chore(pydantic): add optional dependency for testing, docs minor cleanup (#1073)

* chore(pydantic): add optional dependency for testing, docs minor cleanup

* docs: more comments

* chore: add `pydantic` as an optional dependency

Author: georgeh0

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   # requires `pydantic` package to be installed
 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)).

pyproject.toml

@@ -67,10 +67,16 @@ 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.
-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"