bhavnicksm chonkie issues

bhavnicksm / chonkie

🦛 CHONK your texts with Chonkie ✨ - The no-nonsense RAG chunking library

https://pypi.org/project/chonkie/

MIT License

1.54k stars 57 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

[BUG] SDPM & Semantic Chunking Example not working

#59 regstuff closed 1 hour ago
2
[Fix] Add fix for #55

#58 bhavnicksm closed 20 hours ago
0
[Fix] AutoEmbeddings not loading `all-minilm-l6-v2` but loads `All-MiniLM-L6-V2`

#57 bhavnicksm closed 21 hours ago
0
Update DOCS.md - fixed embeddings path after recent change

#56 pratyushmittal closed 21 hours ago
3
[BUG] Newlines are not removed after pre-processing in SemanticChunker

#55 Pringled closed 6 hours ago
3
[Refactor] Optimize similarity calculation by using np.divide for imp…

#54 bhavnicksm closed 2 days ago
0
[Fix] Refactor WordChunker, SentenceChunker pre-chunk splitting for reconstruction tests + minor changes

#53 bhavnicksm closed 2 days ago
0
[Fix] Token counts from Tokenizers and Transformers adding special tokens

#52 bhavnicksm closed 2 days ago
0
[fix] Reorganize optional dependencies in pyproject.toml: rename 'sem…

#51 bhavnicksm closed 2 days ago
0
[DISC] Benchmarking Chonkie Mega-Thread

#50 bhavnicksm opened 2 days ago
0
[FEAT] Add support for Model2VecEmbeddings + Switch default embeddings to Model2VecEmbeddings

#49 bhavnicksm closed 2 days ago
0
Reconstruction Test

#48 mrmps closed 2 days ago
3
[DOCS] Add info about initial embeddings support and how to add custom embeddings

#47 bhavnicksm closed 3 days ago
0
Add initial OpenAIEmbeddings support to Chonkie ✨

#46 bhavnicksm closed 3 days ago
0
Refactor BaseChunker, SemanticChunker and SDPMChunker to support BaseEmbeddings

#45 bhavnicksm closed 4 days ago
0
[FEAT] Add SentenceTransformerEmbeddings, EmbeddingsRegistry and AutoEmbeddings provider support

#44 bhavnicksm closed 4 days ago
0
[DISC] Improving Documentation

#43 bhavnicksm opened 4 days ago
3
[BUG] Chunkers failing the test of recronstruction

#42 mrmps closed 2 days ago
6
[FEAT] - Add model2vec embedding models

#41 sky-2002 closed 2 days ago
15
[FEAT] Min chunk size (for semantic chunkers)

#40 kbarendrecht opened 5 days ago
1
[FEAT] Add async support to SDPMChunker and to SemanticChunker

#39 rodion-m opened 5 days ago
7
[FEAT] Add an ability to use OpenAI / VoyageAI / Cohere embeddings with SDPMChunker via LiteLLM

#38 rodion-m opened 5 days ago
5
[BUG] start_index and end_index inaccurate for repetitive text chunks

#37 bhavnicksm opened 5 days ago
0
[FEAT] Allow configuring backend for Sentence_Transformers (e.g. ONNX, openVINO)

#36 kbarendrecht closed 5 days ago
3
Bump version to 0.2.0.post1 in pyproject.toml and __init__.py

#35 bhavnicksm closed 5 days ago
0
Use `__slots__` instead of `slots=True` for python3.9 support

#34 bhavnicksm closed 5 days ago
0
[BUG] TypeError: dataclass() got an unexpected keyword argument 'slots'

#33 AgentT30 closed 5 days ago
2
Major Update: Fix bugs + Update docs + Add slots to dataclasses + update word & sentence splitting logic + minor changes

#32 bhavnicksm closed 6 days ago
0
[BUG]pyo3_runtime.PanicException: no entry found for key

#31 wbbeyourself closed 5 days ago
4
[DOCS] Fix typo for import tokenizer in quick start example

#30 jasonacox closed 6 days ago
1
[BUG] Fix the start_index and end_index to point to character indices, not token indices

#29 mrmps closed 1 week ago
2
Add initial batching support via `chunk_batch` fn + update DOCS

#28 bhavnicksm closed 1 week ago
0
Update dependency version of SentenceTransformer to at least 2.3.0

#27 bhavnicksm closed 1 week ago
0
[BUG]AttributeError: 'SentenceTransformer' object has no attribute 'similarity'

#26 heweapon closed 1 week ago
6
ImportError: cannot import name 'tokenizer' from 'tokenizers' (/usr/local/lib/python3.10/site-packages/tokenizers/__init__.py)

#25 abchbx closed 1 week ago
1
fix: tokenizer mismatch for `SemanticChunker` + Add BaseEmbeddings

#24 bhavnicksm closed 1 week ago
0
Can I load offline tokenizers in it?

#23 a136214808 opened 1 week ago
2
Update README.md + minor updates

#22 bhavnicksm closed 1 week ago
0
Remove Spacy dependency from 'sentence' install + Add FAQ to DOCS.md

#21 bhavnicksm closed 1 week ago
0
Remove Spacy dependency from Chonkie

#20 bhavnicksm closed 1 week ago
0
Add FastEmbed Support for Embedding Generation/Inference

#19 adithya-s-k closed 1 day ago
5
`TokenChunker` does not support multiple inputs

#18 not-lain closed 1 week ago
5
Update README.md + fix DOCS.md typo

#17 bhavnicksm closed 1 week ago
0
Incorrect import in Docs, SDPMChunker reference

#16 Om-Alve closed 1 week ago
1
Update acknowledgements in README.md for improved clarity and appreci…

#15 bhavnicksm closed 2 weeks ago
0
Development

#14 bhavnicksm closed 2 weeks ago
0
Run Black + Isort + beautify the code a bit

#13 bhavnicksm closed 2 weeks ago
0
Make imports as a part of Chunker __init__ instead of file imports to make Chonkie import faster

#12 bhavnicksm closed 2 weeks ago
0
Bump version to 0.1.1 in pyproject.toml and __init__.py

#11 bhavnicksm closed 2 weeks ago
0
Update README.md

#10 bhavnicksm closed 2 weeks ago
0