name: chonkie
version: 1.7.0
summary: 🦛 CHONK your texts with Chonkie ✨ - The no-nonsense chunking library
license: MIT License
requires_python: >=3.10
python_min: 3.10
install_size: 228.3 KB
module_format: py3-none-any
doc_url: https://docs.chonkie.ai
repo_url: https://github.com/chonkie-inc/chonkie
last_released_at: 2026-07-07T10:06:00Z
releases_last_12mo: 24
avg_days_between_releases: 10.0
platforms: any

## dependencies
tqdm >=4.64.0
numpy >=2.0.0
chonkie-core >=0.10.2
tenacity >=8.0.0
httpx >=0.28.1
tokie >=0.0.10

## extras
[all]
  chonkie[hub]
  chonkie[viz]
  chonkie[cli]
  chonkie[api]
  chonkie[tokenizers]
  chonkie[tiktoken]
  chonkie[chunkers]
  chonkie[embeddings]
  chonkie[handshakes]
  chonkie[genies]
  chonkie[chefs]
[api]
  fastapi >=0.115.0
  uvicorn[standard] >=0.30.0
  sqlalchemy >=2.0.0
  alembic >=1.13.0
  aiosqlite >=0.20.0
  huggingface-hub >=1.5.0
  jsonschema >=4.23.0
[azure-openai]
  azure-identity >=1.23.0
  tiktoken >=0.5.0
  openai >=1.0.0
  pydantic >=2.0.0
[catsu]
  catsu >=0.0.1
[cerebras]
  pydantic >=2.0.0
  cerebras-cloud-sdk >=1.0.0
[chefs]
  chonkie[table]
  chonkie[mistral]
  chonkie[liteparse]
[chroma]
  chromadb >=1.0.0
[chunkers]
  chonkie[code]
  chonkie[neural]
  chonkie[semantic]
  chonkie[teraflopai]
[cli]
  typer >=0.9.0
[code]
  tree-sitter-language-pack >=1.8.0
[cohere]
  tokenizers >=0.16.0
  cohere >=5.13.0
[datasets]
  datasets >=4.0.0
[dev]
  chonkie[all]
  datasets >=1.14.0
  transformers >=4.0.0
  pytest >=6.2.0
  pytest-cov >=4.0.0
  pytest-xdist >=2.5.0
  pytest-asyncio >=0.26.0
  coverage
  ruff >=0.13.3
  ty
  pandas
  tabulate
  openpyxl
  uv >=0.9.18
  requests-cache >=1.2.1
[elastic]
  elasticsearch >=8.0.0
[embeddings]
  chonkie[model2vec]
  chonkie[st]
  chonkie[openai]
  chonkie[gemini]
  chonkie[azure-openai]
  chonkie[voyageai]
  chonkie[cohere]
  chonkie[jina]
  chonkie[catsu]
  chonkie[litellm]
[gemini]
  pydantic >=2.0.0
  google-genai >=1.0.0
[genie]
  pydantic >=2.0.0
  google-genai >=1.0.0
[genies]
  chonkie[genie]
  chonkie[openai]
  chonkie[azure-openai]
  chonkie[groq]
  chonkie[cerebras]
[groq]
  pydantic >=2.0.0
  groq >=0.4.0
[handshakes]
  chonkie[chroma]
  chonkie[qdrant]
  chonkie[tpuf]
  chonkie[pgvector]
  chonkie[weaviate]
  chonkie[datasets]
  chonkie[pinecone]
  chonkie[mongodb]
  chonkie[elastic]
  chonkie[milvus]
  chonkie[lancedb]
[hub]
  huggingface-hub >=0.24.0
  jsonschema >=4.23.0
[jina]
  tokenizers >=0.16.0
[lancedb]
  lancedb >=0.4.0
[litellm]
  litellm >=1.0.0
  tiktoken >=0.5.0
  tokenizers >=0.16.0
[liteparse]
  liteparse >=0.2.0
[milvus]
  pymilvus >=2.1.0
[mistral]
  mistralai >=2.4.0
[model2vec]
  tokenizers >=0.16.0
  model2vec >=0.7.0
  numpy <3.0,>=2.0.0
[mongodb]
  pymongo
[neural]
  transformers >=4.0.0
  torch <3.0,>=2.0.0
[openai]
  tiktoken >=0.5.0
  openai >=1.0.0
  pydantic >=2.0.0
[pgvector]
  vecs >=0.4.0
[pinecone]
  pinecone
[qdrant]
  qdrant-client >=1.0.0
[semantic]
  tokenizers >=0.16.0
  model2vec >=0.3.0
[st]
  tokenizers >=0.16.0
  sentence-transformers >=3.0.0
  accelerate >=1.6.0
[table]
  pandas
  tabulate
  openpyxl
  lxml
[teraflopai]
  teraflopai >=0.1.0
[tiktoken]
  tiktoken >=0.5.0
[tokenizers]
  tokenizers >=0.16.0
[tpuf]
  turbopuffer <3,>=1
[viz]
  rich >=13.0.0
[voyageai]
  tokenizers >=0.16.0
  voyageai >=0.3.2
[weaviate]
  weaviate-client >=4.16.7

## maintainers
Bhavnick Minhas <bhavnick@chonkie.ai>
Shreyash Nigam <shreyash@chonkie.ai>