lint

llama_cloud_services/extract/extract.py

@@ -57,6 +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
@@ -66,6 +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
@@ -78,14 +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())
@@ -436,6 +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()
@@ -451,6 +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:
@@ -468,11 +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)
@@ -501,17 +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())
@@ -614,6 +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_cloud_services/parse/base.py

@@ -276,7 +276,7 @@ class LlamaParse(BasePydanticReader):
         default=None,
         description="A templated suffix to add to the beginning of each page. If it contain `{page_number}`, it will be replaced by the page number.",
     )
-    parsing_mode: Optional[str] = Field(
+    parse_mode: Optional[str] = Field(
         default=None,
         description="The parsing mode to use, see ParsingMode enum for possible values ",
     )
@@ -284,6 +284,10 @@ class LlamaParse(BasePydanticReader):
         default=False,
         description="Use our best parser mode if set to True.",
     )
+    preserve_layout_alignment_across_pages: Optional[bool] = Field(
+        default=False,
+        description="Preserve grid alignment across page in text mode.",
+    )
     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).",
@@ -706,9 +710,17 @@ class LlamaParse(BasePydanticReader):
             )
             data["parsing_instruction"] = self.parsing_instruction
 
+        if self.parse_mode:
+            data["parse_mode"] = self.parse_mode
+
         if self.premium_mode:
             data["premium_mode"] = self.premium_mode
 
+        if self.preserve_layout_alignment_across_pages:
+            data[
+                "preserve_layout_alignment_across_pages"
+            ] = self.preserve_layout_alignment_across_pages
+
         if self.skip_diagonal_text:
             data["skip_diagonal_text"] = self.skip_diagonal_text
 

llama_parse/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
 name = "llama-parse"
-version = "0.6.6"
+version = "0.6.8"
 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"

poetry.lock

@@ -1209,13 +1209,13 @@ type = ["pytest-mypy"]
 
 [[package]]
 name = "iniconfig"
-version = "2.0.0"
+version = "2.1.0"
 description = "brain-dead simple config-ini parsing"
 optional = false
-python-versions = ">=3.7"
+python-versions = ">=3.8"
 files = [
-    {file = "iniconfig-2.0.0-py3-none-any.whl", hash = "sha256:b6a85871a79d2e3b22d2d1b94ac2824226a63c6b741c88f7ae975f18b6778374"},
-    {file = "iniconfig-2.0.0.tar.gz", hash = "sha256:2d91e135bf72d31a410b17c16da610a82cb55f6b0477d1a902134b24a455b8b3"},
+    {file = "iniconfig-2.1.0-py3-none-any.whl", hash = "sha256:9deba5723312380e77435581c6bf4935c94cbfab9b1ed33ef8d238ea168eb760"},
+    {file = "iniconfig-2.1.0.tar.gz", hash = "sha256:3abbd2e30b36733fee78f9c7f7308f2d0050e88f0087fd25c2645f63c773e1c7"},
 ]
 
 [[package]]
@@ -1811,13 +1811,13 @@ rapidfuzz = ">=3.9.0,<4.0.0"
 
 [[package]]
 name = "llama-cloud"
-version = "0.1.15"
+version = "0.1.16"
 description = ""
 optional = false
 python-versions = "<4,>=3.8"
 files = [
-    {file = "llama_cloud-0.1.15-py3-none-any.whl", hash = "sha256:8e7376346d580b244a87d023eb7493506f06b53c898fb2a2e712b9fe7eb5b310"},
-    {file = "llama_cloud-0.1.15.tar.gz", hash = "sha256:3ec98422072ee4290c1e7597bc33889af3f03edb2a50ab09c15d5586d9f8635c"},
+    {file = "llama_cloud-0.1.16-py3-none-any.whl", hash = "sha256:a484cf762d2741282f96033c0c09f6c8ad1b93b4efb7520088647fd845d341d4"},
+    {file = "llama_cloud-0.1.16.tar.gz", hash = "sha256:fc68b24471907958d4862a3db1e973513de76d42f58c29d935b92c06cb1f4e3e"},
 ]
 
 [package.dependencies]
@@ -1966,13 +1966,13 @@ traitlets = "*"
 
 [[package]]
 name = "mistune"
-version = "3.1.2"
+version = "3.1.3"
 description = "A sane and fast Markdown parser with useful plugins and renderers"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "mistune-3.1.2-py3-none-any.whl", hash = "sha256:4b47731332315cdca99e0ded46fc0004001c1299ff773dfb48fbe1fd226de319"},
-    {file = "mistune-3.1.2.tar.gz", hash = "sha256:733bf018ba007e8b5f2d3a9eb624034f6ee26c4ea769a98ec533ee111d504dff"},
+    {file = "mistune-3.1.3-py3-none-any.whl", hash = "sha256:1a32314113cff28aa6432e99e522677c8587fd83e3d51c29b82a52409c842bd9"},
+    {file = "mistune-3.1.3.tar.gz", hash = "sha256:a7035c21782b2becb6be62f8f25d3df81ccb4d6fa477a6525b15af06539f02a0"},
 ]
 
 [package.dependencies]
@@ -2548,19 +2548,19 @@ xmp = ["defusedxml"]
 
 [[package]]
 name = "platformdirs"
-version = "4.3.6"
+version = "4.3.7"
 description = "A small Python package for determining appropriate platform-specific dirs, e.g. a `user data dir`."
 optional = false
-python-versions = ">=3.8"
+python-versions = ">=3.9"
 files = [
-    {file = "platformdirs-4.3.6-py3-none-any.whl", hash = "sha256:73e575e1408ab8103900836b97580d5307456908a03e92031bab39e4554cc3fb"},
-    {file = "platformdirs-4.3.6.tar.gz", hash = "sha256:357fb2acbc885b0419afd3ce3ed34564c13c9b95c89360cd9563f73aa5e2b907"},
+    {file = "platformdirs-4.3.7-py3-none-any.whl", hash = "sha256:a03875334331946f13c549dbd8f4bac7a13a50a895a0eb1e8c6a8ace80d40a94"},
+    {file = "platformdirs-4.3.7.tar.gz", hash = "sha256:eb437d586b6a0986388f0d6f74aa0cde27b48d0e3d66843640bfb6bdcdb6e351"},
 ]
 
 [package.extras]
-docs = ["furo (>=2024.8.6)", "proselint (>=0.14)", "sphinx (>=8.0.2)", "sphinx-autodoc-typehints (>=2.4)"]
-test = ["appdirs (==1.4.4)", "covdefaults (>=2.3)", "pytest (>=8.3.2)", "pytest-cov (>=5)", "pytest-mock (>=3.14)"]
-type = ["mypy (>=1.11.2)"]
+docs = ["furo (>=2024.8.6)", "proselint (>=0.14)", "sphinx (>=8.1.3)", "sphinx-autodoc-typehints (>=3)"]
+test = ["appdirs (==1.4.4)", "covdefaults (>=2.3)", "pytest (>=8.3.4)", "pytest-cov (>=6)", "pytest-mock (>=3.14)"]
+type = ["mypy (>=1.14.1)"]
 
 [[package]]
 name = "pluggy"
@@ -3629,18 +3629,18 @@ win32 = ["pywin32"]
 
 [[package]]
 name = "setuptools"
-version = "76.1.0"
+version = "77.0.3"
 description = "Easily download, build, install, upgrade, and uninstall Python packages"
 optional = false
 python-versions = ">=3.9"
 files = [
-    {file = "setuptools-76.1.0-py3-none-any.whl", hash = "sha256:34750dcb17d046929f545dec9b8349fe42bf4ba13ddffee78428aec422dbfb73"},
-    {file = "setuptools-76.1.0.tar.gz", hash = "sha256:4959b9ad482ada2ba2320c8f1a8d8481d4d8d668908a7a1b84d987375cd7f5bd"},
+    {file = "setuptools-77.0.3-py3-none-any.whl", hash = "sha256:67122e78221da5cf550ddd04cf8742c8fe12094483749a792d56cd669d6cf58c"},
+    {file = "setuptools-77.0.3.tar.gz", hash = "sha256:583b361c8da8de57403743e756609670de6fb2345920e36dc5c2d914c319c945"},
 ]
 
 [package.extras]
 check = ["pytest-checkdocs (>=2.4)", "pytest-ruff (>=0.2.1)", "ruff (>=0.8.0)"]
-core = ["importlib_metadata (>=6)", "jaraco.collections", "jaraco.functools (>=4)", "jaraco.text (>=3.7)", "more_itertools", "more_itertools (>=8.8)", "packaging", "packaging (>=24.2)", "platformdirs (>=4.2.2)", "tomli (>=2.0.1)", "wheel (>=0.43.0)"]
+core = ["importlib_metadata (>=6)", "jaraco.functools (>=4)", "jaraco.text (>=3.7)", "more_itertools", "more_itertools (>=8.8)", "packaging (>=24.2)", "platformdirs (>=4.2.2)", "tomli (>=2.0.1)", "wheel (>=0.43.0)"]
 cover = ["pytest-cov"]
 doc = ["furo", "jaraco.packaging (>=9.3)", "jaraco.tidelift (>=1.4)", "pygments-github-lexers (==0.0.5)", "pyproject-hooks (!=1.1)", "rst.linker (>=1.9)", "sphinx (>=3.5)", "sphinx-favicon", "sphinx-inline-tabs", "sphinx-lint", "sphinx-notfound-page (>=1,<2)", "sphinx-reredirects", "sphinxcontrib-towncrier", "towncrier (<24.7)"]
 enabler = ["pytest-enabler (>=2.2)"]
@@ -4346,4 +4346,4 @@ type = ["pytest-mypy"]
 [metadata]
 lock-version = "2.0"
 python-versions = ">=3.9,<4.0"
-content-hash = "6f0f71e1580c43973c0beac25285de971cc90f0ebf0bbfb585cb95f9d56a799e"
+content-hash = "01117e9c1d468a1ba673c3559578543abc4f2a698e422cae49eab5313d2b492b"

pyproject.toml

@@ -8,7 +8,7 @@ python_version = "3.10"
 
 [tool.poetry]
 name = "llama-cloud-services"
-version = "0.6.6"
+version = "0.6.8"
 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 = "^0.1.15"
+llama-cloud = "^0.1.16"
 pydantic = "!=2.10"
 click = "^8.1.7"
 python-dotenv = "^1.0.1"