Add Geopandas.GeoDataFrame Document Loader (langchain-ai#3817)

Work in Progress.
WIP
Not ready...

Adds Document Loader support for
[Geopandas.GeoDataFrames](https://geopandas.org/)

Example:
- [x] stub out `GeoDataFrameLoader` class
- [x] stub out integration tests
- [ ] Experiment with different geometry text representations
- [ ] Verify CRS is successfully added in metadata
- [ ] Test effectiveness of searches on geometries
- [ ] Test with different geometry types (point, line, polygon with
multi-variants).
- [ ] Add documentation

---------

Co-authored-by: Lance Martin <[email protected]>
Co-authored-by: Bagatur <[email protected]>
Co-authored-by: Lance Martin <[email protected]>

langchain/document_loaders/__init__.py

@@ -51,6 +51,7 @@
 from langchain.document_loaders.figma import FigmaFileLoader
 from langchain.document_loaders.gcs_directory import GCSDirectoryLoader
 from langchain.document_loaders.gcs_file import GCSFileLoader
+from langchain.document_loaders.geodataframe import GeoDataFrameLoader
 from langchain.document_loaders.git import GitLoader
 from langchain.document_loaders.gitbook import GitbookLoader
 from langchain.document_loaders.github import GitHubIssuesLoader
@@ -200,6 +201,7 @@
     "FileSystemBlobLoader",
     "GCSDirectoryLoader",
     "GCSFileLoader",
+    "GeoDataFrameLoader",
     "GitHubIssuesLoader",
     "GitLoader",
     "GitbookLoader",

langchain/document_loaders/geodataframe.py

@@ -0,0 +1,49 @@
+"""Load from Dataframe object"""
+from typing import Any, Iterator, List
+
+from langchain.docstore.document import Document
+from langchain.document_loaders.base import BaseLoader
+
+
+class GeoDataFrameLoader(BaseLoader):
+    """Load geopandas Dataframe."""
+
+    def __init__(self, data_frame: Any, page_content_column: str = "geometry"):
+        """Initialize with geopandas Dataframe.
+
+        Args:
+            data_frame: geopandas DataFrame object.
+            page_content_column: Name of the column containing the page content.
+              Defaults to "geometry".
+        """
+
+        try:
+            import geopandas as gpd
+        except ImportError:
+            raise ValueError(
+                "geopandas package not found, please install it with "
+                "`pip install geopandas`"
+            )
+
+        if not isinstance(data_frame, gpd.GeoDataFrame):
+            raise ValueError(
+                f"Expected data_frame to be a gpd.GeoDataFrame, got {type(data_frame)}"
+            )
+
+        self.data_frame = data_frame
+        self.page_content_column = page_content_column
+
+    def lazy_load(self) -> Iterator[Document]:
+        """Lazy load records from dataframe."""
+
+        for _, row in self.data_frame.iterrows():
+            text = row[self.page_content_column]
+            metadata = row.to_dict()
+            metadata.pop(self.page_content_column)
+            # Enforce str since shapely Point objects
+            # geometry type used in GeoPandas) are not strings
+            yield Document(page_content=str(text), metadata=metadata)
+
+    def load(self) -> List[Document]:
+        """Load full dataframe."""
+        return list(self.lazy_load())