cocoindex 0.1.52__tar.gz → 0.1.54__tar.gz

{cocoindex-0.1.52 → cocoindex-0.1.54}/.github/ISSUE_TEMPLATE//360/237/222/241-feature-request.md

@@ -17,4 +17,4 @@ assignees: ''
 
 ---
 ❤️ Contributors, please refer to 📙[Contributing Guide](https://cocoindex.io/docs/about/contributing).
-Unless the PR can be sent immediately (e.g. just a few lines of code), we recommend you to leave a comment on the issue like **`I'm working on it`**  or **`Can I work on this issue?`** to avoid duplicating work. Our [Discord server](https://discord.com/invite/zpA9S2DR7s) is always open and friendly.
+Unless the PR can be sent immediately (e.g. just a few lines of code), we recommend you to leave a comment on the issue like **`I'm working on it`**  or **`Can I work on this issue?`** to avoid duplicating work. Our [Discord server](https://discord.com/invite/zpA9S2DR7s) is always open and friendly.

{cocoindex-0.1.52 → cocoindex-0.1.54}/.github/scripts/update_version.sh

@@ -19,4 +19,4 @@ else
 fi
 
 # Update Cargo.toml
-sed "${SED_INLINE[@]}" "s/^version = .*/version = \"$VERSION\"/" Cargo.toml
+sed "${SED_INLINE[@]}" "s/^version = .*/version = \"$VERSION\"/" Cargo.toml

cocoindex-0.1.54/.pre-commit-config.yaml

@@ -0,0 +1,71 @@
+ci:
+  autofix_prs: false
+  autoupdate_schedule: 'monthly'
+
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v5.0.0
+    hooks:
+      - id: check-case-conflict
+        # Check for files with names that would conflict on a case-insensitive
+        # filesystem like MacOS HFS+ or Windows FAT.
+      - id: check-merge-conflict
+        # Check for files that contain merge conflict strings.
+      - id: check-symlinks
+        # Checks for symlinks which do not point to anything.
+        exclude: ".*(.github.*)$"
+      - id: detect-private-key
+        # Checks for the existence of private keys.
+      - id: end-of-file-fixer
+        # Makes sure files end in a newline and only a newline.
+        exclude: ".*(data.*|licenses.*|_static.*|\\.ya?ml|\\.jpe?g|\\.png|\\.svg|\\.webp)$"
+      - id: trailing-whitespace
+        # Trims trailing whitespace.
+        exclude_types: [python]  # Covered by Ruff W291.
+        exclude: ".*(data.*|licenses.*|_static.*|\\.ya?ml|\\.jpe?g|\\.png|\\.svg|\\.webp)$"
+
+  - repo: local
+    hooks:
+        - id: maturin-develop
+          name: maturin develop
+          entry: maturin develop
+          language: system
+          files: ^(python/|src/|Cargo\.toml|pyproject\.toml)
+          pass_filenames: false
+
+        - id: cargo-fmt
+          name: cargo fmt
+          entry: cargo fmt
+          language: system
+          types: [rust]
+          pass_filenames: false
+
+        - id: cargo-test
+          name: cargo test
+          entry: cargo test
+          language: system
+          types: [rust]
+          pass_filenames: false
+
+        - id: mypy-check
+          name: mypy type check
+          entry: mypy
+          language: system
+          types: [python]
+          pass_filenames: false
+
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.12.0
+    hooks:
+      - id: ruff-format
+        types: [python]
+        pass_filenames: true
+  
+  - repo: https://github.com/christophmeissner/pytest-pre-commit
+    rev: 1.0.0
+    hooks:
+      - id: pytest
+        language: system
+        types: [python]
+        pass_filenames: false
+        always_run: false

{cocoindex-0.1.52 → cocoindex-0.1.54}/.vscode/settings.json

@@ -6,4 +6,4 @@
     ],
     "editor.formatOnSave": true,
     "python.formatting.provider": "ruff"
-}
+}

{cocoindex-0.1.52 → cocoindex-0.1.54}/CONTRIBUTING.md

@@ -1 +1 @@
-We love contributions from our community ❤️. Please check out our [contributing guide](https://cocoindex.io/docs/about/contributing).
+We love contributions from our community ❤️. Please check out our [contributing guide](https://cocoindex.io/docs/about/contributing).

{cocoindex-0.1.52 → cocoindex-0.1.54}/Cargo.lock

@@ -1040,7 +1040,7 @@ dependencies = [
 
 [[package]]
 name = "cocoindex"
-version = "0.1.52"
+version = "0.1.54"
 dependencies = [
  "anyhow",
  "async-openai",

{cocoindex-0.1.52 → cocoindex-0.1.54}/Cargo.toml

@@ -2,7 +2,7 @@
 name = "cocoindex"
 # Version used for local development is always higher than others to take precedence.
 # Will be overridden for specific release versions.
-version = "0.1.52"
+version = "0.1.54"
 edition = "2024"
 rust-version = "1.86"
 

{cocoindex-0.1.52 → cocoindex-0.1.54}/PKG-INFO

@@ -1,12 +1,13 @@
 Metadata-Version: 2.4
 Name: cocoindex
-Version: 0.1.52
+Version: 0.1.54
 Requires-Dist: sentence-transformers>=3.3.1
 Requires-Dist: click>=8.1.8
 Requires-Dist: rich>=14.0.0
 Requires-Dist: python-dotenv>=1.1.0
 Requires-Dist: pytest ; extra == 'test'
 Requires-Dist: ruff ; extra == 'dev'
+Requires-Dist: pre-commit ; extra == 'dev'
 Provides-Extra: test
 Provides-Extra: dev
 License-File: LICENSE
@@ -51,10 +52,10 @@ Unlike a workflow orchestration framework where data is usually opaque, in CocoI
 
 ```python
 # import
-data['content'] = flow_builder.add_source(...) 
+data['content'] = flow_builder.add_source(...)
 
 # transform
-data['out'] = data['content'] 
+data['out'] = data['content']
     .transform(...)
     .transform(...)
 
@@ -75,17 +76,17 @@ As a data framework, CocoIndex takes it to the next level on data freshness. **I
 The frameworks takes care of
 - Change data capture.
 - Figure out what exactly needs to be updated, and only updating that without having to recompute everything.
-  
+
 This makes it fast to reflect any source updates to the target store. If you have concerns with surfacing stale data to AI agents and are spending lots of efforts working on infra piece to optimize the latency, the framework actually handles it for you.
 
 
 ## Quick Start:
-If you're new to CocoIndex, we recommend checking out 
+If you're new to CocoIndex, we recommend checking out
 - 📖 [Documentation](https://cocoindex.io/docs)
 - ⚡  [Quick Start Guide](https://cocoindex.io/docs/getting_started/quickstart)
-- 🎬 [Quick Start Video Tutorial](https://youtu.be/gv5R8nOXsWU?si=9ioeKYkMEnYevTXT) 
+- 🎬 [Quick Start Video Tutorial](https://youtu.be/gv5R8nOXsWU?si=9ioeKYkMEnYevTXT)
 
-### Setup 
+### Setup
 
 1. Install CocoIndex Python library
 
@@ -155,8 +156,8 @@ It defines an index flow like this:
 | [Google Drive Text Embedding](examples/gdrive_text_embedding) | Index text documents from Google Drive |
 | [Docs to Knowledge Graph](examples/docs_to_knowledge_graph) | Extract relationships from Markdown documents and build a knowledge graph |
 | [Embeddings to Qdrant](examples/text_embedding_qdrant) | Index documents in a Qdrant collection for semantic search |
-| [FastAPI Server with Docker](examples/fastapi_server_docker) | Run the semantic search server in a Dockerized FastAPI setup | 
-| [Product Recommendation](examples/product_recommendation) | Build real-time product recommendations with LLM and graph database| 
+| [FastAPI Server with Docker](examples/fastapi_server_docker) | Run the semantic search server in a Dockerized FastAPI setup |
+| [Product Recommendation](examples/product_recommendation) | Build real-time product recommendations with LLM and graph database|
 | [Image Search with Vision API](examples/image_search) | Generates detailed captions for images using a vision model, embeds them, enables live-updating semantic search via FastAPI and served on a React frontend|
 
 More coming and stay tuned 👀!
@@ -178,7 +179,7 @@ Join our community here:
 - 📜 [Read our blog posts](https://cocoindex.io/blogs/)
 
 ## Support us:
-We are constantly improving, and more features and examples are coming soon. If you love this project, please drop us a star ⭐ at GitHub repo [![GitHub](https://img.shields.io/github/stars/cocoindex-io/cocoindex?color=5B5BD6)](https://github.com/cocoindex-io/cocoindex) to stay tuned and help us grow. 
+We are constantly improving, and more features and examples are coming soon. If you love this project, please drop us a star ⭐ at GitHub repo [![GitHub](https://img.shields.io/github/stars/cocoindex-io/cocoindex?color=5B5BD6)](https://github.com/cocoindex-io/cocoindex) to stay tuned and help us grow.
 
 ## License
 CocoIndex is Apache 2.0 licensed.

{cocoindex-0.1.52 → cocoindex-0.1.54}/README.md

@@ -32,10 +32,10 @@ Unlike a workflow orchestration framework where data is usually opaque, in CocoI
 
 ```python
 # import
-data['content'] = flow_builder.add_source(...) 
+data['content'] = flow_builder.add_source(...)
 
 # transform
-data['out'] = data['content'] 
+data['out'] = data['content']
     .transform(...)
     .transform(...)
 
@@ -56,17 +56,17 @@ As a data framework, CocoIndex takes it to the next level on data freshness. **I
 The frameworks takes care of
 - Change data capture.
 - Figure out what exactly needs to be updated, and only updating that without having to recompute everything.
-  
+
 This makes it fast to reflect any source updates to the target store. If you have concerns with surfacing stale data to AI agents and are spending lots of efforts working on infra piece to optimize the latency, the framework actually handles it for you.
 
 
 ## Quick Start:
-If you're new to CocoIndex, we recommend checking out 
+If you're new to CocoIndex, we recommend checking out
 - 📖 [Documentation](https://cocoindex.io/docs)
 - ⚡  [Quick Start Guide](https://cocoindex.io/docs/getting_started/quickstart)
-- 🎬 [Quick Start Video Tutorial](https://youtu.be/gv5R8nOXsWU?si=9ioeKYkMEnYevTXT) 
+- 🎬 [Quick Start Video Tutorial](https://youtu.be/gv5R8nOXsWU?si=9ioeKYkMEnYevTXT)
 
-### Setup 
+### Setup
 
 1. Install CocoIndex Python library
 
@@ -136,8 +136,8 @@ It defines an index flow like this:
 | [Google Drive Text Embedding](examples/gdrive_text_embedding) | Index text documents from Google Drive |
 | [Docs to Knowledge Graph](examples/docs_to_knowledge_graph) | Extract relationships from Markdown documents and build a knowledge graph |
 | [Embeddings to Qdrant](examples/text_embedding_qdrant) | Index documents in a Qdrant collection for semantic search |
-| [FastAPI Server with Docker](examples/fastapi_server_docker) | Run the semantic search server in a Dockerized FastAPI setup | 
-| [Product Recommendation](examples/product_recommendation) | Build real-time product recommendations with LLM and graph database| 
+| [FastAPI Server with Docker](examples/fastapi_server_docker) | Run the semantic search server in a Dockerized FastAPI setup |
+| [Product Recommendation](examples/product_recommendation) | Build real-time product recommendations with LLM and graph database|
 | [Image Search with Vision API](examples/image_search) | Generates detailed captions for images using a vision model, embeds them, enables live-updating semantic search via FastAPI and served on a React frontend|
 
 More coming and stay tuned 👀!
@@ -159,7 +159,7 @@ Join our community here:
 - 📜 [Read our blog posts](https://cocoindex.io/blogs/)
 
 ## Support us:
-We are constantly improving, and more features and examples are coming soon. If you love this project, please drop us a star ⭐ at GitHub repo [![GitHub](https://img.shields.io/github/stars/cocoindex-io/cocoindex?color=5B5BD6)](https://github.com/cocoindex-io/cocoindex) to stay tuned and help us grow. 
+We are constantly improving, and more features and examples are coming soon. If you love this project, please drop us a star ⭐ at GitHub repo [![GitHub](https://img.shields.io/github/stars/cocoindex-io/cocoindex?color=5B5BD6)](https://github.com/cocoindex-io/cocoindex) to stay tuned and help us grow.
 
 ## License
 CocoIndex is Apache 2.0 licensed.

{cocoindex-0.1.52 → cocoindex-0.1.54}/docs/docs/about/contributing.md

@@ -15,47 +15,52 @@ We use [GitHub Issues](https://github.com/cocoindex-io/cocoindex/issues) to trac
 
 We tag issues with the ["good first issue"](https://github.com/cocoindex-io/cocoindex/issues?q=is%3Aissue+is%3Aopen+label%3A%22good+first+issue%22) label for beginner contributors.
 
-## How to Contribute 
+## How to Contribute
 - If you decide to work on an issue, unless the PR can be sent immediately (e.g. just a few lines of code), we recommend you to leave a comment on the issue like **`I'm working on it`**  or **`Can I work on this issue?`** to avoid duplicating work.
 - For larger features, we recommend you to discuss with us first in our [Discord server](https://discord.com/invite/zpA9S2DR7s) to coordinate the design and work.
 - Our [Discord server](https://discord.com/invite/zpA9S2DR7s) are constantly open. If you are unsure about anything, it is a good place to discuss! We'd love to collaborate and will always be friendly.
 
-## Start hacking! Setting Up Development Environment 
+## Start hacking! Setting Up Development Environment
 Following the steps below to get cocoindex build on latest codebase locally - if you are making changes to cocoindex funcionality and want to test it out.
 
 -   🦀 [Install Rust](https://rust-lang.org/tools/install)
-    
+
     If you don't have Rust installed, run
-    ```bash
+    ```sh
     curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh
     ```
-    Already have Rust? Make sure it's up to date 
-    ```bash 
+    Already have Rust? Make sure it's up to date
+    ```sh
     rustup update
     ```
 
--   (Recommended) Setup Python virtual environment:
-    ```bash
+-   Setup Python virtual environment:
+    ```sh
     python3 -m venv .venv
     ```
-    Activate the virtual environment, before any installings / buildings / runnings:
+    Activate the virtual environment, before any installing / building / running:
 
-    ```bash
+    ```sh
     . .venv/bin/activate
     ```
 
--   Install maturin:
-    ```bash
-    pip install maturin
+-   Install required tools:
+    ```sh
+    pip install maturin mypy pre-commit
     ```
 
 -   Build the library. Run at the root of cocoindex directory:
-    ```bash
+    ```sh
     maturin develop
     ```
 
--   (Optional) Before running a specific example, set extra environment variables, for exposing extra traces, allowing dev UI, etc.
-    ```bash
+-   Install and enable pre-commit hooks. This ensures all checks run automatically before each commit:
+    ```sh
+    pre-commit install
+    ```
+
+-   Before running a specific example, set extra environment variables, for exposing extra traces, allowing dev UI, etc.
+    ```sh
     . ./.env.lib_debug
     ```
 
@@ -67,7 +72,16 @@ To submit your code:
 1. Fork the [CocoIndex repository](https://github.com/cocoindex-io/cocoindex)
 2. [Create a new branch](https://docs.github.com/en/desktop/making-changes-in-a-branch/managing-branches-in-github-desktop) on your fork
 3. Make your changes
-4. [Open a Pull Request (PR)](https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/proposing-changes-to-your-work-with-pull-requests/creating-a-pull-request-from-a-fork) when your work is ready for review
+4. Run the pre-commit checks (automatically triggered on `git commit`)
+
+    :::tip
+    To run them manually (same as CI):
+        ```sh
+        pre-commit run --all-files
+        ```
+    :::
+
+5. [Open a Pull Request (PR)](https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/proposing-changes-to-your-work-with-pull-requests/creating-a-pull-request-from-a-fork) when your work is ready for review
 
 In your PR description, please include:
 - Description of the changes

{cocoindex-0.1.52 → cocoindex-0.1.54}/docs/docs/ai/llm.mdx

@@ -121,3 +121,89 @@ cocoindex.LlmSpec(
 
 You can find the full list of models supported by Anthropic [here](https://docs.anthropic.com/en/docs/about-claude/models/all-models).
 
+### LiteLLM
+
+To use the LiteLLM API, you need to set the environment variable `LITELLM_API_KEY`.
+
+#### 1. Install LiteLLM Proxy
+
+```bash
+pip install 'litellm[proxy]'
+```
+
+#### 2. Create a `config.yml` for LiteLLM
+
+**Example for OpenAI:**
+```yaml
+model_list:
+  - model_name: "*"
+    litellm_params:
+      model: openai/*
+      api_key: os.environ/LITELLM_API_KEY
+```
+
+**Example for DeepSeek:**
+
+First, pull the DeepSeek model with Ollama:
+```bash
+ollama pull deepseek-r1
+```
+Then run it if it's not running:
+```bash
+ollama run deepseek-r1
+```
+
+Then, use this in your `config.yml`:
+```yaml
+model_list:
+  - model_name: "deepseek-r1"
+    litellm_params:
+      model: "ollama_chat/deepseek-r1"
+      api_base: "http://localhost:11434"
+```
+
+#### 3. Run LiteLLM Proxy
+
+```bash
+litellm --config config.yml
+```
+
+#### 4. A Spec for LiteLLM will look like this:
+
+<Tabs>
+<TabItem value="python" label="Python" default>
+
+```python
+cocoindex.LlmSpec(
+    api_type=cocoindex.LlmApiType.LITE_LLM,
+    model="deepseek-r1",
+    address="http://127.0.0.1:4000", # default url of LiteLLM
+)
+```
+
+</TabItem>
+</Tabs>
+
+You can find the full list of models supported by LiteLLM [here](https://docs.litellm.ai/docs/providers).
+
+### OpenRouter
+
+To use the OpenRouter API, you need to set the environment variable `OPENROUTER_API_KEY`.
+You can generate the API key from [here](https://openrouter.ai/settings/keys).
+
+A spec for OpenRouter looks like this:
+
+<Tabs>
+<TabItem value="python" label="Python" default>
+
+```python
+cocoindex.LlmSpec(
+    api_type=cocoindex.LlmApiType.OPEN_ROUTER,
+    model="deepseek/deepseek-r1:free",
+)
+```
+
+</TabItem>
+</Tabs>
+
+You can find the full list of models supported by OpenRouter [here](https://openrouter.ai/models).

{cocoindex-0.1.52 → cocoindex-0.1.54}/docs/docs/core/basics.md

@@ -50,7 +50,7 @@ For the example shown in the [Quickstart](../getting_started/quickstart) section
 
 This creates the following data for the indexing flow:
 
-*   The `Localfile` source creates a `documents` field at the top level, with `filename` (key) and `content` sub fields.
+*   The `LocalFile` source creates a `documents` field at the top level, with `filename` (key) and `content` sub fields.
 *   A "for each" action works on each document, with the following transformations:
     *   The `SplitRecursively` function splits content into chunks, adds a `chunks` field into the current scope (each document), with `location` (key) and `text` sub fields.
     *   A "collect" action works on each chunk, with the following transformations:
@@ -71,7 +71,7 @@ An indexing flow, once set up, maintains a long-lived relationship between data
 
     *   **One time update**: Once triggered, CocoIndex updates the target data to reflect the version of source data up to the current moment.
     *   **Live update**: CocoIndex continuously reacts to changes of source data and updates the target data accordingly, based on various **change capture mechanisms** for the source.
-    
+
     See more details in the [build / update target data](flow_methods#build--update-target-data) section.
 
 3.  CocoIndex intelligently reprocesses to propagate source changes to target by:
@@ -101,4 +101,4 @@ As an indexing flow is long-lived, it needs to store intermediate data to keep t
 CocoIndex uses internal storage for this purpose.
 
 Currently, CocoIndex uses Postgres database as the internal storage.
-See [Settings](settings#databaseconnectionspec) for configuring its location, and `cocoindex setup` CLI command (see [CocoIndex CLI](cli)) creates tables for the internal storage.
+See [Settings](settings#databaseconnectionspec) for configuring its location, and `cocoindex setup` CLI command (see [CocoIndex CLI](cli)) creates tables for the internal storage.

{cocoindex-0.1.52 → cocoindex-0.1.54}/docs/docs/core/cli.mdx

@@ -72,4 +72,4 @@ Use `--help` to see the full list of subcommands, and `subcommand --help` to see
 ```sh
 cocoindex --help       # Show all subcommands
 cocoindex show --help  # Show usage of "show" subcommand
-```
+```

{cocoindex-0.1.52 → cocoindex-0.1.54}/docs/docs/core/custom_function.mdx

@@ -84,7 +84,7 @@ Notes:
 
 ### Function Executor
 
-A function executor defines behavior of a function. It's initantiated for each operation that uses this function.
+A function executor defines behavior of a function. It's instantiated for each operation that uses this function.
 
 The function executor is responsible for:
 
@@ -117,7 +117,7 @@ Notes:
 *   The `cocoindex.op.executor_class()` class decorator also takes optional parameters.
     See [Parameters for custom functions](#parameters-for-custom-functions) for details.
 
-*   A `spec` field must be present in the class, and must be annoated with the spec class name.
+*   A `spec` field must be present in the class, and must be annotated with the spec class name.
 *   The `prepare()` method is optional. It's executed once and only once before any `__call__` execution, to prepare the function execution.
 *   The `__call__()` method is required. It's executed for each specific rows of data.
     Types of arugments and the return value must be decorated, so that CocoIndex will have information about data types of the operation's output fields.
@@ -133,7 +133,7 @@ The cocoindex repository contains the following examples of custom functions def
 *   In the [pdf_embedding](https://github.com/cocoindex-io/cocoindex/blob/main/examples/pdf_embedding/main.py) example, we define a custom function `PdfToMarkdown`
 *   The `SentenceTransformerEmbed` function shipped with the CocoIndex Python package is defined by Python SDK.
     Search for [`SentenceTransformerEmbedExecutor`](https://github.com/search?q=repo%3Acocoindex-io%2Fcocoindex+lang%3Apython+SentenceTransformerEmbedExecutor&type=code) to see the code.
-    
+
 ## Parameters for custom functions
 
 Custom functions take the following additional parameters:

{cocoindex-0.1.52 → cocoindex-0.1.54}/docs/docs/core/flow_def.mdx

@@ -56,7 +56,7 @@ A data scope has a bunch of fields and collectors, and users can add new fields
 
 ### Get or Add a Field
 
-You can get or add a field of a data scope (which is a data slice). 
+You can get or add a field of a data scope (which is a data slice).
 
 :::note
 

{cocoindex-0.1.52 → cocoindex-0.1.54}/docs/docs/core/flow_methods.mdx

@@ -81,7 +81,7 @@ The `update()` async method creates/updates data in the target.
 Once the function returns, the target data is fresh up to the moment when the function is called.
 
 ```python
-stats = await demo_flow.update()
+stats = demo_flow.update()
 print(stats)
 ```
 
@@ -182,10 +182,10 @@ CocoIndex also provides asynchronous versions of APIs for blocking operations, i
     my_updater = cocoindex.FlowLiveUpdater(demo_flow)
     # Start the updater.
     await my_updater.start_async()
-    
+
     # Perform your own logic (e.g. a query loop).
     ...
-    
+
     # Print the update stats.
     print(my_updater.update_stats())
     # Abort the updater.
@@ -245,4 +245,4 @@ demo_flow.evaluate_and_dump(EvaluateAndDumpOptions(output_dir="./eval_output"))
 ```
 
 </TabItem>
-</Tabs>
+</Tabs>

{cocoindex-0.1.52 → cocoindex-0.1.54}/docs/docs/core/settings.mdx

@@ -113,4 +113,4 @@ This is the list of environment variables, each of which has a corresponding fie
 | `COCOINDEX_DATABASE_URL` | `database.url` | Yes |
 | `COCOINDEX_DATABASE_USER` | `database.user` | No |
 | `COCOINDEX_DATABASE_PASSWORD` | `database.password` | No |
-| `COCOINDEX_APP_NAMESPACE` | `app_namespace` | No |
+| `COCOINDEX_APP_NAMESPACE` | `app_namespace` | No |

{cocoindex-0.1.52 → cocoindex-0.1.54}/docs/docs/getting_started/installation.md

@@ -1,5 +1,5 @@
 ---
-title: Installation 
+title: Installation
 description: Setup the CocoIndex environment in 0-3 min
 ---
 
@@ -17,7 +17,7 @@ pip install -U cocoindex
 
 ## 📦 Install Postgres
 
-You can skip this step if you already have a Postgres database with pgvector extension installed. 
+You can skip this step if you already have a Postgres database with pgvector extension installed.
 
 If you don't have a Postgres database:
 
@@ -31,4 +31,3 @@ docker compose -f <(curl -L https://raw.githubusercontent.com/cocoindex-io/cocoi
 ## 🎉 All set!
 
 You can now start using CocoIndex.
-

{cocoindex-0.1.52 → cocoindex-0.1.54}/docs/docs/getting_started/overview.md

@@ -5,7 +5,7 @@ slug: /
 
 # Welcome to CocoIndex
 
-CocoIndex is an ultra-performant real-time data transformation framework for AI, with incremental processing. 
+CocoIndex is an ultra-performant real-time data transformation framework for AI, with incremental processing.
 
 As a data framework, CocoIndex takes it to the next level on data freshness. **Incremental processing** is one of the core values provided by CocoIndex.
 
@@ -17,10 +17,10 @@ CocoIndex follows the idea of [Dataflow programming](https://en.wikipedia.org/wi
 The gist of an example data transformation:
 ```python
 # import
-data['content'] = flow_builder.add_source(...) 
+data['content'] = flow_builder.add_source(...)
 
 # transform
-data['out'] = data['content'] 
+data['out'] = data['content']
     .transform(...)
     .transform(...)
 
@@ -33,4 +33,3 @@ collector.export(...)
 
 Get Started:
 - [Quick Start](https://cocoindex.io/docs/getting_started/quickstart)
-

{cocoindex-0.1.52 → cocoindex-0.1.54}/docs/docs/getting_started/quickstart.md

@@ -19,7 +19,7 @@ This guide will help you get up and running with CocoIndex in just a few minutes
 We'll need to install a bunch of dependencies for this project.
 
 1.  Install CocoIndex:
- 
+
     ```bash
     pip install -U cocoindex
     ```
@@ -149,7 +149,7 @@ documents: 3 added, 0 removed, 0 updated
 
 ## Step 4 (optional): Run queries against the index
 
-CocoIndex excels at transforming your data and storing it (a.k.a. indexing). 
+CocoIndex excels at transforming your data and storing it (a.k.a. indexing).
 The goal of transforming your data is usually to query against it.
 Once you already have your index built, you can directly access the transformed data in the target database.
 CocoIndex also provides utilities for you to do this more seamlessly.
@@ -291,4 +291,4 @@ Next, you may want to:
 *   Learn about [CocoIndex Basics](../core/basics.md).
 *   Learn about other examples in the [examples](https://github.com/cocoindex-io/cocoindex/tree/main/examples) directory.
     *    The `text_embedding` example is this quickstart.
-    *    Pick other examples to learn upon your interest.
+    *    Pick other examples to learn upon your interest.

{cocoindex-0.1.52 → cocoindex-0.1.54}/docs/docs/ops/functions.md

@@ -53,7 +53,7 @@ Input data:
     :::note
 
     We use the `language` field to determine how to split the input text, following these rules:
-    
+
     *   We'll match the input `language` field against the `language_name` or `aliases` of each custom language specification, and use the matched one. If value of `language` is null, it'll be treated as empty string when matching `language_name` or `aliases`.
     *   If no match is found, we'll match the `language` field against the builtin language configurations.
         For all supported builtin language names and aliases (extensions), see [the code](https://github.com/search?q=org%3Acocoindex-io+lang%3Arust++%22static+TREE_SITTER_LANGUAGE_BY_LANG%22&type=code).

{cocoindex-0.1.52 → cocoindex-0.1.54}/docs/docs/ops/sources.md

@@ -22,9 +22,9 @@ The spec takes the following fields:
     If not specified, no files will be excluded.
 
     :::info
-    
+
     `included_patterns` and `excluded_patterns` are using Unix-style glob syntax. See [globset syntax](https://docs.rs/globset/latest/globset/index.html#syntax) for the details.
-    
+
     :::
 
 ### Schema
@@ -131,9 +131,9 @@ The spec takes the following fields:
     If not specified, no files will be excluded.
 
     :::info
-    
+
     `included_patterns` and `excluded_patterns` are using Unix-style glob syntax. See [globset syntax](https://docs.rs/globset/latest/globset/index.html#syntax) for the details.
-    
+
     :::
 
 *   `sqs_queue_url` (type: `str`, optional): if provided, the source will receive change event notifications from Amazon S3 via this SQS queue.

{cocoindex-0.1.52 → cocoindex-0.1.54}/docs/docs/ops/targets.md

@@ -52,7 +52,7 @@ Here's how CocoIndex data elements map to Qdrant elements during export:
 
 | CocoIndex Element | Qdrant Element |
 |-------------------|------------------|
-| an export target  | a unique collection |  
+| an export target  | a unique collection |
 | a collected row   | a point |
 | a field           | a named vector, if fits into Qdrant vector; or a field within payload otherwise |
 

{cocoindex-0.1.52 → cocoindex-0.1.54}/docs/docs/query.mdx

@@ -99,4 +99,3 @@ query = f"SELECT filename, text FROM {table_name} ORDER BY embedding <=> %s DESC
 
 </TabItem>
 </Tabs>
-

{cocoindex-0.1.52 → cocoindex-0.1.54}/docs/sidebars.ts

@@ -61,4 +61,4 @@ const sidebars: SidebarsConfig = {
   ],
 };
 
-export default sidebars;
+export default sidebars;