make text and md optional

.github/workflows/publish_release.yml

@@ -39,10 +39,18 @@ jobs:
           pypi_token: ${{ secrets.LLAMA_PARSE_PYPI_TOKEN }}
           poetry_install_options: "--without dev"
 
+      - name: Wait for PyPI to update
+        run: |
+          sleep 60
+
+      - name: Update llama-parse lock file
+        run: |
+          cd llama_parse && poetry lock
+
       - name: Build and publish llama-parse
         uses: JRubics/poetry-publish@v2.1
         with:
-          working_directory: "llama_parse"
+          package_directory: "./llama_parse"
           pypi_token: ${{ secrets.LLAMA_PARSE_PYPI_TOKEN }}
           poetry_install_options: "--without dev"
 

llama_cloud_services/parse/types.py

@@ -93,8 +93,8 @@ class Page(BaseModel):
     """A page of the document."""
 
     page: int = Field(description="The page number.")
-    text: str = Field(description="The text of the page.")
-    md: str = Field(description="The markdown of the page.")
+    text: Optional[str] = Field(default=None, description="The text of the page.")
+    md: Optional[str] = Field(default=None, description="The markdown of the page.")
     images: List[ImageItem] = Field(
         default_factory=list,
         description="The names of the image IDs in the page, including both objects and page screenshots.",
@@ -189,7 +189,9 @@ class JobResult(BaseModel):
                 for page in self.pages
             ]
         else:
-            text = self._page_separator.join([page.text for page in self.pages])
+            text = self._page_separator.join(
+                [page.text if page.text is not None else "" for page in self.pages]
+            )
             return [Document(text=text, metadata={"file_name": self.file_name})]
 
     async def aget_text_documents(self, split_by_page: bool = False) -> List[Document]:
@@ -234,7 +236,9 @@ class JobResult(BaseModel):
         else:
             return [
                 Document(
-                    text=self._page_separator.join([page.md for page in self.pages]),
+                    text=self._page_separator.join(
+                        [page.md if page.md is not None else "" for page in self.pages]
+                    ),
                     metadata={"file_name": self.file_name},
                 )
             ]

llama_parse/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
 name = "llama-parse"
-version = "0.6.19"
+version = "0.6.20"
 description = "Parse files into RAG-Optimized formats."
 authors = ["Logan Markewich <logan@llamaindex.ai>"]
 license = "MIT"
@@ -13,7 +13,7 @@ packages = [{include = "llama_parse"}]
 
 [tool.poetry.dependencies]
 python = ">=3.9,<4.0"
-llama-cloud-services = ">=0.6.19"
+llama-cloud-services = ">=0.6.20"
 
 [tool.poetry.group.dev.dependencies]
 pytest = "^8.0.0"

pyproject.toml

@@ -8,7 +8,7 @@ python_version = "3.10"
 
 [tool.poetry]
 name = "llama-cloud-services"
-version = "0.6.19"
+version = "0.6.20"
 description = "Tailored SDK clients for LlamaCloud services."
 authors = ["Logan Markewich <logan@runllama.ai>"]
 license = "MIT"