From d230b194e551795f1d23db0182dec1aa9203e6e9 Mon Sep 17 00:00:00 2001
From: Jiangzhou He <hejiangzhou@gmail.com>
Date: Wed, 1 Oct 2025 08:58:05 -0700
Subject: [PATCH 1/3] chore(pydantic): add optional dependency for testing,
 docs minor cleanup

---
 docs/docs/core/data_types.mdx | 18 +++++++-----------
 pyproject.toml                |  7 ++++++-
 2 files changed, 13 insertions(+), 12 deletions(-)

diff --git a/docs/docs/core/data_types.mdx b/docs/docs/core/data_types.mdx
index fd523d8bd..242e07d40 100644
--- a/docs/docs/core/data_types.mdx
+++ b/docs/docs/core/data_types.mdx
@@ -113,12 +113,14 @@ These options define a structured type with named fields, but they differ slight
 - **Dataclass**: A flexible class-based structure, mutable by default, defined using the `@dataclass` decorator.
 - **NamedTuple**: An immutable tuple-based structure, defined using `typing.NamedTuple`.
 - **Pydantic model**: A modern data validation and parsing structure, defined by inheriting from `pydantic.BaseModel`.
+  Make sure you installed the `pydantic` package when using Pydantic model.
 
 For example:
 
 ```python
 from dataclasses import dataclass
 from typing import NamedTuple
+from pydantic import BaseModel
 import datetime
 
 # Using dataclass
@@ -134,17 +136,11 @@ class PersonTuple(NamedTuple):
     last_name: str
     dob: datetime.date
 
-# Using Pydantic (optional dependency)
-try:
-    from pydantic import BaseModel
-    
-    class PersonModel(BaseModel):
-        first_name: str
-        last_name: str
-        dob: datetime.date
-except ImportError:
-    # Pydantic is optional
-    pass
+# Using Pydantic
+class PersonModel(BaseModel):
+    first_name: str
+    last_name: str
+    dob: datetime.date
 ```
 
 All three examples (`Person`, `PersonTuple`, and `PersonModel`) are valid Struct types in CocoIndex, with identical schemas (three fields: `first_name` (Str), `last_name` (Str), `dob` (Date)).
diff --git a/pyproject.toml b/pyproject.toml
index 2f8423c39..6bef9962b 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -70,7 +70,12 @@ lancedb = ["lancedb>=0.25.0"]
 
 # We need to repeat the dependency above to make it available for the `all` feature.
 # Indirect dependencies such as "cocoindex[embeddings]" will not work for local development.
-all = ["sentence-transformers>=3.3.1", "colpali-engine", "lancedb>=0.25.0"]
+all = [
+    "sentence-transformers>=3.3.1",
+    "colpali-engine",
+    "lancedb>=0.25.0",
+    "pydantic>=2.11.9",
+]
 
 [tool.mypy]
 python_version = "3.11"

From 0446338618f4bf6e27e99fb7f7bb8098669707af Mon Sep 17 00:00:00 2001
From: Jiangzhou He <hejiangzhou@gmail.com>
Date: Wed, 1 Oct 2025 09:01:00 -0700
Subject: [PATCH 2/3] docs: more comments

---
 docs/docs/core/data_types.mdx | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/docs/docs/core/data_types.mdx b/docs/docs/core/data_types.mdx
index 242e07d40..4b285e4fa 100644
--- a/docs/docs/core/data_types.mdx
+++ b/docs/docs/core/data_types.mdx
@@ -120,7 +120,7 @@ For example:
 ```python
 from dataclasses import dataclass
 from typing import NamedTuple
-from pydantic import BaseModel
+from pydantic import BaseModel   # requires `pydantic` package to be installed
 import datetime
 
 # Using dataclass

From 8714a6e4c3ee97d9a55133d88222ad24dc5881c3 Mon Sep 17 00:00:00 2001
From: Jiangzhou He <hejiangzhou@gmail.com>
Date: Wed, 1 Oct 2025 09:03:59 -0700
Subject: [PATCH 3/3] chore: add `pydantic` as an optional dependency

---
 pyproject.toml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/pyproject.toml b/pyproject.toml
index 6bef9962b..bb877cd86 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -67,6 +67,7 @@ dev = ["pytest", "pytest-asyncio", "ruff", "mypy", "pre-commit"]
 embeddings = ["sentence-transformers>=3.3.1"]
 colpali = ["colpali-engine"]
 lancedb = ["lancedb>=0.25.0"]
+pydantic = ["pydantic>=2.11.9"]
 
 # We need to repeat the dependency above to make it available for the `all` feature.
 # Indirect dependencies such as "cocoindex[embeddings]" will not work for local development.