cocoindex 0.1.53__tar.gz → 0.1.55__tar.gz

{cocoindex-0.1.53 → cocoindex-0.1.55}/.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-0.1.53 → cocoindex-0.1.55}/.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-0.1.53 → cocoindex-0.1.55}/.github/workflows/CI.yml

@@ -26,7 +26,19 @@ permissions:
   contents: read
 
 jobs:
-  format-check:
+  rust-format-check:
+    name: Check Rust formatting
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: dtolnay/rust-toolchain@stable
+        with:
+          components: rustfmt
+      - name: Check Rust formatting
+        run: |
+          cargo fmt --check
+
+  python-format-check:
     name: Check Python formatting
     runs-on: ubuntu-latest
     steps:

cocoindex-0.1.55/.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-0.1.53 → cocoindex-0.1.55}/.vscode/settings.json

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

{cocoindex-0.1.53 → cocoindex-0.1.55}/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-0.1.53 → cocoindex-0.1.55}/Cargo.lock

@@ -1040,7 +1040,7 @@ dependencies = [
 
 [[package]]
 name = "cocoindex"
-version = "0.1.53"
+version = "0.1.55"
 dependencies = [
  "anyhow",
  "async-openai",
@@ -3293,6 +3293,7 @@ dependencies = [
  "pyo3-ffi",
  "pyo3-macros",
  "unindent",
+ "uuid",
 ]
 
 [[package]]

{cocoindex-0.1.53 → cocoindex-0.1.55}/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 = "0.1.53"
+version = "0.1.55"
 edition = "2024"
 rust-version = "1.86"
 
@@ -15,7 +15,7 @@ name = "cocoindex_engine"
 crate-type = ["cdylib"]
 
 [dependencies]
-pyo3 = { version = "0.25.0", features = ["chrono", "auto-initialize"] }
+pyo3 = { version = "0.25.0", features = ["chrono", "auto-initialize", "uuid"] }
 pythonize = "0.25.0"
 pyo3-async-runtimes = { version = "0.25.0", features = ["tokio-runtime"] }
 

{cocoindex-0.1.53 → cocoindex-0.1.55}/PKG-INFO

@@ -1,12 +1,14 @@
 Metadata-Version: 2.4
 Name: cocoindex
-Version: 0.1.53
+Version: 0.1.55
 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: watchfiles>=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 +53,10 @@ 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 +77,17 @@ 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 +157,8 @@ 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 +180,7 @@ 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-0.1.53 → cocoindex-0.1.55}/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-0.1.53 → cocoindex-0.1.55}/docs/docs/about/contributing.md

@@ -15,22 +15,22 @@ 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
     ```sh
     curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh
     ```
-    Already have Rust? Make sure it's up to date 
-    ```sh 
+    Already have Rust? Make sure it's up to date
+    ```sh
     rustup update
     ```
 
@@ -46,7 +46,7 @@ Following the steps below to get cocoindex build on latest codebase locally - if
 
 -   Install required tools:
     ```sh
-    pip install maturin mypy ruff
+    pip install maturin mypy pre-commit
     ```
 
 -   Build the library. Run at the root of cocoindex directory:
@@ -54,6 +54,11 @@ Following the steps below to get cocoindex build on latest codebase locally - if
     maturin develop
     ```
 
+-   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
@@ -67,10 +72,14 @@ 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. Make sure all tests and linting pass by running
-   ```sh
-   ./check.sh
-   ```
+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
 

cocoindex-0.1.55/docs/docs/ai/llm.mdx

@@ -0,0 +1,309 @@
+---
+title: LLM Support
+description: LLMs integrated with CocoIndex for various built-in functions
+---
+
+import Tabs from '@theme/Tabs';
+import TabItem from '@theme/TabItem';
+
+CocoIndex provides builtin functions integrating with various LLM APIs, for various inference tasks:
+*   [Text Generation](#text-generation): use LLM to generate text.
+*   [Text Embedding](#text-embedding): embed text into a vector space.
+
+## LLM API Types
+
+We support integrating with LLM with different types of APIs.
+Each LLM API type is specified by a `cocoindex.LlmApiType` enum.
+
+We support the following types of LLM APIs:
+
+| API Name | `LlmApiType` enum | Text Generation | Text Embedding |
+|----------|---------------------|--------------------|--------------------|
+| [OpenAI](#openai) | `LlmApiType.OPENAI` | ✅ | ✅ |
+| [Ollama](#ollama) | `LlmApiType.OLLAMA` | ✅ | ❌ |
+| [Google Gemini](#google-gemini) | `LlmApiType.GEMINI` | ✅ | ✅ |
+| [Anthropic](#anthropic) | `LlmApiType.ANTHROPIC` | ✅ | ❌ |
+| [Voyage](#voyage) | `LlmApiType.VOYAGE` | ❌ | ✅ |
+| [LiteLLM](#litellm) | `LlmApiType.LITE_LLM` | ✅ | ❌ |
+| [OpenRouter](#openrouter) | `LlmApiType.OPEN_ROUTER` | ✅ | ❌ |
+
+## LLM Tasks
+
+### Text Generation
+
+Generation is used as a building block for certain CocoIndex functions that process data using LLM generation.
+
+We have one builtin functions using LLM generation for now:
+
+*  [`ExtractByLlm`](/docs/ops/functions#extractbyllm): it extracts information from input text.
+
+#### LLM Spec
+
+When calling a CocoIndex function that uses LLM generation, you need to provide a `cocoindex.LlmSpec` dataclass, to configure the LLM you want to use in these functions.
+It has the following fields:
+
+*   `api_type` (type: [`cocoindex.LlmApiType`](/docs/ai/llm#llm-api-types), required): The type of integrated LLM API to use, e.g. `cocoindex.LlmApiType.OPENAI` or `cocoindex.LlmApiType.OLLAMA`.
+    See supported LLM APIs in the [LLM API integrations](#llm-api-integrations) section below.
+*   `model` (type: `str`, required): The name of the LLM model to use.
+*   `address` (type: `str`, optional): The address of the LLM API.
+
+
+### Text Embedding
+
+Embedding means converting text into a vector space, usually for similarity matching.
+
+We provide a builtin function [`EmbedText`](/docs/ops/functions#embedtext) that converts a given text into a vector space.
+The spec takes the following fields:
+
+*   `api_type` (type: `cocoindex.LlmApiType`, required)
+*   `model` (type: `str`, required)
+*   `address` (type: `str`, optional)
+*   `output_dimension` (type: `int`, optional)
+*   `task_type` (type: `str`, optional)
+
+See documentation for [`EmbedText`](/docs/ops/functions#embedtext) for more details about these fields.
+
+## LLM API Integrations
+
+CocoIndex integrates with various LLM APIs for these functions.
+
+### OpenAI
+
+To use the OpenAI LLM API, you need to set the environment variable `OPENAI_API_KEY`.
+You can generate the API key from [OpenAI Dashboard](https://platform.openai.com/api-keys).
+
+Currently we don't support custom address for OpenAI API.
+
+You can find the full list of models supported by OpenAI [here](https://platform.openai.com/docs/models).
+
+For text generation, a spec for OpenAI looks like this:
+
+<Tabs>
+<TabItem value="python" label="Python" default>
+
+```python
+cocoindex.LlmSpec(
+    api_type=cocoindex.LlmApiType.OPENAI,
+    model="gpt-4o",
+)
+```
+
+</TabItem>
+</Tabs>
+
+For text embedding, a spec for OpenAI looks like this:
+
+<Tabs>
+<TabItem value="python" label="Python" default>
+
+```python
+cocoindex.functions.EmbedText(
+    api_type=cocoindex.LlmApiType.OPENAI,
+    model="text-embedding-3-small",
+)
+```
+
+</TabItem>
+</Tabs>
+
+### Ollama
+
+[Ollama](https://ollama.com/) allows you to run LLM models on your local machine easily. To get started:
+
+*   [Download](https://ollama.com/download) and install Ollama.
+*   Pull your favorite LLM models by the `ollama pull` command, e.g.
+    ```bash
+    ollama pull llama3.2
+    ```
+You can find the [list of models](https://ollama.com/library) supported by Ollama.
+
+A spec for Ollama looks like this:
+
+<Tabs>
+<TabItem value="python" label="Python" default>
+
+```python
+cocoindex.LlmSpec(
+    api_type=cocoindex.LlmApiType.OLLAMA,
+    model="llama3.2:latest",
+    # Optional, use Ollama's default port (11434) on localhost if not specified
+    address="http://localhost:11434",
+)
+```
+
+</TabItem>
+</Tabs>
+
+### Google Gemini
+
+To use the Gemini LLM API, you need to set the environment variable `GEMINI_API_KEY`.
+You can generate the API key from [Google AI Studio](https://aistudio.google.com/apikey).
+
+You can find the full list of models supported by Gemini [here](https://ai.google.dev/gemini-api/docs/models).
+
+For text generation, a spec looks like this:
+
+<Tabs>
+<TabItem value="python" label="Python" default>
+
+```python
+cocoindex.LlmSpec(
+    api_type=cocoindex.LlmApiType.GEMINI,
+    model="gemini-2.0-flash",
+)
+```
+
+</TabItem>
+</Tabs>
+
+For text embedding, a spec looks like this:
+
+<Tabs>
+<TabItem value="python" label="Python" default>
+
+```python
+cocoindex.functions.EmbedText(
+    api_type=cocoindex.LlmApiType.GEMINI,
+    model="text-embedding-004",
+    task_type="SEMANTICS_SIMILARITY",
+)
+```
+
+All supported embedding models can be found [here](https://ai.google.dev/gemini-api/docs/embeddings#embeddings-models).
+Gemini supports task type (optional), which can be found [here](https://ai.google.dev/gemini-api/docs/embeddings#supported-task-types).
+
+
+</TabItem>
+</Tabs>
+
+### Anthropic
+
+To use the Anthropic LLM API, you need to set the environment variable `ANTHROPIC_API_KEY`.
+You can generate the API key from [Anthropic API](https://console.anthropic.com/settings/keys).
+
+A text generation spec for Anthropic looks like this:
+
+<Tabs>
+<TabItem value="python" label="Python" default>
+
+```python
+cocoindex.LlmSpec(
+    api_type=cocoindex.LlmApiType.ANTHROPIC,
+    model="claude-3-5-sonnet-latest",
+)
+```
+
+</TabItem>
+</Tabs>
+
+You can find the full list of models supported by Anthropic [here](https://docs.anthropic.com/en/docs/about-claude/models/all-models).
+
+### Voyage
+
+To use the Voyage LLM API, you need to set the environment variable `VOYAGE_API_KEY`.
+You can generate the API key from [Voyage dashboard](https://dashboard.voyageai.com/organization/api-keys).
+
+A text embedding spec for Voyage looks like this:
+
+<Tabs>
+<TabItem value="python" label="Python" default>
+
+```python
+cocoindex.functions.EmbedText(
+    api_type=cocoindex.LlmApiType.VOYAGE,
+    model="voyage-code-3",
+    task_type="document",
+)
+```
+
+</TabItem>
+</Tabs>
+
+Voyage API supports `document` and `query` as task types (optional, a.k.a. `input_type` in Voyage API, see [Voyage API documentation](https://docs.voyageai.com/reference/embeddings-api) for details).
+
+### 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 DeepSeek:**
+
+Use this in your `config.yml`:
+
+```yaml
+model_list:
+  - model_name: deepseek-chat
+    litellm_params:
+        model: deepseek/deepseek-chat
+        api_key: os.environ/DEEPSEEK_API_KEY
+```
+
+You need to set the environment variable `DEEPSEEK_API_KEY` to your DeepSeek API key.
+
+**Example for Groq:**
+
+Use this in your `config.yml`:
+
+```yaml
+model_list:
+  - model_name: groq-llama-3.3-70b-versatile
+    litellm_params:
+      model: groq/llama-3.3-70b-versatile
+      api_key: "os.environ/GROQ_API_KEY"
+```
+
+You need to set the environment variable `GROQ_API_KEY` to your Groq API key.
+
+
+#### 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-chat",
+    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-0.1.53 → cocoindex-0.1.55}/docs/docs/core/basics.md

@@ -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-0.1.53 → cocoindex-0.1.55}/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
-```
+```