use_vendor_multimodal_model=True is returning "NO_CONTENT"

[Namohar]

When we use "vendor_multimodal_model=True" with Azure OpenAI, we receive a response like "NO_CONTENT." Please assist. Thank you!

[BinaryBrain]

Hi!
Can you provide the jobID and your code?

[Namohar]

@BinaryBrain import os
from dotenv import load_dotenv
from llama_parse import LlamaParse
from llama_index.core import SimpleDirectoryReader
import ssl

Configure SSL

ssl._create_default_https_context = ssl._create_unverified_context

Load environment variables from the .env file

load_dotenv()

Retrieve the API keys and other environment variables

LLAMA_CLOUD_API_KEY = os.getenv("LLAMA_CLOUD_API_KEY")
AZURE_OPENAI_ENDPOINT = os.getenv("AZURE_OPENAI_ENDPOINT")
AZURE_OPENAI_CHAT_COMPLETION_DEPLOYED_MODEL_NAME = os.getenv("AZURE_OPENAI_CHAT_COMPLETION_DEPLOYED_MODEL_NAME")
AZURE_OPENAI_API_KEY = os.getenv("AZURE_OPENAI_API_KEY")
DOWNLOAD_PATH = os.getenv("DOWNLOAD_PATH", "./data")

Check if necessary API keys are loaded correctly

if not LLAMA_CLOUD_API_KEY:
raise ValueError("LLAMA_CLOUD_API_KEY is missing. Please set it in your .env file.")
if not AZURE_OPENAI_API_KEY or not AZURE_OPENAI_ENDPOINT or not AZURE_OPENAI_CHAT_COMPLETION_DEPLOYED_MODEL_NAME:
raise ValueError("Azure OpenAI configuration is missing. Please set the required variables in your .env file.")
try:
# Initialize the LlamaParse parser
parser = LlamaParse(
api_key=LLAMA_CLOUD_API_KEY, # Pass the API key here
result_type="markdown", # "markdown" and "text" are available
use_vendor_multimodal_model=True,
# azure_openai_endpoint=AZURE_OPENAI_ENDPOINT,
azure_openai_deployment_name="gpt-4o",
azure_openai_endpoint=AZURE_OPENAI_ENDPOINT,
azure_openai_api_version="2024-10-01-preview",
azure_openai_key=AZURE_OPENAI_API_KEY,
)
except Exception as e:
print(f"An error occurred while initializing the parser: {e}")

Use SimpleDirectoryReader to parse our file

file_extractor = {".pdf": parser}
documents = SimpleDirectoryReader(input_files=[r'data/canada.pdf'], file_extractor=file_extractor).load_data()

Print the documents (parsed output)

print("Parsed documents:")
print(documents)

[BinaryBrain]

Hi, Can you share the jobID please? Le sam. 4 janv. 2025 à 04:37, Namohar ***@***.***> a écrit :

…

@BinaryBrain <https://github.com/BinaryBrain> import os from dotenv import load_dotenv from llama_parse import LlamaParse from llama_index.core import SimpleDirectoryReader import ssl Configure SSL ssl._create_default_https_context = ssl._create_unverified_context Load environment variables from the .env file load_dotenv() Retrieve the API keys and other environment variables LLAMA_CLOUD_API_KEY = os.getenv("LLAMA_CLOUD_API_KEY") AZURE_OPENAI_ENDPOINT = os.getenv("AZURE_OPENAI_ENDPOINT") AZURE_OPENAI_CHAT_COMPLETION_DEPLOYED_MODEL_NAME = os.getenv("AZURE_OPENAI_CHAT_COMPLETION_DEPLOYED_MODEL_NAME") AZURE_OPENAI_API_KEY = os.getenv("AZURE_OPENAI_API_KEY") DOWNLOAD_PATH = os.getenv("DOWNLOAD_PATH", "./data") Check if necessary API keys are loaded correctly if not LLAMA_CLOUD_API_KEY: raise ValueError("LLAMA_CLOUD_API_KEY is missing. Please set it in your .env file.") if not AZURE_OPENAI_API_KEY or not AZURE_OPENAI_ENDPOINT or not AZURE_OPENAI_CHAT_COMPLETION_DEPLOYED_MODEL_NAME: raise ValueError("Azure OpenAI configuration is missing. Please set the required variables in your .env file.") try: # Initialize the LlamaParse parser parser = LlamaParse( api_key=LLAMA_CLOUD_API_KEY, # Pass the API key here result_type="markdown", # "markdown" and "text" are available use_vendor_multimodal_model=True, # azure_openai_endpoint=AZURE_OPENAI_ENDPOINT, azure_openai_deployment_name="gpt-4o", azure_openai_endpoint=AZURE_OPENAI_ENDPOINT, azure_openai_api_version="2024-10-01-preview", azure_openai_key=AZURE_OPENAI_API_KEY, ) except Exception as e: print(f"An error occurred while initializing the parser: {e}") Use SimpleDirectoryReader to parse our file file_extractor = {".pdf": parser} documents = SimpleDirectoryReader(input_files=[r'data/canada.pdf'], file_extractor=file_extractor).load_data() Print the documents (parsed output) print("Parsed documents:") print(documents) — Reply to this email directly, view it on GitHub <#571 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AAINB7OCESI6DUI5UQZ7Y6L2I5JRFAVCNFSM6AAAAABULN6LT2VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDKNZQGAZTENZUHA> . You are receiving this because you were mentioned.Message ID: ***@***.***>

[Namohar]

@BinaryBrain Not sure on what is JobId and where to get that please.

[PBritto697]

When it's parsing it displays the jobid on terminal window and I think it can also be seen on the history tab in the playground session. Not sure about latter one.