"0.6.84

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

.github/workflows/test_e2e_py.yml

@@ -12,7 +12,6 @@ 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 --timeout=300 --session-timeout=1740 tests/
+	uv run pytest -v -n 32 tests/

py/llama_cloud_services/beta/sheets/client.py

@@ -2,7 +2,7 @@ import asyncio
 import io
 import os
 import time
-from typing import Any, Dict, TYPE_CHECKING
+from typing import TYPE_CHECKING
 
 import httpx
 from llama_cloud.client import AsyncLlamaCloud
@@ -68,8 +68,6 @@ 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.
@@ -80,8 +78,6 @@ 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")
@@ -97,32 +93,15 @@ 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:
@@ -327,8 +306,6 @@ 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),
@@ -341,7 +318,6 @@ 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()
@@ -371,17 +347,12 @@ 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=params,
+                        params={"include_results": include_results_metadata},
                     )
                     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
@@ -444,8 +415,6 @@ 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),
@@ -458,7 +427,6 @@ 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

@@ -654,9 +654,6 @@ 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
@@ -741,10 +738,6 @@ 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
@@ -767,9 +760,6 @@ 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
@@ -792,9 +782,6 @@ 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
@@ -817,9 +804,6 @@ 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
@@ -843,9 +827,6 @@ 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)
@@ -868,9 +849,6 @@ 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

@@ -740,11 +740,9 @@ class LlamaParse(BasePydanticReader):
             file_path = str(file_input)
             file_ext = os.path.splitext(file_path)[1].lower()
             if file_ext not in SUPPORTED_FILE_TYPES:
-                raise Exception(
-                    f"Currently, only the following file types are supported: {SUPPORTED_FILE_TYPES}\n"
-                    f"Current file type: {file_ext}"
-                )
-            mime_type = mimetypes.guess_type(file_path)[0]
+                mime_type = "application/octet-stream"
+            else:
+                mime_type = mimetypes.guess_type(file_path)[0]
             # Open the file here for the duration of the async context
             # load data, set the mime type
             fs = fs or get_default_fs()

py/pyproject.toml

@@ -7,7 +7,6 @@ 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",
@@ -23,7 +22,7 @@ dev = [
 
 [project]
 name = "llama-cloud-services"
-version = "0.6.83"
+version = "0.6.84"
 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")
-    base_url = os.getenv("LLAMA_CLOUD_BASE_URL", "https://api.cloud.llamaindex.ai")
-    project_id = os.getenv("LLAMA_CLOUD_PROJECT_ID")
+    api_key = os.getenv(
+        "LLAMA_CLOUD_API_KEY", "llx-3AEorIw5v0lnJPzEOI9xSl0N8yFx3fguw0Zn8QJHzGWmwg5r"
+    )
+    base_url = os.getenv("LLAMA_CLOUD_BASE_URL", "https://api.staging.llamaindex.ai")
 
     client = LlamaSheets(
         api_key=api_key,
         base_url=base_url,
         max_timeout=300,
         poll_interval=2,
-        project_id=project_id,
     )
     return client
 
@@ -51,7 +51,10 @@ def sample_excel_file():
 
 
 @pytest.mark.skipif(
-    os.environ.get("LLAMA_CLOUD_API_KEY", "") == "",
+    os.environ.get(
+        "LLAMA_CLOUD_API_KEY", "llx-3AEorIw5v0lnJPzEOI9xSl0N8yFx3fguw0Zn8QJHzGWmwg5r"
+    )
+    == "",
     reason="LLAMA_CLOUD_API_KEY not set",
 )
 @pytest.mark.asyncio
@@ -131,7 +134,10 @@ async def test_spreadsheet_extraction_e2e(
 
 
 @pytest.mark.skipif(
-    os.environ.get("LLAMA_CLOUD_API_KEY", "") == "",
+    os.environ.get(
+        "LLAMA_CLOUD_API_KEY", "llx-3AEorIw5v0lnJPzEOI9xSl0N8yFx3fguw0Zn8QJHzGWmwg5r"
+    )
+    == "",
     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
+    expected_name = external_file_id if use_presigned_url else "upload"
     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
+    expected_name = external_file_id if use_presigned_url else "upload"
     assert uploaded_file.name == expected_name
     assert uploaded_file.external_file_id == external_file_id