Top AI Repos β open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
π¦ CHONK docs with Chonkie β¨ β The lightweight ingestion library for fast, efficient and robust RAG pipelines
| Date | Stars |
|---|---|
| 2026-07-24 | 4564 |
| 2026-07-25 | 4568 |
| 2026-07-28 | 4568 |
| 2026-07-30 | 4568 |
| 2026-07-31 | 4614 |
| 2026-08-08 | 4653 |
| 2026-08-16 | 4680 |
| 2026-08-18 | 4686 |
| 2026-08-19 | 4689 |
| 2026-08-20 | 4692 |
| 2026-08-21 | 4693 |
| 2026-08-22 | 4696 |
| 2026-08-23 | 4699 |
| 2026-08-24 | 4701 |
| 2026-08-25 | 4702 |
| 2026-08-26 | 4704 |
| 2026-08-27 | 4704 |
| 2026-08-28 | 4708 |
| 2026-08-29 | 4709 |
| 2026-08-30 | 4711 |
| 2026-08-31 | 4713 |
| 2026-09-01 | 4718 |
| 2026-09-02 | 4719 |
| 2026-09-03 | 4720 |
| 2026-09-04 | 4720 |
| 2026-09-06 | 4723 |
| 2026-09-07 | 4722 |
| 2026-09-08 | 4724 |
| 2026-09-09 | 4728 |
| 2026-09-10 | 4732 |
| 2026-09-11 | 4740 |
| 2026-09-12 | 4740 |
| 2026-09-13 | 4743 |
| 2026-09-14 | 4745 |
| 2026-09-15 | 4749 |
| 2026-09-16 | 4751 |
| 2026-09-17 | 4753 |
| 2026-09-18 | 4754 |
| 2026-09-19 | 4758 |
| 2026-09-20 | 4760 |
Today
+2 stars today
This week
+17 stars this week
This month
+67 stars this month
Momentum
40.0
growth rate 0.36%/day
<div align='center'>

# π¦ Chonkie β¨
[](https://pypi.org/project/chonkie/)
[](https://github.com/chonkie-inc/chonkie/blob/main/LICENSE)
[](https://docs.chonkie.ai)
[](https://github.com/chonkie-inc/chonkie/blob/main/README.md#installation)
[](https://codecov.io/gh/chonkie-inc/chonkie)
[](https://pepy.tech/project/chonkie)
[](https://discord.gg/vH3SkRqmUz)
[](https://github.com/chonkie-inc/chonkie/stargazers)
_The lightweight ingestion library for fast, efficient and robust RAG pipelines_
[Installation](#π¦-installation) β’
[Usage](#π-usage) β’
[Chunkers](#βοΈ-chunkers) β’
[Integrations](#π-integrations) β’
[Benchmarks](#π-benchmarks)
</div>
Tired of making your gazillionth chunker? Sick of the overhead of large libraries? Want to chunk your texts quickly and efficiently? Chonkie the mighty hippo is here to help!
**π Feature-rich**: All the CHONKs you'd ever need </br>
**π End-to-end**: Fetch, CHONK, refine, embed and ship straight to your vector DB! </br>
**β¨ Easy to use**: Install, Import, CHONK </br>
**β‘ Fast**: CHONK at the speed of light! zooooom </br>
**πͺΆ Light-weight**: No bloat, just CHONK </br>
**π 32+ [integrations](#integrations)**: Works with your favorite tools and vector DBs out of the box! </br>
**π¬ οΈMultilingual**: Out-of-the-box support for 56 languages </br>
**βοΈ Cloud-Friendly**: CHONK locally or in the [Cloud](https://labs.chonkie.ai) </br>
**π¦ Cute CHONK mascot**: psst it's a pygmy hippo btw </br>
**β€οΈ [Moto Moto](#acknowledgements)'s favorite python library** </br>
**Chonkie** is a chunking library that "**just works**" β¨
## π¦ Installation
### Basic Installation
Using pip:
```bash
pip install chonkie
```
Or using [uv](https://docs.astral.sh/uv/) (faster):
```bash
uv pip install chonkie
```
### Full Installation
Chonkie follows the rule of minimum installs.
Have a favorite chunker? Read our [docs](https://docs.chonkie.ai) to install only what you need.
Don't want to think about it? Simply install `all` (Not recommended for production environments).
Using pip:
```bash
pip install "chonkie[all]"
```
Or using [uv](https://docs.astral.sh/uv/):
```bash
uv pip install "chonkie[all]"
```
## π Usage
### Basic Usage
Here's a basic example to get you started:
```python
# First import the chunker you want from Chonkie
from chonkie import RecursiveChunker
# Initialize the chunker
chunker = RecursiveChunker()
# Chunk some text
chunks = chunker("Chonkie is the goodest boi! My favorite chunking hippo hehe.")
# Access chunks
for chunk in chunks:
print(f"Chunk: {chunk.text}")
print(f"Tokens: {chunk.token_count}")
```
### Pipeline Usage
You can also use the `chonkie.Pipeline` to chain components together and handle complex workflows. Read more about pipelines in the [docs](https://docs.chonkie.ai/oss/pipelines)!
```python
from chonkie import Pipeline
# Create a pipeline with multiple chunking and refinement steps
pipe = (
Pipeline()
.chunk_with("recursive", tokenizer="gpt2", chunk_size=2048, recipe="markdown")
.chunk_with("semantic", chunk_size=512)
.refine_with("overlap", context_size=128)
.refine_with("embeddings", embedding_model="sentence-transformers/all-MiniLM-L6-v2")
)
# CHONK some Texts!
doc = pipe.run(texts="Chonkie is the goodest boi! My favorite chunking hippo hehe.")
# Access Excerpt of 20,790 characters
Read on GitHubBhavnick @ chonkie.ai Β· @chonkie-inc
1.1k
658
128
53
Aarni Koskela Β· @valohai Β· Finland
50
29
Alan Ponnachan
28
23
Bhavnick Minhas
20
17
Anas Limem Β· Tunisia
16
Aryan Β· Microsoft Β· Belgium
15
8
Joshua
8
8
6
6
hannibal-lee Β· Hong Kong
5
samyak
5
Justin
4
Would you bet a product on this? Bounded 0β100 and slow moving.
matched fp:c1ae7bea108e3630, topic:similarity-search
matched fp:c1ae7bea108e3630, topic:rag