Merge branch 'main' into pierre/new_option_cache_diag

run-llama · May 23, 2024 · a49de41 · a49de41
2 parents b62c5a5 + d19b35c
commit a49de41
Show file tree

Hide file tree

Showing 6 changed files with 1,261 additions and 2 deletions.
diff --git a/examples/caltrain/caltrain_schedule_weekend.pdf b/examples/caltrain/caltrain_schedule_weekend.pdf
diff --git a/examples/caltrain/caltrain_text_mode.ipynb b/examples/caltrain/caltrain_text_mode.ipynb
diff --git a/examples/test_tesla_impact_report/2019-tesla-impact-report-short.pdf b/examples/test_tesla_impact_report/2019-tesla-impact-report-short.pdf
diff --git a/examples/test_tesla_impact_report/test_gpt4o.ipynb b/examples/test_tesla_impact_report/test_gpt4o.ipynb
diff --git a/llama_parse/base.py b/llama_parse/base.py
@@ -64,6 +64,13 @@ class LlamaParse(BasePydanticReader):
     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.",
+    )
+    gpt4o_api_key: Optional[str] = Field(
+        default=None,
+        description="The API key for the GPT-4o API. Lowers the cost of parsing.",
     )
     ignore_errors: bool = Field(
         default=True,
@@ -123,6 +130,8 @@ async def _create_job(
                         "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,
                     },
                 )
                 if not response.is_success:
@@ -341,7 +350,8 @@ def get_images(self, json_result: List[dict], download_path: str) -> List[dict]:
 
                         # 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

diff --git a/pyproject.toml b/pyproject.toml
@@ -4,7 +4,7 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
 name = "llama-parse"
-version = "0.4.2"
+version = "0.4.3"
 description = "Parse files into RAG-Optimized formats."
 authors = ["Logan Markewich <[email protected]>"]
 license = "MIT"