two version of R2R are here HEAD master

4 files changed, 145 insertions, 0 deletions

diff --git a/.venv/lib/python3.12/site-packages/azure/ai/ml/entities/_indexes/input/__init__.py b/.venv/lib/python3.12/site-packages/azure/ai/ml/entities/_indexes/input/__init__.py
new file mode 100644
index 00000000..fdf8caba
--- /dev/null
+++ b/.venv/lib/python3.12/site-packages/azure/ai/ml/entities/_indexes/input/__init__.py
@@ -0,0 +1,5 @@
+# ---------------------------------------------------------
+# Copyright (c) Microsoft Corporation. All rights reserved.
+# ---------------------------------------------------------
+
+__path__ = __import__("pkgutil").extend_path(__path__, __name__)
diff --git a/.venv/lib/python3.12/site-packages/azure/ai/ml/entities/_indexes/input/_ai_search_config.py b/.venv/lib/python3.12/site-packages/azure/ai/ml/entities/_indexes/input/_ai_search_config.py
new file mode 100644
index 00000000..b2163c40
--- /dev/null
+++ b/.venv/lib/python3.12/site-packages/azure/ai/ml/entities/_indexes/input/_ai_search_config.py
@@ -0,0 +1,31 @@
+# ---------------------------------------------------------
+# Copyright (c) Microsoft Corporation. All rights reserved.
+# ---------------------------------------------------------
+
+# General todo: need to determine which args are required or optional when parsed out into groups like this.
+# General todo: move these to more permanent locations?
+
+# Defines stuff related to the resulting created index, like the index type.
+
+from typing import Optional
+from azure.ai.ml._utils._experimental import experimental
+
+
+@experimental
+class AzureAISearchConfig:
+    """Config class for creating an Azure AI Search index.
+
+    :param index_name: The name of the Azure AI Search index.
+    :type index_name: Optional[str]
+    :param connection_id: The Azure AI Search connection ID.
+    :type connection_id: Optional[str]
+    """
+
+    def __init__(
+        self,
+        *,
+        index_name: Optional[str] = None,
+        connection_id: Optional[str] = None,
+    ) -> None:
+        self.index_name = index_name
+        self.connection_id = connection_id
diff --git a/.venv/lib/python3.12/site-packages/azure/ai/ml/entities/_indexes/input/_index_config.py b/.venv/lib/python3.12/site-packages/azure/ai/ml/entities/_indexes/input/_index_config.py
new file mode 100644
index 00000000..0eec691a
--- /dev/null
+++ b/.venv/lib/python3.12/site-packages/azure/ai/ml/entities/_indexes/input/_index_config.py
@@ -0,0 +1,47 @@
+# ---------------------------------------------------------
+# Copyright (c) Microsoft Corporation. All rights reserved.
+# ---------------------------------------------------------
+
+from typing import Optional
+
+
+class IndexConfig:  # pylint: disable=too-many-instance-attributes
+    """Convenience class that contains all config values that for index creation that are
+    NOT specific to the index source data or the created index type. Meant for internal use only
+    to simplify function headers. The user-entry point is a function that
+    should still contain all the fields in this class as individual function parameters.
+
+    Params omitted for brevity and to avoid maintaining duplicate docs. See index creation function
+    for actual parameter descriptions.
+    """
+
+    def __init__(
+        self,
+        *,
+        output_index_name: str,
+        vector_store: str,
+        data_source_url: Optional[str] = None,
+        chunk_size: Optional[int] = None,
+        chunk_overlap: Optional[int] = None,
+        input_glob: Optional[str] = None,
+        max_sample_files: Optional[int] = None,
+        chunk_prepend_summary: Optional[bool] = None,
+        document_path_replacement_regex: Optional[str] = None,
+        embeddings_container: Optional[str] = None,
+        embeddings_model: str,
+        aoai_connection_id: str,
+        _dry_run: bool = False
+    ):
+        self.output_index_name = output_index_name
+        self.vector_store = vector_store
+        self.data_source_url = data_source_url
+        self.chunk_size = chunk_size
+        self.chunk_overlap = chunk_overlap
+        self.input_glob = input_glob
+        self.max_sample_files = max_sample_files
+        self.chunk_prepend_summary = chunk_prepend_summary
+        self.document_path_replacement_regex = document_path_replacement_regex
+        self.embeddings_container = embeddings_container
+        self.embeddings_model = embeddings_model
+        self.aoai_connection_id = aoai_connection_id
+        self._dry_run = _dry_run
diff --git a/.venv/lib/python3.12/site-packages/azure/ai/ml/entities/_indexes/input/_index_data_source.py b/.venv/lib/python3.12/site-packages/azure/ai/ml/entities/_indexes/input/_index_data_source.py
new file mode 100644
index 00000000..92b62b6b
--- /dev/null
+++ b/.venv/lib/python3.12/site-packages/azure/ai/ml/entities/_indexes/input/_index_data_source.py
@@ -0,0 +1,62 @@
+# ---------------------------------------------------------
+# Copyright (c) Microsoft Corporation. All rights reserved.
+# ---------------------------------------------------------
+from typing import Union
+
+from azure.ai.ml._utils._experimental import experimental
+from azure.ai.ml.entities._inputs_outputs import Input
+from azure.ai.ml.constants._common import IndexInputType
+
+
+# General todo: need to determine which args are required or optional when parsed out into groups like this.
+# General todo: move these to more permanent locations?
+
+
+# Defines stuff related to supplying inputs for an index AKA the base data.
+@experimental
+class IndexDataSource:
+    """Base class for configs that define data that will be processed into an ML index.
+    This class should not be instantiated directly. Use one of its child classes instead.
+
+    :param input_type: A type enum describing the source of the index. Used to avoid
+        direct type checking.
+    :type input_type: Union[str, ~azure.ai.ml.constants._common.IndexInputType]
+    """
+
+    def __init__(self, *, input_type: Union[str, IndexInputType]):
+        self.input_type = input_type
+
+
+# Field bundle for creating an index from files located in a Git repo.
+# TODO Does git_url need to specifically be an SSH or HTTPS style link?
+# TODO What is git connection id?
+@experimental
+class GitSource(IndexDataSource):
+    """Config class for creating an ML index from files located in a git repository.
+
+    :param url: A link to the repository to use.
+    :type url: str
+    :param branch_name: The name of the branch to use from the target repository.
+    :type branch_name: str
+    :param connection_id: The connection ID for GitHub
+    :type connection_id: str
+    """
+
+    def __init__(self, *, url: str, branch_name: str, connection_id: str):
+        self.url = url
+        self.branch_name = branch_name
+        self.connection_id = connection_id
+        super().__init__(input_type=IndexInputType.GIT)
+
+
+@experimental
+class LocalSource(IndexDataSource):
+    """Config class for creating an ML index from a collection of local files.
+
+    :param input_data: An input object describing the local location of index source files.
+    :type input_data: ~azure.ai.ml.Input
+    """
+
+    def __init__(self, *, input_data: str):  # todo Make sure type of input_data is correct
+        self.input_data = Input(type="uri_folder", path=input_data)
+        super().__init__(input_type=IndexInputType.LOCAL)