Merge branch 'main' into fastMode

.pre-commit-config.yaml

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

llama_parse/base.py

@@ -73,6 +73,10 @@ class LlamaParse(BasePydanticReader):
         default=None,
         description="The API key for the GPT-4o API. Lowers the cost of parsing.",
     )
+    fast_mode: bool = Field(
+        default=False,
+        description="Super fast mode for parsing. Only output Text, do not extract tables, images, etc.",
+    )
     ignore_errors: bool = Field(
         default=True,
         description="Whether or not to ignore and skip errors raised during parsing.",
@@ -129,6 +133,7 @@ class LlamaParse(BasePydanticReader):
                     data={
                         "language": self.language.value,
                         "parsing_instruction": self.parsing_instruction,
+                        "fast_mode": self.fast_mode,
                         "invalidate_cache": self.invalidate_cache,
                         "skip_diagonal_text": self.skip_diagonal_text,
                         "gpt4o_mode": self.gpt4o_mode,

llama_parse/utils.py

@@ -101,93 +101,59 @@ class Language(str, Enum):
 
 SUPPORTED_FILE_TYPES = [
     ".pdf",
-    # document and presentations
-    ".602",
-    ".abw",
-    ".cgm",
-    ".cwk",
+    # Microsoft word - all versions
     ".doc",
     ".docx",
     ".docm",
     ".dot",
+    ".dotx",
     ".dotm",
-    ".hwp",
-    ".key",
-    ".lwp",
-    ".mw",
-    ".mcw",
-    ".pages",
-    ".pbd",
-    ".ppt",
-    ".pptm",
-    ".pptx",
-    ".pot",
-    ".potm",
-    ".potx",
+    # Rich text format
     ".rtf",
-    ".sda",
-    ".sdd",
-    ".sdp",
-    ".sdw",
-    ".sgl",
-    ".sti",
-    ".sxi",
+    # Microsoft Works
+    ".wps",
+    # Word Perfect
+    ".wpd",
+    # Open Office
     ".sxw",
     ".stw",
     ".sxg",
-    ".txt",
-    ".uof",
-    ".uop",
+    # Apple
+    ".pages",
+    # Mac Write
+    ".mw",
+    ".mcw",
+    # Unified Office Format text
     ".uot",
-    ".vor",
-    ".wpd",
-    ".wps",
-    ".xml",
-    ".zabw",
+    ".uof",
+    ".uos",
+    ".uop",
+    # Microsoft powerpoints
+    ".ppt",
+    ".pptx",
+    ".pot",
+    ".pptm",
+    ".potx",
+    ".potm",
+    # Apple keynote
+    ".key",
+    # Open Office Presentations
+    ".odp",
+    ".odg",
+    ".otp",
+    ".fopd",
+    ".sxi",
+    ".sti",
+    # ebook
     ".epub",
-    # images
+    # html
+    ".html",
+    ".htm",
+    # media,
     ".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",
+    ".gif",
+    ".svg",
 ]