add language enum

README.md

@@ -37,7 +37,8 @@ parser = LlamaParse(
     api_key="llx-...",  # can also be set in your env as LLAMA_CLOUD_API_KEY
     result_type="markdown",  # "markdown" and "text" are available
     num_workers=4, # if multiple files passed, split in `num_workers` API calls
-    verbose=True
+    verbose=True,
+    language="en" # Optionaly you can define a language, default=en
 )
 
 # sync

llama_parse/base.py

@@ -22,6 +22,91 @@ class ResultType(str, Enum):
     TXT = "text"
     MD = "markdown"
 
+class Language(str, Enum):
+    BAZA = "abq"
+    ADYGHE = "ady"
+    AFRIKAANS = "af"
+    ANGIKA = "ang"
+    ARABIC = "ar"
+    ASSAMESE = "as"
+    AVAR = "ava"
+    AZERBAIJANI = "az"
+    BELARUSIAN = "be"
+    BULGARIAN = "bg"
+    BIHARI = "bh"
+    BHOJPURI = "bho"
+    BENGALI = "bn"
+    BOSNIAN = "bs"
+    SIMPLIFIED_CHINESE = "ch_sim"
+    TRADITIONAL_CHINESE = "ch_tra"
+    CHECHEN = "che"
+    CZECH = "cs"
+    WELSH = "cy"
+    DANISH = "da"
+    DARGWA = "dar"
+    GERMAN = "de"
+    ENGLISH = "en"
+    SPANISH = "es"
+    ESTONIAN = "et"
+    PERSIAN_FARSI = "fa"
+    FRENCH = "fr"
+    IRISH = "ga"
+    GOAN_KONKANI = "gom"
+    HINDI = "hi"
+    CROATIAN = "hr"
+    HUNGARIAN = "hu"
+    INDONESIAN = "id"
+    INGUSH = "inh"
+    ICELANDIC = "is"
+    ITALIAN = "it"
+    JAPANESE = "ja"
+    KABARDIAN = "kbd"
+    KANNADA = "kn"
+    KOREAN = "ko"
+    KURDISH = "ku"
+    LATIN = "la"
+    LAK = "lbe"
+    LEZGHIAN = "lez"
+    LITHUANIAN = "lt"
+    LATVIAN = "lv"
+    MAGAHI = "mah"
+    MAITHILI = "mai"
+    MAORI = "mi"
+    MONGOLIAN = "mn"
+    MARATHI = "mr"
+    MALAY = "ms"
+    MALTESE = "mt"
+    NEPALI = "ne"
+    NEWARI = "new"
+    DUTCH = "nl"
+    NORWEGIAN = "no"
+    OCCITAN = "oc"
+    PALI = "pi"
+    POLISH = "pl"
+    PORTUGUESE = "pt"
+    ROMANIAN = "ro"
+    RUSSIAN = "ru"
+    SERBIAN_CYRILLIC = "rs_cyrillic"
+    SERBIAN_LATIN = "rs_latin"
+    NAGPURI = "sck"
+    SLOVAK = "sk"
+    SLOVENIAN = "sl"
+    ALBANIAN = "sq"
+    SWEDISH = "sv"
+    SWAHILI = "sw"
+    TAMIL = "ta"
+    TABASSARAN = "tab"
+    TELUGU = "te"
+    THAI = "th"
+    TAJIK = "tjk"
+    TAGALOG = "tl"
+    TURKISH = "tr"
+    UYGHUR = "ug"
+    UKRANIAN = "uk"
+    URDU = "ur"
+    UZBEK = "uz"
+    VIETNAMESE = "vi"
+
 
 class LlamaParse(BasePydanticReader):
     """A smart-parser for files."""
@@ -51,6 +136,9 @@ class LlamaParse(BasePydanticReader):
     verbose: bool = Field(
         default=True, description="Whether to print the progress of the parsing."
     )
+    language: Optional[str] = Field(
+         default=Language.ENGLISH, description="The language of the text to parse."
+    )
 
     @validator("api_key", pre=True, always=True)
     def validate_api_key(cls, v: str) -> str:
@@ -90,7 +178,7 @@ class LlamaParse(BasePydanticReader):
                 # send the request, start job
                 url = f"{self.base_url}/api/parsing/upload"
                 async with httpx.AsyncClient(timeout=self.max_timeout) as client:
-                    response = await client.post(url, files=files, headers=headers)
+                    response = await client.post(url, files=files, headers=headers, data={"language": self.language})
                     if not response.is_success:
                         raise Exception(f"Failed to parse the PDF file: {response.text}")