Refactor agent fields in llama_cloud_services (#921)

Signed-off-by: Emmanuel Ferdman <emmanuelferdman@gmail.com>

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,

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"
@@ -1073,11 +1082,7 @@ class LlamaParse(BasePydanticReader):
         return current_interval  # Default fallback
 
     async def _get_job_result(
-        self,
-        job_id: str,
-        result_type: str,
-        verbose: bool = False,
-        raise_job_error: bool = True,
+        self, job_id: str, result_type: str, verbose: bool = False
     ) -> Dict[str, Any]:
         start = time.time()
         tries = 0
@@ -1110,25 +1115,7 @@ class LlamaParse(BasePydanticReader):
                         print(".", end="", flush=True)
                     current_interval = self._calculate_backoff(current_interval)
                 else:
-                    if raise_job_error:
-                        raise JobFailedException.from_result(result_json)
-                    else:
-                        error_code = result_json.get("error_code")
-                        error_message = result_json.get("error_message")
-
-                        error_parts = [f"Job ID: {job_id} failed with status: {status}"]
-                        if error_code:
-                            error_parts.append(f"Error code: {error_code}")
-                        if error_message:
-                            error_parts.append(f"Error message: {error_message}")
-                        error_str = ", ".join(error_parts)
-
-                        return {
-                            "pages": [],
-                            "job_metadata": {"job_pages": 0},
-                            "error": error_str,
-                            "status": status,
-                        }
+                    raise JobFailedException.from_result(result_json)
             except (
                 httpx.ConnectError,
                 httpx.ReadError,
@@ -1159,7 +1146,6 @@ class LlamaParse(BasePydanticReader):
         fs: Optional[AbstractFileSystem] = None,
         result_type: Optional[str] = None,
         num_workers: Optional[int] = None,
-        raise_job_error: bool = True,
     ) -> List[Tuple[str, Dict[str, Any]]]:
         if self.partition_pages is None:
             job_results = [
@@ -1168,7 +1154,6 @@ class LlamaParse(BasePydanticReader):
                     extra_info=extra_info,
                     fs=fs,
                     result_type=result_type,
-                    raise_job_error=raise_job_error,
                 )
             ]
         else:
@@ -1178,7 +1163,6 @@ class LlamaParse(BasePydanticReader):
                 fs=fs,
                 result_type=result_type,
                 num_workers=num_workers,
-                raise_job_error=raise_job_error,
             )
         return job_results
 
@@ -1188,7 +1172,6 @@ class LlamaParse(BasePydanticReader):
         extra_info: Optional[dict] = None,
         fs: Optional[AbstractFileSystem] = None,
         result_type: Optional[str] = None,
-        raise_job_error: bool = True,
         **create_kwargs: Any,
     ) -> Tuple[str, Dict[str, Any]]:
         """Create one parse job and wait for the result."""
@@ -1198,10 +1181,7 @@ class LlamaParse(BasePydanticReader):
         if self.verbose:
             print("Started parsing the file under job_id %s" % job_id)
         result = await self._get_job_result(
-            job_id,
-            result_type or self.result_type.value,
-            verbose=self.verbose,
-            raise_job_error=raise_job_error,
+            job_id, result_type or self.result_type.value, verbose=self.verbose
         )
         return job_id, result
 
@@ -1212,7 +1192,6 @@ class LlamaParse(BasePydanticReader):
         fs: Optional[AbstractFileSystem] = None,
         result_type: Optional[str] = None,
         num_workers: Optional[int] = None,
-        raise_job_error: bool = True,
     ) -> List[Tuple[str, Dict[str, Any]]]:
         """Partition a file and run separate parse jobs per partition segment."""
         assert self.partition_pages is not None
@@ -1227,7 +1206,6 @@ class LlamaParse(BasePydanticReader):
                     extra_info=extra_info,
                     fs=fs,
                     result_type=result_type,
-                    raise_job_error=raise_job_error,
                     partition_target_pages=target_pages,
                 )
                 for target_pages in partition_pages(
@@ -1255,33 +1233,28 @@ class LlamaParse(BasePydanticReader):
                 size = self.partition_pages
             if not size:
                 break
-            # Fetch JSON result type first to get accurate pagination data
-            # and then fetch the user's desired result type if needed
-            job_id, json_result = await self._parse_one_unpartitioned(
-                file_path,
-                extra_info=extra_info,
-                fs=fs,
-                result_type=ResultType.JSON.value,
-                raise_job_error=raise_job_error,
-                partition_target_pages=f"{total}-{total + size - 1}",
-            )
-
-            if json_result.get("error"):
-                if results and "NO_DATA_FOUND_IN_FILE" in json_result.get("error", ""):
-                    return results
-                results.append((job_id, json_result))
-                return results
-
-            result_type = result_type or self.result_type.value
-            if result_type == ResultType.JSON.value:
-                job_result = json_result
-            else:
-                job_result = await self._get_job_result(
-                    job_id,
-                    result_type,
-                    verbose=self.verbose,
-                    raise_job_error=raise_job_error,
+            try:
+                # Fetch JSON result type first to get accurate pagination data
+                # and then fetch the user's desired result type if needed
+                job_id, json_result = await self._parse_one_unpartitioned(
+                    file_path,
+                    extra_info=extra_info,
+                    fs=fs,
+                    result_type=ResultType.JSON.value,
+                    partition_target_pages=f"{total}-{total + size - 1}",
                 )
+                result_type = result_type or self.result_type.value
+                if result_type == ResultType.JSON.value:
+                    job_result = json_result
+                else:
+                    job_result = await self._get_job_result(
+                        job_id, result_type, verbose=self.verbose
+                    )
+            except JobFailedException as e:
+                if results and e.error_code == "NO_DATA_FOUND_IN_FILE":
+                    # Expected when we try to read past the end of the file
+                    return results
+                raise
             results.append((job_id, job_result))
             if len(json_result["pages"]) < size:
                 break
@@ -1395,7 +1368,6 @@ class LlamaParse(BasePydanticReader):
         extra_info: Optional[dict] = None,
         fs: Optional[AbstractFileSystem] = None,
         num_workers: Optional[int] = None,
-        raise_job_error: bool = True,
     ) -> List[JobResult]:
         job_results = await self._parse_one(
             file_path,
@@ -1403,7 +1375,6 @@ class LlamaParse(BasePydanticReader):
             fs=fs,
             result_type=ResultType.JSON.value,
             num_workers=num_workers,
-            raise_job_error=raise_job_error,
         )
         return [
             JobResult(
@@ -1423,7 +1394,6 @@ class LlamaParse(BasePydanticReader):
         file_path: Union[List[FileInput], FileInput],
         extra_info: Optional[dict] = None,
         fs: Optional[AbstractFileSystem] = None,
-        raise_job_error: bool = True,
     ) -> Union[List["JobResult"], "JobResult"]:
         """
         Parse the file and return a JobResult object instead of Document objects.
@@ -1435,7 +1405,6 @@ class LlamaParse(BasePydanticReader):
             file_path: Path to the file to parse. Can be a string, path, bytes, file-like object, or a list of these.
             extra_info: Additional metadata to include in the result.
             fs: Optional filesystem to use for reading files.
-            raise_job_error: If True (default), raises JobFailedException when jobs fail. If False, returns JobResult objects with error information.
 
         Returns:
             JobResult object or list of JobResult objects if either multiple files were provided or file(s) were partitioned before parsing.
@@ -1451,11 +1420,7 @@ class LlamaParse(BasePydanticReader):
             else:
                 file_name = str(file_path)
             result = await self._aparse_one(
-                file_path,
-                file_name,
-                extra_info=extra_info,
-                fs=fs,
-                raise_job_error=raise_job_error,
+                file_path, file_name, extra_info=extra_info, fs=fs
             )
             return result[0] if len(result) == 1 else result
 
@@ -1481,7 +1446,6 @@ class LlamaParse(BasePydanticReader):
                             extra_info=extra_info,
                             fs=fs,
                             num_workers=1,
-                            raise_job_error=raise_job_error,
                         )
                         for i, f in enumerate(file_path)
                     ],
@@ -1507,7 +1471,6 @@ class LlamaParse(BasePydanticReader):
         file_path: Union[List[FileInput], FileInput],
         extra_info: Optional[dict] = None,
         fs: Optional[AbstractFileSystem] = None,
-        raise_job_error: bool = True,
     ) -> Union[List["JobResult"], "JobResult"]:
         """
         Parse the file and return a JobResult object instead of Document objects.
@@ -1519,17 +1482,12 @@ class LlamaParse(BasePydanticReader):
             file_path: Path to the file to parse. Can be a string, path, bytes, file-like object, or a list of these.
             extra_info: Additional metadata to include in the result.
             fs: Optional filesystem to use for reading files.
-            raise_job_error: If True (default), raises JobFailedException when jobs fail. If False, returns JobResult objects with error information.
 
         Returns:
             JobResult object or list of JobResult objects if multiple files were provided
         """
         try:
-            return asyncio_run(
-                self.aparse(
-                    file_path, extra_info, fs=fs, raise_job_error=raise_job_error
-                )
-            )
+            return asyncio_run(self.aparse(file_path, extra_info, fs=fs))
         except RuntimeError as e:
             if nest_asyncio_err in str(e):
                 raise RuntimeError(nest_asyncio_msg)
@@ -1796,7 +1754,7 @@ class LlamaParse(BasePydanticReader):
         return sub_docs
 
     async def aget_result(
-        self, job_id: Union[str, List[str]], raise_job_error: bool = True
+        self, job_id: Union[str, List[str]]
     ) -> Union[JobResult, List[JobResult]]:
         """
         Return JobResult object for previously parsed job(s).
@@ -1805,17 +1763,13 @@ class LlamaParse(BasePydanticReader):
 
         Args:
             job_id: Job ID or list of multiple Job IDs to be retrieved.
-            raise_job_error: If True (default), raises JobFailedException when jobs fail. If False, returns JobResult objects with error information.
 
         Returns:
             JobResult object or list of JobResult objects if multiple job IDs were provided.
         """
         if isinstance(job_id, str):
             result = await self._get_job_result(
-                job_id,
-                ResultType.JSON.value,
-                verbose=self.verbose,
-                raise_job_error=raise_job_error,
+                job_id, ResultType.JSON.value, verbose=self.verbose
             )
             return JobResult(
                 job_id=job_id,
@@ -1829,12 +1783,7 @@ class LlamaParse(BasePydanticReader):
         elif isinstance(job_id, list):
             results = []
             jobs = [
-                self._get_job_result(
-                    id_,
-                    ResultType.JSON.value,
-                    verbose=self.verbose,
-                    raise_job_error=raise_job_error,
-                )
+                self._get_job_result(id_, ResultType.JSON.value, verbose=self.verbose)
                 for id_ in job_id
             ]
             results = await run_jobs(
@@ -1859,7 +1808,7 @@ class LlamaParse(BasePydanticReader):
             raise ValueError("The input job_id must be a string or a list of strings.")
 
     def get_result(
-        self, job_id: Union[str, List[str]], raise_job_error: bool = True
+        self, job_id: Union[str, List[str]]
     ) -> Union[JobResult, List[JobResult]]:
         """
         Return JobResult object for previously parsed job(s).
@@ -1868,15 +1817,12 @@ class LlamaParse(BasePydanticReader):
 
         Args:
             job_id: Job ID or list of multiple Job IDs to be retrieved.
-            raise_job_error: If True (default), raises JobFailedException when jobs fail. If False, returns JobResult objects with error information.
 
         Returns:
             JobResult object or list of JobResult objects if multiple job IDs were provided.
         """
         try:
-            return asyncio_run(
-                self.aget_result(job_id, raise_job_error=raise_job_error)
-            )
+            return asyncio_run(self.aget_result(job_id))
         except RuntimeError as e:
             if nest_asyncio_err in str(e):
                 raise RuntimeError(nest_asyncio_msg)

py/llama_parse/pyproject.toml

@@ -11,13 +11,13 @@ dev = [
 
 [project]
 name = "llama-parse"
-version = "0.6.65"
+version = "0.6.67"
 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>=0.6.67"]
 
 [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 = "0.6.67"
 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/tests/parse/test_llama_parse.py

@@ -2,7 +2,6 @@ import os
 import pytest
 import shutil
 from typing import Optional, cast
-from unittest.mock import patch
 from fsspec.implementations.local import LocalFileSystem
 from httpx import AsyncClient
 
@@ -205,10 +204,6 @@ async def test_get_result(markdown_parser: LlamaParse) -> None:
     assert len(result.pages) == len(expected.pages)
 
 
-@pytest.mark.skipif(
-    os.environ.get("LLAMA_CLOUD_API_KEY", "") == "",
-    reason="LLAMA_CLOUD_API_KEY not set",
-)
 @pytest.mark.asyncio
 async def test_parse_audio() -> None:
     parser = LlamaParse()
@@ -216,194 +211,3 @@ async def test_parse_audio() -> None:
 
     result = await parser.aparse(filepath)
     assert result.job_id is not None
-
-
-@pytest.mark.asyncio
-async def test_error_handling_with_raise_job_error_false() -> None:
-    """Test that failed jobs return JobResult objects with error information when raise_job_error=False."""
-
-    parser = LlamaParse(api_key="test_key")
-
-    # Mock error result with full error information
-    mock_error_result = {
-        "pages": [],
-        "job_metadata": {"job_pages": 0},
-        "error": "Job ID: test_job_123 failed with status: ERROR, Error code: INVALID_FILE, Error message: File format not supported",
-        "status": "ERROR",
-    }
-
-    with patch.object(parser, "_create_job", return_value="test_job_123"), patch.object(
-        parser, "_get_job_result", return_value=mock_error_result
-    ):
-        # Test aparse with raise_job_error=False
-        result = await parser.aparse("test_file.txt", raise_job_error=False)
-
-        assert isinstance(result, type(result))  # Check it's a JobResult
-        assert result.job_id == "test_job_123"
-        assert result.error is not None
-        assert "ERROR" in result.error
-        assert "INVALID_FILE" in result.error
-        assert "File format not supported" in result.error
-        assert len(result.pages) == 0
-
-        # Test parse (synchronous version) with raise_job_error=False
-        result_sync = parser.parse("test_file.txt", raise_job_error=False)
-
-        assert isinstance(result_sync, type(result_sync))
-        assert result_sync.job_id == "test_job_123"
-        assert result_sync.error is not None
-        assert "INVALID_FILE" in result_sync.error
-        assert "File format not supported" in result_sync.error
-
-
-@pytest.mark.asyncio
-async def test_error_handling_with_raise_job_error_true() -> None:
-    """Test that failed jobs raise JobFailedException when raise_job_error=True (default behavior)."""
-
-    parser = LlamaParse(api_key="test_key")
-
-    # Mock that _get_job_result will raise JobFailedException when raise_job_error=True
-    from llama_cloud_services.parse.base import JobFailedException
-
-    def mock_get_job_result(job_id, result_type, verbose=False, raise_job_error=True):
-        if raise_job_error:
-            raise JobFailedException(
-                "test_job_123",
-                "ERROR",
-                error_code="INVALID_FILE",
-                error_message="File format not supported",
-            )
-        else:
-            return {
-                "pages": [],
-                "job_metadata": {"job_pages": 0},
-                "error": "Job ID: test_job_123 failed with status: ERROR, Error code: INVALID_FILE, Error message: File format not supported",
-                "status": "ERROR",
-            }
-
-    with patch.object(parser, "_create_job", return_value="test_job_123"), patch.object(
-        parser, "_get_job_result", side_effect=mock_get_job_result
-    ):
-        # Test aparse with raise_job_error=True (default) - should raise exception
-        with pytest.raises(JobFailedException) as exc_info:
-            await parser.aparse("test_file.txt")
-
-        assert exc_info.value.job_id == "test_job_123"
-        assert exc_info.value.status == "ERROR"
-        assert exc_info.value.error_code == "INVALID_FILE"
-
-        # Test parse (synchronous version) with raise_job_error=True (default) - should raise exception
-        with pytest.raises(JobFailedException) as exc_info:
-            parser.parse("test_file.txt")
-
-        assert exc_info.value.job_id == "test_job_123"
-        assert exc_info.value.status == "ERROR"
-
-
-@pytest.mark.asyncio
-async def test_error_handling_with_minimal_fields() -> None:
-    """Test error handling when only status is available (no error_code/error_message) with raise_job_error=False."""
-
-    parser = LlamaParse(api_key="test_key")
-
-    # Mock error result with minimal fields (only what's guaranteed)
-    mock_minimal_error_result = {
-        "pages": [],
-        "job_metadata": {"job_pages": 0},
-        "error": "Job ID: test_job_456 failed with status: CANCELED",
-        "status": "CANCELED",
-    }
-
-    with patch.object(parser, "_create_job", return_value="test_job_456"), patch.object(
-        parser, "_get_job_result", return_value=mock_minimal_error_result
-    ):
-        # Test aparse with a minimal error response and raise_job_error=False
-        result = await parser.aparse("test_file.txt", raise_job_error=False)
-
-        assert isinstance(result, type(result))
-        assert result.job_id == "test_job_456"
-        assert result.error is not None
-        assert "CANCELED" in result.error
-        assert len(result.pages) == 0
-
-
-@pytest.mark.asyncio
-async def test_successful_job_still_works() -> None:
-    """Test that successful jobs still work as before after error handling changes."""
-
-    parser = LlamaParse(api_key="test_key")
-
-    # Mock successful result
-    mock_success_result = {
-        "pages": [
-            {
-                "page": 0,
-                "text": "Sample text content",
-                "md": "# Sample markdown content",
-                "images": [],
-                "charts": [],
-                "tables": [],
-                "layout": [],
-                "items": [],
-                "status": "SUCCESS",
-                "links": [],
-                "width": 612.0,
-                "height": 792.0,
-            }
-        ],
-        "job_metadata": {"job_pages": 1},
-    }
-
-    with patch.object(
-        parser, "_create_job", return_value="success_job_456"
-    ), patch.object(parser, "_get_job_result", return_value=mock_success_result):
-        # Test aparse with a successful job (both with and without raise_job_error parameter)
-        result = await parser.aparse("test_file.txt")
-
-        assert isinstance(result, type(result))
-        assert result.job_id == "success_job_456"
-        assert result.error is None  # No error for successful jobs
-        assert len(result.pages) == 1
-        assert result.pages[0].text == "Sample text content"
-
-        # Test with explicit raise_job_error=False (should work the same for successful jobs)
-        result2 = await parser.aparse("test_file.txt", raise_job_error=False)
-
-        assert isinstance(result2, type(result2))
-        assert result2.job_id == "success_job_456"
-        assert result2.error is None
-        assert len(result2.pages) == 1
-        assert result2.pages[0].text == "Sample text content"
-
-
-@pytest.mark.asyncio
-async def test_get_result_with_raise_job_error_parameter() -> None:
-    """Test that get_result method respects the raise_job_error parameter."""
-
-    parser = LlamaParse(api_key="test_key")
-
-    # Mock error result
-    mock_error_result = {
-        "pages": [],
-        "job_metadata": {"job_pages": 0},
-        "error": "Job ID: test_job_789 failed with status: ERROR, Error code: TIMEOUT, Error message: Job timed out",
-        "status": "ERROR",
-    }
-
-    with patch.object(parser, "_get_job_result", return_value=mock_error_result):
-        # Test aget_result with raise_job_error=False
-        result = await parser.aget_result("test_job_789", raise_job_error=False)
-
-        assert isinstance(result, type(result))
-        assert result.job_id == "test_job_789"
-        assert result.error is not None
-        assert "TIMEOUT" in result.error
-        assert len(result.pages) == 0
-
-        # Test get_result (synchronous version) with raise_job_error=False
-        result_sync = parser.get_result("test_job_789", raise_job_error=False)
-
-        assert isinstance(result_sync, type(result_sync))
-        assert result_sync.job_id == "test_job_789"
-        assert result_sync.error is not None
-        assert "TIMEOUT" in result_sync.error

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(),

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 = "0.6.66"
 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; */