py 3.9

py/llama_cloud_services/beta/agent_data/schema.py

@@ -223,10 +223,12 @@ def parse_extracted_field_metadata(
         k: _parse_extracted_field_metadata_recursive(v)
         for k, v in field_metadata.items()
         if k not in _METADATA_FIELDS_SIBLING_TO_LEAF
+        and k not in _ADDITIONAL_ROOT_METADATA_FIELDS
     }
 
 
 _METADATA_FIELDS_SIBLING_TO_LEAF = {"reasoning"}
+_ADDITIONAL_ROOT_METADATA_FIELDS = {"error"}
 
 
 def _parse_extracted_field_metadata_recursive(
@@ -417,11 +419,14 @@ class ExtractedData(BaseModel, Generic[ExtractedT]):
         """
         file_id = file_id or result.file.id
         file_name = file_name or result.file.name
+        job_id = result.job_id
+        job_field_metadata = result.extraction_metadata.get("field_metadata", {})
+        errors = job_field_metadata.get("error", None)
+        if not isinstance(errors, str):
+            errors = None
 
         try:
-            field_metadata = parse_extracted_field_metadata(
-                result.extraction_metadata.get("field_metadata", {})
-            )
+            field_metadata = parse_extracted_field_metadata(job_field_metadata)
         except ValidationError:
             field_metadata = {}
 
@@ -430,11 +435,15 @@ class ExtractedData(BaseModel, Generic[ExtractedT]):
             return cls.create(
                 data=data,
                 status=status,
-                field_metadata=field_metadata,
+                field_metadata=job_field_metadata,
                 file_id=file_id,
                 file_name=file_name,
                 file_hash=file_hash,
-                metadata=metadata or {},
+                metadata={
+                    **({"field_errors": errors} if errors else {}),
+                    "job_id": job_id,
+                    **(metadata or {}),
+                },
             )
         except ValidationError as e:
             invalid_item = ExtractedData[Dict[str, Any]].create(

py/llama_parse/pyproject.toml

@@ -11,13 +11,13 @@ dev = [
 
 [project]
 name = "llama-parse"
-version = "0.6.58"
+version = "0.6.59"
 description = "Parse files into RAG-Optimized formats."
 authors = [{name = "Logan Markewich", email = "logan@llamaindex.ai"}]
 requires-python = ">=3.9,<4.0"
 readme = "README.md"
 license = "MIT"
-dependencies = ["llama-cloud-services>=0.6.58"]
+dependencies = ["llama-cloud-services>=0.6.59"]
 
 [project.scripts]
 llama-parse = "llama_parse.cli.main:parse"

py/pyproject.toml

@@ -19,7 +19,7 @@ dev = [
 
 [project]
 name = "llama-cloud-services"
-version = "0.6.58"
+version = "0.6.59"
 description = "Tailored SDK clients for LlamaCloud services."
 authors = [{name = "Logan Markewich", email = "logan@runllama.ai"}]
 requires-python = ">=3.9,<4.0"

py/unit_tests/beta/agent/test_agent_data_schema.py

@@ -24,8 +24,8 @@ from llama_cloud_services.beta.agent_data.schema import (
 # Test data models
 class Person(BaseModel):
     name: str
-    age: int
-    email: str
+    age: Optional[int] = None
+    email: Optional[str] = None
 
 
 class Company(BaseModel):
@@ -405,6 +405,7 @@ def create_file(
 
 def create_extract_run(
     id: str = "extract-123",
+    job_id: str = "job-123",
     data: Dict[str, Any] = {"name": "John Doe", "age": 30, "email": "john@example.com"},
     extraction_metadata: Dict[str, Any] = {
         "name": {
@@ -423,6 +424,7 @@ def create_extract_run(
     return ExtractRun.parse_obj(
         {
             "id": id,
+            "job_id": job_id,
             "data": data,
             "extraction_metadata": {
                 "field_metadata": extraction_metadata,
@@ -501,10 +503,9 @@ def test_extracted_data_from_extraction_result_invalid_data():
     # Create ExtractRun with data that doesn't match Person schema
     extract_run = create_extract_run(
         data={
-            "name": "Valid Name",
+            "missing_name": "Valid Name",
             "age": "not_a_number",
-            "missing_email": True,
-        },  # Invalid age, missing email
+        },  # Invalid age, missing name
         extraction_metadata={
             "name": {"confidence": 0.9},
         },
@@ -523,9 +524,8 @@ def test_extracted_data_from_extraction_result_invalid_data():
     assert isinstance(invalid_data, ExtractedData)
     assert invalid_data.status == "error"
     assert invalid_data.data == {
-        "name": "Valid Name",
+        "missing_name": "Valid Name",
         "age": "not_a_number",
-        "missing_email": True,
     }
     assert invalid_data.file_id == "error-file"
     assert invalid_data.file_name == "bad_data.pdf"
@@ -590,3 +590,26 @@ def test_full_parse_nested_dimensions():
     assert result.field_metadata == expected
     parsed = ExtractedData.model_validate_json(result.model_dump_json())
     assert parsed.field_metadata == expected
+
+
+def test_parses_field_metadata_with_error_field():
+    extract_run = create_extract_run(
+        extraction_metadata={
+            "name": {
+                "confidence": 0.95,
+                "citation": [{"page": 1, "matching_text": "John Smith"}],
+            },
+            "error": "This is an error",
+        },
+    )
+
+    parsed = ExtractedData.from_extraction_result(extract_run, Person)
+
+    assert parsed.field_metadata == {
+        "name": ExtractedFieldMetadata(
+            confidence=0.95,
+            citation=[FieldCitation(page=1, matching_text="John Smith")],
+        ),
+    }
+    assert parsed.metadata.get("field_errors") == "This is an error"
+    assert parsed.metadata.get("job_id") == "job-123"

py/uv.lock

@@ -1596,7 +1596,7 @@ wheels = [
 
 [[package]]
 name = "llama-cloud-services"
-version = "0.6.58"
+version = "0.6.59"
 source = { editable = "." }
 dependencies = [
     { name = "click", version = "8.1.8", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.10'" },