update version to 0.6.69

* Support creating indexes in a specified project_id

* Bump

.pre-commit-config.yaml

@@ -29,7 +29,7 @@ repos:
       - id: black-jupyter
         name: black-src
         alias: black
-        exclude: ".*uv.lock"
+        exclude: ".*uv.lock|examples/extract/solar_panel_e2e_comparison.ipynb"
   - repo: https://github.com/pre-commit/mirrors-mypy
     rev: v1.0.1
     hooks:

examples/extract/asset_manager_fund_analysis.ipynb

@@ -7,7 +7,7 @@
    "source": [
     "# Extraction and Analysis over a Fidelity Multi-Fund Annual Report\n",
     "\n",
-    "<a href=\"https://colab.research.google.com/github/run-llama/llama_cloud_services-demo/blob/main/examples/extract/asset_manager_fund_analysis.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>\n",
+    "<a href=\"https://colab.research.google.com/github/run-llama/llama_cloud_services/blob/main/examples/extract/asset_manager_fund_analysis.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>\n",
     "\n",
     "In this notebook we show you how to create an agentic document workflow over a complex document that contains annual reports for multiple funds - each fund reports financials in a standardized reporting structure, and it's all consolidated in the same document.\n",
     "\n",

examples/extract/automotive_sector_analysis.ipynb

@@ -7,7 +7,7 @@
    "source": [
     "# Automotive Equity Research: A Multi-Step Agentic Workflow\n",
     "\n",
-    "<a href=\"https://colab.research.google.com/github/run-llama/llama_cloud_services-demo/blob/main/examples/extract/automotive_sector_analysis.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>\n",
+    "<a href=\"https://colab.research.google.com/github/run-llama/llama_cloud_services/blob/main/examples/extract/automotive_sector_analysis.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>\n",
     "\n",
     "This notebook demonstrates an end‑to‑end agentic workflow using LlamaExtract and the LlamaIndex event‑driven workflow framework for automotive sector analysis.\n",
     "\n",

examples/parse/advanced_rag/dynamic_section_retrieval.ipynb

@@ -7,7 +7,7 @@
    "source": [
     "# Dynamic Section Retrieval with LlamaParse\n",
     "\n",
-    "<a href=\"https://colab.research.google.com/github/run-llama/llama_cloud_services-demo/blob/main/examples/parse/advanced_rag/dynamic_section_retrieval.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>\n",
+    "<a href=\"https://colab.research.google.com/github/run-llama/llama_cloud_services/blob/main/examples/parse/advanced_rag/dynamic_section_retrieval.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>\n",
     "\n",
     "This notebook showcases a concept called \"dynamic section retrieval\".\n",
     "\n",

examples/parse/demo_advanced.ipynb

@@ -6,7 +6,7 @@
    "source": [
     "# Advanced RAG with LlamaParse\n",
     "\n",
-    "<a href=\"https://colab.research.google.com/github/run-llama/llama_parse/blob/main/examples/demo_advanced.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>\n",
+    "<a href=\"https://colab.research.google.com/github/run-llama/llama_parse/blob/main/examples/parse/demo_advanced.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>\n",
     "\n",
     "This notebook is a complete walkthrough for using LlamaParse with advanced indexing/retrieval techniques in LlamaIndex over the Apple 10K Filing. \n",
     "\n",

examples/parse/demo_excel.ipynb

@@ -6,7 +6,7 @@
    "source": [
     "# RAG with Excel Spreadsheet using LlamaPrase\n",
     "\n",
-    "<a href=\"https://colab.research.google.com/github/run-llama/llama_cloud_services/blob/main/examples/demo_excel.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>\n",
+    "<a href=\"https://colab.research.google.com/github/run-llama/llama_cloud_services/blob/main/examples/parse/demo_excel.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>\n",
     "\n",
     "This notebook shows you using LlamaParse with Excel Spreadsheet.\n",
     "\n",

examples/parse/demo_get_charts.ipynb

@@ -7,7 +7,7 @@
    "source": [
     "# Download Charts\n",
     "\n",
-    "<a href=\"https://colab.research.google.com/github/run-llama/llama_cloud_services/blob/main/examples/demo_get_charts.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>\n",
+    "<a href=\"https://colab.research.google.com/github/run-llama/llama_cloud_services/blob/main/examples/parse/demo_get_charts.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>\n",
     "\n",
     "This notebook demonstrates how to download charts from a document using the result object.\n",
     "\n",

examples/parse/demo_insurance.ipynb

@@ -6,7 +6,7 @@
    "source": [
     "# LlamaParse - Fast checking Insurance Contract for Coverage\n",
     "\n",
-    "<a href=\"https://colab.research.google.com/github/run-llama/llama_cloud_services/blob/main/examples/demo_insurance.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>\n",
+    "<a href=\"https://colab.research.google.com/github/run-llama/llama_cloud_services/blob/main/examples/parse/demo_insurance.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>\n",
     "\n",
     "In this notebook we will look at how LlamaParse can be used to extract structured coverage information from an insurance policy.\n",
     "\n",
@@ -36,7 +36,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Download an insurance policy fron IRDAI\n",
+    "## Download an insurance policy from IRDAI\n",
     "\n",
     "The Insurance Regulatory and Development Authority of India (IRDAI) maintains a great resource: https://policyholder.gov.in/web/guest/non-life-insurance-products where all insurance policies available in India are publicly available for download! Let's download a complex health insurance policy as an example."
    ]
@@ -228,11 +228,11 @@
     "    result_type=\"markdown\",\n",
     "    system_prompt_append=\"\"\"\n",
     "This document is an insurance policy.\n",
-    "When a benefits/coverage/exlusion is describe in the document ammend to it add a text in the follwing benefits string format (where coverage could be an exclusion).\n",
+    "When a benefits/coverage/exlusion is describe in the document amend to it add a text in the following benefits string format (where coverage could be an exclusion).\n",
     "\n",
     "For {nameofrisk} and in this condition {whenDoesThecoverageApply} the coverage is {coverageDescription}. \n",
     "                                        \n",
-    "If the document contain a benefits TABLE that describe coverage amounts, do not ouput it as a table, but instead as a list of benefits string.\n",
+    "If the document contain a benefits TABLE that describe coverage amounts, do not output it as a table, but instead as a list of benefits string.\n",
     "                                       \n",
     "\"\"\",\n",
     ").aparse(\"./policy.pdf\")\n",

examples/parse/demo_json_tour.ipynb

@@ -7,7 +7,7 @@
    "source": [
     "# LlamaParse `JobResult` Tour\n",
     "\n",
-    "<a href=\"https://colab.research.google.com/github/run-llama/llama_cloud_services/blob/main/examples/demo_json.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>\n",
+    "<a href=\"https://colab.research.google.com/github/run-llama/llama_cloud_services/blob/main/examples/parse/demo_json.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>\n",
     "\n",
     "The `JobResult` object is the main object returned by the LlamaParse API. It contains all the information about the job, including the parsed data, metadata, and any errors.\n",
     "\n",

examples/parse/demo_languages.ipynb

@@ -9,7 +9,7 @@
     "\n",
     "LlamaParse supports users to specify a `language` parameter before uploading documents, giving users better OCR capabilities over non-English PDFs, parsing images into more accurate representations.\n",
     "\n",
-    "You can specify 80+ different languages: see this file for a full list of supported languages: https://github.com/run-llama/llama_cloud_services/blob/main/llama_parse/base.py.\n",
+    "You can specify 80+ different languages: see this file for a full list of supported languages: https://github.com/run-llama/llama_cloud_services/blob/main/py/llama_cloud_services/parse/base.py.\n",
     "\n",
     "This notebook shows a demo of this in action. \n",
     "\n",

examples/parse/excel/o1_excel_rag.ipynb

@@ -4,7 +4,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "<a href=\"https://colab.research.google.com/github/run-llama/llama_cloud_services/blob/main/examples/excel/o1_excel_rag.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
+    "<a href=\"https://colab.research.google.com/github/run-llama/llama_cloud_services/blob/main/examples/parse/excel/o1_excel_rag.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
    ]
   },
   {

examples/parse/parsing_modes/demo_auto_mode.ipynb

@@ -740,7 +740,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "In this example, these pages aren't going to be that different when parsed, but we can verify which pages triggered auto-made by looking at the [JSON output](https://github.com/run-llama/llama_cloud_services/blob/main/examples/demo_json_tour.ipynb) of LlamaParse:"
+    "In this example, these pages aren't going to be that different when parsed, but we can verify which pages triggered auto-made by looking at the [JSON output](https://github.com/run-llama/llama_cloud_services/blob/main/examples/parse/demo_json_tour.ipynb) of LlamaParse:"
    ]
   },
   {

py/llama_cloud_services/beta/agent_data/client.py

@@ -86,7 +86,7 @@ class AsyncAgentDataClient(Generic[AgentDataT]):
             client=llama_client,
             type=ExtractedPerson,
             collection="extracted_people",
-            agent_url_id="person-extraction-agent"
+            deployment_name="person-extraction-agent"
         )
 
         # Create data
@@ -109,10 +109,12 @@ class AsyncAgentDataClient(Generic[AgentDataT]):
         self,
         type: Type[AgentDataT],
         collection: str = "default",
-        agent_url_id: Optional[str] = None,
+        deployment_name: Optional[str] = None,
         client: Optional[AsyncLlamaCloud] = None,
         token: Optional[str] = None,
         base_url: Optional[str] = None,
+        # deprecated, use deployment_name instead
+        agent_url_id: Optional[str] = None,
     ):
         """
         Initialize the AsyncAgentDataClient.
@@ -123,11 +125,11 @@ class AsyncAgentDataClient(Generic[AgentDataT]):
             collection: Named collection within the agent for organizing data.
                 Defaults to "default". Collections allow logical separation of
                 different data types or workflows within the same agent.
-            agent_url_id: Unique identifier for the agent. This normally appears in the
-                url of an agent within the llama cloud platform. If not provided,
-                will attempt to use the LLAMA_DEPLOY_DEPLOYMENT_NAME environment
-                variable. Data can only be added to an already existing agent in the
-                platform.
+            deployment_name: Unique identifier for the agent deployment. This normally
+                appears in the URL of an agent within the Llama Cloud platform. If not
+                provided, will attempt to use the LLAMA_DEPLOY_DEPLOYMENT_NAME
+                environment variable. Data can only be added to an already existing
+                agent in the platform.
             client: AsyncLlamaCloud client instance for API communication. If not provided, will
                 construct one from the provided api token and base url
             token: Llama Cloud API token. Reads from LLAMA_CLOUD_API_KEY if not provided
@@ -135,15 +137,14 @@ class AsyncAgentDataClient(Generic[AgentDataT]):
                 defaults to https://api.cloud.llamaindex.ai
 
         Raises:
-            ValueError: If agent_url_id is not provided and the
+            ValueError: If deployment_name is not provided and the
                 LLAMA_DEPLOY_DEPLOYMENT_NAME environment variable is not set
 
         Note:
             The client automatically applies retry logic to all API calls with
             exponential backoff for timeout, connection, and HTTP status errors.
         """
-
-        self.agent_url_id = agent_url_id or get_default_agent_id()
+        self.deployment_name = deployment_name or agent_url_id or get_default_agent_id()
 
         self.collection = collection
         if not client:
@@ -164,7 +165,7 @@ class AsyncAgentDataClient(Generic[AgentDataT]):
     @agent_data_retry
     async def create_item(self, data: AgentDataT) -> TypedAgentData[AgentDataT]:
         raw_data = await self.client.beta.create_agent_data(
-            agent_slug=self.agent_url_id,
+            deployment_name=self.deployment_name,
             collection=self.collection,
             data=data.model_dump(),
         )
@@ -211,7 +212,7 @@ class AsyncAgentDataClient(Generic[AgentDataT]):
             include_total: Whether to include the total count in the response. Defaults to False to improve performance. It's recommended to only request on the first page.
         """
         raw = await self.client.beta.search_agent_data_api_v_1_beta_agent_data_search_post(
-            agent_slug=self.agent_url_id,
+            deployment_name=self.deployment_name,
             collection=self.collection,
             filter=filter,
             order_by=order_by,
@@ -254,7 +255,7 @@ class AsyncAgentDataClient(Generic[AgentDataT]):
             page_size: Maximum number of groups to return per page.
         """
         raw = await self.client.beta.aggregate_agent_data_api_v_1_beta_agent_data_aggregate_post(
-            agent_slug=self.agent_url_id,
+            deployment_name=self.deployment_name,
             collection=self.collection,
             page_size=page_size,
             filter=filter,

py/llama_cloud_services/beta/agent_data/schema.py

@@ -10,7 +10,7 @@ CRUD operations, search capabilities, filtering, and aggregation functionality
 for managing agent-generated data at scale.
 
 Key Concepts:
-- Agent Slug: Unique identifier for an agent instance
+- Deployment Name: Unique identifier for an agent deployment
 - Collection: Named grouping of data within an agent (defaults to "default"). Data within a collection should be of the same type.
 - Agent Data: Individual structured data records with metadata and timestamps
 
@@ -26,7 +26,7 @@ Example Usage:
         client=async_llama_cloud,
         type=Person,
         collection="people",
-        agent_url_id="my-extraction-agent-xyz"
+        deployment_name="my-extraction-agent-xyz"
     )
 
     # Create typed data
@@ -78,7 +78,7 @@ class TypedAgentData(BaseModel, Generic[AgentDataT]):
 
     Attributes:
         id: Unique identifier for this data record
-        agent_url_id: Identifier of the agent that created this data
+        deployment_name: Identifier of the agent deployment that created this data
         collection: Named collection within the agent (used for organization)
         data: The actual structured data payload (typed as AgentDataT)
         created_at: Timestamp when the record was first created
@@ -94,8 +94,8 @@ class TypedAgentData(BaseModel, Generic[AgentDataT]):
     """
 
     id: Optional[str] = Field(description="Unique identifier for this data record")
-    agent_url_id: str = Field(
-        description="Identifier of the agent that created this data"
+    deployment_name: str = Field(
+        description="Identifier of the agent deployment that created this data"
     )
     collection: Optional[str] = Field(
         description="Named collection within the agent for data organization"
@@ -124,7 +124,7 @@ class TypedAgentData(BaseModel, Generic[AgentDataT]):
 
         return cls(
             id=raw_data.id,
-            agent_url_id=raw_data.agent_slug,
+            deployment_name=raw_data.deployment_name,
             collection=raw_data.collection,
             data=data,
             created_at=raw_data.created_at,
@@ -222,12 +222,16 @@ def parse_extracted_field_metadata(
     return {
         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
+        if not _is_reasoning_field(k, v) and k not in _ADDITIONAL_ROOT_METADATA_FIELDS
     }
 
 
-_METADATA_FIELDS_SIBLING_TO_LEAF = {"reasoning"}
+def _is_reasoning_field(field_name: str, field_value: Any) -> bool:
+    # There can either be a user specified reasoning field (from the schema), or a reasoning metadata field for the
+    # dict of values
+    return field_name == "reasoning" and isinstance(field_value, str)
+
+
 _ADDITIONAL_ROOT_METADATA_FIELDS = {"error"}
 
 
@@ -257,14 +261,12 @@ def _parse_extracted_field_metadata_recursive(
             except ValidationError:
                 pass
         additional_fields = {
-            k: v
-            for k, v in field_value.items()
-            if k in _METADATA_FIELDS_SIBLING_TO_LEAF
+            k: v for k, v in field_value.items() if _is_reasoning_field(k, v)
         }
         return {
             k: _parse_extracted_field_metadata_recursive(v, additional_fields)
             for k, v in field_value.items()
-            if k not in _METADATA_FIELDS_SIBLING_TO_LEAF
+            if not _is_reasoning_field(k, v)
         }
     elif isinstance(field_value, list):
         return [_parse_extracted_field_metadata_recursive(item) for item in field_value]

py/llama_cloud_services/index/base.py

@@ -489,6 +489,7 @@ class LlamaCloudIndex(BaseManagedIndex):
         name: str,
         project_name: str = DEFAULT_PROJECT_NAME,
         organization_id: Optional[str] = None,
+        project_id: Optional[str] = None,
         api_key: Optional[str] = None,
         base_url: Optional[str] = None,
         app_url: Optional[str] = None,
@@ -504,15 +505,15 @@ class LlamaCloudIndex(BaseManagedIndex):
         app_url = app_url or os.environ.get("LLAMA_CLOUD_APP_URL", DEFAULT_APP_URL)
         client = get_client(api_key, base_url, app_url, timeout)
 
-        # create project if it doesn't exist
-        project = client.projects.upsert_project(
-            organization_id=organization_id, request=ProjectCreate(name=project_name)
-        )
-        if project.id is None:
-            raise ValueError(f"Failed to create/get project {project_name}")
-
-        if verbose:
-            print(f"Created project {project.id} with name {project.name}")
+        if project_id is None:
+            # create project if it doesn't exist
+            project = client.projects.upsert_project(
+                organization_id=organization_id,
+                request=ProjectCreate(name=project_name),
+            )
+            project_id = project.id
+            if verbose:
+                print(f"Created project {project_id} with name {project_name}")
 
         # create pipeline
         pipeline_create = PipelineCreate(
@@ -523,7 +524,7 @@ class LlamaCloudIndex(BaseManagedIndex):
             llama_parse_parameters=llama_parse_parameters or LlamaParseParameters(),
         )
         pipeline = client.pipelines.upsert_pipeline(
-            project_id=project.id, request=pipeline_create
+            project_id=project_id, request=pipeline_create
         )
         if pipeline.id is None:
             raise ValueError(f"Failed to create/get pipeline {name}")
@@ -532,8 +533,7 @@ class LlamaCloudIndex(BaseManagedIndex):
 
         return cls(
             name,
-            project_name=project.name,
-            organization_id=project.organization_id,
+            project_id=project_id,
             api_key=api_key,
             base_url=base_url,
             app_url=app_url,
@@ -606,6 +606,7 @@ class LlamaCloudIndex(BaseManagedIndex):
         name: str,
         project_name: str = DEFAULT_PROJECT_NAME,
         organization_id: Optional[str] = None,
+        project_id: Optional[str] = None,
         api_key: Optional[str] = None,
         base_url: Optional[str] = None,
         app_url: Optional[str] = None,
@@ -631,6 +632,7 @@ class LlamaCloudIndex(BaseManagedIndex):
             verbose=verbose,
             embedding_config=embedding_config,
             transform_config=transform_config,
+            project_id=project_id,
         )
 
         app_url = app_url or os.environ.get("LLAMA_CLOUD_APP_URL", DEFAULT_APP_URL)

py/llama_cloud_services/parse/base.py

@@ -420,6 +420,10 @@ class LlamaParse(BasePydanticReader):
         default=False,
         description="If set to true, the parser will extract sub-tables from the spreadsheet when possible (more than one table per sheet).",
     )
+    spreadsheet_force_formula_computation: Optional[bool] = Field(
+        default=False,
+        description="If set to true, the parser will re-compute values for all spreadsheet cells containing formulas.",
+    )
     specialized_chart_parsing_agentic: Optional[bool] = Field(
         default=False,
         description="If set to true, the parser will use a specialized agentic chart parsing model to extract data from charts. This model is able to understand the chart type and extract the data accordingly.",
@@ -965,6 +969,11 @@ class LlamaParse(BasePydanticReader):
         if self.spreadsheet_extract_sub_tables:
             data["spreadsheet_extract_sub_tables"] = self.spreadsheet_extract_sub_tables
 
+        if self.spreadsheet_force_formula_computation:
+            data[
+                "spreadsheet_force_formula_computation"
+            ] = self.spreadsheet_force_formula_computation
+
         if self.specialized_chart_parsing_agentic:
             data[
                 "specialized_chart_parsing_agentic"

py/llama_parse/pyproject.toml

@@ -11,13 +11,13 @@ dev = [
 
 [project]
 name = "llama-parse"
-version = "0.6.65"
+version = "0.6.69"
 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>=0.6.64"]
+dependencies = ["llama-cloud-services>=0.6.69"]
 
 [project.scripts]
 llama-parse = "llama_parse.cli.main:parse"

py/pyproject.toml

@@ -19,7 +19,7 @@ dev = [
 
 [project]
 name = "llama-cloud-services"
-version = "0.6.65"
+version = "0.6.69"
 description = "Tailored SDK clients for LlamaCloud services."
 authors = [{name = "Logan Markewich", email = "logan@runllama.ai"}]
 requires-python = ">=3.9,<4.0"
@@ -27,7 +27,7 @@ readme = "README.md"
 license = "MIT"
 dependencies = [
   "llama-index-core>=0.12.0",
-  "llama-cloud==0.1.41",
+  "llama-cloud==0.1.42",
   "pydantic>=2.8,!=2.10",
   "click>=8.1.7,<9",
   "python-dotenv>=1.0.1,<2",

py/tests/beta/agent_data/test_agent_data_client.py

@@ -68,7 +68,7 @@ async def test_agent_data_crud_operations():
         client=client,
         type=ExampleData,
         collection=f"test-collection-{test_id[:8]}",
-        agent_url_id=LLAMA_DEPLOY_DEPLOYMENT_NAME,
+        deployment_name=LLAMA_DEPLOY_DEPLOYMENT_NAME,
     )
 
     # Create test data

py/unit_tests/beta/agent/test_agent_data_schema.py

@@ -38,7 +38,7 @@ def test_typed_agent_data_from_raw():
     """Test TypedAgentData.from_raw class method."""
     raw_data = AgentData(
         id="456",
-        agent_slug="extraction-agent",
+        deployment_name="extraction-agent",
         collection="employees",
         data={"name": "Jane Smith", "age": 25, "email": "jane@company.com"},
         created_at=datetime.now(),
@@ -48,7 +48,7 @@ def test_typed_agent_data_from_raw():
     typed_data = TypedAgentData.from_raw(raw_data, Person)
 
     assert typed_data.id == "456"
-    assert typed_data.agent_url_id == "extraction-agent"
+    assert typed_data.deployment_name == "extraction-agent"
     assert typed_data.collection == "employees"
     assert typed_data.data.name == "Jane Smith"
     assert typed_data.data.age == 25
@@ -59,7 +59,7 @@ def test_typed_agent_data_from_raw_validation_error():
     """Test TypedAgentData.from_raw with invalid data."""
     raw_data = AgentData(
         id="789",
-        agent_slug="test-agent",
+        deployment_name="test-agent",
         collection="people",
         data={"name": "Invalid Person", "age": "not_a_number"},  # Invalid age
         created_at=datetime.now(),
@@ -613,3 +613,51 @@ def test_parses_field_metadata_with_error_field():
     }
     assert parsed.metadata.get("field_errors") == "This is an error"
     assert parsed.metadata.get("job_id") == "job-123"
+
+
+REASONING_IN_SCHEMA = {
+    "majority_opinion": {
+        "type": {
+            "citation": [
+                {
+                    "page": 4,
+                    "matching_text": "BARRETT, J., delivered the opinion for a unanimous Court.",
+                },
+                {"page": 11, "matching_text": "Opinion of the Court"},
+            ],
+            "parsing_confidence": 1.0,
+            "extraction_confidence": 0.9999998919950147,
+            "confidence": 0.9999998919950147,
+        },
+        "reasoning": {
+            "citation": [
+                {
+                    "page": 15,
+                    "matching_text": "We hold that §5110(b)(1) is not subject to equitable tolling and affirm the judg...",
+                }
+            ],
+            "parsing_confidence": 1.0,
+            "extraction_confidence": 0.414292785946868,
+            "confidence": 0.414292785946868,
+        },
+    },
+    "reasoning": {
+        "citation": [
+            {
+                "page": 15,
+                "matching_text": "We hold that §5110(b)(1) is not subject to equitable tolling and affirm the judg...",
+            }
+        ],
+        "parsing_confidence": 1.0,
+        "extraction_confidence": 0.414292785946868,
+        "confidence": 0.414292785946868,
+    },
+}
+
+
+def test_field_conflict_in_schema():
+    extracted = parse_extracted_field_metadata(REASONING_IN_SCHEMA)
+    assert isinstance(extracted["reasoning"], ExtractedFieldMetadata)
+    assert isinstance(
+        extracted["majority_opinion"]["reasoning"], ExtractedFieldMetadata
+    )

py/unit_tests/index/test_unit_index.py

@@ -1,16 +1,155 @@
 import pytest
+from unittest.mock import MagicMock, patch
 
+import llama_cloud_services.index.base as base
+from llama_cloud import (
+    PipelineEmbeddingConfig_ManagedOpenaiEmbedding,
+    Project,
+    Pipeline,
+    CloudDocument,
+)
+from llama_index.core.constants import DEFAULT_PROJECT_NAME
 from llama_index.core.indices.managed.base import BaseManagedIndex
-from llama_cloud_services.index import (
-    LlamaCloudIndex,
+from llama_index.core.schema import Document
+from llama_cloud_services.index import LlamaCloudIndex
+
+
+# Simple test data as values, not fixtures
+TEST_PROJECT = Project(id="proj-123", name="test-project", organization_id="org-123")
+
+EMBEDDING_CONFIG = PipelineEmbeddingConfig_ManagedOpenaiEmbedding(
+    type="MANAGED_OPENAI_EMBEDDING"
+)
+TEST_PIPELINE = Pipeline(
+    id="pipe-456",
+    name="test-pipeline",
+    project_id="proj-123",
+    embedding_config=PipelineEmbeddingConfig_ManagedOpenaiEmbedding(
+        type="MANAGED_OPENAI_EMBEDDING"
+    ),
 )
 
 
-def test_class():
+@pytest.fixture
+def mock_client() -> MagicMock:
+    """Mock client with sensible defaults."""
+    client = MagicMock()
+    client.projects.upsert_project.return_value = Project(
+        id="default-proj", name=DEFAULT_PROJECT_NAME, organization_id="default-org"
+    )
+    client.pipelines.upsert_pipeline.return_value = Pipeline(
+        id="default-pipe",
+        name="default",
+        project_id="default-proj",
+        embedding_config=EMBEDDING_CONFIG,
+    )
+    client.pipelines.upsert_batch_pipeline_documents.return_value = [
+        CloudDocument(id="doc-1", text="test", metadata={})
+    ]
+    return client
+
+
+@pytest.fixture(autouse=True)
+def base_patches(mock_client: MagicMock) -> None:
+    """Auto-applied patches for all tests."""
+    with (
+        patch.object(base, "get_client", return_value=mock_client),
+        patch.object(
+            base,
+            "resolve_project_and_pipeline",
+            return_value=(TEST_PROJECT, TEST_PIPELINE),
+        ),
+        patch.object(base.LlamaCloudIndex, "wait_for_completion"),
+    ):
+        yield
+
+
+def test_class() -> None:
     names_of_base_classes = [b.__name__ for b in LlamaCloudIndex.__mro__]
     assert BaseManagedIndex.__name__ in names_of_base_classes
 
 
-def test_conflicting_index_identifiers():
+def test_conflicting_index_identifiers() -> None:
     with pytest.raises(ValueError):
         LlamaCloudIndex(name="test", pipeline_id="test", index_id="test")
+
+
+def test_from_documents_uses_provided_project_id(mock_client: MagicMock) -> None:
+    provided_project_id = "proj-123"
+    organization_id = "org-abc"
+    index_name = "my_new_index"
+
+    # Override resolve to return project with provided ID
+    test_project = Project(
+        id=provided_project_id, name="my_project", organization_id=organization_id
+    )
+    test_pipeline = Pipeline(
+        id="pipe-xyz",
+        name=index_name,
+        project_id=provided_project_id,
+        embedding_config=EMBEDDING_CONFIG,
+    )
+
+    with patch.object(
+        base, "resolve_project_and_pipeline", return_value=(test_project, test_pipeline)
+    ):
+        docs = [Document(text="hello")]
+        index = LlamaCloudIndex.from_documents(
+            documents=docs,
+            name=index_name,
+            project_id=provided_project_id,
+        )
+
+    # Assert - project upsert not called; pipeline uses provided project_id
+    mock_client.projects.upsert_project.assert_not_called()
+    assert mock_client.pipelines.upsert_pipeline.call_count == 1
+    assert (
+        mock_client.pipelines.upsert_pipeline.call_args.kwargs["project_id"]
+        == provided_project_id
+    )
+    assert index.project.id == provided_project_id
+
+
+def test_from_documents_upserts_project_when_project_id_missing(
+    mock_client: MagicMock,
+) -> None:
+    organization_id = "org-xyz"
+    index_name = "my_new_index"
+
+    # Project is created when project_id is not provided
+    upserted_project = Project(
+        id="proj-999", name=DEFAULT_PROJECT_NAME, organization_id=organization_id
+    )
+    mock_client.projects.upsert_project.return_value = upserted_project
+
+    test_pipeline = Pipeline(
+        id="pipe-xyz",
+        name=index_name,
+        project_id=upserted_project.id,
+        embedding_config=EMBEDDING_CONFIG,
+    )
+
+    with patch.object(
+        base,
+        "resolve_project_and_pipeline",
+        return_value=(upserted_project, test_pipeline),
+    ):
+        docs = [Document(text="world")]
+        index = LlamaCloudIndex.from_documents(
+            documents=docs,
+            name=index_name,
+            organization_id=organization_id,
+        )
+
+    # Assert - project was upserted with org id and default project name
+    mock_client.projects.upsert_project.assert_called_once()
+    kwargs = mock_client.projects.upsert_project.call_args.kwargs
+    assert kwargs["organization_id"] == organization_id
+    assert kwargs["request"].name == DEFAULT_PROJECT_NAME
+
+    # Pipeline created under the upserted project id
+    assert (
+        mock_client.pipelines.upsert_pipeline.call_args.kwargs["project_id"]
+        == upserted_project.id
+    )
+    assert index.project.id == upserted_project.id

py/uv.lock

@@ -1582,21 +1582,21 @@ wheels = [
 
 [[package]]
 name = "llama-cloud"
-version = "0.1.41"
+version = "0.1.42"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "certifi" },
     { name = "httpx" },
     { name = "pydantic" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/62/6c/b2e84eebed376aea34c446cab745da5fc4e9dc53309180672299083219d5/llama_cloud-0.1.41.tar.gz", hash = "sha256:dcb741b779e3e740cd64928cfffc8ef70ed0e9bae9ef26acbe1d7e32aa737bdc", size = 109854, upload-time = "2025-09-05T22:45:13.069Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/21/04/ae0694b582d6aab4d6e7957febb7bff048897ac231ad80ba1bd71547d944/llama_cloud-0.1.42.tar.gz", hash = "sha256:485aa0e364ea648e3aaa3b2c54af7bcb6f2242c50b4f86ec022e137413fff464", size = 112480, upload-time = "2025-09-16T20:25:42.631Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/1e/4d/f0af76b389310840ce3483a92560a152025b0eefe4eee0c81102bf3317e6/llama_cloud-0.1.41-py3-none-any.whl", hash = "sha256:c847f288f0d3f4b23f47345088006deae5f2cf3f223ac1819d4c1531e9aaa13e", size = 307646, upload-time = "2025-09-05T22:45:11.597Z" },
+    { url = "https://files.pythonhosted.org/packages/6a/61/85d115699a59d03f0783e119aaf6d534fca95dbe1a4531a8056e6a4774ed/llama_cloud-0.1.42-py3-none-any.whl", hash = "sha256:4ed3edde4a277ff52eeb831188c8476eb079b5e4605ad3142157a0f054b27d96", size = 311857, upload-time = "2025-09-16T20:25:41.479Z" },
 ]
 
 [[package]]
 name = "llama-cloud-services"
-version = "0.6.65"
+version = "0.6.68"
 source = { editable = "." }
 dependencies = [
     { name = "click", version = "8.1.8", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.10'" },
@@ -1631,7 +1631,7 @@ dev = [
 requires-dist = [
     { name = "click", specifier = ">=8.1.7,<9" },
     { name = "eval-type-backport", marker = "python_full_version < '3.10'", specifier = ">=0.2.0,<0.3" },
-    { name = "llama-cloud", specifier = "==0.1.41" },
+    { name = "llama-cloud", specifier = "==0.1.42" },
     { name = "llama-index-core", specifier = ">=0.12.0" },
     { name = "packaging", specifier = ">=25.0" },
     { name = "platformdirs", specifier = ">=4.3.7,<5" },

ts/llama_cloud_services/package.json

@@ -1,6 +1,6 @@
 {
   "name": "llama-cloud-services",
-  "version": "0.3.5",
+  "version": "0.3.6",
   "type": "module",
   "license": "MIT",
   "scripts": {

ts/llama_cloud_services/src/beta/agent/client.ts

@@ -25,20 +25,23 @@ import type {
 export class AgentClient<T = unknown> {
   private client: ReturnType<typeof createClient>;
   private collection: string;
-  private agentUrlId: string;
+  private deploymentName: string;
 
   constructor({
     client = defaultClient,
     collection = "default",
-    agentUrlId = "_public",
+    deploymentName = "_public",
+    agentUrlId,
   }: {
     client?: ReturnType<typeof createClient>;
     collection?: string;
+    deploymentName?: string;
+    // deprecated, use deploymentName instead
     agentUrlId?: string;
   }) {
     this.client = client;
     this.collection = collection;
-    this.agentUrlId = agentUrlId;
+    this.deploymentName = agentUrlId || deploymentName;
   }
 
   /**
@@ -48,7 +51,7 @@ export class AgentClient<T = unknown> {
     const response = await createAgentDataApiV1BetaAgentDataPost({
       throwOnError: true,
       body: {
-        agent_slug: this.agentUrlId,
+        deployment_name: this.deploymentName,
         collection: this.collection,
         data: data as Record<string, unknown>,
       },
@@ -118,7 +121,7 @@ export class AgentClient<T = unknown> {
     const response = await searchAgentDataApiV1BetaAgentDataSearchPost({
       throwOnError: true,
       body: {
-        agent_slug: this.agentUrlId,
+        deployment_name: this.deploymentName,
         ...(this.collection !== undefined && {
           collection: this.collection,
         }),
@@ -165,7 +168,7 @@ export class AgentClient<T = unknown> {
     const response = await aggregateAgentDataApiV1BetaAgentDataAggregatePost({
       throwOnError: true,
       body: {
-        agent_slug: this.agentUrlId,
+        deployment_name: this.deploymentName,
         ...(this.collection !== undefined && {
           collection: this.collection,
         }),
@@ -209,7 +212,7 @@ export class AgentClient<T = unknown> {
   private transformResponse(data: AgentData): TypedAgentData<T> {
     const result: TypedAgentData<T> = {
       id: data.id!,
-      agentUrlId: data.agent_slug,
+      deploymentName: data.deployment_name,
       data: data.data as T,
       createdAt: new Date(data.created_at!),
       updatedAt: new Date(data.updated_at!),
@@ -250,10 +253,10 @@ export interface AgentDataClientOptions {
   /** Base URL for the client */
   /** Base URL of the llama cloud api */
   baseUrl?: string;
-  /** If running in an agent runtime, optionally provide the window url to infer the agent url id */
+  /** If running in an agent runtime, optionally provide the window url to infer the deployment name */
   windowUrl?: string;
-  /** Agent URL ID for the client, if not provided, it will be inferred from the window url, or fall back to "default" */
-  agentUrlId?: string;
+  /** Deployment name for the client, if not provided, it will be inferred from the window url, or fall back to "default" */
+  deploymentName?: string;
   /** Collection name for the client, defaults to "default" */
   collection?: string;
 }
@@ -267,22 +270,25 @@ export function createAgentDataClient<T = unknown>({
   client = defaultClient,
   windowUrl,
   env,
+  deploymentName,
   agentUrlId,
   collection = "default",
 }: {
   client?: ReturnType<typeof createClient>;
   windowUrl?: string;
   env?: Record<string, string>;
+  deploymentName?: string;
+  // deprecated, use deploymentName instead
   agentUrlId?: string;
   collection?: string;
 } = {}): AgentClient<T> {
-  if (env && !agentUrlId) {
-    agentUrlId =
+  if (env && !deploymentName) {
+    deploymentName =
       env.LLAMA_DEPLOY_DEPLOYMENT_NAME ||
       env.NEXT_PUBLIC_LLAMA_DEPLOY_DEPLOYMENT_NAME ||
       env.VITE_LLAMA_DEPLOY_DEPLOYMENT_NAME;
   }
-  if (windowUrl && !agentUrlId) {
+  if (windowUrl && !deploymentName) {
     try {
       const url = new URL(windowUrl);
       const path = url.pathname;
@@ -291,17 +297,18 @@ export function createAgentDataClient<T = unknown>({
         url.hostname.includes("127.0.0.1");
       if (path.startsWith("/deployments/") && !isLocalhost) {
         // /deployments/<agent-url-id>/ui/ -> ["", "deployments", "<agent-url-id>", "ui"]
-        agentUrlId = path.split("/")[2];
+        deploymentName = path.split("/")[2];
       }
     } catch (error) {
       console.warn(
-        "Failed to infer agent url id from window url, falling back to default",
+        "Failed to infer deployment name from window url, falling back to default",
         error,
       );
     }
   }
 
   return new AgentClient({
+    ...(deploymentName && { deploymentName }),
     ...(agentUrlId && { agentUrlId }),
     collection,
     client,

ts/llama_cloud_services/src/beta/agent/types.ts

@@ -87,8 +87,8 @@ export interface ExtractedData<T = unknown> {
 export interface TypedAgentData<T = unknown> {
   /** The unique ID of the agent data record. */
   id: string;
-  /** The ID of the agent that created the data. */
-  agentUrlId: string;
+  /** The deployment name of the agent that created the data. */
+  deploymentName: string;
   /** The collection of the agent data. */
   collection?: string;
   /** The data of the agent data. Usually an ExtractedData&lt;SomeOtherType&gt; */