feat: improve pydantic 1.x compat (#503)

.github/workflows/python.yml

@@ -94,5 +94,5 @@ jobs:
       run: isort --check --diff --quiet .
     - name: Run tests
       run: pytest -m "not slow" -x -v --durations=30 tests
-    # - name: doctest
-    #  run: pytest --doctest-modules lancedb
+    - name: doctest
+      run: pytest --doctest-modules lancedb

docs/src/guides/tables.md

@@ -84,7 +84,17 @@ A Table is a collection of Records in a LanceDB Database. You can follow along o
     ```
 
     ### From Pydantic Models
-    LanceDB supports to create Apache Arrow Schema from a Pydantic BaseModel via pydantic_to_schema() method.
+    When you create an empty table without data, you must specify the table schema.
+    LanceDB supports creating tables by specifying a pyarrow schema or a specialized
+    pydantic model called `LanceModel`.
+
+    For example, the following Content model specifies a table with 5 columns: 
+    movie_id, vector, genres, title, and imdb_id. When you create a table, you can
+    pass the class as the value of the `schema` parameter to `create_table`. 
+    The `vector` column is a `Vector` type, which is a specialized pydantic type that
+    can be configured with the vector dimensions. It is also important to note that
+    LanceDB only understands subclasses of `lancedb.pydantic.LanceModel` 
+    (which itself derives from `pydantic.BaseModel`).
 
     ```python
     from lancedb.pydantic import Vector, LanceModel

docs/src/python/python.md

@@ -26,6 +26,18 @@ pip install lancedb
 
 ## Embeddings
 
+::: lancedb.embeddings.functions.EmbeddingFunctionRegistry
+
+::: lancedb.embeddings.functions.EmbeddingFunction
+
+::: lancedb.embeddings.functions.TextEmbeddingFunction
+
+::: lancedb.embeddings.functions.SentenceTransformerEmbeddings
+
+::: lancedb.embeddings.functions.OpenAIEmbeddings
+
+::: lancedb.embeddings.functions.OpenClipEmbeddings
+
 ::: lancedb.embeddings.with_embeddings
 
 ## Context

python/lancedb/pydantic.py

@@ -128,7 +128,7 @@ def Vector(
         def validate(cls, v):
             if not isinstance(v, (list, range, np.ndarray)) or len(v) != dim:
                 raise TypeError("A list of numbers or numpy.ndarray is needed")
-            return v
+            return cls(v)
 
         if PYDANTIC_VERSION < (2, 0):
 
@@ -238,27 +238,18 @@ def pydantic_to_schema(model: Type[pydantic.BaseModel]) -> pa.Schema:
     >>> from typing import List, Optional
     >>> import pydantic
     >>> from lancedb.pydantic import pydantic_to_schema
-    ...
-    >>> class InnerModel(pydantic.BaseModel):
-    ...     a: str
-    ...     b: Optional[float]
-    >>>
     >>> class FooModel(pydantic.BaseModel):
     ...     id: int
-    ...     s: Optional[str] = None
+    ...     s: str
     ...     vec: List[float]
     ...     li: List[int]
-    ...     inner: InnerModel
+    ...
     >>> schema = pydantic_to_schema(FooModel)
     >>> assert schema == pa.schema([
     ...     pa.field("id", pa.int64(), False),
-    ...     pa.field("s", pa.utf8(), True),
+    ...     pa.field("s", pa.utf8(), False),
     ...     pa.field("vec", pa.list_(pa.float64()), False),
     ...     pa.field("li", pa.list_(pa.int64()), False),
-    ...     pa.field("inner", pa.struct([
-    ...         pa.field("a", pa.utf8(), False),
-    ...         pa.field("b", pa.float64(), True),
-    ...     ]), False),
     ... ])
     """
     fields = _pydantic_model_to_fields(model)