salesforce-data-customcode 6.0.3.dev1__tar.gz → 6.0.4__tar.gz

{salesforce_data_customcode-6.0.3.dev1 → salesforce_data_customcode-6.0.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: salesforce-data-customcode
-Version: 6.0.3.dev1
+Version: 6.0.4
 Summary: Data Cloud Custom Code SDK
 License-Expression: Apache-2.0
 License-File: LICENSE.txt
@@ -341,13 +341,16 @@ from datacustomcode.client import Client, llm_gateway_generate_text_col
 def main():
   client = Client()
   df = client.read_dlo("Input__dll")
+  # llm_gateway_generate_text_col returns a struct
+  # {status, response, error_code, error_message} per row, so per-row
+  # failures don't abort the Spark job. Pick the field you want with [].
   df_generated = df.withColumn(
     "greeting__c",
     llm_gateway_generate_text_col(
         "In one sentence, greet {name} from {city}.",
         {"name": col("name__c"), "city": col("homecity__c")},
         model_id="sfdc_ai__DefaultGPT4Omni", # An AI model in your org
-    ),
+    )["response"],
   )
 
   dlo_name = "Output_dll"

{salesforce_data_customcode-6.0.3.dev1 → salesforce_data_customcode-6.0.4}/README.md

@@ -316,13 +316,16 @@ from datacustomcode.client import Client, llm_gateway_generate_text_col
 def main():
   client = Client()
   df = client.read_dlo("Input__dll")
+  # llm_gateway_generate_text_col returns a struct
+  # {status, response, error_code, error_message} per row, so per-row
+  # failures don't abort the Spark job. Pick the field you want with [].
   df_generated = df.withColumn(
     "greeting__c",
     llm_gateway_generate_text_col(
         "In one sentence, greet {name} from {city}.",
         {"name": col("name__c"), "city": col("homecity__c")},
         model_id="sfdc_ai__DefaultGPT4Omni", # An AI model in your org
-    ),
+    )["response"],
   )
 
   dlo_name = "Output_dll"

{salesforce_data_customcode-6.0.3.dev1 → salesforce_data_customcode-6.0.4}/pyproject.toml

@@ -18,7 +18,7 @@ license = "Apache-2.0"
 name = "salesforce-data-customcode"
 readme = "README.md"
 requires-python = ">=3.10,<3.12"
-version = "6.0.3.dev1"
+version = "6.0.4"
 
 [tool.black]
 exclude = '''
@@ -114,6 +114,7 @@ build = "*"
 coverage = ">=7.0.0,<8.0.0"
 ipykernel = "^6.29.5"
 mypy = "*"
+pipreqs = "*"
 poetry-dynamic-versioning = {extras = ["plugin"], version = "^1.8.2"}
 pre-commit = "*"
 pytest = "*"

{salesforce_data_customcode-6.0.3.dev1 → salesforce_data_customcode-6.0.4}/src/datacustomcode/cli.py

@@ -198,6 +198,7 @@ def zip(path: str, network: str):
     default=None,
     help="SF CLI org alias or username. Fetches credentials via `sf org display`.",
 )
+@click.option("--use-in-feature", default=None, hidden=True, deprecated=True)
 def deploy(
     path: str,
     name: str,
@@ -207,6 +208,7 @@ def deploy(
     profile: str,
     network: str,
     sf_cli_org: Optional[str],
+    use_in_feature: Optional[str],
 ):
     from datacustomcode.constants import USE_IN_FEATURE_MAPPING_FOR_CONNECT_API
     from datacustomcode.deploy import (
@@ -249,13 +251,14 @@ def deploy(
             logger.info(f"Inferred use_in_feature: {use_in_feature}")
         else:
             click.secho(
-                "Error: Could not infer function invoke options. "
-                "Please provide --use-in-feature",
+                "Error: Function signature does not match a supported type. "
+                "Use SearchIndexChunkingV1Request and "
+                "SearchIndexChunkingV1Response in function signature.",
                 fg="red",
             )
             raise click.Abort()
 
-        # Map user-provided feature names to API names
+        # Map feature names to Connect API names
         mapped_feature = USE_IN_FEATURE_MAPPING_FOR_CONNECT_API.get(
             use_in_feature, use_in_feature
         )

{salesforce_data_customcode-6.0.3.dev1 → salesforce_data_customcode-6.0.4}/src/datacustomcode/client.py

@@ -62,15 +62,23 @@ def llm_gateway_generate_text_col(
 ) -> "Column":
     """Build a Spark Column that runs the LLM Gateway per row.
 
+    The returned Column yields a struct ``{status, response, error_code,
+    error_message}`` for each row. Use ``[...]`` (or ``getField``) to pick the
+    field you want, e.g. ``llm_gateway_generate_text_col(...)["response"]``.
+    Per-row failures populate ``status`` / ``error_code`` / ``error_message``
+    so a single bad row does not abort the whole Spark job.
+
     Example:
 
-        >>> df.withColumn(
-        ...     "greeting__c",
-        ...     llm_gateway_generate_text_col(
-        ...         "In one sentence, greet {name} from {city}.",
-        ...         {"name": col("name__c"), "city": col("homecity__c")},
-        ...         model_id="sfdc_ai__DefaultGPT4Omni",
-        ...     ),
+        >>> result = llm_gateway_generate_text_col(
+        ...     "In one sentence, greet {name} from {city}.",
+        ...     {"name": col("name__c"), "city": col("homecity__c")},
+        ...     model_id="sfdc_ai__DefaultGPT4Omni",
+        ... )
+        >>> df.withColumn("greeting__c", result["response"])
+        >>> # …or keep the struct around and inspect failures:
+        >>> df.withColumn("llm", result).select(
+        ...     "llm.status", "llm.response", "llm.error_message"
         ... )
 
     Args:
@@ -81,7 +89,11 @@ def llm_gateway_generate_text_col(
         model_id: LLM model id. Defaults to ``sfdc_ai__DefaultGPT4Omni``.
 
     Returns:
-        A Spark ``Column`` that, when evaluated, produces the generated text.
+        A Spark ``Column`` of ``StructType`` with fields ``status``,
+        ``response``, ``error_code``, and ``error_message`` (all nullable
+        strings). On success, ``status == "SUCCESS"`` and ``response`` holds
+        the generated text; on failure, ``status == "ERROR"`` and the
+        ``error_*`` fields carry diagnostic detail.
     """
     gateway = Client()._get_spark_llm_gateway()
     return gateway.llm_gateway_generate_text_col(template, values, model_id=model_id)

{salesforce_data_customcode-6.0.3.dev1 → salesforce_data_customcode-6.0.4}/src/datacustomcode/deploy.py

@@ -26,12 +26,13 @@ from typing import (
     Callable,
     Dict,
     List,
+    Optional,
     Union,
 )
 
 from loguru import logger
 import pydantic
-from pydantic import BaseModel
+from pydantic import BaseModel, model_validator
 import requests
 
 from datacustomcode.cmd import cmd_output
@@ -366,23 +367,86 @@ class BaseConfig(BaseModel):
     entryPoint: str
 
 
+class DataObjectField(BaseModel):
+    name: str
+    label: str
+    dataType: str
+    isPrimaryKey: bool = False
+    keyQualifierFieldName: Optional[str] = None
+
+
+class DataObject(BaseModel):
+    name: str
+    label: str
+    type: str
+    category: str
+    fields: list[DataObjectField]
+
+
 class DataTransformConfig(BaseConfig):
     sdkVersion: str
     dataspace: str
     permissions: Permissions
+    dataObjects: Optional[list[DataObject]] = None
 
 
 class FunctionConfig(BaseConfig):
     pass
 
 
+class DloPermission(BaseModel):
+    dlo: list[str]
+
+
+class DmoPermission(BaseModel):
+    dmo: list[str]
+
+
 class Permissions(BaseModel):
-    read: Union[DloPermission]
-    write: Union[DloPermission]
+    read: Union[DloPermission, DmoPermission]
+    write: Union[DloPermission, DmoPermission]
+
+    @model_validator(mode="after")
+    def _no_mixed_layers(self) -> "Permissions":
+        read_is_dlo = isinstance(self.read, DloPermission)
+        write_is_dlo = isinstance(self.write, DloPermission)
+        if read_is_dlo != write_is_dlo:
+            raise ValueError(
+                "permissions.read and permissions.write must both reference "
+                "DLOs or both reference DMOs (got "
+                f"read={type(self.read).__name__}, "
+                f"write={type(self.write).__name__})"
+            )
+        return self
 
 
-class DloPermission(BaseModel):
-    dlo: list[str]
+def _permission_entries(perm: Union[DloPermission, DmoPermission]) -> list[str]:
+    """Return the list of object names regardless of layer (DLO or DMO)."""
+    if isinstance(perm, DloPermission):
+        return perm.dlo
+    return perm.dmo
+
+
+def _data_object_to_output(obj: DataObject) -> dict[str, Any]:
+    """Convert a config.json DataObject into an outputDataObjects entry."""
+    fields: list[dict[str, Any]] = []
+    for field in obj.fields:
+        entry: dict[str, Any] = {
+            "isPrimaryKey": field.isPrimaryKey,
+            "label": field.label,
+            "name": field.name,
+            "type": field.dataType,
+        }
+        if field.keyQualifierFieldName is not None:
+            entry["keyQualifierField"] = field.keyQualifierFieldName
+        fields.append(entry)
+    return {
+        "category": obj.category,
+        "fields": fields,
+        "label": obj.label,
+        "name": obj.name,
+        "type": obj.type,
+    }
 
 
 def get_config(directory: str) -> BaseConfig:
@@ -404,10 +468,17 @@ def get_config(directory: str) -> BaseConfig:
     except json.JSONDecodeError as err:
         raise ValueError(f"config.json at {config_path} is not valid JSON") from err
     except pydantic.ValidationError as err:
-        missing_fields = [str(err["loc"][0]) for err in err.errors()]
+        errors = err.errors()
+        missing = [e for e in errors if e.get("type") == "missing"]
+        if missing and len(missing) == len(errors):
+            missing_fields = [str(e["loc"][0]) for e in missing]
+            raise ValueError(
+                f"config.json at {config_path} is missing required "
+                f"fields: {', '.join(missing_fields)}"
+            ) from err
+        messages = [str(e.get("msg", "")) for e in errors]
         raise ValueError(
-            f"config.json at {config_path} is missing required "
-            f"fields: {', '.join(missing_fields)}"
+            f"config.json at {config_path} is invalid: {'; '.join(messages)}"
         ) from err
 
 
@@ -421,26 +492,45 @@ def create_data_transform(
     script_name = metadata.name
     request_hydrated = DATA_TRANSFORM_REQUEST_TEMPLATE.copy()
 
-    # Add nodes for each write DLO
-    for i, dlo in enumerate(data_transform_config.permissions.write.dlo, 1):
+    # Add nodes for each write entry (DLO or DMO)
+    for i, name in enumerate(
+        _permission_entries(data_transform_config.permissions.write), 1
+    ):
         request_hydrated["nodes"][f"node{i}"] = {
-            "relation_name": dlo,
+            "relation_name": name,
             "config": {"materialized": "table"},
             "compiled_code": "",
         }
 
-    # Add sources for each read DLO
-    for i, dlo in enumerate(data_transform_config.permissions.read.dlo, 1):
-        request_hydrated["sources"][f"source{i}"] = {"relation_name": dlo}
+    # Add sources for each read entry (DLO or DMO)
+    for i, name in enumerate(
+        _permission_entries(data_transform_config.permissions.read), 1
+    ):
+        request_hydrated["sources"][f"source{i}"] = {"relation_name": name}
 
     request_hydrated["macros"]["macro.byoc"]["arguments"][0]["name"] = script_name
 
+    definition: dict[str, Any] = {
+        "type": "DCSQL",
+        "manifest": request_hydrated,
+        "version": "56.0",
+    }
+
+    # outputDataObjects is only set for DMO-backed transforms. The server requires
+    # the schema of any DMO created/updated by the transform; DLO transforms use
+    # an existing materialized table and must not include this field.
+    if isinstance(data_transform_config.permissions.write, DmoPermission):
+        if not data_transform_config.dataObjects:
+            raise ValueError(
+                "DMO transforms require 'dataObjects' in config.json describing "
+                "the schema of each output DMO."
+            )
+        definition["outputDataObjects"] = [
+            _data_object_to_output(obj) for obj in data_transform_config.dataObjects
+        ]
+
     body = {
-        "definition": {
-            "type": "DCSQL",
-            "manifest": request_hydrated,
-            "version": "56.0",
-        },
+        "definition": definition,
         "label": f"{metadata.name}",
         "name": f"{metadata.name}",
         "type": "BATCH",

{salesforce_data_customcode-6.0.3.dev1 → salesforce_data_customcode-6.0.4}/src/datacustomcode/io/writer/base.py

@@ -27,11 +27,21 @@ if TYPE_CHECKING:
 class WriteMode(str, Enum):
     APPEND = "append"
     OVERWRITE = "overwrite"
-    OVERWRITE_PARTITIONS = "overwrite_partitions"
+    OVERWRITE_PARTITIONS = "overwrite_partitions"  # Deprecated: raises error if used
     MERGE = "merge"
     MERGE_UPSERT_DELETE = "merge_upsert_delete"
 
 
+class MergeRecordType(str, Enum):
+    """Values for the _merge_record_type column used by MERGE_UPSERT_DELETE."""
+
+    UPSERT = "UPSERT"
+    DELETE = "DELETE"
+
+
+MERGE_RECORD_TYPE_COLUMN = "_merge_record_type"
+
+
 class BaseDataCloudWriter(BaseDataAccessLayer):
     """Base class for Data Cloud writers."""
 

{salesforce_data_customcode-6.0.3.dev1 → salesforce_data_customcode-6.0.4}/src/datacustomcode/llm_gateway/spark_base.py

@@ -50,4 +50,13 @@ class SparkLLMGateway(ABC, UserExtendableNamedConfigMixin):
         values: Union[Dict[str, "Column"], "Column"],
         model_id: Optional[str] = None,
     ) -> "Column":
-        """Build a Spark ``Column`` that invokes the LLM Gateway per row."""
+        """Build a Spark ``Column`` that invokes the LLM Gateway per row and
+        yields a struct ``{status, response, error_code, error_message}``.
+
+        Select an individual field, e.g.
+        ``llm_gateway_generate_text_col(...)["response"]``. Returning a struct
+        means a single failing row doesn't abort the Spark job.
+        Failing row leaves the rest of the DataFrame intact — callers can
+        inspect ``status`` / ``error_code`` per row instead of having the
+        Spark job abort.
+        """

{salesforce_data_customcode-6.0.3.dev1 → salesforce_data_customcode-6.0.4}/src/datacustomcode/llm_gateway/spark_default.py

@@ -28,10 +28,16 @@ if TYPE_CHECKING:
     from pyspark.sql import Column
 
     from datacustomcode.llm_gateway.base import LLMGateway
+    from datacustomcode.llm_gateway.types.generate_text_response import (
+        GenerateTextResponse,
+    )
 
 
 _DEFAULT_LLM_MODEL_ID = "sfdc_ai__DefaultGPT4Omni"
 
+_STATUS_SUCCESS = "SUCCESS"
+_STATUS_ERROR = "ERROR"
+
 
 class DefaultSparkLLMGateway(SparkLLMGateway):
 
@@ -60,9 +66,17 @@ class DefaultSparkLLMGateway(SparkLLMGateway):
         values: Union[Dict[str, "Column"], "Column"],
         model_id: Optional[str] = None,
     ) -> "Column":
-
+        """Build a per-row UDF that returns a struct ``{status, response,
+        error_code, error_message}`` so per-row failures do not abort the
+        Spark job. Callers select the field they want, e.g.
+        ``llm_gateway_generate_text_col(...)["response"]``.
+        """
         from pyspark.sql.functions import struct, udf
-        from pyspark.sql.types import StringType
+        from pyspark.sql.types import (
+            StringType,
+            StructField,
+            StructType,
+        )
 
         if isinstance(values, dict):
             values_col = struct(*[v.alias(k) for k, v in values.items()])
@@ -70,19 +84,32 @@ class DefaultSparkLLMGateway(SparkLLMGateway):
             values_col = values
 
         gateway = self._llm_gateway
+        result_schema = StructType(
+            [
+                StructField("status", StringType(), True),
+                StructField("response", StringType(), True),
+                StructField("error_code", StringType(), True),
+                StructField("error_message", StringType(), True),
+            ]
+        )
 
-        def _generate(values_row: Any) -> str:
+        def _generate(values_row: Any) -> Dict[str, Optional[str]]:
             if values_row is None:
-                return ""
+                return {
+                    "status": _STATUS_ERROR,
+                    "response": None,
+                    "error_code": None,
+                    "error_message": "values column was null for this row",
+                }
             subs = (
                 values_row.asDict()
                 if hasattr(values_row, "asDict")
                 else dict(values_row)
             )
             prompt = template.format(**subs)
-            return _invoke_llm_gateway(gateway, prompt, model_id)
+            return _invoke_llm_gateway_as_struct(gateway, prompt, model_id)
 
-        return udf(_generate, StringType())(values_col)
+        return udf(_generate, result_schema)(values_col)
 
 
 def _build_underlying_gateway() -> "LLMGateway":
@@ -97,22 +124,33 @@ def _build_underlying_gateway() -> "LLMGateway":
     return cfg.to_object()
 
 
-def _invoke_llm_gateway(
+def _call_llm_gateway(
     gateway: "LLMGateway",
     prompt: str,
     model_id: Optional[str],
-) -> str:
-    from datacustomcode.llm_gateway.errors import LLMGatewayCallError
+) -> "GenerateTextResponse":
+    """Build the request and dispatch it to the underlying gateway."""
     from datacustomcode.llm_gateway.types.generate_text_request_builder import (
         GenerateTextRequestBuilder,
     )
 
-    builder = (
+    request = (
         GenerateTextRequestBuilder()
         .set_prompt(prompt)
         .set_model(model_id or _DEFAULT_LLM_MODEL_ID)
+        .build()
     )
-    response = gateway.generate_text(builder.build())
+    return gateway.generate_text(request)
+
+
+def _invoke_llm_gateway(
+    gateway: "LLMGateway",
+    prompt: str,
+    model_id: Optional[str],
+) -> str:
+    from datacustomcode.llm_gateway.errors import LLMGatewayCallError
+
+    response = _call_llm_gateway(gateway, prompt, model_id)
     if response.is_error:
         raise LLMGatewayCallError(
             f"LLM Gateway call failed: status_code={response.status_code}, "
@@ -123,3 +161,24 @@ def _invoke_llm_gateway(
             error_message=str(response.data) if response.data else None,
         )
     return response.text
+
+
+def _invoke_llm_gateway_as_struct(
+    gateway: "LLMGateway",
+    prompt: str,
+    model_id: Optional[str],
+) -> Dict[str, Optional[str]]:
+    response = _call_llm_gateway(gateway, prompt, model_id)
+    if response.is_error:
+        return {
+            "status": _STATUS_ERROR,
+            "response": None,
+            "error_code": response.error_code or None,
+            "error_message": str(response.data) if response.data else None,
+        }
+    return {
+        "status": _STATUS_SUCCESS,
+        "response": response.text,
+        "error_code": None,
+        "error_message": None,
+    }

{salesforce_data_customcode-6.0.3.dev1 → salesforce_data_customcode-6.0.4}/src/datacustomcode/run.py

@@ -201,8 +201,20 @@ def run_function_with_test(entrypoint: str, test_file: str) -> None:
 
 
 def add_py_folder(entrypoint: str):
-    default_py_folder = "py-files"  # Hardcoded folder name
+    """Add py-files subfolder and entrypoint directory to sys.path.
+
+    This ensures:
+    1. py-files/ is available for additional dependencies
+    2. The entrypoint directory is available for local module imports
+    """
+    default_py_folder = "py-files"
     cwd = Path.cwd().joinpath(entrypoint)
-    py_folder = cwd.parent.joinpath(default_py_folder)
+    entrypoint_dir = cwd.parent
+    py_folder = entrypoint_dir.joinpath(default_py_folder)
+
+    # Add py-files folder if it exists
+    if py_folder.exists():
+        sys.path.insert(0, str(py_folder))
 
-    sys.path.append(str(py_folder))
+    # Add entrypoint directory to allow local module imports
+    sys.path.insert(0, str(entrypoint_dir))

{salesforce_data_customcode-6.0.3.dev1 → salesforce_data_customcode-6.0.4}/src/datacustomcode/templates/function/.devcontainer/devcontainer.json

@@ -5,6 +5,6 @@
 		"dockerfile": "../Dockerfile"
 	},
 	"features": {
-		"ghcr.io/devcontainers/features/git:1": {},
+		"ghcr.io/devcontainers/features/git:1": {}
 	}
 }

salesforce_data_customcode-6.0.4/src/datacustomcode/templates/function/payload/entrypoint.py

@@ -0,0 +1,67 @@
+import logging
+
+from utility import extract_citations, split_text_into_chunks
+
+from datacustomcode.function import Runtime
+from datacustomcode.function.feature_types.chunking import (
+    ChunkType,
+    SearchIndexChunkingV1Output,
+    SearchIndexChunkingV1Request,
+    SearchIndexChunkingV1Response,
+)
+
+logger = logging.getLogger(__name__)
+logging.basicConfig(level=logging.INFO)
+
+# Default max chunk size (can be overridden if contract adds max_characters field)
+DEFAULT_MAX_CHUNK_SIZE = 50
+
+
+def function(
+    request: SearchIndexChunkingV1Request, runtime: Runtime
+) -> SearchIndexChunkingV1Response:
+    """Chunk documents into smaller pieces for search indexing.
+
+    Args:
+        request: SearchIndexChunkingV1Request with input documents
+        runtime: Runtime context (unused but required by contract)
+
+    Returns:
+        SearchIndexChunkingV1Response with chunked output
+    """
+    print(f"Received {len(request.input)} documents to chunk")
+
+    chunks = []
+    seq_no = 1
+
+    # Use default max chunk size
+    max_chunk_size = DEFAULT_MAX_CHUNK_SIZE
+
+    # Process each document
+    for doc_idx, doc in enumerate(request.input):
+        text = doc.text
+        metadata = doc.metadata
+
+        print(f"Processing document {doc_idx + 1}: {len(text)} characters")
+
+        # Split the text using our simple chunking algorithm
+        text_chunks = split_text_into_chunks(text, max_chunk_size, overlap=20)
+
+        # Create chunk outputs
+        for chunk_text in text_chunks:
+            citations = extract_citations(metadata)
+
+            chunk_output = SearchIndexChunkingV1Output(
+                chunk_type=ChunkType.TEXT,
+                text=chunk_text.strip(),
+                seq_no=seq_no,
+                citations=citations,
+            )
+            chunks.append(chunk_output)
+
+            print(f"Chunk {seq_no}: {len(chunk_text)} chars")
+            seq_no += 1
+
+    print(f"Generated {len(chunks)} chunks total")
+
+    return SearchIndexChunkingV1Response(output=chunks)