyter-client = ">=7.4.4"
@ -2845,14 +2865,14 @@ files = [
[[package]] [[package]]
name = "mistune" name = "mistune"
version = "2.0.4" version = "2.0.5"
description = "A sane Markdown parser with useful plugins and renderers" description = "A sane Markdown parser with useful plugins and renderers"
category = "dev" category = "dev"
optional = false optional = false
python-versions = "*" python-versions = "*"
files = [ files = [
{file = "mistune-2.0.4-py2.py3-none-any.whl", hash = "sha256:182cc5ee6f8ed1b807de6b7bb50155df7b66495412836b9a74c8fbdfc75fe36d"}, {file = "mistune-2.0.5-py2.py3-none-any.whl", hash = "sha256:bad7f5d431886fcbaf5f758118ecff70d31f75231b34024a1341120340a65ce8"},
{file = "mistune-2.0.4.tar.gz", hash = "sha256:9ee0a66053e2267aba772c71e06891fa8f1af6d4b01d5e84e267b4570d4d9808"}, {file = "mistune-2.0.5.tar.gz", hash = "sha256:0246113cb2492db875c6be56974a7c893333bf26cd92891c85f63151cee09d34"},
] ]
[[package]] [[package]]
@ -3042,14 +3062,14 @@ reports = ["lxml"]
[[package]] [[package]]
name = "mypy-extensions" name = "mypy-extensions"
version = "0.4.3" version = "1.0.0"
description = "Experimental type system extensions for programs checked with the mypy typechecker." description = "Type system extensions for programs checked with the mypy type checker."
category = "main" category = "main"
optional = false optional = false
python-versions = "*" python-versions = ">=3.5"
files = [ files = [
{file = "mypy_extensions-0.4.3-py2.py3-none-any.whl", hash = "sha256:090fedd75945a69ae91ce1303b5824f428daf5a028d2f6ab8a299250a846f15d"}, {file = "mypy_extensions-1.0.0-py3-none-any.whl", hash = "sha256:4392f6c0eb8a5668a69e23d168ffa70f0be9ccfd32b5cc2d26a34ae5b844552d"},
{file = "mypy_extensions-0.4.3.tar.gz", hash = "sha256:2d82818f5bb3e369420cb3c4060a7970edba416647068eb4c5343488a6c604a8"}, {file = "mypy_extensions-1.0.0.tar.gz", hash = "sha256:75dbf8955dc00442a438fc4d0666508a9a97b6bd41aa2f0ffe9d2f2725af0782"},
] ]
[[package]] [[package]]
@ -3355,40 +3375,40 @@ test = ["pytest", "pytest-console-scripts", "pytest-tornasync"]
[[package]] [[package]]
name = "numpy" name = "numpy"
version = "1.24.1" version = "1.24.2"
description = "Fundamental package for array computing in Python" description = "Fundamental package for array computing in Python"
category = "main" category = "main"
optional = false optional = false
python-versions = ">=3.8" python-versions = ">=3.8"
files = [ files = [
{file = "numpy-1.24.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:179a7ef0889ab769cc03573b6217f54c8bd8e16cef80aad369e1e8185f994cd7"}, {file = "numpy-1.24.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:eef70b4fc1e872ebddc38cddacc87c19a3709c0e3e5d20bf3954c147b1dd941d"},
{file = "numpy-1.24.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:b09804ff570b907da323b3d762e74432fb07955701b17b08ff1b5ebaa8cfe6a9"}, {file = "numpy-1.24.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:e8d2859428712785e8a8b7d2b3ef0a1d1565892367b32f915c4a4df44d0e64f5"},
{file = "numpy-1.24.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f1b739841821968798947d3afcefd386fa56da0caf97722a5de53e07c4ccedc7"}, {file = "numpy-1.24.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6524630f71631be2dabe0c541e7675db82651eb998496bbe16bc4f77f0772253"},
{file = "numpy-1.24.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0e3463e6ac25313462e04aea3fb8a0a30fb906d5d300f58b3bc2c23da6a15398"}, {file = "numpy-1.24.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a51725a815a6188c662fb66fb32077709a9ca38053f0274640293a14fdd22978"},
{file = "numpy-1.24.1-cp310-cp310-win32.whl", hash = "sha256:b31da69ed0c18be8b77bfce48d234e55d040793cebb25398e2a7d84199fbc7e2"}, {file = "numpy-1.24.2-cp310-cp310-win32.whl", hash = "sha256:2620e8592136e073bd12ee4536149380695fbe9ebeae845b81237f986479ffc9"},
{file = "numpy-1.24.1-cp310-cp310-win_amd64.whl", hash = "sha256:b07b40f5fb4fa034120a5796288f24c1fe0e0580bbfff99897ba6267af42def2"}, {file = "numpy-1.24.2-cp310-cp310-win_amd64.whl", hash = "sha256:97cf27e51fa078078c649a51d7ade3c92d9e709ba2bfb97493007103c741f1d0"},
{file = "numpy-1.24.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:7094891dcf79ccc6bc2a1f30428fa5edb1e6fb955411ffff3401fb4ea93780a8"}, {file = "numpy-1.24.2-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:7de8fdde0003f4294655aa5d5f0a89c26b9f22c0a58790c38fae1ed392d44a5a"},
{file = "numpy-1.24.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:28e418681372520c992805bb723e29d69d6b7aa411065f48216d8329d02ba032"}, {file = "numpy-1.24.2-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:4173bde9fa2a005c2c6e2ea8ac1618e2ed2c1c6ec8a7657237854d42094123a0"},
{file = "numpy-1.24.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e274f0f6c7efd0d577744f52032fdd24344f11c5ae668fe8d01aac0422611df1"}, {file = "numpy-1.24.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4cecaed30dc14123020f77b03601559fff3e6cd0c048f8b5289f4eeabb0eb281"},
{file = "numpy-1.24.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0044f7d944ee882400890f9ae955220d29b33d809a038923d88e4e01d652acd9"}, {file = "numpy-1.24.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9a23f8440561a633204a67fb44617ce2a299beecf3295f0d13c495518908e910"},
{file = "numpy-1.24.1-cp311-cp311-win32.whl", hash = "sha256:442feb5e5bada8408e8fcd43f3360b78683ff12a4444670a7d9e9824c1817d36"}, {file = "numpy-1.24.2-cp311-cp311-win32.whl", hash = "sha256:e428c4fbfa085f947b536706a2fc349245d7baa8334f0c5723c56a10595f9b95"},
{file = "numpy-1.24.1-cp311-cp311-win_amd64.whl", hash = "sha256:de92efa737875329b052982e37bd4371d52cabf469f83e7b8be9bb7752d67e51"}, {file = "numpy-1.24.2-cp311-cp311-win_amd64.whl", hash = "sha256:557d42778a6869c2162deb40ad82612645e21d79e11c1dc62c6e82a2220ffb04"},
{file = "numpy-1.24.1-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:b162ac10ca38850510caf8ea33f89edcb7b0bb0dfa5592d59909419986b72407"}, {file = "numpy-1.24.2-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:d0a2db9d20117bf523dde15858398e7c0858aadca7c0f088ac0d6edd360e9ad2"},
{file = "numpy-1.24.1-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:26089487086f2648944f17adaa1a97ca6aee57f513ba5f1c0b7ebdabbe2b9954"}, {file = "numpy-1.24.2-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:c72a6b2f4af1adfe193f7beb91ddf708ff867a3f977ef2ec53c0ffb8283ab9f5"},
{file = "numpy-1.24.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:caf65a396c0d1f9809596be2e444e3bd4190d86d5c1ce21f5fc4be60a3bc5b36"}, {file = "numpy-1.24.2-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c29e6bd0ec49a44d7690ecb623a8eac5ab8a923bce0bea6293953992edf3a76a"},
{file = "numpy-1.24.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b0677a52f5d896e84414761531947c7a330d1adc07c3a4372262f25d84af7bf7"}, {file = "numpy-1.24.2-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2eabd64ddb96a1239791da78fa5f4e1693ae2dadc82a76bc76a14cbb2b966e96"},
{file = "numpy-1.24.1-cp38-cp38-win32.whl", hash = "sha256:dae46bed2cb79a58d6496ff6d8da1e3b95ba09afeca2e277628171ca99b99db1"}, {file = "numpy-1.24.2-cp38-cp38-win32.whl", hash = "sha256:e3ab5d32784e843fc0dd3ab6dcafc67ef806e6b6828dc6af2f689be0eb4d781d"},
{file = "numpy-1.24.1-cp38-cp38-win_amd64.whl", hash = "sha256:6ec0c021cd9fe732e5bab6401adea5a409214ca5592cd92a114f7067febcba0c"}, {file = "numpy-1.24.2-cp38-cp38-win_amd64.whl", hash = "sha256:76807b4063f0002c8532cfeac47a3068a69561e9c8715efdad3c642eb27c0756"},
{file = "numpy-1.24.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:28bc9750ae1f75264ee0f10561709b1462d450a4808cd97c013046073ae64ab6"}, {file = "numpy-1.24.2-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:4199e7cfc307a778f72d293372736223e39ec9ac096ff0a2e64853b866a8e18a"},
{file = "numpy-1.24.1-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:84e789a085aabef2f36c0515f45e459f02f570c4b4c4c108ac1179c34d475ed7"}, {file = "numpy-1.24.2-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:adbdce121896fd3a17a77ab0b0b5eedf05a9834a18699db6829a64e1dfccca7f"},
{file = "numpy-1.24.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8e669fbdcdd1e945691079c2cae335f3e3a56554e06bbd45d7609a6cf568c700"}, {file = "numpy-1.24.2-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:889b2cc88b837d86eda1b17008ebeb679d82875022200c6e8e4ce6cf549b7acb"},
{file = "numpy-1.24.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ef85cf1f693c88c1fd229ccd1055570cb41cdf4875873b7728b6301f12cd05bf"}, {file = "numpy-1.24.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f64bb98ac59b3ea3bf74b02f13836eb2e24e48e0ab0145bbda646295769bd780"},
{file = "numpy-1.24.1-cp39-cp39-win32.whl", hash = "sha256:87a118968fba001b248aac90e502c0b13606721b1343cdaddbc6e552e8dfb56f"}, {file = "numpy-1.24.2-cp39-cp39-win32.whl", hash = "sha256:63e45511ee4d9d976637d11e6c9864eae50e12dc9598f531c035265991910468"},
{file = "numpy-1.24.1-cp39-cp39-win_amd64.whl", hash = "sha256:ddc7ab52b322eb1e40521eb422c4e0a20716c271a306860979d450decbb51b8e"}, {file = "numpy-1.24.2-cp39-cp39-win_amd64.whl", hash = "sha256:a77d3e1163a7770164404607b7ba3967fb49b24782a6ef85d9b5f54126cc39e5"},
{file = "numpy-1.24.1-pp38-pypy38_pp73-macosx_10_9_x86_64.whl", hash = "sha256:ed5fb71d79e771ec930566fae9c02626b939e37271ec285e9efaf1b5d4370e7d"}, {file = "numpy-1.24.2-pp38-pypy38_pp73-macosx_10_9_x86_64.whl", hash = "sha256:92011118955724465fb6853def593cf397b4a1367495e0b59a7e69d40c4eb71d"},
{file = "numpy-1.24.1-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ad2925567f43643f51255220424c23d204024ed428afc5aad0f86f3ffc080086"}, {file = "numpy-1.24.2-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f9006288bcf4895917d02583cf3411f98631275bc67cce355a7f39f8c14338fa"},
{file = "numpy-1.24.1-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:cfa1161c6ac8f92dea03d625c2d0c05e084668f4a06568b77a25a89111621566"}, {file = "numpy-1.24.2-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:150947adbdfeceec4e5926d956a06865c1c690f2fd902efede4ca6fe2e657c3f"},
{file = "numpy-1.24.1.tar.gz", hash = "sha256:2386da9a471cc00a1f47845e27d916d5ec5346ae9696e01a8a34760858fe9dd2"}, {file = "numpy-1.24.2.tar.gz", hash = "sha256:003a9f530e880cb2cd177cba1af7220b9aa42def9c4afc2a2fc3ee6be7eb2b22"},
] ]
[[package]] [[package]]
@ -3558,7 +3578,7 @@ testing = ["docopt", "pytest (<6.0.0)"]
name = "pathspec" name = "pathspec"
version = "0.11.0" version = "0.11.0"
description = "Utility library for gitignore style pattern matching of file paths." description = "Utility library for gitignore style pattern matching of file paths."
category = "dev" category = "main"
optional = false optional = false
python-versions = ">=3.7" python-versions = ">=3.7"
files = [ files = [
@ -3746,19 +3766,19 @@ files = [
[[package]] [[package]]
name = "platformdirs" name = "platformdirs"
version = "2.6.2" version = "3.0.0"
description = "A small Python package for determining appropriate platform-specific dirs, e.g. a \"user data dir\"." description = "A small Python package for determining appropriate platform-specific dirs, e.g. a \"user data dir\"."
category = "dev" category = "main"
optional = false optional = false
python-versions = ">=3.7" python-versions = ">=3.7"
files = [ files = [
{file = "platformdirs-2.6.2-py3-none-any.whl", hash = "sha256:83c8f6d04389165de7c9b6f0c682439697887bca0aa2f1c87ef1826be3584490"}, {file = "platformdirs-3.0.0-py3-none-any.whl", hash = "sha256:b1d5eb14f221506f50d6604a561f4c5786d9e80355219694a1b244bcd96f4567"},
{file = "platformdirs-2.6.2.tar.gz", hash = "sha256:e1fea1fe471b9ff8332e229df3cb7de4f53eeea4998d3b6bfff542115e998bd2"}, {file = "platformdirs-3.0.0.tar.gz", hash = "sha256:8a1228abb1ef82d788f74139988b137e78692984ec7b08eaa6c65f1723af28f9"},
] ]
[package.extras] [package.extras]
docs = ["furo (>=2022.12.7)", "proselint (>=0.13)", "sphinx (>=5.3)", "sphinx-autodoc-typehints (>=1.19.5)"] docs = ["furo (>=2022.12.7)", "proselint (>=0.13)", "sphinx (>=6.1.3)", "sphinx-autodoc-typehints (>=1.22,!=1.23.4)"]
test = ["appdirs (==1.4.4)", "covdefaults (>=2.2.2)", "pytest (>=7.2)", "pytest-cov (>=4)", "pytest-mock (>=3.10)"] test = ["appdirs (==1.4.4)", "covdefaults (>=2.2.2)", "pytest (>=7.2.1)", "pytest-cov (>=4)", "pytest-mock (>=3.10)"]
[[package]] [[package]]
name = "playwright" name = "playwright"
@ -4205,6 +4225,28 @@ files = [
[package.extras] [package.extras]
diagrams = ["jinja2", "railroad-diagrams"] diagrams = ["jinja2", "railroad-diagrams"]
[[package]]
name = "pypdf"
version = "3.4.0"
description = "A pure-python PDF library capable of splitting, merging, cropping, and transforming PDF files"
category = "main"
optional = true
python-versions = ">=3.6"
files = [
{file = "pypdf-3.4.0-py3-none-any.whl", hash = "sha256:1f40d69a40ed99528cc3c8782bfe719bc26cf31d9a4958c06f17b5ee3d2ae0f4"},
{file = "pypdf-3.4.0.tar.gz", hash = "sha256:3aac40e539e6a25a31bdc0240229e7ac6670eec9932ebd27e95106c5d83befe8"},
]
[package.dependencies]
typing_extensions = {version = ">=3.10.0.0", markers = "python_version < \"3.10\""}
[package.extras]
crypto = ["PyCryptodome"]
dev = ["black", "flit", "pip-tools", "pre-commit (<2.18.0)", "pytest-cov", "wheel"]
docs = ["myst_parser", "sphinx", "sphinx_rtd_theme"]
full = ["Pillow", "PyCryptodome"]
image = ["Pillow"]
[[package]] [[package]]
name = "pyrsistent" name = "pyrsistent"
version = "0.19.3" version = "0.19.3"
@ -4635,14 +4677,14 @@ test = ["pytest (>=6,!=7.0.0,!=7.0.1)", "pytest-cov (>=3.0.0)", "pytest-qt"]
[[package]] [[package]]
name = "redis" name = "redis"
version = "4.4.2" version = "4.5.1"
description = "Python client for Redis database and key-value store" description = "Python client for Redis database and key-value store"
category = "main" category = "main"
optional = true optional = true
python-versions = ">=3.7" python-versions = ">=3.7"
files = [ files = [
{file = "redis-4.4.2-py3-none-any.whl", hash = "sha256:e6206448e2f8a432871d07d432c13ed6c2abcf6b74edb436c99752b1371be387"}, {file = "redis-4.5.1-py3-none-any.whl", hash = "sha256:5deb072d26e67d2be1712603bfb7947ec3431fb0eec9c578994052e33035af6d"},
{file = "redis-4.4.2.tar.gz", hash = "sha256:a010f6cb7378065040a02839c3f75c7e0fb37a87116fb4a95be82a95552776c7"}, {file = "redis-4.5.1.tar.gz", hash = "sha256:1eec3741cda408d3a5f84b78d089c8b8d895f21b3b050988351e925faf202864"},
] ]
[package.dependencies] [package.dependencies]
@ -5043,14 +5085,14 @@ files = [
[[package]] [[package]]
name = "setuptools" name = "setuptools"
version = "67.0.0" version = "67.2.0"
description = "Easily download, build, install, upgrade, and uninstall Python packages" description = "Easily download, build, install, upgrade, and uninstall Python packages"
category = "main" category = "main"
optional = true optional = false
python-versions = ">=3.7" python-versions = ">=3.7"
files = [ files = [
{file = "setuptools-67.0.0-py3-none-any.whl", hash = "sha256:9d790961ba6219e9ff7d9557622d2fe136816a264dd01d5997cfc057d804853d"}, {file = "setuptools-67.2.0-py3-none-any.whl", hash = "sha256:16ccf598aab3b506593c17378473978908a2734d7336755a8769b480906bec1c"},
{file = "setuptools-67.0.0.tar.gz", hash = "sha256:883131c5b6efa70b9101c7ef30b2b7b780a4283d5fc1616383cdf22c83cbefe6"}, {file = "setuptools-67.2.0.tar.gz", hash = "sha256:b440ee5f7e607bb8c9de15259dba2583dd41a38879a7abc1d43a71c59524da48"},
] ]
[package.extras] [package.extras]
@ -5341,19 +5383,20 @@ themes = ["myst-parser (>=0.12.9,<0.13.0)", "pydata-sphinx-theme (>=0.4.0,<0.5.0
[[package]] [[package]]
name = "sphinx-rtd-theme" name = "sphinx-rtd-theme"
version = "1.1.1" version = "1.2.0"
description = "Read the Docs theme for Sphinx" description = "Read the Docs theme for Sphinx"
category = "dev" category = "dev"
optional = false optional = false
python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,>=2.7" python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,>=2.7"
files = [ files = [
{file = "sphinx_rtd_theme-1.1.1-py2.py3-none-any.whl", hash = "sha256:31faa07d3e97c8955637fc3f1423a5ab2c44b74b8cc558a51498c202ce5cbda7"}, {file = "sphinx_rtd_theme-1.2.0-py2.py3-none-any.whl", hash = "sha256:f823f7e71890abe0ac6aaa6013361ea2696fc8d3e1fa798f463e82bdb77eeff2"},
{file = "sphinx_rtd_theme-1.1.1.tar.gz", hash = "sha256:6146c845f1e1947b3c3dd4432c28998a1693ccc742b4f9ad7c63129f0757c103"}, {file = "sphinx_rtd_theme-1.2.0.tar.gz", hash = "sha256:a0d8bd1a2ed52e0b338cbe19c4b2eef3c5e7a048769753dac6a9f059c7b641b8"},
] ]
[package.dependencies] [package.dependencies]
docutils = "<0.18" docutils = "<0.19"
sphinx = ">=1.6,<6" sphinx = ">=1.6,<7"
sphinxcontrib-jquery = {version = ">=2.0.0,<3.0.0 || >3.0.0", markers = "python_version > \"3\""}
[package.extras] [package.extras]
dev = ["bump2version", "sphinxcontrib-httpdomain", "transifex-client", "wheel"] dev = ["bump2version", "sphinxcontrib-httpdomain", "transifex-client", "wheel"]
@ -5407,20 +5450,35 @@ test = ["pytest"]
[[package]] [[package]]
name = "sphinxcontrib-htmlhelp" name = "sphinxcontrib-htmlhelp"
version = "2.0.0" version = "2.0.1"
description = "sphinxcontrib-htmlhelp is a sphinx extension which renders HTML help files" description = "sphinxcontrib-htmlhelp is a sphinx extension which renders HTML help files"
category = "dev" category = "dev"
optional = false optional = false
python-versions = ">=3.6" python-versions = ">=3.8"
files = [ files = [
{file = "sphinxcontrib-htmlhelp-2.0.0.tar.gz", hash = "sha256:f5f8bb2d0d629f398bf47d0d69c07bc13b65f75a81ad9e2f71a63d4b7a2f6db2"}, {file = "sphinxcontrib-htmlhelp-2.0.1.tar.gz", hash = "sha256:0cbdd302815330058422b98a113195c9249825d681e18f11e8b1f78a2f11efff"},
{file = "sphinxcontrib_htmlhelp-2.0.0-py2.py3-none-any.whl", hash = "sha256:d412243dfb797ae3ec2b59eca0e52dac12e75a241bf0e4eb861e450d06c6ed07"}, {file = "sphinxcontrib_htmlhelp-2.0.1-py3-none-any.whl", hash = "sha256:c38cb46dccf316c79de6e5515e1770414b797162b23cd3d06e67020e1d2a6903"},
] ]
[package.extras] [package.extras]
lint = ["docutils-stubs", "flake8", "mypy"] lint = ["docutils-stubs", "flake8", "mypy"]
test = ["html5lib", "pytest"] test = ["html5lib", "pytest"]
[[package]]
name = "sphinxcontrib-jquery"
version = "2.0.0"
description = "Extension to include jQuery on newer Sphinx releases"
category = "dev"
optional = false
python-versions = ">=2.7"
files = [
{file = "sphinxcontrib-jquery-2.0.0.tar.gz", hash = "sha256:8fb65f6dba84bf7bcd1aea1f02ab3955ac34611d838bcc95d4983b805b234daa"},
{file = "sphinxcontrib_jquery-2.0.0-py3-none-any.whl", hash = "sha256:ed47fa425c338ffebe3c37e1cdb56e30eb806116b85f01055b158c7057fdb995"},
]
[package.dependencies]
setuptools = "*"
[[package]] [[package]]
name = "sphinxcontrib-jsmath" name = "sphinxcontrib-jsmath"
version = "1.0.1" version = "1.0.1"
@ -5632,14 +5690,14 @@ widechars = ["wcwidth"]
[[package]] [[package]]
name = "tenacity" name = "tenacity"
version = "8.1.0" version = "8.2.1"
description = "Retry code until it succeeds" description = "Retry code until it succeeds"
category = "main" category = "main"
optional = false optional = false
python-versions = ">=3.6" python-versions = ">=3.6"
files = [ files = [
{file = "tenacity-8.1.0-py3-none-any.whl", hash = "sha256:35525cd47f82830069f0d6b73f7eb83bc5b73ee2fff0437952cedf98b27653ac"}, {file = "tenacity-8.2.1-py3-none-any.whl", hash = "sha256:dd1b769ca7002fda992322939feca5bee4fa11f39146b0af14e0b8d9f27ea854"},
{file = "tenacity-8.1.0.tar.gz", hash = "sha256:e48c437fdf9340f5666b92cd7990e96bc5fc955e1298baf4a907e3972067a445"}, {file = "tenacity-8.2.1.tar.gz", hash = "sha256:c7bb4b86425b977726a7b49971542d4f67baf72096597d283f3ffd01f33b92df"},
] ]
[package.extras] [package.extras]
@ -6001,33 +6059,33 @@ files = [
[[package]] [[package]]
name = "tiktoken" name = "tiktoken"
version = "0.1.2" version = "0.2.0"
description = "" description = ""
category = "main" category = "main"
optional = true optional = true
python-versions = ">=3.8" python-versions = ">=3.8"
files = [ files = [
{file = "tiktoken-0.1.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:ff47d0e5257c3ba744f5d2873772d0b68ecf85b6b278a8d79bc06fae1197f23f"}, {file = "tiktoken-0.2.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:d06705b55bb5f6c194285b6d15ad31bd7586d44fe433be31bc3694cf8c70169c"},
{file = "tiktoken-0.1.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:41e3ac9254c5dcafbde3ee466de5ef3a363b445d94f13ba493bcbe3ba37f84db"}, {file = "tiktoken-0.2.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:29f2969945fc430f817c907f59a2da9e7b797fe65527ba5b9442618643a0dc86"},
{file = "tiktoken-0.1.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:011a64de1a8e84fb14a9562a1e94e3d5688729b68a8bfd46d9e16339a4acaa25"}, {file = "tiktoken-0.2.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:546455f27b6f7981d17de265b8b99e2fef980fbc3fde1d94b551f8354902000e"},
{file = "tiktoken-0.1.2-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:d17d3f70ea74f6d5739b23ad424291fe995e88ba28e9d77686744402fb6d0d3f"}, {file = "tiktoken-0.2.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:54b5dc05f934ac68e8da4d2cc3acd77bc6968114b09669056f1bff12acc57049"},
{file = "tiktoken-0.1.2-cp310-cp310-win_amd64.whl", hash = "sha256:377d3fd24eeed7b3ce01969df19c881c79379880006b4b3e71a8e8f5e8e33670"}, {file = "tiktoken-0.2.0-cp310-cp310-win_amd64.whl", hash = "sha256:5d3c48cb5649ce6bb2b207377dfdaa855e1e771b2e7f59fb251182c227573619"},
{file = "tiktoken-0.1.2-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:db7a0953bd4a33f1050063aefe09804e16fa03a1f696779fb907bdbee250cb6b"}, {file = "tiktoken-0.2.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:a55f983735745df9a87161d9e0ce9ef7d216039d389246be98c6d416bbb2452f"},
{file = "tiktoken-0.1.2-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:d3753a7328869a27d2a62eedcb4ed4e368b25a3dbc4187bd88f6408046722169"}, {file = "tiktoken-0.2.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:175de868393039a85fdf4c7cfb9b8883d1b248b9a3d9d0129d30414f5a59c333"},
{file = "tiktoken-0.1.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e763fd35ec11aab0c44af32ab70a9fd2a2d09d9e9879e244c215cc45ae6d0d7d"}, {file = "tiktoken-0.2.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d6cd97b8cd14e3fe6647baa71c67f7f6b21a401fa996ccc3d93bf0ae02162af2"},
{file = "tiktoken-0.1.2-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:98ec25cf476a267764cd104c3cceed442b51aa0e68195c2db1cd46551428ca01"}, {file = "tiktoken-0.2.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:806e2b8c0b9786c0e3212e8b3a6ac8f5840066c00a31b89e6c8d9ba0421e77d7"},
{file = "tiktoken-0.1.2-cp311-cp311-win_amd64.whl", hash = "sha256:abf1212983c767ebf4535b6da71463e5e8c5bbf2aedc20f971f6f436ab17597a"}, {file = "tiktoken-0.2.0-cp311-cp311-win_amd64.whl", hash = "sha256:57b753aa9813f06fa5a26da2622114bf9769a8d1dca1b276d3613ee15da5b09d"},
{file = "tiktoken-0.1.2-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:82d76e6734dd43a4fc1962f0d411e2520a822d3bb69dd6b455c6780e4deefbee"}, {file = "tiktoken-0.2.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:aa3c15b87bb2cea56ecc8fe4c7bf105c5c2dc4090c2df97c141100488297173a"},
{file = "tiktoken-0.1.2-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:edf4ec8ff718206b7cf4f3dd9240cca519a7cfce961fbab255983cbcb400190c"}, {file = "tiktoken-0.2.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:bd98fc4a9ec967a089c62497f21277b53aa3e15a6fec731ac707eea4d5527938"},
{file = "tiktoken-0.1.2-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f972f2da4a607b3bcce928d1a9491289bfc6113810477be2e709ae68359435d8"}, {file = "tiktoken-0.2.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ab10ad3280f348a0d3bfea6d503c6aa84676b159692701bc7604e67129bd2135"},
{file = "tiktoken-0.1.2-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:816934bf8eddeb5f136975c3d1de598f138baa0c9610b6600abc3d62f2bfe5ff"}, {file = "tiktoken-0.2.0-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:59296d495aa6aec375a75f07da44fabb9720632c9404b41b9cbfe95e17966345"},
{file = "tiktoken-0.1.2-cp38-cp38-win_amd64.whl", hash = "sha256:f31293fdc187356aed38f38d806fedbb7ed2860b7ba93b8436e280effc63e418"}, {file = "tiktoken-0.2.0-cp38-cp38-win_amd64.whl", hash = "sha256:3b078e6109d522c5ffc52859520eef6c17a3b120ed52b79f48cae0badff08fe0"},
{file = "tiktoken-0.1.2-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:abee473ecf06532bb76b2d1ee987a7dce72bb94c0a65bc91d581c2290d1105c5"}, {file = "tiktoken-0.2.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:aef47e8037652b18d2665b77e1f9416d3a86ccd383b039d0dfcb7d92085cef6d"},
{file = "tiktoken-0.1.2-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:ee12f0f311da111b4a77db96bcd4053b6a9a6ba1d9ff09072f3918ca1ee9e22f"}, {file = "tiktoken-0.2.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:d0f62f8349a5412962326dbc41c3823a1f381d8ab62afbee94480d8296499d8e"},
{file = "tiktoken-0.1.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:77e9ea1c8b5f72be37594de99557f75e19714947aab1ed5bba9adcdb517f61de"}, {file = "tiktoken-0.2.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9d0dbf7e1940427c11f0c8ab9046ad98d774850b21559b37ca60ff30d3a14620"},
{file = "tiktoken-0.1.2-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:aee05c72d8be144f493bf46ec464b28b246b891d2c4baf05794d91a5ae678366"}, {file = "tiktoken-0.2.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:8f1a7c6bec42a2fb5309a161d1b891fe5e181d4b620a962923a925f45fe25697"},
{file = "tiktoken-0.1.2-cp39-cp39-win_amd64.whl", hash = "sha256:66d0c260fb4702fca3b1f5df4d083fcf76bce8a83bd20921dde311dffe4c42e8"}, {file = "tiktoken-0.2.0-cp39-cp39-win_amd64.whl", hash = "sha256:3349fd809d17b722814a6a700e4bc0125527f39057b57a02ed42f53bb4e6e2f5"},
{file = "tiktoken-0.1.2.tar.gz", hash = "sha256:bd34664940ef351e128dbcee03f475a8cc8471929152d5c1fd0124a064b84917"}, {file = "tiktoken-0.2.0.tar.gz", hash = "sha256:df41a3d478499757b5b32eae5e97657cf159d8d9e6764049dd7c3abb49e1b40f"},
] ]
[package.dependencies] [package.dependencies]
@ -6125,7 +6183,7 @@ files = [
name = "tomli" name = "tomli"
version = "2.0.1" version = "2.0.1"
description = "A lil' TOML parser" description = "A lil' TOML parser"
category = "dev" category = "main"
optional = false optional = false
python-versions = ">=3.7" python-versions = ">=3.7"
files = [ files = [
@ -6257,14 +6315,14 @@ telegram = ["requests"]
[[package]] [[package]]
name = "traitlets" name = "traitlets"
version = "5.8.1" version = "5.9.0"
description = "Traitlets Python configuration system" description = "Traitlets Python configuration system"
category = "dev" category = "dev"
optional = false optional = false
python-versions = ">=3.7" python-versions = ">=3.7"
files = [ files = [
{file = "traitlets-5.8.1-py3-none-any.whl", hash = "sha256:a1ca5df6414f8b5760f7c5f256e326ee21b581742114545b462b35ffe3f04861"}, {file = "traitlets-5.9.0-py3-none-any.whl", hash = "sha256:9e6ec080259b9a5940c797d58b613b5e31441c2257b87c2e795c5228ae80d2d8"},
{file = "traitlets-5.8.1.tar.gz", hash = "sha256:32500888f5ff7bbf3b9267ea31748fa657aaf34d56d85e60f91dda7dc7f5785b"}, {file = "traitlets-5.9.0.tar.gz", hash = "sha256:f6cde21a9c68cf756af02035f72d5a723bf607e862e7be33ece505abf4a3bad9"},
] ]
[package.extras] [package.extras]
@ -6273,14 +6331,14 @@ test = ["argcomplete (>=2.0)", "pre-commit", "pytest", "pytest-mock"]
[[package]] [[package]]
name = "transformers" name = "transformers"
version = "4.26.0" version = "4.26.1"
description = "State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow" description = "State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow"
category = "main" category = "main"
optional = true optional = true
python-versions = ">=3.7.0" python-versions = ">=3.7.0"
files = [ files = [
{file = "transformers-4.26.0-py3-none-any.whl", hash = "sha256:6a902eee6098d9a737faadf185b8df5a169acc695ebbde5a81b90528f43e665f"}, {file = "transformers-4.26.1-py3-none-any.whl", hash = "sha256:dae2fa15290c1f526e1b629b0e235eea5e4c04078fcaf1f197a70d51b4f65df2"},
{file = "transformers-4.26.0.tar.gz", hash = "sha256:d7859bd83829a3682ca632197ee5c72556e1063d199ab84eec35c4f23b3d73a3"}, {file = "transformers-4.26.1.tar.gz", hash = "sha256:32dc474157367f8e551f470af0136a1ddafc9e18476400c3869f1ef4f0c12042"},
] ]
[package.dependencies] [package.dependencies]
@ -6376,26 +6434,26 @@ cryptography = ">=35.0.0"
[[package]] [[package]]
name = "types-pyyaml" name = "types-pyyaml"
version = "6.0.12.3" version = "6.0.12.5"
description = "Typing stubs for PyYAML" description = "Typing stubs for PyYAML"
category = "dev" category = "dev"
optional = false optional = false
python-versions = "*" python-versions = "*"
files = [ files = [
{file = "types-PyYAML-6.0.12.3.tar.gz", hash = "sha256:17ce17b3ead8f06e416a3b1d5b8ddc6cb82a422bb200254dd8b469434b045ffc"}, {file = "types-PyYAML-6.0.12.5.tar.gz", hash = "sha256:3b61b7a8111ce368eb366e4a13f3e94e568bc2ed6227e01520a50ee07993bf38"},
{file = "types_PyYAML-6.0.12.3-py3-none-any.whl", hash = "sha256:879700e9f215afb20ab5f849590418ab500989f83a57e635689e1d50ccc63f0c"}, {file = "types_PyYAML-6.0.12.5-py3-none-any.whl", hash = "sha256:dcaf87b65b839e7b641721346ef8b12a87f94071e15205a64ac93ca0e0afc77a"},
] ]
[[package]] [[package]]
name = "types-redis" name = "types-redis"
version = "4.4.0.4" version = "4.4.0.6"
description = "Typing stubs for redis" description = "Typing stubs for redis"
category = "dev" category = "dev"
optional = false optional = false
python-versions = "*" python-versions = "*"
files = [ files = [
{file = "types-redis-4.4.0.4.tar.gz", hash = "sha256:b70829ca3401d3153d628e28d860070eff1b36b2fa3e5af3e583c1d167383cab"}, {file = "types-redis-4.4.0.6.tar.gz", hash = "sha256:57f8b3706afe47ef36496d70a97a3783560e6cb19e157be12985dbb31de1d853"},
{file = "types_redis-4.4.0.4-py3-none-any.whl", hash = "sha256:802e893ad3f88e03d3a2feb0d23a715d60b0bb330bc598a52f1de237fc2547a5"}, {file = "types_redis-4.4.0.6-py3-none-any.whl", hash = "sha256:8b40d6bf3a54352d4cb2aa7d01294c572a39d40a9d289b96bdf490b51d3a42d2"},
] ]
[package.dependencies] [package.dependencies]
@ -6404,14 +6462,14 @@ types-pyOpenSSL = "*"
[[package]] [[package]]
name = "types-requests" name = "types-requests"
version = "2.28.11.8" version = "2.28.11.12"
description = "Typing stubs for requests" description = "Typing stubs for requests"
category = "dev" category = "dev"
optional = false optional = false
python-versions = "*" python-versions = "*"
files = [ files = [
{file = "types-requests-2.28.11.8.tar.gz", hash = "sha256:e67424525f84adfbeab7268a159d3c633862dafae15c5b19547ce1b55954f0a3"}, {file = "types-requests-2.28.11.12.tar.gz", hash = "sha256:fd530aab3fc4f05ee36406af168f0836e6f00f1ee51a0b96b7311f82cb675230"},
{file = "types_requests-2.28.11.8-py3-none-any.whl", hash = "sha256:61960554baca0008ae7e2db2bd3b322ca9a144d3e80ce270f5fb640817e40994"}, {file = "types_requests-2.28.11.12-py3-none-any.whl", hash = "sha256:dbc2933635860e553ffc59f5e264264981358baffe6342b925e3eb8261f866ee"},
] ]
[package.dependencies] [package.dependencies]
@ -6419,26 +6477,26 @@ types-urllib3 = "<1.27"
[[package]] [[package]]
name = "types-toml" name = "types-toml"
version = "0.10.8.1" version = "0.10.8.3"
description = "Typing stubs for toml" description = "Typing stubs for toml"
category = "dev" category = "dev"
optional = false optional = false
python-versions = "*" python-versions = "*"
files = [ files = [
{file = "types-toml-0.10.8.1.tar.gz", hash = "sha256:171bdb3163d79a520560f24ba916a9fc9bff81659c5448a9fea89240923722be"}, {file = "types-toml-0.10.8.3.tar.gz", hash = "sha256:f37244eff4cd7eace9cb70d0bac54d3eba77973aa4ef26c271ac3d1c6503a48e"},
{file = "types_toml-0.10.8.1-py3-none-any.whl", hash = "sha256:b7b5c4977f96ab7b5ac06d8a6590d17c0bf252a96efc03b109c2711fb3e0eafd"}, {file = "types_toml-0.10.8.3-py3-none-any.whl", hash = "sha256:a2286a053aea6ab6ff814659272b1d4a05d86a1dd52b807a87b23511993b46c5"},
] ]
[[package]] [[package]]
name = "types-urllib3" name = "types-urllib3"
version = "1.26.25.4" version = "1.26.25.5"
description = "Typing stubs for urllib3" description = "Typing stubs for urllib3"
category = "dev" category = "dev"
optional = false optional = false
python-versions = "*" python-versions = "*"
files = [ files = [
{file = "types-urllib3-1.26.25.4.tar.gz", hash = "sha256:eec5556428eec862b1ac578fb69aab3877995a99ffec9e5a12cf7fbd0cc9daee"}, {file = "types-urllib3-1.26.25.5.tar.gz", hash = "sha256:5630e578246d170d91ebe3901788cd28d53c4e044dc2e2488e3b0d55fb6895d8"},
{file = "types_urllib3-1.26.25.4-py3-none-any.whl", hash = "sha256:ed6b9e8a8be488796f72306889a06a3fc3cb1aa99af02ab8afb50144d7317e49"}, {file = "types_urllib3-1.26.25.5-py3-none-any.whl", hash = "sha256:e8f25c8bb85cde658c72ee931e56e7abd28803c26032441eea9ff4a4df2b0c31"},
] ]
[[package]] [[package]]
@ -6642,14 +6700,14 @@ files = [
[[package]] [[package]]
name = "websocket-client" name = "websocket-client"
version = "1.5.0" version = "1.5.1"
description = "WebSocket client for Python with low level API options" description = "WebSocket client for Python with low level API options"
category = "dev" category = "dev"
optional = false optional = false
python-versions = ">=3.7" python-versions = ">=3.7"
files = [ files = [
{file = "websocket-client-1.5.0.tar.gz", hash = "sha256:561ca949e5bbb5d33409a37235db55c279235c78ee407802f1d2314fff8a8536"}, {file = "websocket-client-1.5.1.tar.gz", hash = "sha256:3f09e6d8230892547132177f575a4e3e73cfdf06526e20cc02aa1c3b47184d40"},
{file = "websocket_client-1.5.0-py3-none-any.whl", hash = "sha256:fb5d81b95d350f3a54838ebcb4c68a5353bbd1412ae8f068b1e5280faeb13074"}, {file = "websocket_client-1.5.1-py3-none-any.whl", hash = "sha256:cdf5877568b7e83aa7cf2244ab56a3213de587bbe0ce9d8b9600fc77b455d89e"},
] ]
[package.extras] [package.extras]
@ -6929,14 +6987,14 @@ multidict = ">=4.0"
[[package]] [[package]]
name = "zipp" name = "zipp"
version = "3.12.0" version = "3.13.0"
description = "Backport of pathlib-compatible object wrapper for zip files" description = "Backport of pathlib-compatible object wrapper for zip files"
category = "dev" category = "dev"
optional = false optional = false
python-versions = ">=3.7" python-versions = ">=3.7"
files = [ files = [
{file = "zipp-3.12.0-py3-none-any.whl", hash = "sha256:9eb0a4c5feab9b08871db0d672745b53450d7f26992fd1e4653aa43345e97b86"}, {file = "zipp-3.13.0-py3-none-any.whl", hash = "sha256:e8b2a36ea17df80ffe9e2c4fda3f693c3dad6df1697d3cd3af232db680950b0b"},
{file = "zipp-3.12.0.tar.gz", hash = "sha256:73efd63936398aac78fd92b6f4865190119d6c91b531532e798977ea8dd402eb"}, {file = "zipp-3.13.0.tar.gz", hash = "sha256:23f70e964bc11a34cef175bc90ba2914e1e4545ea1e3e2f67c079671883f9cb6"},
] ]
[package.extras] [package.extras]
@ -6944,7 +7002,7 @@ docs = ["furo", "jaraco.packaging (>=9)", "jaraco.tidelift (>=1.4)", "rst.linker
testing = ["flake8 (<5)", "func-timeout", "jaraco.functools", "jaraco.itertools", "more-itertools", "pytest (>=6)", "pytest-black (>=0.3.7)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=1.3)", "pytest-flake8", "pytest-mypy (>=0.9.1)"] testing = ["flake8 (<5)", "func-timeout", "jaraco.functools", "jaraco.itertools", "more-itertools", "pytest (>=6)", "pytest-black (>=0.3.7)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=1.3)", "pytest-flake8", "pytest-mypy (>=0.9.1)"]
[extras] [extras]
all = ["cohere", "openai", "nlpcloud", "huggingface_hub", "manifest-ml", "elasticsearch", "google-search-results", "faiss-cpu", "sentence-transformers", "transformers", "spacy", "nltk", "wikipedia", "beautifulsoup4", "tiktoken", "torch", "jinja2", "pinecone-client", "weaviate-client", "redis", "google-api-python-client", "wolframalpha", "qdrant-client", "tensorflow-text"] all = ["cohere", "openai", "nlpcloud", "huggingface_hub", "manifest-ml", "elasticsearch", "google-search-results", "faiss-cpu", "sentence-transformers", "transformers", "spacy", "nltk", "wikipedia", "beautifulsoup4", "tiktoken", "torch", "jinja2", "pinecone-client", "weaviate-client", "redis", "google-api-python-client", "wolframalpha", "qdrant-client", "tensorflow-text", "pypdf"]
llms = ["cohere", "openai", "nlpcloud", "huggingface_hub", "manifest-ml", "torch", "transformers"] llms = ["cohere", "openai", "nlpcloud", "huggingface_hub", "manifest-ml", "torch", "transformers"]
[metadata] [metadata]

View File

@ -44,6 +44,8 @@ huggingface_hub = {version = "^0", optional = true}
google-search-results = {version = "^2", optional = true} google-search-results = {version = "^2", optional = true}
sentence-transformers = {version = "^2", optional = true} sentence-transformers = {version = "^2", optional = true}
aiohttp = "^3.8.3" aiohttp = "^3.8.3"
pypdf = {version = "^3.4.0", optional = true}
black = "^23.1.0"
[tool.poetry.group.docs.dependencies] [tool.poetry.group.docs.dependencies]
@ -72,7 +74,6 @@ pytest-asyncio = "^0.20.3"
[tool.poetry.group.lint.dependencies] [tool.poetry.group.lint.dependencies]
flake8-docstrings = "^1.6.0" flake8-docstrings = "^1.6.0"
black = "^22.10.0"
isort = "^5.10.1" isort = "^5.10.1"
flake8 = "^6.0.0" flake8 = "^6.0.0"
types-toml = "^0.10.8.1" types-toml = "^0.10.8.1"
@ -92,7 +93,7 @@ playwright = "^1.28.0"
[tool.poetry.extras] [tool.poetry.extras]
llms = ["cohere", "openai", "nlpcloud", "huggingface_hub", "manifest-ml", "torch", "transformers"] llms = ["cohere", "openai", "nlpcloud", "huggingface_hub", "manifest-ml", "torch", "transformers"]
all = ["cohere", "openai", "nlpcloud", "huggingface_hub", "manifest-ml", "elasticsearch", "google-search-results", "faiss-cpu", "sentence-transformers", "transformers", "spacy", "nltk", "wikipedia", "beautifulsoup4", "tiktoken", "torch", "jinja2", "pinecone-client", "weaviate-client", "redis", "google-api-python-client", "wolframalpha", "qdrant-client", "tensorflow-text"] all = ["cohere", "openai", "nlpcloud", "huggingface_hub", "manifest-ml", "elasticsearch", "google-search-results", "faiss-cpu", "sentence_transformers", "transformers", "spacy", "nltk", "wikipedia", "beautifulsoup4", "tiktoken", "torch", "jinja2", "pinecone-client", "weaviate-client", "redis", "google-api-python-client", "wolframalpha", "qdrant-client", "tensorflow-text", "pypdf"]
[tool.isort] [tool.isort]
profile = "black" profile = "black"

Binary file not shown.

View File

@ -0,0 +1,20 @@
"""Test splitting with page numbers included."""
from langchain.document_loaders import PagedPDFSplitter
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.vectorstores import FAISS
import os
def test_pdf_pagesplitter() -> None:
"""Test splitting with page numbers included."""
loader = PagedPDFSplitter(chunk_size=250)
script_dir = os.path.dirname(__file__)
splits, metadatas = loader.load_and_split(
os.path.join(script_dir, "examples/hello.pdf"))
assert "pages" in metadatas[0]
assert "key" in metadatas[0]
assert len(splits) == len(metadatas)
faiss_index = FAISS.from_texts(splits, OpenAIEmbeddings(), metadatas=metadatas)
docs = faiss_index.similarity_search("Complete this sentence: Hello", k=1)
assert "Hello World" in docs[0].page_content