---
title: "CocoIndex Changelog 2025-07-07"
description: "CocoIndex updates: in-process setup/drop API, EmbedText building block, SplitRecursively improvements, union/NumPy types, and the Kuzu graph target."
last_updated: 2025-07-07
doc_version: "2025-07-07"
canonical: https://cocoindex.io/blogs/cocoindex-changelog-2025-07-07/
---
# CocoIndex Changelog 2025-07-07

> CocoIndex updates: in-process setup/drop API, EmbedText building block, SplitRecursively improvements, union/NumPy types, and the Kuzu graph target.

Published: 2025-07-07 · Canonical: https://cocoindex.io/blogs/cocoindex-changelog-2025-07-07/

In the past weeks, we've added support for an in-process API and convenient CLI options for setup / drop, 
native support for EmbedText as a building block, major improvement to support codebase indexing and many core improvements over 10+ releases.

We are also very excited about the great suggestions from our users and community, and many of our changes come directly from user feedback. 
Thank you ❤️!

Full changelog: [v0.1.45...v0.1.57](https://github.com/cocoindex-io/cocoindex/compare/v0.1.45...v0.1.57).

## We officially crossed 2k stars on GitHub! 🎉

CocoIndex crossed 2k stars last week with one day on GitHub Trending in Rust.
Thank you to everyone who contributed, starred the repo and shared the love! 
Let’s make the best ETL framework for AI 🚀 !

## CocoInsight

We announced a major milestone on the CocoIndex companion - CocoInsight.  
It has zero pipeline data retention and connects to your on-premise CocoIndex server for pipeline insights. 
This makes data directly visible and makes it easy to develop ETL pipelines.

## Flexible API for flow backend setup / drop
CocoIndex [automatically handles](https://cocoindex.io/blogs/schema-inference-for-qdrant) the flow setup - keeping everything in sync for the target stores (e.g., Qdrant, Postgres) 
automatically without explicit schema setup, all inferred from the flow itself.

As a follow-up, we've provided an in-process API and convenient CLI options for setup / drop.

Previously, automatic flow backend setup / drop was only supported by `cocoindex setup` and `cocoindex drop` CLI commands.  

This was less flexible and convenient: 
- This must happen as a separate process.
- `setup` works for all loaded flows, but doesn't work for a single flow.

These limitations came from simplification of our early implementation. We rebuilt the related logic and supported a lightweight in-process API for flow backend setup and drop.

With the new change, you can run

```python
flow1.setup()  # Apply setup updates for flow1. It's noop if already up-to-date.
flow1.drop()   # Drop the setup for flow1

# We also support doing it for all
cocoindex.setup_all()
cocoindex.drop_all()
```

With this, you can programmatically set up your flow in your code before using the `update()` API to build the index:

```python
flow1.setup()
flow1.update()
```

In addition, `cocoindex update` CLI starts to support a `--setup` option, which automatically pushes setup changes 
before running the flow in the same CLI invocation.

```sh
cocoindex update --setup main
```
See [the document](https://cocoindex.io/docs/programming_guide/core_concepts/) for more details.

This is a major framework update. We've made significant improvements to state management, 
including smarter handling of when to load global metadata, when to trigger setup, and how each component updates. 
We're committed to taking care of the underlying infrastructure so developers can focus on what matters: the data and the logic.

## New building block: EmbedText 
CocoIndex provides native builtins for different sources, targets and transformations, based on a standardized interface.
Components can be switched by one-line code change.

We are committed to making it convenient to plug in the best from the ecosystem seamlessly. 

`EmbedText` embeds text into a vector space using various LLM APIs that support text embedding. 
It has native OpenAI, Gemini, and Voyage support. 
You can view more about EmbedText in this [documentation](https://cocoindex.io/docs/ops/litellm/). 

Example:

```python
text.transform(
    cocoindex.functions.EmbedText(
        api_type=cocoindex.LlmApiType.VOYAGE,
        model="voyage-code-3",
    )
)
```

## Optimization: skip source row reprocessing on unchanged content hash
CocoIndex supports incremental processing out-of-the-box that only reprocesses what's changed at minimum. 
It can be at a source level, or during a transformation, e.g., a few chunks in a document have changed.

This improvement saves reprocessing cost when the content of a source row doesn't change. 
Previously we used an *ordinal* (e.g. based on file modification time for file-based sources) to determine if there's content change. 
Sometimes modification time changes without content change (e.g. Git always uses the current time after checkout), 
and we want to skip processing in this case too.

## Major improvements on `SplitRecursively` function 
We've made major improvements on native support for [`SplitRecursively`](https://cocoindex.io/docs/ops/text/) (for chunking) building blocks. 

- Holistically planning the way to chunk to minimize "cost", considering the following factors:
    - AST structural level
    - Literal styles (new lines, double new lines)
    - Efficiency of overlap leverage
- Also for non-dividable elements (e.g. large comments, large strings), fall back to regex-based text chunking
- Add line/column to output of `SplitRecursively`
- Support customizing separators for the splitter

Check out this example of how to use `SplitRecursively` to index a codebase: 
[codebase-indexing](https://cocoindex.io/blogs/index-codebase-v1/).

## Union types

We’ve added support for union types for [basic types](https://cocoindex.io/docs/common_resources/data_types/). 
Union types are supported in Python (e.g. `str | int`). 

You can read more about union types [here](https://cocoindex.io/docs/common_resources/data_types/).

## NumPy type support

CocoIndex started to support NumPy numeric types and array types in CocoIndex functions. Specifically:

- `numpy.int64`: binds to *Int64*
- `numpy.float32`: binds to *Float32*
- `numpy.float64`: binds to *Float64*
- `numpy.typing.NDArray[T]`, where `T` is any NumPy numeric type above: binds to *Vector*

See [the document](https://cocoindex.io/docs/common_resources/data_types/) for more details.

## Supporting more LLM APIs

We’ve added LiteLLM (Proxy) and OpenRouter support. Read more [here](https://cocoindex.io/docs/ops/litellm/).

## New target store - Kuzu

[CocoIndex](https://github.com/cocoindex-io/cocoindex) now provides native support for [Kuzu](https://kuzudb.com) as a target graph data store. 
This integration features a high performance knowledge graph stack with real-time updates. 
You can read more [here](https://cocoindex.io/blogs/kuzu-integration).

## Thanks to the community

Welcome new contributors to the CocoIndex community! We are so excited to have you!

### @lemorage

Thanks to [@lemorage](https://github.com/lemorage) for the contributions! CocoIndex has received a series of high-quality PRs from him, and we truly appreciate his excellent work and passion for the project. @lemorage has also been helping us keep the repo healthy as a first responder to breaking changes. Thank you so much!

- use theme aligning with user system preferences [#572](https://github.com/cocoindex-io/cocoindex/pull/572)
- feat: add NumPy array support for vector representations [#586](https://github.com/cocoindex-io/cocoindex/pull/586)
- fix: remove unsupported type casting in integer vector handling [#619](https://github.com/cocoindex-io/cocoindex/pull/619)
- feat: support scalar NumPy value encodings [#620](https://github.com/cocoindex-io/cocoindex/pull/620)
- ops: add pre-commit and hooks for code checking [#641](https://github.com/cocoindex-io/cocoindex/pull/641)

### @vumichien

Thanks to [@vumichien](https://github.com/vumichien) for the contributions, especially PR #629, which tackles some complex and core aspects of CocoIndex. We really appreciate the thoughtful work and sustained effort over the past few weeks.

- chore: update Rust version to 1.86 and remove unused `as_any` methods [#597](https://github.com/cocoindex-io/cocoindex/pull/597)
- feat(cli): add force option to setup and drop commands for bypassing confirmation prompts [#602](https://github.com/cocoindex-io/cocoindex/pull/602)
- feat: allow optional database configuration [#608](https://github.com/cocoindex-io/cocoindex/pull/608)
- feat: add content hash support for change detection in source processing [#629](https://github.com/cocoindex-io/cocoindex/pull/629)

### @chardoncs

Thanks to [@chardoncs](https://github.com/chardoncs) for the contributions! We appreciate the work on supporting union types for basic types.

- feat: support union type for basic types [#510](https://github.com/cocoindex-io/cocoindex/pull/510)

### @par4m

Thanks to [@par4m](https://github.com/par4m) for the contributions! We appreciate the work on adding LiteLLM and OpenRouter support, which gives users more flexibility to pick their favorite models.

- feat(llm): Add LiteLLM (Proxy) Support [#630](https://github.com/cocoindex-io/cocoindex/pull/630)
- feat(llm): Add OpenRouter Support [#635](https://github.com/cocoindex-io/cocoindex/pull/635)

### @cijiugechu

Thanks to [@cijiugechu](https://github.com/cijiugechu) for the contributions! We appreciate the work on performance optimizations.

- chore(example): replace deprecated startup event with `lifespan` [#590](https://github.com/cocoindex-io/cocoindex/pull/590)
- chore(server): upgrade to `axum` 0.8 [#591](https://github.com/cocoindex-io/cocoindex/pull/591)
- perf(google_drive): generate `EXPORT_MIME_TYPES` at compile time [#593](https://github.com/cocoindex-io/cocoindex/pull/593)

### @theparthgupta

Thanks to [@theparthgupta](https://github.com/theparthgupta) for the contributions! We appreciate the work on making sentence_transformers an optional dependency, which helps reduce the base package size and gives users more flexibility.

- feat: make sentence_transformers an optional dependency [#674](https://github.com/cocoindex-io/cocoindex/pull/674)

### @dubin555

Thanks to [@dubin555](https://github.com/dubin555) for the contributions! We appreciate the work on improving logging information.

- chore: add more info in log [#614](https://github.com/cocoindex-io/cocoindex/pull/614)

### @TwistingTwists

Thanks to [@TwistingTwists](https://github.com/TwistingTwists) for the contributions! We appreciate the work on improving unit tests for Python values.

- fix: unit tests for python values [#452](https://github.com/cocoindex-io/cocoindex/pull/452)

### @SaiSakthidar

Thanks to [@SaiSakthidar](https://github.com/SaiSakthidar) for the contributions! We appreciate the work on migrating custom UUID conversion logic to the pyo3.uuid package, which improves code maintainability.

- feat: Migrated custom UUID conversion logic to pyo3.uuid package [#663](https://github.com/cocoindex-io/cocoindex/pull/663)

## Support our work
We are constantly improving CocoIndex, and more features are coming soon!
Stay tuned and follow us by starring our [GitHub repo](https://github.com/cocoindex-io/cocoindex).

## Sitemap

- [Blog index](https://cocoindex.io/blogs/)
- [Site index (llms.txt)](https://cocoindex.io/llms.txt)
- [Full blog corpus](https://cocoindex.io/llms-full.txt)
- [Markdown sitemap](https://cocoindex.io/sitemap.md)
- [XML sitemap](https://cocoindex.io/sitemap.xml)
- [RSS feed](https://cocoindex.io/blogs/rss.xml)