Bump to version 0.6.7 (#656)

llama_cloud_services/extract/extract.py

@@ -22,6 +22,7 @@ from llama_cloud import (
     Project,
     ExtractTarget,
     LlamaExtractSettings,
+    PaginatedExtractRunsResponse,
 )
 from llama_cloud.client import AsyncLlamaCloud
 from llama_cloud_services.extract.utils import JSONObjectType, augment_async_errors
@@ -56,6 +57,8 @@ class ExtractionAgent:
         num_workers: int = 4,
         show_progress: bool = True,
         verbose: bool = False,
+        verify: Optional[bool] = True,
+        httpx_timeout: Optional[float] = 60,
     ):
         self._client = client
         self._agent = agent
@@ -65,6 +68,8 @@ class ExtractionAgent:
         self.max_timeout = max_timeout
         self.num_workers = num_workers
         self.show_progress = show_progress
+        self.verify = verify
+        self.httpx_timeout = httpx_timeout
         self._verbose = verbose
         self._data_schema: Union[JSONObjectType, None] = None
         self._config: Union[ExtractConfig, None] = None
@@ -77,14 +82,20 @@ class ExtractionAgent:
 
         def run_coro() -> T:
             async def wrapped_coro() -> T:
+                # Get the original client to preserve its configuration
+                original_client = self._client._client_wrapper.httpx_client
+
+                # Create a new client with the same configuration as the original
                 async with httpx.AsyncClient(
-                    timeout=self._client._client_wrapper.httpx_client.timeout,
+                    verify=self.verify,
+                    timeout=self.httpx_timeout,
                 ) as client:
-                    original_client = self._client._client_wrapper.httpx_client
+                    # Temporarily replace the client
                     self._client._client_wrapper.httpx_client = client
                     try:
                         return await coro
                     finally:
+                        # Restore the original client
                         self._client._client_wrapper.httpx_client = original_client
 
             return asyncio.run(wrapped_coro())
@@ -380,15 +391,29 @@ class ExtractionAgent:
             )
         )
 
-    def list_extraction_runs(self) -> List[ExtractRun]:
+    def delete_extraction_run(self, run_id: str) -> None:
+        """Delete an extraction run by ID.
+
+        Args:
+            run_id (str): The ID of the extraction run to delete
+        """
+        self._run_in_thread(
+            self._client.llama_extract.delete_extraction_run(run_id=run_id)
+        )
+
+    def list_extraction_runs(
+        self, page: int = 0, limit: int = 100
+    ) -> PaginatedExtractRunsResponse:
         """List extraction runs for the extraction agent.
 
         Returns:
-            List[ExtractRun]: List of extraction runs
+            PaginatedExtractRunsResponse: Paginated list of extraction runs
         """
         return self._run_in_thread(
             self._client.llama_extract.list_extract_runs(
                 extraction_agent_id=self.id,
+                skip=page * limit,
+                limit=limit,
             )
         )
 
@@ -421,6 +446,12 @@ class LlamaExtract(BaseComponent):
     verbose: bool = Field(
         default=False, description="Show verbose output when extracting files."
     )
+    verify: Optional[bool] = Field(
+        default=True, description="Simple SSL verification option."
+    )
+    httpx_timeout: Optional[float] = Field(
+        default=60, description="Timeout for the httpx client."
+    )
     _async_client: AsyncLlamaCloud = PrivateAttr()
     _thread_pool: ThreadPoolExecutor = PrivateAttr()
     _project_id: Optional[str] = PrivateAttr()
@@ -436,6 +467,8 @@ class LlamaExtract(BaseComponent):
         show_progress: bool = True,
         project_id: Optional[str] = None,
         organization_id: Optional[str] = None,
+        verify: Optional[bool] = True,
+        httpx_timeout: Optional[float] = 60,
         verbose: bool = False,
     ):
         if not api_key:
@@ -453,11 +486,18 @@ class LlamaExtract(BaseComponent):
             max_timeout=max_timeout,
             num_workers=num_workers,
             show_progress=show_progress,
+            verify=verify,
+            httpx_timeout=httpx_timeout,
             verbose=verbose,
         )
+        self._httpx_client = httpx.AsyncClient(verify=verify, timeout=httpx_timeout)
+        self.verify = verify
+        self.httpx_timeout = httpx_timeout
 
         self._async_client = AsyncLlamaCloud(
-            token=self.api_key, base_url=self.base_url, timeout=None
+            token=self.api_key,
+            base_url=self.base_url,
+            httpx_client=self._httpx_client,
         )
         self._thread_pool = ThreadPoolExecutor(
             max_workers=min(10, (os.cpu_count() or 1) + 4)
@@ -486,17 +526,22 @@ class LlamaExtract(BaseComponent):
         def run_coro() -> T:
             # Create a new client for this thread
             async def wrapped_coro() -> T:
+                assert (
+                    self._httpx_client is not None
+                ), "httpx_client should be initialized"
+                # Create a new client with the same configuration as the original
                 async with httpx.AsyncClient(
-                    timeout=self._async_client._client_wrapper.httpx_client.timeout,
+                    verify=self.verify,
+                    timeout=self.httpx_timeout,
                 ) as client:
-                    # Replace the client in the coro's context
-                    original_client = self._async_client._client_wrapper.httpx_client
+                    # Temporarily replace the client
                     self._async_client._client_wrapper.httpx_client = client
                     try:
                         return await coro
                     finally:
+                        # Restore the original client
                         self._async_client._client_wrapper.httpx_client = (
-                            original_client
+                            self._httpx_client
                         )
 
             return asyncio.run(wrapped_coro())
@@ -599,6 +644,8 @@ class LlamaExtract(BaseComponent):
             num_workers=self.num_workers,
             show_progress=self.show_progress,
             verbose=self.verbose,
+            verify=self.verify,
+            httpx_timeout=self.httpx_timeout,
         )
 
     def list_agents(self) -> List[ExtractionAgent]:

llama_parse/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
 name = "llama-parse"
-version = "0.6.5"
+version = "0.6.7"
 description = "Parse files into RAG-Optimized formats."
 authors = ["Logan Markewich <logan@llamaindex.ai>"]
 license = "MIT"
@@ -13,7 +13,7 @@ packages = [{include = "llama_parse"}]
 
 [tool.poetry.dependencies]
 python = ">=3.9,<4.0"
-llama-cloud-services = ">=0.6.5"
+llama-cloud-services = ">=0.6.7"
 
 [tool.poetry.group.dev.dependencies]
 pytest = "^8.0.0"

pyproject.toml

@@ -8,7 +8,7 @@ python_version = "3.10"
 
 [tool.poetry]
 name = "llama-cloud-services"
-version = "0.6.5"
+version = "0.6.7"
 description = "Tailored SDK clients for LlamaCloud services."
 authors = ["Logan Markewich <logan@runllama.ai>"]
 license = "MIT"
@@ -18,7 +18,7 @@ packages = [{include = "llama_cloud_services"}]
 [tool.poetry.dependencies]
 python = ">=3.9,<4.0"
 llama-index-core = ">=0.11.0"
-llama-cloud = "^0.1.14"
+llama-cloud = "^0.1.16"
 pydantic = "!=2.10"
 click = "^8.1.7"
 python-dotenv = "^1.0.1"

tests/extract/test_extract_api.py

@@ -182,7 +182,14 @@ class TestExtractionAgent:
         assert "new_field" in updated_agent.data_schema["properties"]
 
     def test_list_extraction_runs(self, test_agent: ExtractionAgent):
-        assert len(test_agent.list_extraction_runs()) == 0
+        assert test_agent.list_extraction_runs().total == 0
         test_agent.extract(TEST_PDF)
         runs = test_agent.list_extraction_runs()
-        assert len(runs) > 0
+        assert runs.total > 0
+
+    def test_delete_extraction_run(self, test_agent: ExtractionAgent):
+        assert test_agent.list_extraction_runs().total == 0
+        run = test_agent.extract(TEST_PDF)
+        test_agent.delete_extraction_run(run.id)
+        runs = test_agent.list_extraction_runs()
+        assert runs.total == 0

tests/report/test_llama_report.py

@@ -81,6 +81,11 @@ async def test_create_and_delete_report(
 
 
 @pytest.mark.asyncio
+@pytest.mark.xfail(
+    condition=lambda: os.getenv("CI"),
+    reason="Report plan sometimes times out",
+    raises=TimeoutError,
+)
 async def test_report_plan_workflow(report: ReportClient) -> None:
     """Test the report planning workflow."""
     # Wait for the plan