fix index tests

* Add timeouts

* Session timeouts too

.github/workflows/test_e2e_py.yml

@@ -12,6 +12,7 @@ env:
 jobs:
   test_e2e:
     runs-on: ubuntu-latest
+    timeout-minutes: 30
     strategy:
       # You can use PyPy versions in python-version.
       # For example, pypy-2.7 and pypy-3.8

py/Makefile

@@ -15,4 +15,4 @@ test:	## Run unit tests via pytest
 
 .PHONY: e2e
 e2e:	## Run all tests. Run with high parallelism using xdist since tests are bottlenecked bound by the slow backend parsing
-	uv run pytest -v -n 32 tests/
+	uv run pytest -v -n 32 --timeout=300 --session-timeout=1740 tests/

py/llama_cloud_services/beta/sheets/client.py

@@ -2,7 +2,7 @@ import asyncio
 import io
 import os
 import time
-from typing import TYPE_CHECKING
+from typing import Any, Dict, TYPE_CHECKING
 
 import httpx
 from llama_cloud.client import AsyncLlamaCloud
@@ -68,6 +68,8 @@ class LlamaSheets:
         max_timeout: int = 300,
         poll_interval: int = 5,
         max_retries: int = 3,
+        project_id: str | None = None,
+        organization_id: str | None = None,
         async_httpx_client: httpx.AsyncClient | None = None,
     ) -> None:
         """Initialize the LlamaSheets client.
@@ -78,6 +80,8 @@ class LlamaSheets:
             max_timeout: Maximum time to wait for job completion in seconds
             poll_interval: Interval between status checks in seconds
             max_retries: Maximum number of retries for failed requests
+            project_id: Project ID for file operations. If not provided, will use LLAMA_CLOUD_PROJECT_ID env var
+            organization_id: Organization ID for file operations. If not provided, will use LLAMA_CLOUD_ORGANIZATION_ID env var
             async_httpx_client: Optional custom async httpx client
         """
         self.api_key = api_key or os.environ.get("LLAMA_CLOUD_API_KEY")
@@ -93,15 +97,32 @@ class LlamaSheets:
         self.poll_interval = poll_interval
         self.max_retries = max_retries
 
+        self.project_id = project_id or os.environ.get("LLAMA_CLOUD_PROJECT_ID")
+        self.organization_id = organization_id or os.environ.get(
+            "LLAMA_CLOUD_ORGANIZATION_ID"
+        )
+
         self._async_client: httpx.AsyncClient | None = async_httpx_client
         self._files_client = FileClient(
             AsyncLlamaCloud(
                 token=self.api_key,
                 base_url=self.base_url,
                 httpx_client=async_httpx_client,
-            )
+            ),
+            project_id=self.project_id,
+            organization_id=self.organization_id,
         )
 
+    def _get_default_params(self) -> dict[str, str]:
+        """Get default query parameters for API requests"""
+        params = {}
+        if self.project_id is not None:
+            params["project_id"] = self.project_id
+        if self.organization_id is not None:
+            params["organization_id"] = self.organization_id
+
+        return params
+
     def _get_async_client(self) -> httpx.AsyncClient:
         """Get or create the async httpx client"""
         if self._async_client is None:
@@ -306,6 +327,8 @@ class LlamaSheets:
             "config": config.model_dump(mode="json", exclude_none=True),
         }
 
+        params = self._get_default_params()
+
         try:
             async for attempt in AsyncRetrying(
                 stop=stop_after_attempt(self.max_retries),
@@ -318,6 +341,7 @@ class LlamaSheets:
                     response = await client.post(
                         f"{self.base_url}/api/v1/beta/sheets/jobs",
                         headers=self._get_headers(),
+                        params=params,
                         json=payload,
                     )
                     response.raise_for_status()
@@ -347,12 +371,17 @@ class LlamaSheets:
             ):
                 with attempt:
                     client = self._get_async_client()
+                    params: Dict[str, Any] = {
+                        "include_results": include_results_metadata,
+                        **self._get_default_params(),
+                    }
                     response = await client.get(
                         f"{self.base_url}/api/v1/beta/sheets/jobs/{job_id}",
                         headers=self._get_headers(),
-                        params={"include_results": include_results_metadata},
+                        params=params,
                     )
                     response.raise_for_status()
+
                     return SpreadsheetJobResult.model_validate(response.json())
         except Exception as e:
             raise SpreadsheetAPIError(f"Failed to get job status: {e}") from e
@@ -415,6 +444,8 @@ class LlamaSheets:
         # Get presigned URL
         presigned_response = None
         result_type_str = str(result_type)
+        params = self._get_default_params()
+
         try:
             async for attempt in AsyncRetrying(
                 stop=stop_after_attempt(self.max_retries),
@@ -427,6 +458,7 @@ class LlamaSheets:
                     response = await client.get(
                         f"{self.base_url}/api/v1/beta/sheets/jobs/{job_id}/regions/{region_id}/result/{result_type_str}",
                         headers=self._get_headers(),
+                        params=params,
                     )
                     response.raise_for_status()
                     presigned_response = PresignedUrlResponse.model_validate(

py/llama_cloud_services/index/base.py

@@ -654,6 +654,9 @@ class LlamaCloudIndex(BaseManagedIndex):
             ],
         )
 
+        # Trigger a sync
+        client.pipelines.sync_pipeline(pipeline_id=index.pipeline.id)
+
         doc_ids = [doc.id for doc in upserted_documents]
         index.wait_for_completion(
             doc_ids=doc_ids, verbose=verbose, raise_on_error=raise_on_error
@@ -738,6 +741,10 @@ class LlamaCloudIndex(BaseManagedIndex):
                     )
                 ],
             )
+
+            # Trigger a sync
+            self._client.pipelines.sync_pipeline(pipeline_id=self.pipeline.id)
+
             upserted_document = upserted_documents[0]
             self.wait_for_completion(
                 doc_ids=[upserted_document.id], verbose=verbose, raise_on_error=True
@@ -760,6 +767,9 @@ class LlamaCloudIndex(BaseManagedIndex):
                     )
                 ],
             )
+            # Trigger a sync
+            await self._aclient.pipelines.sync_pipeline(pipeline_id=self.pipeline.id)
+
             upserted_document = upserted_documents[0]
             await self.await_for_completion(
                 doc_ids=[upserted_document.id], verbose=verbose, raise_on_error=True
@@ -782,6 +792,9 @@ class LlamaCloudIndex(BaseManagedIndex):
                     )
                 ],
             )
+            # Trigger a sync
+            self._client.pipelines.sync_pipeline(pipeline_id=self.pipeline.id)
+
             upserted_document = upserted_documents[0]
             self.wait_for_completion(
                 doc_ids=[upserted_document.id], verbose=verbose, raise_on_error=True
@@ -804,6 +817,9 @@ class LlamaCloudIndex(BaseManagedIndex):
                     )
                 ],
             )
+            # Trigger a sync
+            await self._aclient.pipelines.sync_pipeline(pipeline_id=self.pipeline.id)
+
             upserted_document = upserted_documents[0]
             await self.await_for_completion(
                 doc_ids=[upserted_document.id], verbose=verbose, raise_on_error=True
@@ -827,6 +843,9 @@ class LlamaCloudIndex(BaseManagedIndex):
                     for doc in documents
                 ],
             )
+            # Trigger a sync
+            self._client.pipelines.sync_pipeline(pipeline_id=self.pipeline.id)
+
             doc_ids = [doc.id for doc in upserted_documents]
             self.wait_for_completion(doc_ids=doc_ids, verbose=True, raise_on_error=True)
             return [True] * len(doc_ids)
@@ -849,6 +868,9 @@ class LlamaCloudIndex(BaseManagedIndex):
                     for doc in documents
                 ],
             )
+            # Trigger a sync
+            await self._aclient.pipelines.sync_pipeline(pipeline_id=self.pipeline.id)
+
             doc_ids = [doc.id for doc in upserted_documents]
             await self.await_for_completion(
                 doc_ids=doc_ids, verbose=True, raise_on_error=True

py/llama_cloud_services/parse/base.py

@@ -285,7 +285,7 @@ class LlamaParse(BasePydanticReader):
         description="Note: Non compatible with gpt-4o. If set to true, the parser will use a faster mode to extract text from documents. This mode will skip OCR of images, and table/heading reconstruction.",
     )
 
-    guess_xlsx_sheet_names: Optional[bool] = Field(
+    guess_xlsx_sheet_name: Optional[bool] = Field(
         default=False,
         description="Whether to guess the sheet names of the xlsx file.",
     )
@@ -313,6 +313,10 @@ class LlamaParse(BasePydanticReader):
         default=False,
         description="If set to true, the parser will ignore document elements for layout detection and only rely on a vision model.",
     )
+    inline_images_in_markdown: Optional[bool] = Field(
+        default=False,
+        description="If set to true, the parser will inline images in the markdown output.",
+    )
     input_s3_region: Optional[str] = Field(
         default=None,
         description="The region of the input S3 bucket if input_s3_path is specified.",
@@ -329,6 +333,10 @@ class LlamaParse(BasePydanticReader):
         default=None,
         description="The maximum timeout in seconds to wait for the parsing to finish. Override default timeout of 30 minutes. Minimum is 120 seconds.",
     )
+    keep_page_separator_when_merging_tables: Optional[bool] = Field(
+        default=False,
+        description="If set to true, the parser will keep the page separator when merging tables across pages.",
+    )
     language: Optional[str] = Field(
         default="en", description="The language of the text to parse."
     )
@@ -400,6 +408,10 @@ class LlamaParse(BasePydanticReader):
         default=False,
         description="If set, the parser will try to preserve very small text lines. This can be useful for documents containing vector graphics with very small text lines that may not be recognized by OCR or a vision model (such as in CAD drawings).",
     )
+    presentation_out_of_bounds_content: Optional[bool] = Field(
+        default=False,
+        description="If set to true, the parser will include out-of-bounds content in presentation files.",
+    )
     precise_bounding_box: Optional[bool] = Field(
         default=False,
         description="If set to true, the parser will use a more precise bounding box to extract text from documents. This will increase the accuracy of the parsing job, but reduce the speed.",
@@ -416,6 +428,14 @@ class LlamaParse(BasePydanticReader):
         default=None,
         description="A suffix to add after error message in failed pages. If not set, no suffix will be used.",
     )
+    remove_hidden_text: Optional[bool] = Field(
+        default=False,
+        description="If set to true, the parser will remove hidden text from the document.",
+    )
+    save_images: Optional[bool] = Field(
+        default=True,
+        description="If set to true, the parser will save images extracted from the document.",
+    )
     skip_diagonal_text: Optional[bool] = Field(
         default=False,
         description="If set to true, the parser will ignore diagonal text (when the text rotation in degrees modulo 90 is not 0).",
@@ -440,6 +460,10 @@ class LlamaParse(BasePydanticReader):
         default=False,
         description="If set to true, the parser will use a specialized one-shot chart parsing model to extract data from charts. This model is able to understand the chart type and extract the data accordingly. It is more accurate than the efficient model, but also more expensive.",
     )
+    specialized_image_parsing: Optional[bool] = Field(
+        default=False,
+        description="If set to true, the parser will use a specialized image parsing model to extract data from images.",
+    )
     strict_mode_buggy_font: Optional[bool] = Field(
         default=False,
         description="If set to true, the parser will fail if it can't extract text from a document because of a buggy font.",
@@ -584,6 +608,23 @@ class LlamaParse(BasePydanticReader):
         description="Automatically check for Python SDK updates.",
     )
 
+    @model_validator(mode="before")
+    @classmethod
+    def handle_deprecated_params(cls, data: Dict[str, Any]) -> Dict[str, Any]:
+        # Handle deprecated guess_xlsx_sheet_names -> guess_xlsx_sheet_name
+        if "guess_xlsx_sheet_names" in data:
+            warnings.warn(
+                "The parameter 'guess_xlsx_sheet_names' is deprecated and will be removed in a future release. "
+                "Use 'guess_xlsx_sheet_name' instead.",
+                DeprecationWarning,
+                stacklevel=2,
+            )
+            # Only set the new parameter if it's not already explicitly set
+            if "guess_xlsx_sheet_name" not in data:
+                data["guess_xlsx_sheet_name"] = data["guess_xlsx_sheet_names"]
+            del data["guess_xlsx_sheet_names"]
+        return data
+
     @model_validator(mode="before")
     @classmethod
     def warn_extra_params(cls, data: Dict[str, Any]) -> Dict[str, Any]:
@@ -824,8 +865,8 @@ class LlamaParse(BasePydanticReader):
             )
             data["formatting_instruction"] = self.formatting_instruction
 
-        if self.guess_xlsx_sheet_names:
-            data["guess_xlsx_sheet_names"] = self.guess_xlsx_sheet_names
+        if self.guess_xlsx_sheet_name:
+            data["guess_xlsx_sheet_name"] = self.guess_xlsx_sheet_name
 
         if self.html_make_all_elements_visible:
             data["html_make_all_elements_visible"] = self.html_make_all_elements_visible
@@ -849,6 +890,9 @@ class LlamaParse(BasePydanticReader):
                 "ignore_document_elements_for_layout_detection"
             ] = self.ignore_document_elements_for_layout_detection
 
+        if self.inline_images_in_markdown:
+            data["inline_images_in_markdown"] = self.inline_images_in_markdown
+
         if input_url is not None:
             files = None
             data["input_url"] = str(input_url)
@@ -877,6 +921,11 @@ class LlamaParse(BasePydanticReader):
         if self.job_timeout_in_seconds is not None:
             data["job_timeout_in_seconds"] = self.job_timeout_in_seconds
 
+        if self.keep_page_separator_when_merging_tables:
+            data[
+                "keep_page_separator_when_merging_tables"
+            ] = self.keep_page_separator_when_merging_tables
+
         if self.language:
             data["language"] = self.language
 
@@ -955,6 +1004,11 @@ class LlamaParse(BasePydanticReader):
         if self.preserve_very_small_text:
             data["preserve_very_small_text"] = self.preserve_very_small_text
 
+        if self.presentation_out_of_bounds_content:
+            data[
+                "presentation_out_of_bounds_content"
+            ] = self.presentation_out_of_bounds_content
+
         if self.preset is not None:
             data["preset"] = self.preset
 
@@ -974,6 +1028,11 @@ class LlamaParse(BasePydanticReader):
                 "replace_failed_page_with_error_message_suffix"
             ] = self.replace_failed_page_with_error_message_suffix
 
+        if self.remove_hidden_text:
+            data["remove_hidden_text"] = self.remove_hidden_text
+
+        data["save_images"] = self.save_images
+
         if self.skip_diagonal_text:
             data["skip_diagonal_text"] = self.skip_diagonal_text
 
@@ -998,6 +1057,9 @@ class LlamaParse(BasePydanticReader):
         if self.specialized_chart_parsing_plus:
             data["specialized_chart_parsing_plus"] = self.specialized_chart_parsing_plus
 
+        if self.specialized_image_parsing:
+            data["specialized_image_parsing"] = self.specialized_image_parsing
+
         if self.strict_mode_buggy_font:
             data["strict_mode_buggy_font"] = self.strict_mode_buggy_font
 

py/llama_parse/pyproject.toml

@@ -11,7 +11,7 @@ dev = [
 
 [project]
 name = "llama-parse"
-version = "0.6.82"
+version = "0.6.83"
 description = "Parse files into RAG-Optimized formats."
 authors = [{name = "Logan Markewich", email = "logan@llamaindex.ai"}]
 requires-python = ">=3.9,<4.0"

py/pyproject.toml

@@ -7,6 +7,7 @@ dev = [
   "pytest>=8.0.0,<9",
   "pytest-xdist>=3.6.1,<4",
   "pytest-asyncio",
+  "pytest-timeout>=2.3.1",
   "ipykernel>=6.29.0,<7",
   "pre-commit==3.2.0",
   "autoevals>=0.0.114,<0.0.115",
@@ -22,7 +23,7 @@ dev = [
 
 [project]
 name = "llama-cloud-services"
-version = "0.6.82"
+version = "0.6.83"
 description = "Tailored SDK clients for LlamaCloud services."
 authors = [{name = "Logan Markewich", email = "logan@runllama.ai"}]
 requires-python = ">=3.9,<4.0"

py/tests/beta/sheets/test_sheets.py

@@ -10,16 +10,16 @@ from llama_cloud_services.beta.sheets.types import SpreadsheetParsingConfig
 @pytest.fixture
 def sheets_client():
     """Create a LlamaSheets client for testing."""
-    api_key = os.getenv(
-        "LLAMA_CLOUD_API_KEY", "llx-3AEorIw5v0lnJPzEOI9xSl0N8yFx3fguw0Zn8QJHzGWmwg5r"
-    )
-    base_url = os.getenv("LLAMA_CLOUD_BASE_URL", "https://api.staging.llamaindex.ai")
+    api_key = os.getenv("LLAMA_CLOUD_API_KEY")
+    base_url = os.getenv("LLAMA_CLOUD_BASE_URL", "https://api.cloud.llamaindex.ai")
+    project_id = os.getenv("LLAMA_CLOUD_PROJECT_ID")
 
     client = LlamaSheets(
         api_key=api_key,
         base_url=base_url,
         max_timeout=300,
         poll_interval=2,
+        project_id=project_id,
     )
     return client
 
@@ -51,10 +51,7 @@ def sample_excel_file():
 
 
 @pytest.mark.skipif(
-    os.environ.get(
-        "LLAMA_CLOUD_API_KEY", "llx-3AEorIw5v0lnJPzEOI9xSl0N8yFx3fguw0Zn8QJHzGWmwg5r"
-    )
-    == "",
+    os.environ.get("LLAMA_CLOUD_API_KEY", "") == "",
     reason="LLAMA_CLOUD_API_KEY not set",
 )
 @pytest.mark.asyncio
@@ -134,10 +131,7 @@ async def test_spreadsheet_extraction_e2e(
 
 
 @pytest.mark.skipif(
-    os.environ.get(
-        "LLAMA_CLOUD_API_KEY", "llx-3AEorIw5v0lnJPzEOI9xSl0N8yFx3fguw0Zn8QJHzGWmwg5r"
-    )
-    == "",
+    os.environ.get("LLAMA_CLOUD_API_KEY", "") == "",
     reason="LLAMA_CLOUD_API_KEY not set",
 )
 @pytest.mark.asyncio

py/tests/test_files_client.py

@@ -78,7 +78,7 @@ async def test_upload_bytes(
     uploaded_file = await file_client.upload_bytes(file_bytes, external_file_id)
 
     assert isinstance(uploaded_file, File)
-    expected_name = external_file_id if use_presigned_url else "upload"
+    expected_name = external_file_id
     assert uploaded_file.name == expected_name
     assert uploaded_file.external_file_id == external_file_id
 
@@ -100,7 +100,7 @@ async def test_upload_buffer(
     uploaded_file = await file_client.upload_buffer(buffer, external_file_id, file_size)
 
     assert isinstance(uploaded_file, File)
-    expected_name = external_file_id if use_presigned_url else "upload"
+    expected_name = external_file_id
     assert uploaded_file.name == expected_name
     assert uploaded_file.external_file_id == external_file_id