lint remove trailing space

lint
add option to API call
2026-07-21 03:55:22 -04:00 · 2024-06-07 11:25:56 +08:00 · 2024-06-07 10:59:47 +08:00 · 2024-06-07 10:45:36 +08:00 · 2024-06-07 10:42:39 +08:00 · 2024-06-07 10:40:30 +08:00
1 changed files with 20 additions and 0 deletions
@@ -65,6 +65,22 @@ class LlamaParse(BasePydanticReader):
        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.",
    )
+    do_not_cache: Optional[bool] = Field(
+        default=False,
+        description="If set to true, the document will not be cached. This mean that you will be re-charged it you reprocess them as they will not be cached.",
+    )
+    fast_mode: Optional[bool] = Field(
+        default=False,
+        description="Note: Non compatible with gpt-4o. If set to true, the parser will use a faster mode to extract text from documents. This mode will skip OCR of images, and table/heading reconstruction.",
+    )
+    do_not_unroll_columns: Optional[bool] = Field(
+        default=False,
+        description="If set to true, the parser will keep column in the text according to document layout. Reduce reconstruction accuracy, and LLM's/embedings performances in most case.",
+    )
+    page_separator: Optional[str] = Field(
+        default=None,
+        description="The page separator to use to split the text. Default is None, which means the parser will use the default separator '\\n---\\n'.",
+    )
    gpt4o_mode: bool = Field(
        default=False,
        description="Whether to use gpt-4o extract text from documents.",
@@ -131,6 +147,10 @@ class LlamaParse(BasePydanticReader):
                        "parsing_instruction": self.parsing_instruction,
                        "invalidate_cache": self.invalidate_cache,
                        "skip_diagonal_text": self.skip_diagonal_text,
+                        "do_not_cache": self.do_not_cache,
+                        "fast_mode": self.fast_mode,
+                        "do_not_unroll_columns": self.do_not_unroll_columns,
+                        "page_separator": self.page_separator,
                        "gpt4o_mode": self.gpt4o_mode,
                        "gpt4o_api_key": self.gpt4o_api_key,
                    },
Author	SHA1	Message	Date
Pierre-Loic Doulcet	106d4591aa	lint remove trailing space	2024-06-07 11:25:56 +08:00
Pierre-Loic Doulcet	50eb0901a3	lint	2024-06-07 10:59:47 +08:00
Pierre-Loic Doulcet	f78f6f1bca	add option to API call	2024-06-07 10:45:36 +08:00
Pierre-Loic Doulcet	5af1fb6687	merge fix	2024-06-07 10:42:39 +08:00
Pierre-Loic Doulcet	91d8bc92b0	Add new parameters to the parser	2024-06-07 10:40:30 +08:00
Logan Markewich	790a470136	fix tests	2024-05-29 18:14:00 -06:00
Logan Markewich	3513c47505	linting	2024-05-29 18:05:03 -06:00
Pierre-Loic Doulcet	e91f1940ec	Add spreadsheet extensions	2024-05-29 15:41:07 -07:00