improve error handling

README.md

@@ -87,13 +87,18 @@ parser = LlamaParse(
     language="en",  # Optionally you can define a language, default=en
 )
 
-with open("./my_file1.pdf", "rb") as f:
-    documents = parser.load_data(f)
+file_name = "my_file1.pdf"
+extra_info = {"file_name": file_name}
+
+with open(f"./{file_name}", "rb") as f:
+    # must provide extra_info with file_name key with passing file object
+    documents = parser.load_data(f, extra_info=extra_info)
 
 # you can also pass file bytes directly
-with open("./my_file1.pdf", "rb") as f:
+with open(f"./{file_name}", "rb") as f:
     file_bytes = f.read()
-    documents = parser.load_data(file_bytes)
+    # must provide extra_info with file_name key with passing file bytes
+    documents = parser.load_data(file_bytes, extra_info=extra_info)
 ```
 
 ## Using with `SimpleDirectoryReader`

llama_parse/base.py

@@ -308,7 +308,8 @@ class LlamaParse(BasePydanticReader):
                     continue
 
                 # Allowed values "PENDING", "SUCCESS", "ERROR", "CANCELED"
-                status = result.json()["status"]
+                result_json = result.json()
+                status = result_json["status"]
                 if status == "SUCCESS":
                     parsed_result = await client.get(result_url, headers=headers)
                     return parsed_result.json()
@@ -320,6 +321,14 @@ class LlamaParse(BasePydanticReader):
                         print(".", end="", flush=True)
 
                     await asyncio.sleep(self.check_interval)
+                else:
+                    error_code = result_json.get("error_code", "No error code found")
+                    error_message = result_json.get(
+                        "error_message", "No error message found"
+                    )
+
+                    exception_str = f"Job ID: {job_id} failed with status: {status}, Error code: {error_code}, Error message: {error_message}"
+                    raise Exception(exception_str)
 
     async def _aload_data(
         self,

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
 name = "llama-parse"
-version = "0.5.6"
+version = "0.5.7"
 description = "Parse files into RAG-Optimized formats."
 authors = ["Logan Markewich <logan@llamaindex.ai>"]
 license = "MIT"