corvic-engine 0.3.0rc56__tar.gz → 0.3.0rc58__tar.gz

{corvic_engine-0.3.0rc56 → corvic_engine-0.3.0rc58}/Cargo.lock

@@ -22,7 +22,7 @@ checksum = "baf1de4339761588bc0619e3cbc0120ee582ebb74b53b4efbf79117bd2da40fd"
 
 [[package]]
 name = "corvic-engine"
-version = "0.3.0-rc.56"
+version = "0.3.0-rc.58"
 dependencies = [
  "numpy",
  "pyo3",
@@ -63,7 +63,7 @@ checksum = "48c757948c5ede0e46177b7add2e67155f70e33c07fea8284df6576da70b3719"
 
 [[package]]
 name = "engine-walk"
-version = "0.3.0-rc.56"
+version = "0.3.0-rc.58"
 dependencies = [
  "version_check",
 ]

{corvic_engine-0.3.0rc56 → corvic_engine-0.3.0rc58}/Cargo.toml

@@ -3,7 +3,7 @@ resolver = "2"
 members = ["python"]
 
 [workspace.package]
-version = "0.3.0-rc.56"
+version = "0.3.0-rc.58"
 edition = "2021"
 publish = false
 

{corvic_engine-0.3.0rc56 → corvic_engine-0.3.0rc58}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: corvic-engine
-Version: 0.3.0rc56
+Version: 0.3.0rc58
 Classifier: Environment :: Console
 Classifier: License :: Other/Proprietary License
 Classifier: Programming Language :: Python :: Implementation :: CPython

{corvic_engine-0.3.0rc56 → corvic_engine-0.3.0rc58}/pyproject.toml

@@ -20,7 +20,7 @@ authors = [
 ]
 readme = "README.md"
 description = "Seamless embedding generation and retrieval."
-version = "0.3.0-rc.56" # sync this with tool.poetry.version below
+version = "0.3.0-rc.58" # sync this with tool.poetry.version below
 
 # TODO(ddn): Pull dependencies from tool.poetry.dependencies. We use maturin as
 # the build system but poetry for the development environment.
@@ -74,7 +74,7 @@ packages = [
 ]
 description = ""
 authors = []
-version = "0.3.0-rc.56"
+version = "0.3.0-rc.58"
 
 [tool.poetry.scripts]
 check = "corvic_check.cli:main"

{corvic_engine-0.3.0rc56 → corvic_engine-0.3.0rc58}/python/corvic/model/_completion_model.py

@@ -121,6 +121,10 @@ class CompletionModel(
             )
         return None
 
+    @property
+    def is_validated(self) -> bool:
+        return self.proto_self.is_validated
+
     @classmethod
     def create(
         cls,
@@ -213,3 +217,8 @@ class CompletionModel(
         proto_self = copy.deepcopy(self.proto_self)
         proto_self.last_validation_time.FromDatetime(last_validation_time)
         return CompletionModel(self.client, proto_self)
+
+    def with_is_validated(self, *, is_validated: bool) -> CompletionModel:
+        proto_self = copy.deepcopy(self.proto_self)
+        proto_self.is_validated = is_validated
+        return CompletionModel(self.client, proto_self)

{corvic_engine-0.3.0rc56 → corvic_engine-0.3.0rc58}/python/corvic/model/_proto_orm_convert.py

@@ -225,6 +225,7 @@ def completion_model_orm_to_proto(
         last_validation_time=timestamp_orm_to_proto(
             completion_model_orm.last_validation_time
         ),
+        is_validated=completion_model_orm.is_validated,
     )
 
 
@@ -579,6 +580,7 @@ def completion_model_proto_to_orm(
         parameters=proto_obj.parameters,
         secret_api_key=proto_obj.secret_api_key,
         last_validation_time=proto_obj.last_validation_time.ToDatetime(),
+        is_validated=proto_obj.is_validated,
     )
     return add_orm_org_mixin_to_session(
         orm_obj, proto_obj, orm.CompletionModelID, session

{corvic_engine-0.3.0rc56 → corvic_engine-0.3.0rc58}/python/corvic/model/_source.py

@@ -187,6 +187,14 @@ class Source(BelongsToRoomModel[SourceID, models_pb2.Source, orm.Source]):
             proto_self=proto_self,
         )
 
+    def with_property_table(self, props: Table) -> Self:
+        proto_self = copy.deepcopy(self.proto_self)
+        proto_self.prop_table_op_graph.CopyFrom(props.op_graph.to_proto())
+        return self.__class__(
+            self.client,
+            proto_self=proto_self,
+        )
+
     @classmethod
     def orm_load_options(cls) -> list[LoaderOption]:
         return [

{corvic_engine-0.3.0rc56 → corvic_engine-0.3.0rc58}/python/corvic/model/_space.py

@@ -836,13 +836,20 @@ class TabularSpace(Space):
                     pa.string(),
                 )
 
-            op = (
-                op.concat_list(
+            if len(embedding_column_tmp_names):
+                op = op.concat_list(
                     column_names=embedding_column_tmp_names,
                     concat_list_column_name=embedding_column_tmp_name,
+                ).and_then(reduce_dimension)
+            else:
+                op = op.add_literal_column(
+                    column_name=embedding_column_tmp_name,
+                    literal=[],
+                    dtype=pa.large_list(pa.float32()),
+                    ftype=op_graph.feature_type.embedding(),
                 )
-                .and_then(reduce_dimension)
-                .and_then(select_columns)
+            op = (
+                op.and_then(select_columns)
                 .and_then(update_feature_types)
                 .and_then(rename_columns)
                 .and_then(add_literal_column)

{corvic_engine-0.3.0rc56 → corvic_engine-0.3.0rc58}/python/corvic/op_graph/_schema.py

@@ -2,8 +2,6 @@
 
 from __future__ import annotations
 
-from collections.abc import Sequence
-
 import polars as pl
 import pyarrow as pa
 
@@ -14,7 +12,7 @@ from corvic.op_graph.feature_types import FeatureType
 
 def _infer_possible_feature_types(
     data_type: pa.DataType,
-) -> Sequence[FeatureType]:
+) -> list[FeatureType]:
     if pa.types.is_integer(data_type):
         # TODO(thunt): Add multi-categorical in future versions
         return [
@@ -168,6 +166,6 @@ class Field:
     def rename(self, new_name: str) -> Field:
         return Field(new_name, self.dtype, self.ftype)
 
-    def possible_feature_types(self) -> Sequence[FeatureType]:
+    def possible_feature_types(self) -> list[FeatureType]:
         """Infer possible feature types given the data type."""
         return _infer_possible_feature_types(self.dtype)

{corvic_engine-0.3.0rc56 → corvic_engine-0.3.0rc58}/python/corvic/op_graph/_transformations.py

@@ -142,11 +142,11 @@ def replace_op_source(  # noqa: C901
         case op.AddLiteralColumn():
             new_proto = root_op.to_proto()
             new_proto.add_literal_column.source.CopyFrom(new_source.to_proto())
-            return Ok(op.from_proto(new_proto))
+            return Ok(op.from_proto(new_proto, skip_validate=True))
         case op.CombineColumns():
             new_proto = root_op.to_proto()
             new_proto.combine_columns.source.CopyFrom(new_source.to_proto())
-            return Ok(op.from_proto(new_proto))
+            return Ok(op.from_proto(new_proto, skip_validate=True))
         case op.EmbedColumn():
             return new_source.embed_column(
                 column_name=root_op.column_name,
@@ -183,7 +183,7 @@ def replace_op_source(  # noqa: C901
         case op.TruncateList():
             new_proto = root_op.to_proto()
             new_proto.truncate_list.source.CopyFrom(new_source.to_proto())
-            return Ok(op.from_proto(new_proto))
+            return Ok(op.from_proto(new_proto, skip_validate=True))
         case op.Union():
             new_tables = list[op.Op]()
             for table in root_op.sources():

{corvic_engine-0.3.0rc56 → corvic_engine-0.3.0rc58}/python/corvic/op_graph/ops.py

@@ -59,7 +59,7 @@ from corvic.op_graph.row_filters import RowFilter
 from corvic.op_graph.row_filters import from_proto as row_filters_from_proto
 from corvic.op_graph.sample_strategy import SampleStrategy
 from corvic.op_graph.sample_strategy import from_proto as sample_strategy_from_proto
-from corvic.pa_scalar import PyValue, from_value, to_value
+from corvic.pa_scalar import PyValue, Scalar, from_value, to_value
 from corvic.proto_wrapper import OneofProtoWrapper
 from corvic.result import InternalError, InvalidArgumentError, Ok
 from corvic_generated.algorithm.graph.v1 import graph_pb2
@@ -1275,7 +1275,7 @@ class _Base(OneofProtoWrapper[table_pb2.TableComputeOp], ABC):
     def add_literal_column(
         self,
         column_name: str,
-        literal: struct_pb2.Value | float | str | bool,
+        literal: struct_pb2.Value | Scalar | PyValue,
         dtype: pa.DataType,
         ftype: FeatureType | None = None,
     ) -> Ok[AddLiteralColumn] | InvalidArgumentError:
@@ -1313,8 +1313,13 @@ class _Base(OneofProtoWrapper[table_pb2.TableComputeOp], ABC):
         separator: str,
     ) -> Ok[CombineColumns] | InvalidArgumentError:
         for col in column_names:
-            if not self.schema.has_column(col):
+            field = self.schema.get(col)
+            if not field:
                 return InvalidArgumentError("no column with given name", given_name=col)
+            if pa.types.is_binary(field.dtype) | pa.types.is_large_binary(field.dtype):
+                return InvalidArgumentError(
+                    "cannot concat binary columns", given_name=col
+                )
 
         if self.schema.has_column(combined_column_name):
             return InvalidArgumentError("name given for combined column already exists")
@@ -1698,6 +1703,9 @@ class _Base(OneofProtoWrapper[table_pb2.TableComputeOp], ABC):
         Returns:
             An AddDecisionTreeSummaryOp.
         """
+        if max_depth < 0:
+            return InvalidArgumentError("max_depth must be strictly positive")
+
         return Ok(
             from_proto(
                 table_pb2.AddDecisionTreeSummaryOp(
@@ -2938,16 +2946,26 @@ def _make_schema_for_combine_columns(op: CombineColumns):
                 if column.ftype != ftype:
                     ftype = feature_type.unknown()
 
-            dtype = (
-                pl.DataFrame(schema=schema.to_polars())
-                .with_columns(
-                    pl.concat_list(*op.column_names).alias(op.combined_column_name)
+            if op.column_names:
+                dtype = (
+                    pl.DataFrame(schema=schema.to_polars())
+                    .with_columns(
+                        pl.concat_list(*op.column_names).alias(op.combined_column_name)
+                    )
+                    .to_arrow()
+                    .schema.field(op.combined_column_name)
+                    .type
+                )
+            else:
+                dtype = (
+                    pl.DataFrame(schema=schema.to_polars())
+                    .with_columns(
+                        pl.Series(op.combined_column_name, [], pl.List(pl.Float32))
+                    )
+                    .to_arrow()
+                    .schema.field(op.combined_column_name)
+                    .type
                 )
-                .to_arrow()
-                .schema.field(op.combined_column_name)
-                .type
-            )
-
     return Schema(
         [
             *op.source.schema,

{corvic_engine-0.3.0rc56 → corvic_engine-0.3.0rc58}/python/corvic/orm/__init__.py

@@ -381,6 +381,7 @@ class CompletionModel(SoftDeleteMixin, BelongsToOrgMixin, Base, kw_only=True):
         server_default=None,
         default=None,
     )
+    is_validated: sa_orm.Mapped[bool] = sa_orm.mapped_column(default=False)
 
     @property
     def model_key(self):

{corvic_engine-0.3.0rc56 → corvic_engine-0.3.0rc58}/python/corvic/orm/ids.py

@@ -15,6 +15,8 @@ from corvic.result import Ok
 
 ORMIdentifier = TypeVar("ORMIdentifier")
 
+_MAX_INT_ID = 2**63 - 1
+
 
 class BaseID(Generic[ORMIdentifier], abc.ABC):
     """Base class for all API object identifiers."""
@@ -72,7 +74,10 @@ class BaseIDFromInt(BaseID[int]):
         if not self._value:
             return InvalidORMIdentifierError("id was empty")
         try:
-            return Ok(int(self._value))
+            value = int(self._value)
+            if value > _MAX_INT_ID:
+                return InvalidORMIdentifierError("id too large", id_value=self._value)
+            return Ok(value)
         except ValueError:
             return InvalidORMIdentifierError(
                 "conversion to orm failed", id_value=self._value

{corvic_engine-0.3.0rc56 → corvic_engine-0.3.0rc58}/python/corvic/system/in_memory_executor.py

@@ -12,6 +12,7 @@ from typing import Any, Final, cast
 
 import numpy as np
 import polars as pl
+import polars.selectors as cs
 import pyarrow as pa
 import pyarrow.parquet as pq
 import structlog
@@ -778,9 +779,14 @@ class InMemoryExecutor(OpGraphExecutor):
                 )
 
             case op_graph.ConcatList():
-                result_df = source_df.with_columns(
-                    pl.concat_list(*op.column_names).alias(op.combined_column_name)
-                )
+                if op.column_names:
+                    result_df = source_df.with_columns(
+                        pl.concat_list(*op.column_names).alias(op.combined_column_name)
+                    )
+                else:
+                    result_df = source_df.with_columns(
+                        pl.Series(op.combined_column_name, [])
+                    )
 
         return Ok(_SchemaAndBatches.from_dataframe(result_df, source_batches.metrics))
 
@@ -1394,17 +1400,41 @@ class InMemoryExecutor(OpGraphExecutor):
                 pass
             case err:
                 return err
+
         df_input = _as_df(source_batches)
+        dataframe = df_input[list({*op.feature_column_names, op.label_column_name})]
+        boolean_columns = [
+            name
+            for name, dtype in dataframe.schema.items()
+            if dtype == pl.Boolean() and name in op.feature_column_names
+        ]
 
-        features = df_input[op.feature_column_names]
-        classes = df_input[op.label_column_name]
+        # Drop Nan and Null and infinite rows as not supported by decision tree
+        dataframe = dataframe.with_columns(
+            *[pl.col(col).cast(pl.Float32) for col in op.feature_column_names]
+        )
+        dataframe = dataframe.drop_nans().drop_nulls()
+        try:
+            # is_infinite is not implemented for all datatypes
+            dataframe = dataframe.filter(~pl.any_horizontal(cs.numeric().is_infinite()))
+        except pl.exceptions.InvalidOperationError as err:
+            return InvalidArgumentError.from_(err)
+
+        if not len(dataframe):
+            return InvalidArgumentError(
+                "a minimum of 1 sample is required by DecisionTreeClassifier"
+            )
+        features = dataframe[op.feature_column_names]
+        classes = dataframe[op.label_column_name]
         max_depth = op.max_depth
 
-        binary_columns = [
-            name for name, dtype in features.schema.items() if dtype == pl.Boolean()
-        ]
-
         from sklearn.tree import DecisionTreeClassifier, export_graphviz, export_text
+        from sklearn.utils.multiclass import check_classification_targets
+
+        try:
+            check_classification_targets(classes)
+        except ValueError as err:
+            return InvalidArgumentError.from_(err)
 
         decision_tree = DecisionTreeClassifier(random_state=0, max_depth=max_depth)
         try:
@@ -1426,11 +1456,11 @@ class InMemoryExecutor(OpGraphExecutor):
             max_depth=max_depth,
         )
 
-        for binary_column in binary_columns:
+        for boolean_column in boolean_columns:
             tree_str = tree_str.replace(
-                f"{binary_column} <= 0.50", f"NOT {binary_column}"
+                f"{boolean_column} <= 0.50", f"NOT {boolean_column}"
             )
-            tree_str = tree_str.replace(f"{binary_column} >  0.50", binary_column)
+            tree_str = tree_str.replace(f"{boolean_column} >  0.50", boolean_column)
 
         metrics = source_batches.metrics.copy()
         metrics[op.output_metric_key] = table_pb2.DecisionTreeSummary(

{corvic_engine-0.3.0rc56 → corvic_engine-0.3.0rc58}/python/corvic/table/table.py

@@ -412,12 +412,18 @@ class Table:
             case _:
                 return more_itertools.flatten(map(cls._get_staging_ops, op.sources()))
 
-    def head(self) -> InvalidArgumentError | Ok[Table]:
-        """Get up to the first 10 rows of the table."""
-        return self.op_graph.limit_rows(num_rows=10).map(
+    def head(self, num_rows: int = 10) -> InvalidArgumentError | Ok[Table]:
+        """Get the first `num_rows` rows of the table."""
+        return self.op_graph.limit_rows(num_rows=num_rows).map(
             lambda op: Table(self.client, op)
         )
 
+    def sample_rows(self, num_rows: int = 10) -> InvalidArgumentError | Ok[Table]:
+        """Get a sample of `num_rows` rows of the table."""
+        return self.op_graph.sample_rows(
+            sample_strategy=op_graph.sample_strategy.uniform_random(), num_rows=num_rows
+        ).map(lambda op: Table(self.client, op))
+
     def distinct_rows(self) -> Table:
         return Table(
             self.client,

{corvic_engine-0.3.0rc56 → corvic_engine-0.3.0rc58}/python/corvic_generated/model/v1alpha/models_pb2.py

@@ -22,7 +22,7 @@ from corvic_generated.status.v1 import event_pb2 as corvic_dot_status_dot_v1_dot
 from google.protobuf import timestamp_pb2 as google_dot_protobuf_dot_timestamp__pb2
 
 
-DESCRIPTOR = _descriptor_pool.Default().AddSerializedFile(b'\n!corvic/model/v1alpha/models.proto\x12\x14\x63orvic.model.v1alpha\x1a\x19\x63orvic/orm/v1/agent.proto\x1a$corvic/orm/v1/completion_model.proto\x1a corvic/orm/v1/feature_view.proto\x1a\x1c\x63orvic/orm/v1/pipeline.proto\x1a\x19\x63orvic/orm/v1/space.proto\x1a\x19\x63orvic/orm/v1/table.proto\x1a\x1c\x63orvic/status/v1/event.proto\x1a\x1fgoogle/protobuf/timestamp.proto\"\x90\x01\n\x04Room\x12\x0e\n\x02id\x18\x01 \x01(\tR\x02id\x12\x12\n\x04name\x18\x02 \x01(\tR\x04name\x12\x15\n\x06org_id\x18\x03 \x01(\tR\x05orgId\x12>\n\ncreated_at\x18\x04 \x01(\x0b\x32\x1a.google.protobuf.TimestampH\x00R\tcreatedAt\x88\x01\x01\x42\r\n\x0b_created_at\"\xd8\x03\n\x08Resource\x12\x0e\n\x02id\x18\x01 \x01(\tR\x02id\x12\x12\n\x04name\x18\x02 \x01(\tR\x04name\x12 \n\x0b\x64\x65scription\x18\x03 \x01(\tR\x0b\x64\x65scription\x12\x1b\n\tmime_type\x18\x04 \x01(\tR\x08mimeType\x12\x10\n\x03url\x18\x05 \x01(\tR\x03url\x12\x12\n\x04size\x18\x06 \x01(\x04R\x04size\x12\x10\n\x03md5\x18\x07 \x01(\tR\x03md5\x12#\n\roriginal_path\x18\x08 \x01(\tR\x0coriginalPath\x12\x17\n\x07room_id\x18\t \x01(\tR\x06roomId\x12\x15\n\x06org_id\x18\x0b \x01(\tR\x05orgId\x12\x1f\n\x0bpipeline_id\x18\r \x01(\tR\npipelineId\x12.\n\x13pipeline_input_name\x18\x0f \x01(\tR\x11pipelineInputName\x12<\n\rrecent_events\x18\x0e \x03(\x0b\x32\x17.corvic.status.v1.EventR\x0crecentEvents\x12>\n\ncreated_at\x18\x0c \x01(\x0b\x32\x1a.google.protobuf.TimestampH\x00R\tcreatedAt\x88\x01\x01\x42\r\n\x0b_created_at\"\xfc\x02\n\x06Source\x12\x0e\n\x02id\x18\x01 \x01(\tR\x02id\x12\x12\n\x04name\x18\x02 \x01(\tR\x04name\x12\x43\n\x0etable_op_graph\x18\x03 \x01(\x0b\x32\x1d.corvic.orm.v1.TableComputeOpR\x0ctableOpGraph\x12\x17\n\x07room_id\x18\x04 \x01(\tR\x06roomId\x12\x15\n\x06org_id\x18\x06 \x01(\tR\x05orgId\x12\x1f\n\x0bpipeline_id\x18\x08 \x01(\tR\npipelineId\x12>\n\ncreated_at\x18\x07 \x01(\x0b\x32\x1a.google.protobuf.TimestampH\x00R\tcreatedAt\x88\x01\x01\x12Q\n\x13prop_table_op_graph\x18\t \x01(\x0b\x32\x1d.corvic.orm.v1.TableComputeOpH\x01R\x10propTableOpGraph\x88\x01\x01\x42\r\n\x0b_created_atB\x16\n\x14_prop_table_op_graph\"\xe9\x03\n\x08Pipeline\x12\x0e\n\x02id\x18\x01 \x01(\tR\x02id\x12\x12\n\x04name\x18\x02 \x01(\tR\x04name\x12 \n\x0b\x64\x65scription\x18\t \x01(\tR\x0b\x64\x65scription\x12\x17\n\x07room_id\x18\x03 \x01(\tR\x06roomId\x12X\n\x0esource_outputs\x18\x05 \x03(\x0b\x32\x31.corvic.model.v1alpha.Pipeline.SourceOutputsEntryR\rsourceOutputs\x12^\n\x17pipeline_transformation\x18\x06 \x01(\x0b\x32%.corvic.orm.v1.PipelineTransformationR\x16pipelineTransformation\x12\x15\n\x06org_id\x18\x07 \x01(\tR\x05orgId\x12>\n\ncreated_at\x18\x08 \x01(\x0b\x32\x1a.google.protobuf.TimestampH\x00R\tcreatedAt\x88\x01\x01\x1a^\n\x12SourceOutputsEntry\x12\x10\n\x03key\x18\x01 \x01(\tR\x03key\x12\x32\n\x05value\x18\x02 \x01(\x0b\x32\x1c.corvic.model.v1alpha.SourceR\x05value:\x02\x38\x01\x42\r\n\x0b_created_at\"\xca\x02\n\x11\x46\x65\x61tureViewSource\x12\x0e\n\x02id\x18\x01 \x01(\tR\x02id\x12\x34\n\x06source\x18\x02 \x01(\x0b\x32\x1c.corvic.model.v1alpha.SourceR\x06source\x12\x43\n\x0etable_op_graph\x18\x03 \x01(\x0b\x32\x1d.corvic.orm.v1.TableComputeOpR\x0ctableOpGraph\x12+\n\x11\x64rop_disconnected\x18\x04 \x01(\x08R\x10\x64ropDisconnected\x12\x15\n\x06org_id\x18\x05 \x01(\tR\x05orgId\x12>\n\ncreated_at\x18\x06 \x01(\x0b\x32\x1a.google.protobuf.TimestampH\x00R\tcreatedAt\x88\x01\x01\x12\x17\n\x07room_id\x18\x07 \x01(\tR\x06roomIdB\r\n\x0b_created_at\"\x9c\x03\n\x0b\x46\x65\x61tureView\x12\x0e\n\x02id\x18\x01 \x01(\tR\x02id\x12\x12\n\x04name\x18\x02 \x01(\tR\x04name\x12 \n\x0b\x64\x65scription\x18\x03 \x01(\tR\x0b\x64\x65scription\x12\x17\n\x07room_id\x18\x04 \x01(\tR\x06roomId\x12P\n\x13\x66\x65\x61ture_view_output\x18\x05 \x01(\x0b\x32 .corvic.orm.v1.FeatureViewOutputR\x11\x66\x65\x61tureViewOutput\x12Y\n\x14\x66\x65\x61ture_view_sources\x18\x06 \x03(\x0b\x32\'.corvic.model.v1alpha.FeatureViewSourceR\x12\x66\x65\x61tureViewSources\x12\x1b\n\tspace_ids\x18\x07 \x03(\tR\x08spaceIds\x12\x15\n\x06org_id\x18\x08 \x01(\tR\x05orgId\x12>\n\ncreated_at\x18\t \x01(\x0b\x32\x1a.google.protobuf.TimestampH\x00R\tcreatedAt\x88\x01\x01\x42\r\n\x0b_created_at\"\xfa\x02\n\x05Space\x12\x0e\n\x02id\x18\x01 \x01(\tR\x02id\x12\x12\n\x04name\x18\x02 \x01(\tR\x04name\x12 \n\x0b\x64\x65scription\x18\x03 \x01(\tR\x0b\x64\x65scription\x12\x17\n\x07room_id\x18\x04 \x01(\tR\x06roomId\x12I\n\x10space_parameters\x18\x05 \x01(\x0b\x32\x1e.corvic.orm.v1.SpaceParametersR\x0fspaceParameters\x12\x44\n\x0c\x66\x65\x61ture_view\x18\x06 \x01(\x0b\x32!.corvic.model.v1alpha.FeatureViewR\x0b\x66\x65\x61tureView\x12\x1b\n\tauto_sync\x18\t \x01(\x08R\x08\x61utoSync\x12\x15\n\x06org_id\x18\x07 \x01(\tR\x05orgId\x12>\n\ncreated_at\x18\x08 \x01(\x0b\x32\x1a.google.protobuf.TimestampH\x00R\tcreatedAt\x88\x01\x01\x42\r\n\x0b_created_at\"\x85\x02\n\x05\x41gent\x12\x0e\n\x02id\x18\x01 \x01(\tR\x02id\x12\x12\n\x04name\x18\x02 \x01(\tR\x04name\x12\x17\n\x07room_id\x18\x03 \x01(\tR\x06roomId\x12I\n\x10\x61gent_parameters\x18\x04 \x01(\x0b\x32\x1e.corvic.orm.v1.AgentParametersR\x0f\x61gentParameters\x12\x15\n\x06org_id\x18\x05 \x01(\tR\x05orgId\x12>\n\ncreated_at\x18\t \x01(\x0b\x32\x1a.google.protobuf.TimestampH\x00R\tcreatedAt\x88\x01\x01\x42\r\n\x0b_created_atJ\x04\x08\x06\x10\x07R\x08messages\"\x99\x03\n\x0f\x43ompletionModel\x12\x0e\n\x02id\x18\x01 \x01(\tR\x02id\x12\x12\n\x04name\x18\x02 \x01(\tR\x04name\x12 \n\x0b\x64\x65scription\x18\x03 \x01(\tR\x0b\x64\x65scription\x12\x15\n\x06org_id\x18\x04 \x01(\tR\x05orgId\x12H\n\nparameters\x18\x05 \x01(\x0b\x32(.corvic.orm.v1.CompletionModelParametersR\nparameters\x12$\n\x0esecret_api_key\x18\x06 \x01(\tR\x0csecretApiKey\x12>\n\ncreated_at\x18\x07 \x01(\x0b\x32\x1a.google.protobuf.TimestampH\x00R\tcreatedAt\x88\x01\x01\x12Q\n\x14last_validation_time\x18\x08 \x01(\x0b\x32\x1a.google.protobuf.TimestampH\x01R\x12lastValidationTime\x88\x01\x01\x42\r\n\x0b_created_atB\x17\n\x15_last_validation_timeb\x06proto3')
+DESCRIPTOR = _descriptor_pool.Default().AddSerializedFile(b'\n!corvic/model/v1alpha/models.proto\x12\x14\x63orvic.model.v1alpha\x1a\x19\x63orvic/orm/v1/agent.proto\x1a$corvic/orm/v1/completion_model.proto\x1a corvic/orm/v1/feature_view.proto\x1a\x1c\x63orvic/orm/v1/pipeline.proto\x1a\x19\x63orvic/orm/v1/space.proto\x1a\x19\x63orvic/orm/v1/table.proto\x1a\x1c\x63orvic/status/v1/event.proto\x1a\x1fgoogle/protobuf/timestamp.proto\"\x90\x01\n\x04Room\x12\x0e\n\x02id\x18\x01 \x01(\tR\x02id\x12\x12\n\x04name\x18\x02 \x01(\tR\x04name\x12\x15\n\x06org_id\x18\x03 \x01(\tR\x05orgId\x12>\n\ncreated_at\x18\x04 \x01(\x0b\x32\x1a.google.protobuf.TimestampH\x00R\tcreatedAt\x88\x01\x01\x42\r\n\x0b_created_at\"\xd8\x03\n\x08Resource\x12\x0e\n\x02id\x18\x01 \x01(\tR\x02id\x12\x12\n\x04name\x18\x02 \x01(\tR\x04name\x12 \n\x0b\x64\x65scription\x18\x03 \x01(\tR\x0b\x64\x65scription\x12\x1b\n\tmime_type\x18\x04 \x01(\tR\x08mimeType\x12\x10\n\x03url\x18\x05 \x01(\tR\x03url\x12\x12\n\x04size\x18\x06 \x01(\x04R\x04size\x12\x10\n\x03md5\x18\x07 \x01(\tR\x03md5\x12#\n\roriginal_path\x18\x08 \x01(\tR\x0coriginalPath\x12\x17\n\x07room_id\x18\t \x01(\tR\x06roomId\x12\x15\n\x06org_id\x18\x0b \x01(\tR\x05orgId\x12\x1f\n\x0bpipeline_id\x18\r \x01(\tR\npipelineId\x12.\n\x13pipeline_input_name\x18\x0f \x01(\tR\x11pipelineInputName\x12<\n\rrecent_events\x18\x0e \x03(\x0b\x32\x17.corvic.status.v1.EventR\x0crecentEvents\x12>\n\ncreated_at\x18\x0c \x01(\x0b\x32\x1a.google.protobuf.TimestampH\x00R\tcreatedAt\x88\x01\x01\x42\r\n\x0b_created_at\"\xfc\x02\n\x06Source\x12\x0e\n\x02id\x18\x01 \x01(\tR\x02id\x12\x12\n\x04name\x18\x02 \x01(\tR\x04name\x12\x43\n\x0etable_op_graph\x18\x03 \x01(\x0b\x32\x1d.corvic.orm.v1.TableComputeOpR\x0ctableOpGraph\x12\x17\n\x07room_id\x18\x04 \x01(\tR\x06roomId\x12\x15\n\x06org_id\x18\x06 \x01(\tR\x05orgId\x12\x1f\n\x0bpipeline_id\x18\x08 \x01(\tR\npipelineId\x12>\n\ncreated_at\x18\x07 \x01(\x0b\x32\x1a.google.protobuf.TimestampH\x00R\tcreatedAt\x88\x01\x01\x12Q\n\x13prop_table_op_graph\x18\t \x01(\x0b\x32\x1d.corvic.orm.v1.TableComputeOpH\x01R\x10propTableOpGraph\x88\x01\x01\x42\r\n\x0b_created_atB\x16\n\x14_prop_table_op_graph\"\xe9\x03\n\x08Pipeline\x12\x0e\n\x02id\x18\x01 \x01(\tR\x02id\x12\x12\n\x04name\x18\x02 \x01(\tR\x04name\x12 \n\x0b\x64\x65scription\x18\t \x01(\tR\x0b\x64\x65scription\x12\x17\n\x07room_id\x18\x03 \x01(\tR\x06roomId\x12X\n\x0esource_outputs\x18\x05 \x03(\x0b\x32\x31.corvic.model.v1alpha.Pipeline.SourceOutputsEntryR\rsourceOutputs\x12^\n\x17pipeline_transformation\x18\x06 \x01(\x0b\x32%.corvic.orm.v1.PipelineTransformationR\x16pipelineTransformation\x12\x15\n\x06org_id\x18\x07 \x01(\tR\x05orgId\x12>\n\ncreated_at\x18\x08 \x01(\x0b\x32\x1a.google.protobuf.TimestampH\x00R\tcreatedAt\x88\x01\x01\x1a^\n\x12SourceOutputsEntry\x12\x10\n\x03key\x18\x01 \x01(\tR\x03key\x12\x32\n\x05value\x18\x02 \x01(\x0b\x32\x1c.corvic.model.v1alpha.SourceR\x05value:\x02\x38\x01\x42\r\n\x0b_created_at\"\xca\x02\n\x11\x46\x65\x61tureViewSource\x12\x0e\n\x02id\x18\x01 \x01(\tR\x02id\x12\x34\n\x06source\x18\x02 \x01(\x0b\x32\x1c.corvic.model.v1alpha.SourceR\x06source\x12\x43\n\x0etable_op_graph\x18\x03 \x01(\x0b\x32\x1d.corvic.orm.v1.TableComputeOpR\x0ctableOpGraph\x12+\n\x11\x64rop_disconnected\x18\x04 \x01(\x08R\x10\x64ropDisconnected\x12\x15\n\x06org_id\x18\x05 \x01(\tR\x05orgId\x12>\n\ncreated_at\x18\x06 \x01(\x0b\x32\x1a.google.protobuf.TimestampH\x00R\tcreatedAt\x88\x01\x01\x12\x17\n\x07room_id\x18\x07 \x01(\tR\x06roomIdB\r\n\x0b_created_at\"\x9c\x03\n\x0b\x46\x65\x61tureView\x12\x0e\n\x02id\x18\x01 \x01(\tR\x02id\x12\x12\n\x04name\x18\x02 \x01(\tR\x04name\x12 \n\x0b\x64\x65scription\x18\x03 \x01(\tR\x0b\x64\x65scription\x12\x17\n\x07room_id\x18\x04 \x01(\tR\x06roomId\x12P\n\x13\x66\x65\x61ture_view_output\x18\x05 \x01(\x0b\x32 .corvic.orm.v1.FeatureViewOutputR\x11\x66\x65\x61tureViewOutput\x12Y\n\x14\x66\x65\x61ture_view_sources\x18\x06 \x03(\x0b\x32\'.corvic.model.v1alpha.FeatureViewSourceR\x12\x66\x65\x61tureViewSources\x12\x1b\n\tspace_ids\x18\x07 \x03(\tR\x08spaceIds\x12\x15\n\x06org_id\x18\x08 \x01(\tR\x05orgId\x12>\n\ncreated_at\x18\t \x01(\x0b\x32\x1a.google.protobuf.TimestampH\x00R\tcreatedAt\x88\x01\x01\x42\r\n\x0b_created_at\"\xfa\x02\n\x05Space\x12\x0e\n\x02id\x18\x01 \x01(\tR\x02id\x12\x12\n\x04name\x18\x02 \x01(\tR\x04name\x12 \n\x0b\x64\x65scription\x18\x03 \x01(\tR\x0b\x64\x65scription\x12\x17\n\x07room_id\x18\x04 \x01(\tR\x06roomId\x12I\n\x10space_parameters\x18\x05 \x01(\x0b\x32\x1e.corvic.orm.v1.SpaceParametersR\x0fspaceParameters\x12\x44\n\x0c\x66\x65\x61ture_view\x18\x06 \x01(\x0b\x32!.corvic.model.v1alpha.FeatureViewR\x0b\x66\x65\x61tureView\x12\x1b\n\tauto_sync\x18\t \x01(\x08R\x08\x61utoSync\x12\x15\n\x06org_id\x18\x07 \x01(\tR\x05orgId\x12>\n\ncreated_at\x18\x08 \x01(\x0b\x32\x1a.google.protobuf.TimestampH\x00R\tcreatedAt\x88\x01\x01\x42\r\n\x0b_created_at\"\x85\x02\n\x05\x41gent\x12\x0e\n\x02id\x18\x01 \x01(\tR\x02id\x12\x12\n\x04name\x18\x02 \x01(\tR\x04name\x12\x17\n\x07room_id\x18\x03 \x01(\tR\x06roomId\x12I\n\x10\x61gent_parameters\x18\x04 \x01(\x0b\x32\x1e.corvic.orm.v1.AgentParametersR\x0f\x61gentParameters\x12\x15\n\x06org_id\x18\x05 \x01(\tR\x05orgId\x12>\n\ncreated_at\x18\t \x01(\x0b\x32\x1a.google.protobuf.TimestampH\x00R\tcreatedAt\x88\x01\x01\x42\r\n\x0b_created_atJ\x04\x08\x06\x10\x07R\x08messages\"\xbc\x03\n\x0f\x43ompletionModel\x12\x0e\n\x02id\x18\x01 \x01(\tR\x02id\x12\x12\n\x04name\x18\x02 \x01(\tR\x04name\x12 \n\x0b\x64\x65scription\x18\x03 \x01(\tR\x0b\x64\x65scription\x12\x15\n\x06org_id\x18\x04 \x01(\tR\x05orgId\x12H\n\nparameters\x18\x05 \x01(\x0b\x32(.corvic.orm.v1.CompletionModelParametersR\nparameters\x12$\n\x0esecret_api_key\x18\x06 \x01(\tR\x0csecretApiKey\x12Q\n\x14last_validation_time\x18\x08 \x01(\x0b\x32\x1a.google.protobuf.TimestampH\x00R\x12lastValidationTime\x88\x01\x01\x12!\n\x0cis_validated\x18\t \x01(\x08R\x0bisValidated\x12>\n\ncreated_at\x18\x07 \x01(\x0b\x32\x1a.google.protobuf.TimestampH\x01R\tcreatedAt\x88\x01\x01\x42\x17\n\x15_last_validation_timeB\r\n\x0b_created_atb\x06proto3')
 
 _globals = globals()
 _builder.BuildMessageAndEnumDescriptors(DESCRIPTOR, _globals)
@@ -50,5 +50,5 @@ if _descriptor._USE_C_DESCRIPTORS == False:
   _globals['_AGENT']._serialized_start=2932
   _globals['_AGENT']._serialized_end=3193
   _globals['_COMPLETIONMODEL']._serialized_start=3196
-  _globals['_COMPLETIONMODEL']._serialized_end=3605
+  _globals['_COMPLETIONMODEL']._serialized_end=3640
 # @@protoc_insertion_point(module_scope)

{corvic_engine-0.3.0rc56 → corvic_engine-0.3.0rc58}/python/corvic_generated/model/v1alpha/models_pb2.pyi

@@ -183,21 +183,23 @@ class Agent(_message.Message):
     def __init__(self, id: _Optional[str] = ..., name: _Optional[str] = ..., room_id: _Optional[str] = ..., agent_parameters: _Optional[_Union[_agent_pb2.AgentParameters, _Mapping]] = ..., org_id: _Optional[str] = ..., created_at: _Optional[_Union[_timestamp_pb2.Timestamp, _Mapping]] = ...) -> None: ...
 
 class CompletionModel(_message.Message):
-    __slots__ = ("id", "name", "description", "org_id", "parameters", "secret_api_key", "created_at", "last_validation_time")
+    __slots__ = ("id", "name", "description", "org_id", "parameters", "secret_api_key", "last_validation_time", "is_validated", "created_at")
     ID_FIELD_NUMBER: _ClassVar[int]
     NAME_FIELD_NUMBER: _ClassVar[int]
     DESCRIPTION_FIELD_NUMBER: _ClassVar[int]
     ORG_ID_FIELD_NUMBER: _ClassVar[int]
     PARAMETERS_FIELD_NUMBER: _ClassVar[int]
     SECRET_API_KEY_FIELD_NUMBER: _ClassVar[int]
-    CREATED_AT_FIELD_NUMBER: _ClassVar[int]
     LAST_VALIDATION_TIME_FIELD_NUMBER: _ClassVar[int]
+    IS_VALIDATED_FIELD_NUMBER: _ClassVar[int]
+    CREATED_AT_FIELD_NUMBER: _ClassVar[int]
     id: str
     name: str
     description: str
     org_id: str
     parameters: _completion_model_pb2.CompletionModelParameters
     secret_api_key: str
-    created_at: _timestamp_pb2.Timestamp
     last_validation_time: _timestamp_pb2.Timestamp
-    def __init__(self, id: _Optional[str] = ..., name: _Optional[str] = ..., description: _Optional[str] = ..., org_id: _Optional[str] = ..., parameters: _Optional[_Union[_completion_model_pb2.CompletionModelParameters, _Mapping]] = ..., secret_api_key: _Optional[str] = ..., created_at: _Optional[_Union[_timestamp_pb2.Timestamp, _Mapping]] = ..., last_validation_time: _Optional[_Union[_timestamp_pb2.Timestamp, _Mapping]] = ...) -> None: ...
+    is_validated: bool
+    created_at: _timestamp_pb2.Timestamp
+    def __init__(self, id: _Optional[str] = ..., name: _Optional[str] = ..., description: _Optional[str] = ..., org_id: _Optional[str] = ..., parameters: _Optional[_Union[_completion_model_pb2.CompletionModelParameters, _Mapping]] = ..., secret_api_key: _Optional[str] = ..., last_validation_time: _Optional[_Union[_timestamp_pb2.Timestamp, _Mapping]] = ..., is_validated: bool = ..., created_at: _Optional[_Union[_timestamp_pb2.Timestamp, _Mapping]] = ...) -> None: ...

corvic_engine-0.3.0rc56/python/corvic_generated/config/v1/settings_pb2.py

@@ -1,128 +0,0 @@
-# -*- coding: utf-8 -*-
-# Generated by the protocol buffer compiler.  DO NOT EDIT!
-# source: corvic/config/v1/settings.proto
-# Protobuf Python Version: 4.25.3
-"""Generated protocol buffer code."""
-from google.protobuf import descriptor as _descriptor
-from google.protobuf import descriptor_pool as _descriptor_pool
-from google.protobuf import symbol_database as _symbol_database
-from google.protobuf.internal import builder as _builder
-# @@protoc_insertion_point(imports)
-
-_sym_db = _symbol_database.Default()
-
-
-
-
-DESCRIPTOR = _descriptor_pool.Default().AddSerializedFile(b'\n\x1f\x63orvic/config/v1/settings.proto\x12\x10\x63orvic.config.v1\"\x7f\n\nMetaConfig\x12#\n\renvvar_prefix\x18\x01 \x01(\tR\x0c\x65nvvarPrefix\x12)\n\x10nested_separator\x18\x02 \x01(\tR\x0fnestedSeparator\x12!\n\x0cvia_launcher\x18\x03 \x01(\x08R\x0bviaLauncher\"\'\n\rMetricsConfig\x12\x16\n\x06\x65xport\x18\x01 \x01(\x08R\x06\x65xport\"&\n\x10\x43hatServerConfig\x12\x12\n\x04port\x18\x01 \x01(\rR\x04port\"\x81\t\n\rRocksetConfig\x12+\n\x11\x64\x65\x66\x61ult_workspace\x18\x01 \x01(\tR\x10\x64\x65\x66\x61ultWorkspace\x12-\n\x12\x64\x65\x66\x61ult_collection\x18\x02 \x01(\tR\x11\x64\x65\x66\x61ultCollection\x12%\n\x0e\x64\x65\x66\x61ult_region\x18\x03 \x01(\tR\rdefaultRegion\x12\x1b\n\tapi_token\x18\x04 \x01(\tR\x08\x61piToken\x12U\n\x0cintegrations\x18\x05 \x03(\x0b\x32\x31.corvic.config.v1.RocksetConfig.IntegrationsEntryR\x0cintegrations\x12R\n\x0b\x63ollections\x18\x06 \x03(\x0b\x32\x30.corvic.config.v1.RocksetConfig.CollectionsEntryR\x0b\x63ollections\x12\"\n\x0corganization\x18\x07 \x01(\tR\x0corganization\x1av\n\x11IntegrationConfig\x12\x34\n\x16rockset_integration_id\x18\x01 \x01(\tR\x14rocksetIntegrationId\x12+\n\x11supported_buckets\x18\x02 \x03(\tR\x10supportedBuckets\x1ar\n\x11IntegrationsEntry\x12\x10\n\x03key\x18\x01 \x01(\tR\x03key\x12G\n\x05value\x18\x02 \x01(\x0b\x32\x31.corvic.config.v1.RocksetConfig.IntegrationConfigR\x05value:\x02\x38\x01\x1a\xb4\x01\n\x0e\x43ollectionArgs\x12)\n\x10integration_name\x18\x01 \x01(\tR\x0fintegrationName\x12\x1f\n\x0b\x62ucket_name\x18\x02 \x01(\tR\nbucketName\x12*\n\x11gcs_output_prefix\x18\x03 \x01(\tR\x0fgcsOutputPrefix\x12*\n\x11\x63reate_if_missing\x18\x04 \x01(\x08R\x0f\x63reateIfMissing\x1a\xeb\x01\n\x10\x43ollectionConfig\x12\x12\n\x04name\x18\x01 \x01(\tR\x04name\x12\x1c\n\tworkspace\x18\x02 \x01(\tR\tworkspace\x12\x12\n\x04host\x18\x03 \x01(\tR\x04host\x12\x16\n\x04kind\x18\x04 \x01(\tB\x02\x18\x01R\x04kind\x12 \n\x0b\x64\x65scription\x18\x05 \x01(\tR\x0b\x64\x65scription\x12W\n\x0f\x63ollection_args\x18\x06 \x01(\x0b\x32..corvic.config.v1.RocksetConfig.CollectionArgsR\x0e\x63ollectionArgs\x1ap\n\x10\x43ollectionsEntry\x12\x10\n\x03key\x18\x01 \x01(\tR\x03key\x12\x46\n\x05value\x18\x02 \x01(\x0b\x32\x30.corvic.config.v1.RocksetConfig.CollectionConfigR\x05value:\x02\x38\x01\"\x89\x03\n\x0e\x45mbedgenConfig\x12\x1f\n\x0b\x64\x65\x66\x61ult_tag\x18\x01 \x01(\tR\ndefaultTag\x12\x36\n\x17rockset_collection_name\x18\x02 \x01(\tR\x15rocksetCollectionName\x12\x31\n\x15\x63hunk_text_field_name\x18\x03 \x01(\tR\x12\x63hunkTextFieldName\x12\\\n,gcs_notification_config_embed_gen_config_key\x18\x04 \x01(\tR&gcsNotificationConfigEmbedGenConfigKey\x12]\n\x12\x64ocument_processor\x18\x05 \x01(\x0b\x32..corvic.config.v1.EmbedgenConfig.DocProcConfigR\x11\x64ocumentProcessor\x1a.\n\rDocProcConfig\x12\x1d\n\nbatch_size\x18\x01 \x01(\rR\tbatchSize\"\xfe\x02\n\nChatConfig\x12\x31\n\x15max_messages_per_page\x18\x01 \x01(\rR\x12maxMessagesPerPage\x12=\n\x1bget_messages_period_seconds\x18\x02 \x01(\x01R\x18getMessagesPeriodSeconds\x12)\n\x10\x63ompletion_model\x18\x03 \x01(\tR\x0f\x63ompletionModel\x12%\n\x0eretriever_type\x18\x04 \x01(\tR\rretrieverType\x12)\n\x10obfuscation_seed\x18\x05 \x01(\tR\x0fobfuscationSeed\x12\x41\n\x06\x63lient\x18\x06 \x01(\x0b\x32).corvic.config.v1.ChatConfig.ClientConfigR\x06\x63lient\x1a>\n\x0c\x43lientConfig\x12\x1a\n\x08hostname\x18\x01 \x01(\tR\x08hostname\x12\x12\n\x04port\x18\x02 \x01(\rR\x04port\"2\n\x08\x44\x42\x43onfig\x12\x12\n\x04host\x18\x01 \x01(\tR\x04host\x12\x12\n\x04name\x18\x02 \x01(\tR\x04name\"\xfa\x02\n\x0cIngestConfig\x12\x35\n\x15store_id_metadata_key\x18\x01 \x01(\tB\x02\x18\x01R\x12storeIdMetadataKey\x12\x43\n\x06server\x18\x02 \x01(\x0b\x32+.corvic.config.v1.IngestConfig.ServerConfigR\x06server\x12\x43\n\x06\x63lient\x18\x03 \x01(\x0b\x32+.corvic.config.v1.IngestConfig.ClientConfigR\x06\x63lient\x1ai\n\x0cServerConfig\x12\x16\n\x06\x62ucket\x18\x01 \x01(\tR\x06\x62ucket\x12\x16\n\x06prefix\x18\x02 \x01(\tR\x06prefix\x12)\n\x10obfuscation_seed\x18\x03 \x01(\tR\x0fobfuscationSeed\x1a>\n\x0c\x43lientConfig\x12\x1a\n\x08hostname\x18\x01 \x01(\tR\x08hostname\x12\x12\n\x04port\x18\x02 \x01(\rR\x04port\"8\n\x10\x45xperimentConfig\x12$\n\x0egcs_run_prefix\x18\x01 \x01(\tR\x0cgcsRunPrefix\"c\n\x15\x43ompletionModelConfig\x12\x16\n\x06\x65ngine\x18\x01 \x01(\tR\x06\x65ngine\x12\x14\n\x05model\x18\x02 \x01(\tR\x05model\x12\x1c\n\ttokenizer\x18\x03 \x01(\tR\ttokenizer\"\xd7\x01\n\x14\x45mbeddingModelConfig\x12\x16\n\x06\x65ngine\x18\x01 \x01(\tR\x06\x65ngine\x12\x14\n\x05model\x18\x02 \x01(\tR\x05model\x12 \n\x0b\x63\x61rdinality\x18\x03 \x01(\x04R\x0b\x63\x61rdinality\x12H\n\x05\x65xtra\x18\x04 \x01(\x0b\x32\x32.corvic.config.v1.EmbeddingModelConfig.ExtraConfigR\x05\x65xtra\x1a%\n\x0b\x45xtraConfig\x12\x16\n\x06\x64\x65vice\x18\x01 \x01(\tR\x06\x64\x65vice\"\xd3\x08\n\x11HuggingfaceConfig\x12*\n\x0fmodel_proxy_url\x18\x01 \x01(\tB\x02\x18\x01R\rmodelProxyUrl\x12:\n\x19\x64\x65\x66\x61ult_inference_timeout\x18\x03 \x01(\rR\x17\x64\x65\x66\x61ultInferenceTimeout\x12\x33\n\x16\x64\x65\x66\x61ult_max_new_tokens\x18\x04 \x01(\x04R\x13\x64\x65\x66\x61ultMaxNewTokens\x12\x1b\n\tapi_token\x18\x05 \x01(\tR\x08\x61piToken\x12m\n\x13inference_endpoints\x18\x06 \x01(\x0b\x32<.corvic.config.v1.HuggingfaceConfig.InferenceEndpointsConfigR\x12inferenceEndpoints\x1a\x94\x06\n\x18InferenceEndpointsConfig\x12o\n\x0b\x63ompletions\x18\x01 \x03(\x0b\x32M.corvic.config.v1.HuggingfaceConfig.InferenceEndpointsConfig.CompletionsEntryR\x0b\x63ompletions\x12l\n\nembeddings\x18\x02 \x03(\x0b\x32L.corvic.config.v1.HuggingfaceConfig.InferenceEndpointsConfig.EmbeddingsEntryR\nembeddings\x1a~\n\x0f\x43ompletionModel\x12\x17\n\x07hf_host\x18\x01 \x01(\tR\x06hfHost\x12\x17\n\x07hf_name\x18\x02 \x01(\tR\x06hfName\x12!\n\x0chf_namespace\x18\x03 \x01(\tR\x0bhfNamespace\x12\x16\n\x06models\x18\x04 \x03(\tR\x06models\x1a\x8c\x01\n\x10\x43ompletionsEntry\x12\x10\n\x03key\x18\x01 \x01(\tR\x03key\x12\x62\n\x05value\x18\x02 \x01(\x0b\x32L.corvic.config.v1.HuggingfaceConfig.InferenceEndpointsConfig.CompletionModelR\x05value:\x02\x38\x01\x1a}\n\x0e\x45mbeddingModel\x12\x17\n\x07hf_host\x18\x01 \x01(\tR\x06hfHost\x12\x17\n\x07hf_name\x18\x02 \x01(\tR\x06hfName\x12!\n\x0chf_namespace\x18\x03 \x01(\tR\x0bhfNamespace\x12\x16\n\x06models\x18\x04 \x03(\tR\x06models\x1a\x8a\x01\n\x0f\x45mbeddingsEntry\x12\x10\n\x03key\x18\x01 \x01(\tR\x03key\x12\x61\n\x05value\x18\x02 \x01(\x0b\x32K.corvic.config.v1.HuggingfaceConfig.InferenceEndpointsConfig.EmbeddingModelR\x05value:\x02\x38\x01\"\xa7\x03\n\x0fRetrieverConfig\x12@\n\x1c\x64\x65\x66\x61ult_similarity_threshold\x18\x01 \x01(\x01R\x1a\x64\x65\x66\x61ultSimilarityThreshold\x12,\n\x12\x64\x65\x66\x61ult_max_chunks\x18\x02 \x01(\x04R\x10\x64\x65\x66\x61ultMaxChunks\x12\x1f\n\x0b\x64\x65\x66\x61ult_tag\x18\x03 \x01(\tR\ndefaultTag\x12\x38\n\x18\x64\x65\x66\x61ult_embeddings_model\x18\x04 \x01(\tR\x16\x64\x65\x66\x61ultEmbeddingsModel\x12\x41\n\x1d\x64\x65\x66\x61ult_embeddings_model_name\x18\x05 \x01(\tR\x1a\x64\x65\x66\x61ultEmbeddingsModelName\x12:\n\x19\x64\x65\x66\x61ult_embeddings_engine\x18\x06 \x01(\tR\x17\x64\x65\x66\x61ultEmbeddingsEngine\x12\x12\n\x04type\x18\x07 \x01(\tR\x04type\x12\x36\n\x17rockset_collection_name\x18\x08 \x01(\tR\x15rocksetCollectionName\"\x9c\x01\n\x10\x43ompletionConfig\x12\x38\n\x18\x64\x65\x66\x61ult_completion_model\x18\x01 \x01(\tR\x16\x64\x65\x66\x61ultCompletionModel\x12(\n\x10no_chunk_message\x18\x02 \x01(\tR\x0enoChunkMessage\x12$\n\x0esys_prompt_rag\x18\x03 \x01(\tR\x0csysPromptRag\"7\n\x0eWorkflowConfig\x12%\n\x0estorage_prefix\x18\x01 \x01(\tR\rstoragePrefix\"\xb7\x03\n\x11\x44\x61taStagingConfig\x12,\n\x12rockset_api_server\x18\x01 \x01(\tR\x10rocksetApiServer\x12+\n\x11rockset_workspace\x18\x02 \x01(\tR\x10rocksetWorkspace\x12-\n\x12rockset_collection\x18\x03 \x01(\tR\x11rocksetCollection\x12/\n\x13rockset_integration\x18\x04 \x01(\tR\x12rocksetIntegration\x12\x1d\n\ngcs_bucket\x18\x05 \x01(\tR\tgcsBucket\x12?\n\x1cgcs_unstructured_data_prefix\x18\x06 \x01(\tR\x19gcsUnstructuredDataPrefix\x12\x31\n\x15gcs_table_data_prefix\x18\x07 \x01(\tR\x12gcsTableDataPrefix\x12(\n\x10\x62lob_name_column\x18\x08 \x01(\tR\x0e\x62lobNameColumn\x12*\n\x11row_number_column\x18\t \x01(\tR\x0frowNumberColumn\"a\n\x05\x41uth0\x12\x1b\n\tclient_id\x18\x01 \x01(\tR\x08\x63lientId\x12#\n\rclient_secret\x18\x02 \x01(\tR\x0c\x63lientSecret\x12\x16\n\x06\x64omain\x18\x03 \x01(\tR\x06\x64omain\"\xf1\x0b\n\x08Settings\x12#\n\x0bload_dotenv\x18\x01 \x01(\x08\x42\x02\x18\x01R\nloadDotenv\x12\x34\n\x06\x63onfig\x18\x02 \x01(\x0b\x32\x1c.corvic.config.v1.MetaConfigR\x06\x63onfig\x12\x19\n\x08\x64\x65v_mode\x18\x03 \x01(\tR\x07\x64\x65vMode\x12\x39\n\x07metrics\x18\x04 \x01(\x0b\x32\x1f.corvic.config.v1.MetricsConfigR\x07metrics\x12G\n\x0b\x63hat_server\x18\x05 \x01(\x0b\x32\".corvic.config.v1.ChatServerConfigB\x02\x18\x01R\nchatServer\x12@\n\x08\x65mbedgen\x18\x06 \x01(\x0b\x32 .corvic.config.v1.EmbedgenConfigB\x02\x18\x01R\x08\x65mbedgen\x12\x34\n\x04\x63hat\x18\x07 \x01(\x0b\x32\x1c.corvic.config.v1.ChatConfigB\x02\x18\x01R\x04\x63hat\x12*\n\x02\x64\x62\x18\x08 \x01(\x0b\x32\x1a.corvic.config.v1.DBConfigR\x02\x64\x62\x12\x36\n\x06ingest\x18\t \x01(\x0b\x32\x1e.corvic.config.v1.IngestConfigR\x06ingest\x12\x61\n\x11\x63ompletion_models\x18\n \x03(\x0b\x32\x30.corvic.config.v1.Settings.CompletionModelsEntryB\x02\x18\x01R\x10\x63ompletionModels\x12Z\n\x10\x65mbedding_models\x18\x0b \x03(\x0b\x32/.corvic.config.v1.Settings.EmbeddingModelsEntryR\x0f\x65mbeddingModels\x12I\n\x0bhuggingface\x18\x0c \x01(\x0b\x32#.corvic.config.v1.HuggingfaceConfigB\x02\x18\x01R\x0bhuggingface\x12\x43\n\tretriever\x18\r \x01(\x0b\x32!.corvic.config.v1.RetrieverConfigB\x02\x18\x01R\tretriever\x12\x46\n\ncompletion\x18\x0e \x01(\x0b\x32\".corvic.config.v1.CompletionConfigB\x02\x18\x01R\ncompletion\x12\x39\n\x07rockset\x18\x0f \x01(\x0b\x32\x1f.corvic.config.v1.RocksetConfigR\x07rockset\x12\x32\n\x15google_identity_token\x18\x10 \x01(\tR\x13googleIdentityToken\x12\x1d\n\ncheck_name\x18\x11 \x01(\tR\tcheckName\x12\x17\n\x07test_db\x18\x12 \x01(\tR\x06testDb\x12<\n\x08workflow\x18\x13 \x01(\x0b\x32 .corvic.config.v1.WorkflowConfigR\x08workflow\x12\x46\n\x0c\x64\x61ta_staging\x18\x14 \x01(\x0b\x32#.corvic.config.v1.DataStagingConfigR\x0b\x64\x61taStaging\x12\x42\n\nexperiment\x18\x15 \x01(\x0b\x32\".corvic.config.v1.ExperimentConfigR\nexperiment\x12-\n\x05\x61uth0\x18\x16 \x01(\x0b\x32\x17.corvic.config.v1.Auth0R\x05\x61uth0\x1al\n\x15\x43ompletionModelsEntry\x12\x10\n\x03key\x18\x01 \x01(\tR\x03key\x12=\n\x05value\x18\x02 \x01(\x0b\x32\'.corvic.config.v1.CompletionModelConfigR\x05value:\x02\x38\x01\x1aj\n\x14\x45mbeddingModelsEntry\x12\x10\n\x03key\x18\x01 \x01(\tR\x03key\x12<\n\x05value\x18\x02 \x01(\x0b\x32&.corvic.config.v1.EmbeddingModelConfigR\x05value:\x02\x38\x01\x62\x06proto3')
-
-_globals = globals()
-_builder.BuildMessageAndEnumDescriptors(DESCRIPTOR, _globals)
-_builder.BuildTopDescriptorsAndMessages(DESCRIPTOR, 'corvic.config.v1.settings_pb2', _globals)
-if _descriptor._USE_C_DESCRIPTORS == False:
-  DESCRIPTOR._options = None
-  _globals['_ROCKSETCONFIG_INTEGRATIONSENTRY']._options = None
-  _globals['_ROCKSETCONFIG_INTEGRATIONSENTRY']._serialized_options = b'8\001'
-  _globals['_ROCKSETCONFIG_COLLECTIONCONFIG'].fields_by_name['kind']._options = None
-  _globals['_ROCKSETCONFIG_COLLECTIONCONFIG'].fields_by_name['kind']._serialized_options = b'\030\001'
-  _globals['_ROCKSETCONFIG_COLLECTIONSENTRY']._options = None
-  _globals['_ROCKSETCONFIG_COLLECTIONSENTRY']._serialized_options = b'8\001'
-  _globals['_INGESTCONFIG'].fields_by_name['store_id_metadata_key']._options = None
-  _globals['_INGESTCONFIG'].fields_by_name['store_id_metadata_key']._serialized_options = b'\030\001'
-  _globals['_HUGGINGFACECONFIG_INFERENCEENDPOINTSCONFIG_COMPLETIONSENTRY']._options = None
-  _globals['_HUGGINGFACECONFIG_INFERENCEENDPOINTSCONFIG_COMPLETIONSENTRY']._serialized_options = b'8\001'
-  _globals['_HUGGINGFACECONFIG_INFERENCEENDPOINTSCONFIG_EMBEDDINGSENTRY']._options = None
-  _globals['_HUGGINGFACECONFIG_INFERENCEENDPOINTSCONFIG_EMBEDDINGSENTRY']._serialized_options = b'8\001'
-  _globals['_HUGGINGFACECONFIG'].fields_by_name['model_proxy_url']._options = None
-  _globals['_HUGGINGFACECONFIG'].fields_by_name['model_proxy_url']._serialized_options = b'\030\001'
-  _globals['_SETTINGS_COMPLETIONMODELSENTRY']._options = None
-  _globals['_SETTINGS_COMPLETIONMODELSENTRY']._serialized_options = b'8\001'
-  _globals['_SETTINGS_EMBEDDINGMODELSENTRY']._options = None
-  _globals['_SETTINGS_EMBEDDINGMODELSENTRY']._serialized_options = b'8\001'
-  _globals['_SETTINGS'].fields_by_name['load_dotenv']._options = None
-  _globals['_SETTINGS'].fields_by_name['load_dotenv']._serialized_options = b'\030\001'
-  _globals['_SETTINGS'].fields_by_name['chat_server']._options = None
-  _globals['_SETTINGS'].fields_by_name['chat_server']._serialized_options = b'\030\001'
-  _globals['_SETTINGS'].fields_by_name['embedgen']._options = None
-  _globals['_SETTINGS'].fields_by_name['embedgen']._serialized_options = b'\030\001'
-  _globals['_SETTINGS'].fields_by_name['chat']._options = None
-  _globals['_SETTINGS'].fields_by_name['chat']._serialized_options = b'\030\001'
-  _globals['_SETTINGS'].fields_by_name['completion_models']._options = None
-  _globals['_SETTINGS'].fields_by_name['completion_models']._serialized_options = b'\030\001'
-  _globals['_SETTINGS'].fields_by_name['huggingface']._options = None
-  _globals['_SETTINGS'].fields_by_name['huggingface']._serialized_options = b'\030\001'
-  _globals['_SETTINGS'].fields_by_name['retriever']._options = None
-  _globals['_SETTINGS'].fields_by_name['retriever']._serialized_options = b'\030\001'
-  _globals['_SETTINGS'].fields_by_name['completion']._options = None
-  _globals['_SETTINGS'].fields_by_name['completion']._serialized_options = b'\030\001'
-  _globals['_METACONFIG']._serialized_start=53
-  _globals['_METACONFIG']._serialized_end=180
-  _globals['_METRICSCONFIG']._serialized_start=182
-  _globals['_METRICSCONFIG']._serialized_end=221
-  _globals['_CHATSERVERCONFIG']._serialized_start=223
-  _globals['_CHATSERVERCONFIG']._serialized_end=261
-  _globals['_ROCKSETCONFIG']._serialized_start=264
-  _globals['_ROCKSETCONFIG']._serialized_end=1417
-  _globals['_ROCKSETCONFIG_INTEGRATIONCONFIG']._serialized_start=648
-  _globals['_ROCKSETCONFIG_INTEGRATIONCONFIG']._serialized_end=766
-  _globals['_ROCKSETCONFIG_INTEGRATIONSENTRY']._serialized_start=768
-  _globals['_ROCKSETCONFIG_INTEGRATIONSENTRY']._serialized_end=882
-  _globals['_ROCKSETCONFIG_COLLECTIONARGS']._serialized_start=885
-  _globals['_ROCKSETCONFIG_COLLECTIONARGS']._serialized_end=1065
-  _globals['_ROCKSETCONFIG_COLLECTIONCONFIG']._serialized_start=1068
-  _globals['_ROCKSETCONFIG_COLLECTIONCONFIG']._serialized_end=1303
-  _globals['_ROCKSETCONFIG_COLLECTIONSENTRY']._serialized_start=1305
-  _globals['_ROCKSETCONFIG_COLLECTIONSENTRY']._serialized_end=1417
-  _globals['_EMBEDGENCONFIG']._serialized_start=1420
-  _globals['_EMBEDGENCONFIG']._serialized_end=1813
-  _globals['_EMBEDGENCONFIG_DOCPROCCONFIG']._serialized_start=1767
-  _globals['_EMBEDGENCONFIG_DOCPROCCONFIG']._serialized_end=1813
-  _globals['_CHATCONFIG']._serialized_start=1816
-  _globals['_CHATCONFIG']._serialized_end=2198
-  _globals['_CHATCONFIG_CLIENTCONFIG']._serialized_start=2136
-  _globals['_CHATCONFIG_CLIENTCONFIG']._serialized_end=2198
-  _globals['_DBCONFIG']._serialized_start=2200
-  _globals['_DBCONFIG']._serialized_end=2250
-  _globals['_INGESTCONFIG']._serialized_start=2253
-  _globals['_INGESTCONFIG']._serialized_end=2631
-  _globals['_INGESTCONFIG_SERVERCONFIG']._serialized_start=2462
-  _globals['_INGESTCONFIG_SERVERCONFIG']._serialized_end=2567
-  _globals['_INGESTCONFIG_CLIENTCONFIG']._serialized_start=2136
-  _globals['_INGESTCONFIG_CLIENTCONFIG']._serialized_end=2198
-  _globals['_EXPERIMENTCONFIG']._serialized_start=2633
-  _globals['_EXPERIMENTCONFIG']._serialized_end=2689
-  _globals['_COMPLETIONMODELCONFIG']._serialized_start=2691
-  _globals['_COMPLETIONMODELCONFIG']._serialized_end=2790
-  _globals['_EMBEDDINGMODELCONFIG']._serialized_start=2793
-  _globals['_EMBEDDINGMODELCONFIG']._serialized_end=3008
-  _globals['_EMBEDDINGMODELCONFIG_EXTRACONFIG']._serialized_start=2971
-  _globals['_EMBEDDINGMODELCONFIG_EXTRACONFIG']._serialized_end=3008
-  _globals['_HUGGINGFACECONFIG']._serialized_start=3011
-  _globals['_HUGGINGFACECONFIG']._serialized_end=4118
-  _globals['_HUGGINGFACECONFIG_INFERENCEENDPOINTSCONFIG']._serialized_start=3330
-  _globals['_HUGGINGFACECONFIG_INFERENCEENDPOINTSCONFIG']._serialized_end=4118
-  _globals['_HUGGINGFACECONFIG_INFERENCEENDPOINTSCONFIG_COMPLETIONMODEL']._serialized_start=3581
-  _globals['_HUGGINGFACECONFIG_INFERENCEENDPOINTSCONFIG_COMPLETIONMODEL']._serialized_end=3707
-  _globals['_HUGGINGFACECONFIG_INFERENCEENDPOINTSCONFIG_COMPLETIONSENTRY']._serialized_start=3710
-  _globals['_HUGGINGFACECONFIG_INFERENCEENDPOINTSCONFIG_COMPLETIONSENTRY']._serialized_end=3850
-  _globals['_HUGGINGFACECONFIG_INFERENCEENDPOINTSCONFIG_EMBEDDINGMODEL']._serialized_start=3852
-  _globals['_HUGGINGFACECONFIG_INFERENCEENDPOINTSCONFIG_EMBEDDINGMODEL']._serialized_end=3977
-  _globals['_HUGGINGFACECONFIG_INFERENCEENDPOINTSCONFIG_EMBEDDINGSENTRY']._serialized_start=3980
-  _globals['_HUGGINGFACECONFIG_INFERENCEENDPOINTSCONFIG_EMBEDDINGSENTRY']._serialized_end=4118
-  _globals['_RETRIEVERCONFIG']._serialized_start=4121
-  _globals['_RETRIEVERCONFIG']._serialized_end=4544
-  _globals['_COMPLETIONCONFIG']._serialized_start=4547
-  _globals['_COMPLETIONCONFIG']._serialized_end=4703
-  _globals['_WORKFLOWCONFIG']._serialized_start=4705
-  _globals['_WORKFLOWCONFIG']._serialized_end=4760
-  _globals['_DATASTAGINGCONFIG']._serialized_start=4763
-  _globals['_DATASTAGINGCONFIG']._serialized_end=5202
-  _globals['_AUTH0']._serialized_start=5204
-  _globals['_AUTH0']._serialized_end=5301
-  _globals['_SETTINGS']._serialized_start=5304
-  _globals['_SETTINGS']._serialized_end=6825
-  _globals['_SETTINGS_COMPLETIONMODELSENTRY']._serialized_start=6609
-  _globals['_SETTINGS_COMPLETIONMODELSENTRY']._serialized_end=6717
-  _globals['_SETTINGS_EMBEDDINGMODELSENTRY']._serialized_start=6719
-  _globals['_SETTINGS_EMBEDDINGMODELSENTRY']._serialized_end=6825
-# @@protoc_insertion_point(module_scope)