vrr/SurfSense
2
0
Fork 0
mirror of https://github.com/MODSetter/SurfSense.git synced 2025-09-01 10:09:08 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: Shifted to RecursiveChunker and CodeChunker

Browse source 
- Codebase Q/A should be lot better now.
This commit is contained in:
DESKTOP-RTLN3BA\$punk 2025-04-29 23:02:07 -07:00
parent 3bc78e6a1b
commit 22da221ad5
5 changed files with 285 additions and 69 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

14
surfsense_backend/app/config/__init__.py
View file

@ -1,12 +1,10 @@
import os
from pathlib import Path
from chonkie import AutoEmbeddings, LateChunker
from rerankers import Reranker
from langchain_community.chat_models import ChatLiteLLM
from chonkie import AutoEmbeddings, CodeChunker, RecursiveChunker
from dotenv import load_dotenv
from langchain_community.chat_models import ChatLiteLLM
from rerankers import Reranker
# Get the base directory of the project
BASE_DIR = Path(__file__).resolve().parent.parent.parent
@ -39,10 +37,12 @@ class Config:
# Chonkie Configuration | Edit this to your needs
EMBEDDING_MODEL = os.getenv("EMBEDDING_MODEL")
embedding_model_instance = AutoEmbeddings.get_embeddings(EMBEDDING_MODEL)
chunker_instance = LateChunker(
embedding_model=EMBEDDING_MODEL,
chunker_instance = RecursiveChunker(
chunk_size=embedding_model_instance.max_seq_length,
)
code_chunker_instance = CodeChunker(
chunk_size=embedding_model_instance.max_seq_length
)
# Reranker's Configuration | Pinecode, Cohere etc. Read more at https://github.com/AnswerDotAI/rerankers?tab=readme-ov-file#usage
RERANKERS_MODEL_NAME = os.getenv("RERANKERS_MODEL_NAME")

40
surfsense_backend/app/tasks/background_tasks.py
View file

@ -80,7 +80,7 @@ async def add_crawled_url_document(
# Process chunks
chunks = [
Chunk(content=chunk.text, embedding=chunk.embedding)
Chunk(content=chunk.text, embedding=config.embedding_model_instance.embed(chunk.text))
for chunk in config.chunker_instance.chunk(content_in_markdown)
]
@ -166,7 +166,7 @@ async def add_extension_received_document(
# Process chunks
chunks = [
Chunk(content=chunk.text, embedding=chunk.embedding)
Chunk(content=chunk.text, embedding=config.embedding_model_instance.embed(chunk.text))
for chunk in config.chunker_instance.chunk(content.pageContent)
]
@ -215,7 +215,7 @@ async def add_received_file_document(
# Process chunks
chunks = [
Chunk(content=chunk.text, embedding=chunk.embedding)
Chunk(content=chunk.text, embedding=config.embedding_model_instance.embed(chunk.text))
for chunk in config.chunker_instance.chunk(file_in_markdown)
]
@ -256,14 +256,14 @@ async def add_youtube_video_document(
"""
try:
from youtube_transcript_api import YouTubeTranscriptApi
# Extract video ID from URL
def get_youtube_video_id(url: str):
from urllib.parse import urlparse, parse_qs
parsed_url = urlparse(url)
hostname = parsed_url.hostname
if hostname == "youtu.be":
return parsed_url.path[1:]
if hostname in ("www.youtube.com", "youtube.com"):
@ -275,26 +275,27 @@ async def add_youtube_video_document(
if parsed_url.path.startswith("/v/"):
return parsed_url.path.split("/")[2]
return None
# Get video ID
video_id = get_youtube_video_id(url)
if not video_id:
raise ValueError(f"Could not extract video ID from URL: {url}")
# Get video metadata
import json
from urllib.parse import urlencode
from urllib.request import urlopen
params = {"format": "json", "url": f"https://www.youtube.com/watch?v={video_id}"}
params = {"format": "json",
"url": f"https://www.youtube.com/watch?v={video_id}"}
oembed_url = "https://www.youtube.com/oembed"
query_string = urlencode(params)
full_url = oembed_url + "?" + query_string
with urlopen(full_url) as response:
response_text = response.read()
video_data = json.loads(response_text.decode())
# Get video transcript
try:
captions = YouTubeTranscriptApi.get_transcript(video_id)
@ -309,7 +310,7 @@ async def add_youtube_video_document(
transcript_text = "\n".join(transcript_segments)
except Exception as e:
transcript_text = f"No captions available for this video. Error: {str(e)}"
# Format document metadata in a more maintainable way
metadata_sections = [
("METADATA", [
@ -343,17 +344,18 @@ async def add_youtube_video_document(
summary_chain = SUMMARY_PROMPT_TEMPLATE | config.long_context_llm_instance
summary_result = await summary_chain.ainvoke({"document": combined_document_string})
summary_content = summary_result.content
summary_embedding = config.embedding_model_instance.embed(summary_content)
summary_embedding = config.embedding_model_instance.embed(
summary_content)
# Process chunks
chunks = [
Chunk(content=chunk.text, embedding=chunk.embedding)
Chunk(content=chunk.text, embedding=config.embedding_model_instance.embed(chunk.text))
for chunk in config.chunker_instance.chunk(transcript_text)
]
# Create document
from app.db import Document, DocumentType
document = Document(
title=video_data.get("title", "YouTube Video"),
document_type=DocumentType.YOUTUBE_VIDEO,
@ -369,11 +371,11 @@ async def add_youtube_video_document(
chunks=chunks,
search_space_id=search_space_id
)
session.add(document)
await session.commit()
await session.refresh(document)
return document
except SQLAlchemyError as db_error:
await session.rollback()

10
surfsense_backend/app/tasks/connectors_indexing_tasks.py
View file

@ -222,7 +222,7 @@ async def index_slack_messages(
# Process chunks
chunks = [
Chunk(content=chunk.text, embedding=chunk.embedding)
Chunk(content=chunk.text, embedding=config.embedding_model_instance.embed(chunk.text))
for chunk in config.chunker_instance.chunk(channel_content)
]
@ -515,7 +515,7 @@ async def index_notion_pages(
# Process chunks
logger.debug(f"Chunking content for page {page_title}")
chunks = [
Chunk(content=chunk.text, embedding=chunk.embedding)
Chunk(content=chunk.text, embedding=config.embedding_model_instance.embed(chunk.text))
for chunk in config.chunker_instance.chunk(markdown_content)
]
@ -720,8 +720,8 @@ async def index_github_repos(
# Chunk the content
try:
chunks_data = [
Chunk(content=chunk.text, embedding=chunk.embedding)
for chunk in config.chunker_instance.chunk(file_content)
Chunk(content=chunk.text, embedding=config.embedding_model_instance.embed(chunk.text))
for chunk in config.code_chunker_instance.chunk(file_content)
]
except Exception as chunk_err:
logger.error(f"Failed to chunk file {full_path_key}: {chunk_err}")
@ -984,7 +984,7 @@ async def index_linear_issues(
# Process chunks - using the full issue content with comments
chunks = [
Chunk(content=chunk.text, embedding=chunk.embedding)
Chunk(content=chunk.text, embedding=config.embedding_model_instance.embed(chunk.text))
for chunk in config.chunker_instance.chunk(issue_content)
]

2
surfsense_backend/pyproject.toml
View file

@ -7,7 +7,7 @@ requires-python = ">=3.12"
dependencies = [
"alembic>=1.13.0",
"asyncpg>=0.30.0",
"chonkie[all]>=0.4.1",
"chonkie[all]>=1.0.6",
"fastapi>=0.115.8",
"fastapi-users[oauth,sqlalchemy]>=14.0.1",
"firecrawl-py>=1.12.0",

288
surfsense_backend/uv.lock generated
View file

@ -13,6 +13,24 @@ resolution-markers = [
"(python_full_version < '3.12.4' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version < '3.12.4' and sys_platform != 'darwin' and sys_platform != 'linux')",
]
[[package]]
name = "accelerate"
version = "1.6.0"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "huggingface-hub" },
{ name = "numpy" },
{ name = "packaging" },
{ name = "psutil" },
{ name = "pyyaml" },
{ name = "safetensors" },
{ name = "torch" },
]
sdist = { url = "https://files.pythonhosted.org/packages/8a/6e/c29a1dcde7db07f47870ed63e5124086b11874ad52ccd533dc1ca2c799da/accelerate-1.6.0.tar.gz", hash = "sha256:28c1ef1846e690944f98b68dc7b8bb6c51d032d45e85dcbb3adb0c8b99dffb32", size = 363804 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/63/b1/8198e3cdd11a426b1df2912e3381018c4a4a55368f6d0857ba3ca418ef93/accelerate-1.6.0-py3-none-any.whl", hash = "sha256:1aee717d3d3735ad6d09710a7c26990ee4652b79b4e93df46551551b5227c2aa", size = 354748 },
]
[[package]]
name = "aiofiles"
version = "24.1.0"
@ -201,19 +219,6 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/fc/30/d4986a882011f9df997a55e6becd864812ccfcd821d64aac8570ee39f719/attrs-25.1.0-py3-none-any.whl", hash = "sha256:c75a69e28a550a7e93789579c22aa26b0f5b83b75dc4e08fe092980051e1090a", size = 63152 },
]
[[package]]
name = "autotiktokenizer"
version = "0.2.2"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "huggingface-hub" },
{ name = "tiktoken" },
]
sdist = { url = "https://files.pythonhosted.org/packages/a6/1a/c6f494750dc67c2e5b06b91ae9565d46adb384f25f61a7136ff79dd02413/autotiktokenizer-0.2.2.tar.gz", hash = "sha256:f0954f14cedfe538b96ba0eed2e39996378c0bdf649fd977d6a047e419e05fdb", size = 15401 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/d8/7b/c34469a1495d755bac1c80fbf3c0c2c29eb03ffe61172d889426025173bd/autotiktokenizer-0.2.2-py3-none-any.whl", hash = "sha256:ebbf15d9d5516fcb3287a8153bd8efbcc932f9c99089b2357255413cf37815d9", size = 8957 },
]
[[package]]
name = "backoff"
version = "2.2.1"
@ -363,23 +368,36 @@ wheels = [
[[package]]
name = "chonkie"
version = "0.4.1"
version = "1.0.6"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "autotiktokenizer" },
{ name = "tokenizers" },
{ name = "tqdm" },
]
sdist = { url = "https://files.pythonhosted.org/packages/2e/94/4a1bc8bdf06e7327bb256abb85767647125286c9bbc7cbcd77a550b96d63/chonkie-0.4.1.tar.gz", hash = "sha256:164216efa01af02e750e7cb218cea87918a18f83ebbd8f020b25557f1ed36aa9", size = 43284 }
sdist = { url = "https://files.pythonhosted.org/packages/5a/db/16d5d23a216db734bcb68e61c466ff48a55dc0d2cdc7ecdd73aaea1f6f7d/chonkie-1.0.6.tar.gz", hash = "sha256:feefad3cbbb62b4a55f4c6409bd8d8f0ee180d8319c4d32e31539a768955b3b0", size = 70056 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/c0/b5/c0d77500a413794773edb630bdc7061121c237a4eaf6ce222226c200d603/chonkie-0.4.1-py3-none-any.whl", hash = "sha256:af7d95d17f4ed60a26e32f0bad60f807287e3301189114755d727657ed2ef964", size = 51193 },
{ url = "https://files.pythonhosted.org/packages/bc/46/d6d9789eb6e61bfa073a13fd2b5cbbcf022a7781adbb060a25d82f16437e/chonkie-1.0.6-py3-none-any.whl", hash = "sha256:d8cfcf665cb6a64ac6ca87da61207372a88b9e5a7bb697faade78069c853e4b1", size = 89526 },
]
[package.optional-dependencies]
all = [
{ name = "accelerate" },
{ name = "cohere" },
{ name = "google-genai" },
{ name = "huggingface-hub" },
{ name = "jsonschema" },
{ name = "magika" },
{ name = "model2vec" },
{ name = "numpy" },
{ name = "openai" },
{ name = "pydantic" },
{ name = "rich" },
{ name = "sentence-transformers" },
{ name = "tiktoken" },
{ name = "torch" },
{ name = "transformers" },
{ name = "tree-sitter" },
{ name = "tree-sitter-language-pack" },
]
[[package]]
@ -394,6 +412,26 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/7e/d4/7ebdbd03970677812aac39c869717059dbb71a4cfc033ca6e5221787892c/click-8.1.8-py3-none-any.whl", hash = "sha256:63c132bbbed01578a06712a2d1f497bb62d9c1c0d329b7903a866228027263b2", size = 98188 },
]
[[package]]
name = "cohere"
version = "5.15.0"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "fastavro" },
{ name = "httpx" },
{ name = "httpx-sse" },
{ name = "pydantic" },
{ name = "pydantic-core" },
{ name = "requests" },
{ name = "tokenizers" },
{ name = "types-requests" },
{ name = "typing-extensions" },
]
sdist = { url = "https://files.pythonhosted.org/packages/a1/33/69c7d1b25a20eafef4197a1444c7f87d5241e936194e54876ea8996157e6/cohere-5.15.0.tar.gz", hash = "sha256:e802d4718ddb0bb655654382ebbce002756a3800faac30296cde7f1bdc6ff2cc", size = 135021 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/c7/87/94694db7fe6df979fbc03286eaabdfa98f1c8fa532960e5afdf965e10960/cohere-5.15.0-py3-none-any.whl", hash = "sha256:22ff867c2a6f2fc2b585360c6072f584f11f275ef6d9242bac24e0fa2df1dfb5", size = 259522 },
]
[[package]]
name = "colorama"
version = "0.4.6"
@ -660,6 +698,26 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/a6/08/9968963c1fb8c34627b7f1fbcdfe9438540f87dc7c9bfb59bb4fd19a4ecf/fastapi_users_db_sqlalchemy-7.0.0-py3-none-any.whl", hash = "sha256:5fceac018e7cfa69efc70834dd3035b3de7988eb4274154a0dbe8b14f5aa001e", size = 6891 },
]
[[package]]
name = "fastavro"
version = "1.10.0"
source = { registry = "https://pypi.org/simple" }
sdist = { url = "https://files.pythonhosted.org/packages/f3/67/7121d2221e998706cac00fa779ec44c1c943cb65e8a7ed1bd57d78d93f2c/fastavro-1.10.0.tar.gz", hash = "sha256:47bf41ac6d52cdfe4a3da88c75a802321321b37b663a900d12765101a5d6886f", size = 987970 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/9c/a4/8e69c0a5cd121e5d476237de1bde5a7947f791ae45768ae52ed0d3ea8d18/fastavro-1.10.0-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:cfe57cb0d72f304bd0dcc5a3208ca6a7363a9ae76f3073307d095c9d053b29d4", size = 1036343 },
{ url = "https://files.pythonhosted.org/packages/1e/01/aa219e2b33e5873d27b867ec0fad9f35f23d461114e1135a7e46c06786d2/fastavro-1.10.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:74e517440c824cb65fb29d3e3903a9406f4d7c75490cef47e55c4c82cdc66270", size = 3263368 },
{ url = "https://files.pythonhosted.org/packages/a7/ba/1766e2d7d95df2e95e9e9a089dc7a537c0616720b053a111a918fa7ee6b6/fastavro-1.10.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:203c17d44cadde76e8eecb30f2d1b4f33eb478877552d71f049265dc6f2ecd10", size = 3328933 },
{ url = "https://files.pythonhosted.org/packages/2e/40/26e56696b9696ab4fbba25a96b8037ca3f9fd8a8cc55b4b36400ef023e49/fastavro-1.10.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:6575be7f2b5f94023b5a4e766b0251924945ad55e9a96672dc523656d17fe251", size = 3258045 },
{ url = "https://files.pythonhosted.org/packages/4e/bc/2f6c92c06c5363372abe828bccdd95762f2c1983b261509f94189c38c8a1/fastavro-1.10.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:fe471deb675ed2f01ee2aac958fbf8ebb13ea00fa4ce7f87e57710a0bc592208", size = 3418001 },
{ url = "https://files.pythonhosted.org/packages/0c/ce/cfd16546c04ebbca1be80873b533c788cec76f7bfac231bfac6786047572/fastavro-1.10.0-cp312-cp312-win_amd64.whl", hash = "sha256:567ff515f2a5d26d9674b31c95477f3e6022ec206124c62169bc2ffaf0889089", size = 487855 },
{ url = "https://files.pythonhosted.org/packages/c9/c4/163cf154cc694c2dccc70cd6796db6214ac668a1260bf0310401dad188dc/fastavro-1.10.0-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:82263af0adfddb39c85f9517d736e1e940fe506dfcc35bc9ab9f85e0fa9236d8", size = 1022741 },
{ url = "https://files.pythonhosted.org/packages/38/01/a24598f5f31b8582a92fe9c41bf91caeed50d5b5eaa7576e6f8b23cb488d/fastavro-1.10.0-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:566c193109ff0ff84f1072a165b7106c4f96050078a4e6ac7391f81ca1ef3efa", size = 3237421 },
{ url = "https://files.pythonhosted.org/packages/a7/bf/08bcf65cfb7feb0e5b1329fafeb4a9b95b7b5ec723ba58c7dbd0d04ded34/fastavro-1.10.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e400d2e55d068404d9fea7c5021f8b999c6f9d9afa1d1f3652ec92c105ffcbdd", size = 3300222 },
{ url = "https://files.pythonhosted.org/packages/53/4d/a6c25f3166328f8306ec2e6be1123ed78a55b8ab774a43a661124508881f/fastavro-1.10.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:9b8227497f71565270f9249fc9af32a93644ca683a0167cfe66d203845c3a038", size = 3233276 },
{ url = "https://files.pythonhosted.org/packages/47/1c/b2b2ce2bf866a248ae23e96a87b3b8369427ff79be9112073039bee1d245/fastavro-1.10.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:8e62d04c65461b30ac6d314e4197ad666371e97ae8cb2c16f971d802f6c7f514", size = 3388936 },
{ url = "https://files.pythonhosted.org/packages/1f/2c/43927e22a2d57587b3aa09765098a6d833246b672d34c10c5f135414745a/fastavro-1.10.0-cp313-cp313-win_amd64.whl", hash = "sha256:86baf8c9740ab570d0d4d18517da71626fe9be4d1142bea684db52bd5adb078f", size = 483967 },
]
[[package]]
name = "filelock"
version = "3.17.0"
@ -858,6 +916,24 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/94/b6/60f2910485d32f7bba92cc33e5053b3f29d61fccaa57e5e58c600bb7e0d2/google_cloud_vision-3.10.1-py3-none-any.whl", hash = "sha256:91959ea12b0d6a8442e30c0a5062cd305f349a4840f9184b5061b3153bbd8476", size = 526076 },
]
[[package]]
name = "google-genai"
version = "1.12.1"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "anyio" },
{ name = "google-auth" },
{ name = "httpx" },
{ name = "pydantic" },
{ name = "requests" },
{ name = "typing-extensions" },
{ name = "websockets" },
]
sdist = { url = "https://files.pythonhosted.org/packages/38/9c/c907dbea921663bb7c41f415337bedd08259d17da8d156396c7237611744/google_genai-1.12.1.tar.gz", hash = "sha256:5c7eda422360643ce602a3f6b23152470ec1039310ef40080cbe4e71237f6391", size = 167752 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/29/2c/5b454dec837328eb167e78f45a14da502af223f8b94a4824e2fd0df74f19/google_genai-1.12.1-py3-none-any.whl", hash = "sha256:7cbc1bc029712946ce41bcf80c0eaa89eb8c09c308efbbfe30fd491f402c258a", size = 165940 },
]
[[package]]
name = "googleapis-common-protos"
version = "1.69.2"
@ -1490,6 +1566,24 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/80/83/8c54533b3576f4391eebea88454738978669a6cad0d8e23266224007939d/lxml-5.3.1-cp313-cp313-win_amd64.whl", hash = "sha256:91fb6a43d72b4f8863d21f347a9163eecbf36e76e2f51068d59cd004c506f332", size = 3814484 },
]
[[package]]
name = "magika"
version = "0.6.1"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "click" },
{ name = "numpy" },
{ name = "onnxruntime" },
{ name = "python-dotenv" },
]
sdist = { url = "https://files.pythonhosted.org/packages/6d/18/ea70f6abd36f455037340f12c8125918c726d08cd6e01f0b76b6884e0c38/magika-0.6.1.tar.gz", hash = "sha256:e3dd22c73936630b1cd79d0f412d6d9a53dc99ba5e3709b1ac53f56bc998e635", size = 3030234 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/1f/be/c9f7bb9ee94abe8d344b660672001313e459c67b867b24abe32d5c80a9ce/magika-0.6.1-py3-none-any.whl", hash = "sha256:15838d2469f1394d8e9598bc7fceea1ede7f35aebe9675c6b45c6b5c48315931", size = 2968516 },
{ url = "https://files.pythonhosted.org/packages/3c/b9/016b174520e81faef5edb31b6c7a73966dc84ee33acd23a2e7b775df7ba4/magika-0.6.1-py3-none-macosx_11_0_arm64.whl", hash = "sha256:dadd036296a2e4840fd48fa0712848fe122da438e8f607dc8f19ca4663c359dc", size = 12408519 },
{ url = "https://files.pythonhosted.org/packages/02/b7/e7dfeb235823a82d676c68a748541c24db0249b854f945f6e3cec11c1b7e/magika-0.6.1-py3-none-manylinux_2_28_x86_64.whl", hash = "sha256:133c0e1a844361de86ca2dd7c530e38b324e86177d30c52e36fd82101c190b5c", size = 15089294 },
{ url = "https://files.pythonhosted.org/packages/64/f0/bec5bff0125d08c1bc3baef88beeb910121085249f67b5994ea961615b55/magika-0.6.1-py3-none-win_amd64.whl", hash = "sha256:0342b6230ea9aea7ab4b8fa92e1b46f1cc62e724d452ee8d6821a37f56738d22", size = 12378455 },
]
[[package]]
name = "makefun"
version = "1.15.6"
@ -1643,7 +1737,7 @@ wheels = [
[[package]]
name = "model2vec"
version = "0.4.0"
version = "0.4.1"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "jinja2" },
@ -1655,9 +1749,9 @@ dependencies = [
{ name = "tokenizers" },
{ name = "tqdm" },
]
sdist = { url = "https://files.pythonhosted.org/packages/83/e2/3fb7bd8c612f71ad3abded92e7401f97f1e71427d3a68a3fb85f39394b17/model2vec-0.4.0.tar.gz", hash = "sha256:48d4a3da040499b0090f736eb8f22ea0fdd35b67462d81d789c70004423adbae", size = 2486998 }
sdist = { url = "https://files.pythonhosted.org/packages/b8/c1/3cd6cab10e8b7da8c32acebf85672d38a26f5f03165bfeaa617a5ec0bb61/model2vec-0.4.1.tar.gz", hash = "sha256:fc6038416679eebe448951708f2d0bebdee8510f47970af1c81a8f054a3c3f9f", size = 2660626 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/93/7d/39ff093c4e45303a06e3c5825c6144cbd21f18a1393a154bbf93232b0f1a/model2vec-0.4.0-py3-none-any.whl", hash = "sha256:df30685a55841c61c6638e4f329648e76b148507bd778801d7bfcd6b970a4f2f", size = 38593 },
{ url = "https://files.pythonhosted.org/packages/cd/76/c8575f90f521017597c5e57e3bfef61e3f27d9cb6c741a82a24d72b10a60/model2vec-0.4.1-py3-none-any.whl", hash = "sha256:04a397a17da9b967082b6baa4c494f0be48c89ec4e1a3975b4f290f045238a38", size = 41972 },
]
[[package]]
@ -1764,18 +1858,40 @@ wheels = [
[[package]]
name = "numpy"
version = "1.26.4"
version = "2.2.5"
source = { registry = "https://pypi.org/simple" }
sdist = { url = "https://files.pythonhosted.org/packages/65/6e/09db70a523a96d25e115e71cc56a6f9031e7b8cd166c1ac8438307c14058/numpy-1.26.4.tar.gz", hash = "sha256:2a02aba9ed12e4ac4eb3ea9421c420301a0c6460d9830d74a9df87efa4912010", size = 15786129 }
sdist = { url = "https://files.pythonhosted.org/packages/dc/b2/ce4b867d8cd9c0ee84938ae1e6a6f7926ebf928c9090d036fc3c6a04f946/numpy-2.2.5.tar.gz", hash = "sha256:a9c0d994680cd991b1cb772e8b297340085466a6fe964bc9d4e80f5e2f43c291", size = 20273920 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/95/12/8f2020a8e8b8383ac0177dc9570aad031a3beb12e38847f7129bacd96228/numpy-1.26.4-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:b3ce300f3644fb06443ee2222c2201dd3a89ea6040541412b8fa189341847218", size = 20335901 },
{ url = "https://files.pythonhosted.org/packages/75/5b/ca6c8bd14007e5ca171c7c03102d17b4f4e0ceb53957e8c44343a9546dcc/numpy-1.26.4-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:03a8c78d01d9781b28a6989f6fa1bb2c4f2d51201cf99d3dd875df6fbd96b23b", size = 13685868 },
{ url = "https://files.pythonhosted.org/packages/79/f8/97f10e6755e2a7d027ca783f63044d5b1bc1ae7acb12afe6a9b4286eac17/numpy-1.26.4-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9fad7dcb1aac3c7f0584a5a8133e3a43eeb2fe127f47e3632d43d677c66c102b", size = 13925109 },
{ url = "https://files.pythonhosted.org/packages/0f/50/de23fde84e45f5c4fda2488c759b69990fd4512387a8632860f3ac9cd225/numpy-1.26.4-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:675d61ffbfa78604709862923189bad94014bef562cc35cf61d3a07bba02a7ed", size = 17950613 },
{ url = "https://files.pythonhosted.org/packages/4c/0c/9c603826b6465e82591e05ca230dfc13376da512b25ccd0894709b054ed0/numpy-1.26.4-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:ab47dbe5cc8210f55aa58e4805fe224dac469cde56b9f731a4c098b91917159a", size = 13572172 },
{ url = "https://files.pythonhosted.org/packages/76/8c/2ba3902e1a0fc1c74962ea9bb33a534bb05984ad7ff9515bf8d07527cadd/numpy-1.26.4-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:1dda2e7b4ec9dd512f84935c5f126c8bd8b9f2fc001e9f54af255e8c5f16b0e0", size = 17786643 },
{ url = "https://files.pythonhosted.org/packages/28/4a/46d9e65106879492374999e76eb85f87b15328e06bd1550668f79f7b18c6/numpy-1.26.4-cp312-cp312-win32.whl", hash = "sha256:50193e430acfc1346175fcbdaa28ffec49947a06918b7b92130744e81e640110", size = 5677803 },
{ url = "https://files.pythonhosted.org/packages/16/2e/86f24451c2d530c88daf997cb8d6ac622c1d40d19f5a031ed68a4b73a374/numpy-1.26.4-cp312-cp312-win_amd64.whl", hash = "sha256:08beddf13648eb95f8d867350f6a018a4be2e5ad54c8d8caed89ebca558b2818", size = 15517754 },
{ url = "https://files.pythonhosted.org/packages/e2/f7/1fd4ff108cd9d7ef929b8882692e23665dc9c23feecafbb9c6b80f4ec583/numpy-2.2.5-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:ee461a4eaab4f165b68780a6a1af95fb23a29932be7569b9fab666c407969051", size = 20948633 },
{ url = "https://files.pythonhosted.org/packages/12/03/d443c278348371b20d830af155ff2079acad6a9e60279fac2b41dbbb73d8/numpy-2.2.5-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:ec31367fd6a255dc8de4772bd1658c3e926d8e860a0b6e922b615e532d320ddc", size = 14176123 },
{ url = "https://files.pythonhosted.org/packages/2b/0b/5ca264641d0e7b14393313304da48b225d15d471250376f3fbdb1a2be603/numpy-2.2.5-cp312-cp312-macosx_14_0_arm64.whl", hash = "sha256:47834cde750d3c9f4e52c6ca28a7361859fcaf52695c7dc3cc1a720b8922683e", size = 5163817 },
{ url = "https://files.pythonhosted.org/packages/04/b3/d522672b9e3d28e26e1613de7675b441bbd1eaca75db95680635dd158c67/numpy-2.2.5-cp312-cp312-macosx_14_0_x86_64.whl", hash = "sha256:2c1a1c6ccce4022383583a6ded7bbcda22fc635eb4eb1e0a053336425ed36dfa", size = 6698066 },
{ url = "https://files.pythonhosted.org/packages/a0/93/0f7a75c1ff02d4b76df35079676b3b2719fcdfb39abdf44c8b33f43ef37d/numpy-2.2.5-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9d75f338f5f79ee23548b03d801d28a505198297534f62416391857ea0479571", size = 14087277 },
{ url = "https://files.pythonhosted.org/packages/b0/d9/7c338b923c53d431bc837b5b787052fef9ae68a56fe91e325aac0d48226e/numpy-2.2.5-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3a801fef99668f309b88640e28d261991bfad9617c27beda4a3aec4f217ea073", size = 16135742 },
{ url = "https://files.pythonhosted.org/packages/2d/10/4dec9184a5d74ba9867c6f7d1e9f2e0fb5fe96ff2bf50bb6f342d64f2003/numpy-2.2.5-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:abe38cd8381245a7f49967a6010e77dbf3680bd3627c0fe4362dd693b404c7f8", size = 15581825 },
{ url = "https://files.pythonhosted.org/packages/80/1f/2b6fcd636e848053f5b57712a7d1880b1565eec35a637fdfd0a30d5e738d/numpy-2.2.5-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:5a0ac90e46fdb5649ab6369d1ab6104bfe5854ab19b645bf5cda0127a13034ae", size = 17899600 },
{ url = "https://files.pythonhosted.org/packages/ec/87/36801f4dc2623d76a0a3835975524a84bd2b18fe0f8835d45c8eae2f9ff2/numpy-2.2.5-cp312-cp312-win32.whl", hash = "sha256:0cd48122a6b7eab8f06404805b1bd5856200e3ed6f8a1b9a194f9d9054631beb", size = 6312626 },
{ url = "https://files.pythonhosted.org/packages/8b/09/4ffb4d6cfe7ca6707336187951992bd8a8b9142cf345d87ab858d2d7636a/numpy-2.2.5-cp312-cp312-win_amd64.whl", hash = "sha256:ced69262a8278547e63409b2653b372bf4baff0870c57efa76c5703fd6543282", size = 12645715 },
{ url = "https://files.pythonhosted.org/packages/e2/a0/0aa7f0f4509a2e07bd7a509042967c2fab635690d4f48c6c7b3afd4f448c/numpy-2.2.5-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:059b51b658f4414fff78c6d7b1b4e18283ab5fa56d270ff212d5ba0c561846f4", size = 20935102 },
{ url = "https://files.pythonhosted.org/packages/7e/e4/a6a9f4537542912ec513185396fce52cdd45bdcf3e9d921ab02a93ca5aa9/numpy-2.2.5-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:47f9ed103af0bc63182609044b0490747e03bd20a67e391192dde119bf43d52f", size = 14191709 },
{ url = "https://files.pythonhosted.org/packages/be/65/72f3186b6050bbfe9c43cb81f9df59ae63603491d36179cf7a7c8d216758/numpy-2.2.5-cp313-cp313-macosx_14_0_arm64.whl", hash = "sha256:261a1ef047751bb02f29dfe337230b5882b54521ca121fc7f62668133cb119c9", size = 5149173 },
{ url = "https://files.pythonhosted.org/packages/e5/e9/83e7a9432378dde5802651307ae5e9ea07bb72b416728202218cd4da2801/numpy-2.2.5-cp313-cp313-macosx_14_0_x86_64.whl", hash = "sha256:4520caa3807c1ceb005d125a75e715567806fed67e315cea619d5ec6e75a4191", size = 6684502 },
{ url = "https://files.pythonhosted.org/packages/ea/27/b80da6c762394c8ee516b74c1f686fcd16c8f23b14de57ba0cad7349d1d2/numpy-2.2.5-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3d14b17b9be5f9c9301f43d2e2a4886a33b53f4e6fdf9ca2f4cc60aeeee76372", size = 14084417 },
{ url = "https://files.pythonhosted.org/packages/aa/fc/ebfd32c3e124e6a1043e19c0ab0769818aa69050ce5589b63d05ff185526/numpy-2.2.5-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2ba321813a00e508d5421104464510cc962a6f791aa2fca1c97b1e65027da80d", size = 16133807 },
{ url = "https://files.pythonhosted.org/packages/bf/9b/4cc171a0acbe4666f7775cfd21d4eb6bb1d36d3a0431f48a73e9212d2278/numpy-2.2.5-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:a4cbdef3ddf777423060c6f81b5694bad2dc9675f110c4b2a60dc0181543fac7", size = 15575611 },
{ url = "https://files.pythonhosted.org/packages/a3/45/40f4135341850df48f8edcf949cf47b523c404b712774f8855a64c96ef29/numpy-2.2.5-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:54088a5a147ab71a8e7fdfd8c3601972751ded0739c6b696ad9cb0343e21ab73", size = 17895747 },
{ url = "https://files.pythonhosted.org/packages/f8/4c/b32a17a46f0ffbde8cc82df6d3daeaf4f552e346df143e1b188a701a8f09/numpy-2.2.5-cp313-cp313-win32.whl", hash = "sha256:c8b82a55ef86a2d8e81b63da85e55f5537d2157165be1cb2ce7cfa57b6aef38b", size = 6309594 },
{ url = "https://files.pythonhosted.org/packages/13/ae/72e6276feb9ef06787365b05915bfdb057d01fceb4a43cb80978e518d79b/numpy-2.2.5-cp313-cp313-win_amd64.whl", hash = "sha256:d8882a829fd779f0f43998e931c466802a77ca1ee0fe25a3abe50278616b1471", size = 12638356 },
{ url = "https://files.pythonhosted.org/packages/79/56/be8b85a9f2adb688e7ded6324e20149a03541d2b3297c3ffc1a73f46dedb/numpy-2.2.5-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:e8b025c351b9f0e8b5436cf28a07fa4ac0204d67b38f01433ac7f9b870fa38c6", size = 20963778 },
{ url = "https://files.pythonhosted.org/packages/ff/77/19c5e62d55bff507a18c3cdff82e94fe174957bad25860a991cac719d3ab/numpy-2.2.5-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:8dfa94b6a4374e7851bbb6f35e6ded2120b752b063e6acdd3157e4d2bb922eba", size = 14207279 },
{ url = "https://files.pythonhosted.org/packages/75/22/aa11f22dc11ff4ffe4e849d9b63bbe8d4ac6d5fae85ddaa67dfe43be3e76/numpy-2.2.5-cp313-cp313t-macosx_14_0_arm64.whl", hash = "sha256:97c8425d4e26437e65e1d189d22dff4a079b747ff9c2788057bfb8114ce1e133", size = 5199247 },
{ url = "https://files.pythonhosted.org/packages/4f/6c/12d5e760fc62c08eded0394f62039f5a9857f758312bf01632a81d841459/numpy-2.2.5-cp313-cp313t-macosx_14_0_x86_64.whl", hash = "sha256:352d330048c055ea6db701130abc48a21bec690a8d38f8284e00fab256dc1376", size = 6711087 },
{ url = "https://files.pythonhosted.org/packages/ef/94/ece8280cf4218b2bee5cec9567629e61e51b4be501e5c6840ceb593db945/numpy-2.2.5-cp313-cp313t-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8b4c0773b6ada798f51f0f8e30c054d32304ccc6e9c5d93d46cb26f3d385ab19", size = 14059964 },
{ url = "https://files.pythonhosted.org/packages/39/41/c5377dac0514aaeec69115830a39d905b1882819c8e65d97fc60e177e19e/numpy-2.2.5-cp313-cp313t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:55f09e00d4dccd76b179c0f18a44f041e5332fd0e022886ba1c0bbf3ea4a18d0", size = 16121214 },
{ url = "https://files.pythonhosted.org/packages/db/54/3b9f89a943257bc8e187145c6bc0eb8e3d615655f7b14e9b490b053e8149/numpy-2.2.5-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:02f226baeefa68f7d579e213d0f3493496397d8f1cff5e2b222af274c86a552a", size = 15575788 },
{ url = "https://files.pythonhosted.org/packages/b1/c4/2e407e85df35b29f79945751b8f8e671057a13a376497d7fb2151ba0d290/numpy-2.2.5-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:c26843fd58f65da9491165072da2cccc372530681de481ef670dcc8e27cfb066", size = 17893672 },
{ url = "https://files.pythonhosted.org/packages/29/7e/d0b44e129d038dba453f00d0e29ebd6eaf2f06055d72b95b9947998aca14/numpy-2.2.5-cp313-cp313t-win32.whl", hash = "sha256:1a161c2c79ab30fe4501d5a2bbfe8b162490757cf90b7f05be8b80bc02f7bb8e", size = 6377102 },
{ url = "https://files.pythonhosted.org/packages/63/be/b85e4aa4bf42c6502851b971f1c326d583fcc68227385f92089cf50a7b45/numpy-2.2.5-cp313-cp313t-win_amd64.whl", hash = "sha256:d403c84991b5ad291d3809bace5e85f4bbf44a04bdc9a88ed2bb1807b3360bb8", size = 12750096 },
]
[[package]]
@ -2813,15 +2929,15 @@ flashrank = [
[[package]]
name = "rich"
version = "13.9.4"
version = "14.0.0"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "markdown-it-py" },
{ name = "pygments" },
]
sdist = { url = "https://files.pythonhosted.org/packages/ab/3a/0316b28d0761c6734d6bc14e770d85506c986c85ffb239e688eeaab2c2bc/rich-13.9.4.tar.gz", hash = "sha256:439594978a49a09530cff7ebc4b5c7103ef57baf48d5ea3184f21d9a2befa098", size = 223149 }
sdist = { url = "https://files.pythonhosted.org/packages/a1/53/830aa4c3066a8ab0ae9a9955976fb770fe9c6102117c8ec4ab3ea62d89e8/rich-14.0.0.tar.gz", hash = "sha256:82f1bc23a6a21ebca4ae0c45af9bdbc492ed20231dcb63f297d6d1021a9d5725", size = 224078 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/19/71/39c7c0d87f8d4e6c020a393182060eaefeeae6c01dab6a84ec346f2567df/rich-13.9.4-py3-none-any.whl", hash = "sha256:6049d5e6ec054bf2779ab3358186963bac2ea89175919d699e378b99738c2a90", size = 242424 },
{ url = "https://files.pythonhosted.org/packages/0d/9b/63f4c7ebc259242c89b3acafdb37b41d1185c07ff0011164674e9076b491/rich-14.0.0-py3-none-any.whl", hash = "sha256:1c9491e1951aac09caffd42f448ee3d04e58923ffe14993f6e83068dc395d7e0", size = 243229 },
]
[[package]]
@ -3112,7 +3228,7 @@ dependencies = [
requires-dist = [
{ name = "alembic", specifier = ">=1.13.0" },
{ name = "asyncpg", specifier = ">=0.30.0" },
{ name = "chonkie", extras = ["all"], specifier = ">=0.4.1" },
{ name = "chonkie", extras = ["all"], specifier = ">=1.0.6" },
{ name = "fastapi", specifier = ">=0.115.8" },
{ name = "fastapi-users", extras = ["oauth", "sqlalchemy"], specifier = ">=14.0.1" },
{ name = "firecrawl-py", specifier = ">=1.12.0" },
@ -3339,6 +3455,91 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/b6/1a/efeecb8d83705f2f4beac98d46f2148c95ecd7babfb31b5c0f1e7017e83d/transformers-4.48.3-py3-none-any.whl", hash = "sha256:78697f990f5ef350c23b46bf86d5081ce96b49479ab180b2de7687267de8fd36", size = 9669412 },
]
[[package]]
name = "tree-sitter"
version = "0.24.0"
source = { registry = "https://pypi.org/simple" }
sdist = { url = "https://files.pythonhosted.org/packages/a7/a2/698b9d31d08ad5558f8bfbfe3a0781bd4b1f284e89bde3ad18e05101a892/tree-sitter-0.24.0.tar.gz", hash = "sha256:abd95af65ca2f4f7eca356343391ed669e764f37748b5352946f00f7fc78e734", size = 168304 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/e9/57/3a590f287b5aa60c07d5545953912be3d252481bf5e178f750db75572bff/tree_sitter-0.24.0-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:14beeff5f11e223c37be7d5d119819880601a80d0399abe8c738ae2288804afc", size = 140788 },
{ url = "https://files.pythonhosted.org/packages/61/0b/fc289e0cba7dbe77c6655a4dd949cd23c663fd62a8b4d8f02f97e28d7fe5/tree_sitter-0.24.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:26a5b130f70d5925d67b47db314da209063664585a2fd36fa69e0717738efaf4", size = 133945 },
{ url = "https://files.pythonhosted.org/packages/86/d7/80767238308a137e0b5b5c947aa243e3c1e3e430e6d0d5ae94b9a9ffd1a2/tree_sitter-0.24.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5fc5c3c26d83c9d0ecb4fc4304fba35f034b7761d35286b936c1db1217558b4e", size = 564819 },
{ url = "https://files.pythonhosted.org/packages/bf/b3/6c5574f4b937b836601f5fb556b24804b0a6341f2eb42f40c0e6464339f4/tree_sitter-0.24.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:772e1bd8c0931c866b848d0369b32218ac97c24b04790ec4b0e409901945dd8e", size = 579303 },
{ url = "https://files.pythonhosted.org/packages/0a/f4/bd0ddf9abe242ea67cca18a64810f8af230fc1ea74b28bb702e838ccd874/tree_sitter-0.24.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:24a8dd03b0d6b8812425f3b84d2f4763322684e38baf74e5bb766128b5633dc7", size = 581054 },
{ url = "https://files.pythonhosted.org/packages/8c/1c/ff23fa4931b6ef1bbeac461b904ca7e49eaec7e7e5398584e3eef836ec96/tree_sitter-0.24.0-cp312-cp312-win_amd64.whl", hash = "sha256:f9e8b1605ab60ed43803100f067eed71b0b0e6c1fb9860a262727dbfbbb74751", size = 120221 },
{ url = "https://files.pythonhosted.org/packages/b2/2a/9979c626f303177b7612a802237d0533155bf1e425ff6f73cc40f25453e2/tree_sitter-0.24.0-cp312-cp312-win_arm64.whl", hash = "sha256:f733a83d8355fc95561582b66bbea92ffd365c5d7a665bc9ebd25e049c2b2abb", size = 108234 },
{ url = "https://files.pythonhosted.org/packages/61/cd/2348339c85803330ce38cee1c6cbbfa78a656b34ff58606ebaf5c9e83bd0/tree_sitter-0.24.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:0d4a6416ed421c4210f0ca405a4834d5ccfbb8ad6692d4d74f7773ef68f92071", size = 140781 },
{ url = "https://files.pythonhosted.org/packages/8b/a3/1ea9d8b64e8dcfcc0051028a9c84a630301290995cd6e947bf88267ef7b1/tree_sitter-0.24.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:e0992d483677e71d5c5d37f30dfb2e3afec2f932a9c53eec4fca13869b788c6c", size = 133928 },
{ url = "https://files.pythonhosted.org/packages/fe/ae/55c1055609c9428a4aedf4b164400ab9adb0b1bf1538b51f4b3748a6c983/tree_sitter-0.24.0-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:57277a12fbcefb1c8b206186068d456c600dbfbc3fd6c76968ee22614c5cd5ad", size = 564497 },
{ url = "https://files.pythonhosted.org/packages/ce/d0/f2ffcd04882c5aa28d205a787353130cbf84b2b8a977fd211bdc3b399ae3/tree_sitter-0.24.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d25fa22766d63f73716c6fec1a31ee5cf904aa429484256bd5fdf5259051ed74", size = 578917 },
{ url = "https://files.pythonhosted.org/packages/af/82/aebe78ea23a2b3a79324993d4915f3093ad1af43d7c2208ee90be9273273/tree_sitter-0.24.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:7d5d9537507e1c8c5fa9935b34f320bfec4114d675e028f3ad94f11cf9db37b9", size = 581148 },
{ url = "https://files.pythonhosted.org/packages/a1/b4/6b0291a590c2b0417cfdb64ccb8ea242f270a46ed429c641fbc2bfab77e0/tree_sitter-0.24.0-cp313-cp313-win_amd64.whl", hash = "sha256:f58bb4956917715ec4d5a28681829a8dad5c342cafd4aea269f9132a83ca9b34", size = 120207 },
{ url = "https://files.pythonhosted.org/packages/a8/18/542fd844b75272630229c9939b03f7db232c71a9d82aadc59c596319ea6a/tree_sitter-0.24.0-cp313-cp313-win_arm64.whl", hash = "sha256:23641bd25dcd4bb0b6fa91b8fb3f46cc9f1c9f475efe4d536d3f1f688d1b84c8", size = 108232 },
]
[[package]]
name = "tree-sitter-c-sharp"
version = "0.23.1"
source = { registry = "https://pypi.org/simple" }
sdist = { url = "https://files.pythonhosted.org/packages/22/85/a61c782afbb706a47d990eaee6977e7c2bd013771c5bf5c81c617684f286/tree_sitter_c_sharp-0.23.1.tar.gz", hash = "sha256:322e2cfd3a547a840375276b2aea3335fa6458aeac082f6c60fec3f745c967eb", size = 1317728 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/58/04/f6c2df4c53a588ccd88d50851155945cff8cd887bd70c175e00aaade7edf/tree_sitter_c_sharp-0.23.1-cp39-abi3-macosx_10_9_x86_64.whl", hash = "sha256:2b612a6e5bd17bb7fa2aab4bb6fc1fba45c94f09cb034ab332e45603b86e32fd", size = 372235 },
{ url = "https://files.pythonhosted.org/packages/99/10/1aa9486f1e28fc22810fa92cbdc54e1051e7f5536a5e5b5e9695f609b31e/tree_sitter_c_sharp-0.23.1-cp39-abi3-macosx_11_0_arm64.whl", hash = "sha256:1a8b98f62bc53efcd4d971151950c9b9cd5cbe3bacdb0cd69fdccac63350d83e", size = 419046 },
{ url = "https://files.pythonhosted.org/packages/0f/21/13df29f8fcb9ba9f209b7b413a4764b673dfd58989a0dd67e9c7e19e9c2e/tree_sitter_c_sharp-0.23.1-cp39-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:986e93d845a438ec3c4416401aa98e6a6f6631d644bbbc2e43fcb915c51d255d", size = 415999 },
{ url = "https://files.pythonhosted.org/packages/ca/72/fc6846795bcdae2f8aa94cc8b1d1af33d634e08be63e294ff0d6794b1efc/tree_sitter_c_sharp-0.23.1-cp39-abi3-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a8024e466b2f5611c6dc90321f232d8584893c7fb88b75e4a831992f877616d2", size = 402830 },
{ url = "https://files.pythonhosted.org/packages/fe/3a/b6028c5890ce6653807d5fa88c72232c027c6ceb480dbeb3b186d60e5971/tree_sitter_c_sharp-0.23.1-cp39-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:7f9bf876866835492281d336b9e1f9626ab668737f74e914c31d285261507da7", size = 397880 },
{ url = "https://files.pythonhosted.org/packages/47/d2/4facaa34b40f8104d8751746d0e1cd2ddf0beb9f1404b736b97f372bd1f3/tree_sitter_c_sharp-0.23.1-cp39-abi3-win_amd64.whl", hash = "sha256:ae9a9e859e8f44e2b07578d44f9a220d3fa25b688966708af6aa55d42abeebb3", size = 377562 },
{ url = "https://files.pythonhosted.org/packages/d8/88/3cf6bd9959d94d1fec1e6a9c530c5f08ff4115a474f62aedb5fedb0f7241/tree_sitter_c_sharp-0.23.1-cp39-abi3-win_arm64.whl", hash = "sha256:c81548347a93347be4f48cb63ec7d60ef4b0efa91313330e69641e49aa5a08c5", size = 375157 },
]
[[package]]
name = "tree-sitter-embedded-template"
version = "0.23.2"
source = { registry = "https://pypi.org/simple" }
sdist = { url = "https://files.pythonhosted.org/packages/28/d6/5a58ea2f0480f5ed188b733114a8c275532a2fd1568b3898793b13d28af5/tree_sitter_embedded_template-0.23.2.tar.gz", hash = "sha256:7b24dcf2e92497f54323e617564d36866230a8bfb719dbb7b45b461510dcddaa", size = 8471 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/ef/c1/be0c48ed9609b720e74ade86f24ea086e353fe9c7405ee9630c3d52d09a2/tree_sitter_embedded_template-0.23.2-cp39-abi3-macosx_10_9_x86_64.whl", hash = "sha256:a505c2d2494464029d79db541cab52f6da5fb326bf3d355e69bf98b84eb89ae0", size = 9554 },
{ url = "https://files.pythonhosted.org/packages/6d/a5/7c12f5d302525ee36d1eafc28a68e4454da5bad208436d547326bee4ed76/tree_sitter_embedded_template-0.23.2-cp39-abi3-macosx_11_0_arm64.whl", hash = "sha256:28028b93b42cc3753261ae7ce066675d407f59de512417524f9c3ab7792b1d37", size = 10051 },
{ url = "https://files.pythonhosted.org/packages/cd/87/95aaba8b64b849200bd7d4ae510cc394ecaef46a031499cbff301766970d/tree_sitter_embedded_template-0.23.2-cp39-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ec399d59ce93ffb60759a2d96053eed529f3c3f6a27128f261710d0d0de60e10", size = 17532 },
{ url = "https://files.pythonhosted.org/packages/13/f8/8c837b898f00b35f9f3f76a4abc525e80866a69343083c9ff329e17ecb03/tree_sitter_embedded_template-0.23.2-cp39-abi3-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bcfa01f62b88d50dbcb736cc23baec8ddbfe08daacfdc613eee8c04ab65efd09", size = 17394 },
{ url = "https://files.pythonhosted.org/packages/89/9b/893adf9e465d2d7f14870871bf2f3b30045e5ac417cb596f667a72eda493/tree_sitter_embedded_template-0.23.2-cp39-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:6debd24791466f887109a433c31aa4a5deeba2b217817521c745a4e748a944ed", size = 16439 },
{ url = "https://files.pythonhosted.org/packages/40/96/e79934572723673db9f867000500c6eea61a37705e02c7aee9ee031bbb6f/tree_sitter_embedded_template-0.23.2-cp39-abi3-win_amd64.whl", hash = "sha256:158fecb38be5b15db0190ef7238e5248f24bf32ae3cab93bc1197e293a5641eb", size = 12572 },
{ url = "https://files.pythonhosted.org/packages/63/06/27f678b9874e4e2e39ddc6f5cce3374c8c60e6046ea8588a491ab6fc9fcb/tree_sitter_embedded_template-0.23.2-cp39-abi3-win_arm64.whl", hash = "sha256:9f1f3b79fe273f3d15a5b64c85fc6ebfb48decfbe8542accd05f5b7694860df0", size = 11232 },
]
[[package]]
name = "tree-sitter-language-pack"
version = "0.7.2"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "tree-sitter" },
{ name = "tree-sitter-c-sharp" },
{ name = "tree-sitter-embedded-template" },
{ name = "tree-sitter-yaml" },
]
sdist = { url = "https://files.pythonhosted.org/packages/9b/1e/2d63d93025fd5b527327c3fd348955cebaec02a3f1bcec88ab4d88ddfc39/tree_sitter_language_pack-0.7.2.tar.gz", hash = "sha256:46fc96cc3bddfee7091fdedec2ae7e34218679e58241e8319bf82026f6d02eae", size = 59264078 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/da/9d/2c6272bf4fd18a22d8c07d3c983940dbece4f0e9e21f5c78f15a2740f435/tree_sitter_language_pack-0.7.2-cp39-abi3-macosx_10_13_universal2.whl", hash = "sha256:4036603020bd32060d9931a64f8c3d8637de575f350f11534971012e51a27a95", size = 28132977 },
{ url = "https://files.pythonhosted.org/packages/2b/e2/0f2511019c27b870061f9ad719074095ef84cd7857a730765bfa066384be/tree_sitter_language_pack-0.7.2-cp39-abi3-manylinux2014_aarch64.whl", hash = "sha256:801926dbc81eeca4ce97b846cc899dcf3fecfdc3b2514a68eeeb118f70ac686d", size = 17576769 },
{ url = "https://files.pythonhosted.org/packages/3a/88/7b38233def5c359503ad4d36533f96f9fe2943a8eeeced66b36312c49e1b/tree_sitter_language_pack-0.7.2-cp39-abi3-manylinux2014_x86_64.whl", hash = "sha256:77be80335fb585f48eb268b0e07ca54f3da8f30c2eab7be749113f116c3ef316", size = 17433872 },
{ url = "https://files.pythonhosted.org/packages/f8/27/fc5dce240b68a1ed876bc80b2238fbaaa0f695dbaf88660728a0239a2b20/tree_sitter_language_pack-0.7.2-cp39-abi3-win_amd64.whl", hash = "sha256:d71c6b4c14b3370ca783319ede7a581a10e6dd1bdfe5d31d316d9216981a6406", size = 14316050 },
]
[[package]]
name = "tree-sitter-yaml"
version = "0.7.0"
source = { registry = "https://pypi.org/simple" }
sdist = { url = "https://files.pythonhosted.org/packages/93/04/6de8be8112c50450cab753fcd6b74d8368c60f6099bf551cee0bec69563a/tree_sitter_yaml-0.7.0.tar.gz", hash = "sha256:9c8bb17d9755c3b0e757260917240c0d19883cd3b59a5d74f205baa8bf8435a4", size = 85085 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/69/1d/243dbdf59fae8a4109e19f0994e2627ddedb2e16b7cf99bd42be64367742/tree_sitter_yaml-0.7.0-cp39-abi3-macosx_10_9_x86_64.whl", hash = "sha256:e21553ac190ae05bf82796df8beb4d9158ba195b5846018cb36fbc3a35bd0679", size = 43335 },
{ url = "https://files.pythonhosted.org/packages/e2/63/e5d5868a1498e20fd07e7db62933766fd64950279862e3e7f150b88ec69d/tree_sitter_yaml-0.7.0-cp39-abi3-macosx_11_0_arm64.whl", hash = "sha256:c022054f1f9b54201082ea83073a6c24c42d0436ad8ee99ff2574cba8f928c28", size = 44574 },
{ url = "https://files.pythonhosted.org/packages/f5/ba/9cff9a3fddb1b6b38bc71ce1dfdb8892ab15a4042c104f4582e30318b412/tree_sitter_yaml-0.7.0-cp39-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1cd1725142f19e41c51d27c99cfc60780f596e069eb181cfa6433d993a19aa3d", size = 93088 },
{ url = "https://files.pythonhosted.org/packages/19/09/39d29d9a22cee0b3c3e4f3fdbd23e4534b9c2a84b5f962f369eafcfbf88c/tree_sitter_yaml-0.7.0-cp39-abi3-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9d1b268378254f75bb27396d83c96d886ccbfcda6bd8c2778e94e3e1d2459085", size = 91367 },
{ url = "https://files.pythonhosted.org/packages/b0/b7/285653b894b351436917b5fe5e738eecaeb2128b4e4bf72bfe0c6043f62e/tree_sitter_yaml-0.7.0-cp39-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:27c2e7f4f49ddf410003abbb82a7b00ec77ea263d8ef08dbce1a15d293eed2fd", size = 87405 },
{ url = "https://files.pythonhosted.org/packages/bb/73/0cdc82ea653c190475a4f63dd4a1f4efd5d1c7d09d2668b8d84008a4c4f8/tree_sitter_yaml-0.7.0-cp39-abi3-win_amd64.whl", hash = "sha256:98dce0d6bc376f842cfb1d3c32512eea95b37e61cd2c87074bb4b05c999917c8", size = 45360 },
{ url = "https://files.pythonhosted.org/packages/2e/32/af2d676b0176a958f22a75b04be836e09476a10844baab78c018a5030297/tree_sitter_yaml-0.7.0-cp39-abi3-win_arm64.whl", hash = "sha256:f0f8d8e05fa8e70f08d0f18a209d6026e171844f4ea7090e7c779b9c375b3a31", size = 43650 },
]
[[package]]
name = "triton"
version = "3.2.0"
@ -3348,6 +3549,18 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/c7/30/37a3384d1e2e9320331baca41e835e90a3767303642c7a80d4510152cbcf/triton-3.2.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e5dfa23ba84541d7c0a531dfce76d8bcd19159d50a4a8b14ad01e91734a5c1b0", size = 253154278 },
]
[[package]]
name = "types-requests"
version = "2.32.0.20250328"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "urllib3" },
]
sdist = { url = "https://files.pythonhosted.org/packages/00/7d/eb174f74e3f5634eaacb38031bbe467dfe2e545bc255e5c90096ec46bc46/types_requests-2.32.0.20250328.tar.gz", hash = "sha256:c9e67228ea103bd811c96984fac36ed2ae8da87a36a633964a21f199d60baf32", size = 22995 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/cc/15/3700282a9d4ea3b37044264d3e4d1b1f0095a4ebf860a99914fd544e3be3/types_requests-2.32.0.20250328-py3-none-any.whl", hash = "sha256:72ff80f84b15eb3aa7a8e2625fffb6a93f2ad5a0c20215fc1dcfa61117bcb2a2", size = 20663 },
]
[[package]]
name = "typing-extensions"
version = "4.12.2"
@ -3381,7 +3594,7 @@ wheels = [
[[package]]
name = "unstructured"
version = "0.16.25"
version = "0.17.2"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "backoff" },
@ -3406,9 +3619,9 @@ dependencies = [
{ name = "unstructured-client" },
{ name = "wrapt" },
]
sdist = { url = "https://files.pythonhosted.org/packages/64/31/98c4c78e305d1294888adf87fd5ee30577a4c393951341ca32b43f167f1e/unstructured-0.16.25.tar.gz", hash = "sha256:73b9b0f51dbb687af572ecdb849a6811710b9cac797ddeab8ee80fa07d8aa5e6", size = 1683097 }
sdist = { url = "https://files.pythonhosted.org/packages/b4/49/b95ff4b609d7328cd0394ac9d8ad69839e11a1f879462496afcf4887154a/unstructured-0.17.2.tar.gz", hash = "sha256:af18c3caef0a6c562cf77e34ee8b6ff522b605031d2336ffe565df66f126aa46", size = 1684745 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/12/4f/ad08585b5c8a33c82ea119494c4d3023f4796958c56e668b15cc282ec0a0/unstructured-0.16.25-py3-none-any.whl", hash = "sha256:14719ccef2830216cf1c5bf654f75e2bf07b17ca5dcee9da5ac74618130fd337", size = 1769286 },
{ url = "https://files.pythonhosted.org/packages/cb/88/061a9dedd4e8cc0c31097c3275a9ef1fd7307e26afac5cd582487386e1b8/unstructured-0.17.2-py3-none-any.whl", hash = "sha256:527dd26a4b273aebef2f9119c9d4f0d0ce17640038d92296d23abe89be123840", size = 1771563 },
]
[package.optional-dependencies]
@ -3418,6 +3631,7 @@ all-docs = [
{ name = "markdown" },
{ name = "networkx" },
{ name = "onnx" },
{ name = "onnxruntime" },
{ name = "openpyxl" },
{ name = "pandas" },
{ name = "pdf2image" },