add new mode and params for openai (#179)

add new mode

llama_parse/base.py

@@ -57,6 +57,14 @@ class LlamaParse(BasePydanticReader):
     parsing_instruction: Optional[str] = Field(
         default="", description="The parsing instruction for the parser."
     )
+    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,
         description="Whether or not to ignore and skip errors raised during parsing.",
@@ -113,6 +121,8 @@ class LlamaParse(BasePydanticReader):
                     data={
                         "language": self.language.value,
                         "parsing_instruction": self.parsing_instruction,
+                        "gpt4o_mode": self.gpt4o_mode,
+                        "gpt4o_api_key": self.gpt4o_api_key,
                     },
                 )
                 if not response.is_success:
@@ -309,6 +319,11 @@ class LlamaParse(BasePydanticReader):
     def get_images(self, json_result: List[dict], download_path: str) -> List[dict]:
         """Download images from the parsed result."""
         headers = {"Authorization": f"Bearer {self.api_key}"}
+
+        # make the download path
+        if not os.path.exists(download_path):
+            os.makedirs(download_path)
+
         try:
             images = []
             for result in json_result:
@@ -318,9 +333,16 @@ class LlamaParse(BasePydanticReader):
                         print(f"> Image for page {page['page']}: {page['images']}")
                     for image in page["images"]:
                         image_name = image["name"]
+
+                        # get the full path
                         image_path = os.path.join(
                             download_path, f"{job_id}-{image_name}"
                         )
+
+                        # get a valid image path
+                        if not image_path.endswith(".png"):
+                            image_path += ".png"
+
                         image["path"] = image_path
                         image["job_id"] = job_id
                         image["original_pdf_path"] = result["file_path"]

llama_parse/utils.py

@@ -146,4 +146,7 @@ SUPPORTED_FILE_TYPES = [
     ".sti",
     # ebook
     ".epub",
+    # html
+    ".html",
+    ".htm",
 ]

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
 name = "llama-parse"
-version = "0.4.1"
+version = "0.4.3"
 description = "Parse files into RAG-Optimized formats."
 authors = ["Logan Markewich <logan@llamaindex.ai>"]
 license = "MIT"