Add spreadsheet extensions (#203)

* Add spreadsheet extensions

* linting

* fix tests

---------

Co-authored-by: Logan Markewich <logan.markewich@live.com>

.pre-commit-config.yaml

@@ -72,7 +72,7 @@ repos:
         args:
           [
             "--ignore-words-list",
-            "astroid,gallary,momento,narl,ot,rouge,nin,gere,te,inh",
+            "astroid,gallary,momento,narl,ot,rouge,nin,gere,te,inh,vor",
           ]
   - repo: https://github.com/srstevenson/nb-clean
     rev: 3.1.0

llama_parse/base.py

@@ -57,6 +57,14 @@ class LlamaParse(BasePydanticReader):
     parsing_instruction: Optional[str] = Field(
         default="", description="The parsing instruction for the parser."
     )
+    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).",
+    )
+    invalidate_cache: Optional[bool] = Field(
+        default=False,
+        description="If set to true, the cache will be ignored and the document re-processes. All document are kept in cache for 48hours after the job was completed to avoid processing 2 time the same document.",
+    )
     gpt4o_mode: bool = Field(
         default=False,
         description="Whether to use gpt-4o extract text from documents.",
@@ -121,6 +129,8 @@ class LlamaParse(BasePydanticReader):
                     data={
                         "language": self.language.value,
                         "parsing_instruction": self.parsing_instruction,
+                        "invalidate_cache": self.invalidate_cache,
+                        "skip_diagonal_text": self.skip_diagonal_text,
                         "gpt4o_mode": self.gpt4o_mode,
                         "gpt4o_api_key": self.gpt4o_api_key,
                     },
@@ -341,7 +351,8 @@ class LlamaParse(BasePydanticReader):
 
                         # get a valid image path
                         if not image_path.endswith(".png"):
-                            image_path += ".png"
+                            if not image_path.endswith(".jpg"):
+                                image_path += ".png"
 
                         image["path"] = image_path
                         image["job_id"] = job_id

llama_parse/utils.py

@@ -101,52 +101,93 @@ class Language(str, Enum):
 
 SUPPORTED_FILE_TYPES = [
     ".pdf",
-    # Microsoft word - all versions
+    # document and presentations
+    ".602",
+    ".abw",
+    ".cgm",
+    ".cwk",
     ".doc",
     ".docx",
     ".docm",
     ".dot",
-    ".dotx",
     ".dotm",
-    # Rich text format
+    ".hwp",
+    ".key",
+    ".lwp",
+    ".mw",
+    ".mcw",
+    ".pages",
+    ".pbd",
+    ".ppt",
+    ".pptm",
+    ".pptx",
+    ".pot",
+    ".potm",
+    ".potx",
     ".rtf",
-    # Microsoft Works
-    ".wps",
-    # Word Perfect
-    ".wpd",
-    # Open Office
+    ".sda",
+    ".sdd",
+    ".sdp",
+    ".sdw",
+    ".sgl",
+    ".sti",
+    ".sxi",
     ".sxw",
     ".stw",
     ".sxg",
-    # Apple
-    ".pages",
-    # Mac Write
-    ".mw",
-    ".mcw",
-    # Unified Office Format text
-    ".uot",
+    ".txt",
     ".uof",
-    ".uos",
     ".uop",
-    # Microsoft powerpoints
-    ".ppt",
-    ".pptx",
-    ".pot",
-    ".pptm",
-    ".potx",
-    ".potm",
-    # Apple keynote
-    ".key",
-    # Open Office Presentations
-    ".odp",
-    ".odg",
-    ".otp",
-    ".fopd",
-    ".sxi",
-    ".sti",
-    # ebook
+    ".uot",
+    ".vor",
+    ".wpd",
+    ".wps",
+    ".xml",
+    ".zabw",
     ".epub",
-    # html
-    ".html",
+    # images
+    ".jpg",
+    ".jpeg",
+    ".png",
+    ".gif",
+    ".bmp",
+    ".svg",
+    ".tiff",
+    ".webp",
+    # web
     ".htm",
+    ".html",
+    # spreadsheets
+    ".xlsx",
+    ".xls",
+    ".xlsm",
+    ".xlsb",
+    ".xlw",
+    ".csv",
+    ".dif",
+    ".sylk",
+    ".slk",
+    ".prn",
+    ".numbers",
+    ".et",
+    ".ods",
+    ".fods",
+    ".uos1",
+    ".uos2",
+    ".dbf",
+    ".wk1",
+    ".wk2",
+    ".wk3",
+    ".wk4",
+    ".wks",
+    ".123",
+    ".wq1",
+    ".wq2",
+    ".wb1",
+    ".wb2",
+    ".wb3",
+    ".qpw",
+    ".xlr",
+    ".eth",
+    ".tsv",
 ]

poetry.lock

@@ -1,4 +1,4 @@
-# This file is automatically @generated by Poetry 1.6.1 and should not be changed by hand.
+# This file is automatically @generated by Poetry 1.8.2 and should not be changed by hand.
 
 [[package]]
 name = "aiohttp"
@@ -1354,8 +1354,8 @@ files = [
 [package.dependencies]
 numpy = [
     {version = ">=1.20.3", markers = "python_version < \"3.10\""},
-    {version = ">=1.21.0", markers = "python_version >= \"3.10\" and python_version < \"3.11\""},
     {version = ">=1.23.2", markers = "python_version >= \"3.11\""},
+    {version = ">=1.21.0", markers = "python_version >= \"3.10\" and python_version < \"3.11\""},
 ]
 python-dateutil = ">=2.8.2"
 pytz = ">=2020.1"
@@ -1838,6 +1838,7 @@ files = [
     {file = "PyYAML-6.0.1-cp311-cp311-win_amd64.whl", hash = "sha256:bf07ee2fef7014951eeb99f56f39c9bb4af143d8aa3c21b1677805985307da34"},
     {file = "PyYAML-6.0.1-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:855fb52b0dc35af121542a76b9a84f8d1cd886ea97c84703eaa6d88e37a2ad28"},
     {file = "PyYAML-6.0.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:40df9b996c2b73138957fe23a16a4f0ba614f4c0efce1e9406a184b6d07fa3a9"},
+    {file = "PyYAML-6.0.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a08c6f0fe150303c1c6b71ebcd7213c2858041a7e01975da3a99aed1e7a378ef"},
     {file = "PyYAML-6.0.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6c22bec3fbe2524cde73d7ada88f6566758a8f7227bfbf93a408a9d86bcc12a0"},
     {file = "PyYAML-6.0.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:8d4e9c88387b0f5c7d5f281e55304de64cf7f9c0021a3525bd3b1c542da3b0e4"},
     {file = "PyYAML-6.0.1-cp312-cp312-win32.whl", hash = "sha256:d483d2cdf104e7c9fa60c544d92981f12ad66a457afae824d146093b8c294c54"},
@@ -2081,13 +2082,13 @@ files = [
 
 [[package]]
 name = "requests"
-version = "2.31.0"
+version = "2.32.2"
 description = "Python HTTP for Humans."
 optional = false
-python-versions = ">=3.7"
+python-versions = ">=3.8"
 files = [
-    {file = "requests-2.31.0-py3-none-any.whl", hash = "sha256:58cd2187c01e70e6e26505bca751777aa9f2ee0b7f4300988b709f44e013003f"},
-    {file = "requests-2.31.0.tar.gz", hash = "sha256:942c5a758f98d790eaed1a29cb6eefc7ffb0d1cf7af05c3d2791656dbd6ad1e1"},
+    {file = "requests-2.32.2-py3-none-any.whl", hash = "sha256:fc06670dd0ed212426dfeb94fc1b983d917c4f9847c863f313c9dfaaffb7c23c"},
+    {file = "requests-2.32.2.tar.gz", hash = "sha256:dd951ff5ecf3e3b3aa26b40703ba77495dab41da839ae72ef3c8e5d8e2433289"},
 ]
 
 [package.dependencies]
@@ -2327,13 +2328,13 @@ files = [
 
 [[package]]
 name = "tqdm"
-version = "4.66.2"
+version = "4.66.3"
 description = "Fast, Extensible Progress Meter"
 optional = false
 python-versions = ">=3.7"
 files = [
-    {file = "tqdm-4.66.2-py3-none-any.whl", hash = "sha256:1ee4f8a893eb9bef51c6e35730cebf234d5d0b6bd112b0271e10ed7c24a02bd9"},
-    {file = "tqdm-4.66.2.tar.gz", hash = "sha256:6cd52cdf0fef0e0f543299cfc96fec90d7b8a7e88745f411ec33eb44d5ed3531"},
+    {file = "tqdm-4.66.3-py3-none-any.whl", hash = "sha256:4f41d54107ff9a223dca80b53efe4fb654c67efaba7f47bada3ee9d50e05bd53"},
+    {file = "tqdm-4.66.3.tar.gz", hash = "sha256:23097a41eba115ba99ecae40d06444c15d1c0c698d527a01c6c8bd1c5d0647e5"},
 ]
 
 [package.dependencies]

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
 name = "llama-parse"
-version = "0.4.3"
+version = "0.4.4"
 description = "Parse files into RAG-Optimized formats."
 authors = ["Logan Markewich <logan@llamaindex.ai>"]
 license = "MIT"