run-llama/llama_cloud_services
1
0
Fork 0
mirror of https://github.com/run-llama/llama_cloud_services.git synced 2026-08-26 16:56:36 -04:00
Code Issues 352 Packages Projects Releases 10 Wiki Activity

Couldn't use Azure OpenAI deployed model for Llama Parse #333

New Issue
Open
opened 2026-02-16 00:17:31 -05:00 by yindo · 0 comments
yindo commented 2026-02-16 00:17:31 -05:00
Owner
Copy Link
Copy Source

Originally created by @tituslhy on GitHub (Nov 18, 2024).

Describe the bug
I was following this example notebook on Llama Parse but was unable to replicate the results using my gpt4o model on Azure OpenAI.

Files
The file I used is available in the example notebook on llama parse

Job IDs
286f9c91-2244-4bce-bf40-624246be8f75
a77c610c-e2be-4d47-8849-09295b26677e
1fa80bba-a23f-4818-b2d2-6e2ace6c1d05

The different job ids were me filling in the blanks of my azure_endpoint. I noticed that the Llama Parse Docs require the azure_endpoint to be beyond "https://.openai.azure.com/" unlike the AzureOpenAI LLM object so the job IDs were me testing

  1. Just "https://.openai.azure.com/"
  2. Up to f"https://{org}.openai.azure.com/deployments/chat/completions?api-version={version}"
  3. "https://{org}.openai.azure.com/deployments/chat/completions?api-version=<{version}>" with the extra "<>" in front of {version}

** Code **

from llama_parse import LlamaParse

parser = LlamaParse(
    result_type="markdown",
    use_vendor_multimodal_model=True,
    split_by_page=True,
    verbose = True,
    azure_openai_deployment_name=deployment_name,
    azure_openai_endpoint = azure_endpoint,
    azure_openai_api_version = api_version,
    azure_openai_key = api_key
)
documents = parser.load_data("./2019-tesla-impact-report-15.pdf")

** Results: **

[Document(id_='2bcbdf4a-bd05-47ad-b43c-3a6f66380008', embedding=None, metadata={}, excluded_embed_metadata_keys=[], excluded_llm_metadata_keys=[], relationships={}, text='NO_CONTENT_HERE', mimetype='text/plain', start_char_idx=None, end_char_idx=None, text_template='{metadata_str}\n\n{content}', metadata_template='{key}: {value}', metadata_seperator='\n'),
 Document(id_='c717118b-fad2-4dd3-b4fb-bc23838ca91d', embedding=None, metadata={}, excluded_embed_metadata_keys=[], excluded_llm_metadata_keys=[], relationships={}, text='NO_CONTENT_HERE', mimetype='text/plain', start_char_idx=None, end_char_idx=None, text_template='{metadata_str}\n\n{content}', metadata_template='{key}: {value}', metadata_seperator='\n'),
 Document(id_='a44fce52-c9af-4cb9-8bec-e156467b684a', embedding=None, metadata={}, excluded_embed_metadata_keys=[], excluded_llm_metadata_keys=[], relationships={}, text='NO_CONTENT_HERE', mimetype='text/plain', start_char_idx=None, end_char_idx=None, text_template='{metadata_str}\n\n{content}', metadata_template='{key}: {value}', metadata_seperator='\n'),
 Document(id_='d3296420-f2af-4b88-a2e3-51fbb3447c5d', embedding=None, metadata={}, excluded_embed_metadata_keys=[], excluded_llm_metadata_keys=[], relationships={}, text='NO_CONTENT_HERE', mimetype='text/plain', start_char_idx=None, end_char_idx=None, text_template='{metadata_str}\n\n{content}', metadata_template='{key}: {value}', metadata_seperator='\n'),
 Document(id_='4cb174c0-7d9a-4452-91c0-685b6fec3eac', embedding=None, metadata={}, excluded_embed_metadata_keys=[], excluded_llm_metadata_keys=[], relationships={}, text='NO_CONTENT_HERE', mimetype='text/plain', start_char_idx=None, end_char_idx=None, text_template='{metadata_str}\n\n{content}', metadata_template='{key}: {value}', metadata_seperator='\n'),
 Document(id_='6d58c8df-af55-4a97-ab20-ee36bfc8ba61', embedding=None, metadata={}, excluded_embed_metadata_keys=[], excluded_llm_metadata_keys=[], relationships={}, text='NO_CONTENT_HERE', mimetype='text/plain', start_char_idx=None, end_char_idx=None, text_template='{metadata_str}\n\n{content}', metadata_template='{key}: {value}', metadata_seperator='\n'),
 Document(id_='34e55283-4049-469c-8801-c3345a40c76b', embedding=None, metadata={}, excluded_embed_metadata_keys=[], excluded_llm_metadata_keys=[], relationships={}, text='NO_CONTENT_HERE', mimetype='text/plain', start_char_idx=None, end_char_idx=None, text_template='{metadata_str}\n\n{content}', metadata_template='{key}: {value}', metadata_seperator='\n'),
 Document(id_='49a0f8f9-f76e-4016-b574-cbedd4abbd95', embedding=None, metadata={}, excluded_embed_metadata_keys=[], excluded_llm_metadata_keys=[], relationships={}, text='NO_CONTENT_HERE', mimetype='text/plain', start_char_idx=None, end_char_idx=None, text_template='{metadata_str}\n\n{content}', metadata_template='{key}: {value}', metadata_seperator='\n'),
 Document(id_='f021e308-c701-415c-a734-0ac5db293181', embedding=None, metadata={}, excluded_embed_metadata_keys=[], excluded_llm_metadata_keys=[], relationships={}, text='NO_CONTENT_HERE', mimetype='text/plain', start_char_idx=None, end_char_idx=None, text_template='{metadata_str}\n\n{content}', metadata_template='{key}: {value}', metadata_seperator='\n'),
 Document(id_='bcf52338-3461-444c-86d8-9dc55ebe0900', embedding=None, metadata={}, excluded_embed_metadata_keys=[], excluded_llm_metadata_keys=[], relationships={}, text='NO_CONTENT_HERE', mimetype='text/plain', start_char_idx=None, end_char_idx=None, text_template='{metadata_str}\n\n{content}', metadata_template='{key}: {value}', metadata_seperator='\n'),
 Document(id_='f62ec862-190a-417e-ad6c-db8ca3109093', embedding=None, metadata={}, excluded_embed_metadata_keys=[], excluded_llm_metadata_keys=[], relationships={}, text='NO_CONTENT_HERE', mimetype='text/plain', start_char_idx=None, end_char_idx=None, text_template='{metadata_str}\n\n{content}', metadata_template='{key}: {value}', metadata_seperator='\n'),
 Document(id_='99d11a72-1e42-4148-89d8-d453c0d334df', embedding=None, metadata={}, excluded_embed_metadata_keys=[], excluded_llm_metadata_keys=[], relationships={}, text='NO_CONTENT_HERE', mimetype='text/plain', start_char_idx=None, end_char_idx=None, text_template='{metadata_str}\n\n{content}', metadata_template='{key}: {value}', metadata_seperator='\n'),
 Document(id_='4064790f-91d7-487c-8025-11c53a830308', embedding=None, metadata={}, excluded_embed_metadata_keys=[], excluded_llm_metadata_keys=[], relationships={}, text='NO_CONTENT_HERE', mimetype='text/plain', start_char_idx=None, end_char_idx=None, text_template='{metadata_str}\n\n{content}', metadata_template='{key}: {value}', metadata_seperator='\n'),
 Document(id_='ef3c3ba1-1556-46a9-bbd9-810906472f91', embedding=None, metadata={}, excluded_embed_metadata_keys=[], excluded_llm_metadata_keys=[], relationships={}, text='NO_CONTENT_HERE', mimetype='text/plain', start_char_idx=None, end_char_idx=None, text_template='{metadata_str}\n\n{content}', metadata_template='{key}: {value}', metadata_seperator='\n'),
 Document(id_='eda1dc8d-70e9-457d-836f-c528ea962576', embedding=None, metadata={}, excluded_embed_metadata_keys=[], excluded_llm_metadata_keys=[], relationships={}, text='NO_CONTENT_HERE', mimetype='text/plain', start_char_idx=None, end_char_idx=None, text_template='{metadata_str}\n\n{content}', metadata_template='{key}: {value}', metadata_seperator='\n')

Documents full of "NO_CONTENT_HERE".

Client:
Please remove untested options:

  • Notebook
Originally created by @tituslhy on GitHub (Nov 18, 2024). **Describe the bug** I was following this [example notebook](https://github.com/run-llama/llama_parse/blob/main/examples/test_tesla_impact_report/test_gpt4o.ipynb) on Llama Parse but was unable to replicate the results using my gpt4o model on Azure OpenAI. **Files** The file I used is available in the example notebook on llama parse **Job IDs** 286f9c91-2244-4bce-bf40-624246be8f75 a77c610c-e2be-4d47-8849-09295b26677e 1fa80bba-a23f-4818-b2d2-6e2ace6c1d05 The different job ids were me filling in the blanks of my azure_endpoint. I noticed that the [Llama Parse Docs](https://docs.cloud.llamaindex.ai/llamaparse/features/multimodal) require the azure_endpoint to be beyond "https://<org>.openai.azure.com/" unlike the AzureOpenAI LLM object so the job IDs were me testing 1. Just "https://<org>.openai.azure.com/" 2. Up to f"https://{org}.openai.azure.com/deployments/chat/completions?api-version={version}" 3. "https://{org}.openai.azure.com/deployments/chat/completions?api-version=<{version}>" with the extra "<>" in front of {version} ** Code ** ``` from llama_parse import LlamaParse parser = LlamaParse( result_type="markdown", use_vendor_multimodal_model=True, split_by_page=True, verbose = True, azure_openai_deployment_name=deployment_name, azure_openai_endpoint = azure_endpoint, azure_openai_api_version = api_version, azure_openai_key = api_key ) documents = parser.load_data("./2019-tesla-impact-report-15.pdf") ``` ** Results: ** ``` [Document(id_='2bcbdf4a-bd05-47ad-b43c-3a6f66380008', embedding=None, metadata={}, excluded_embed_metadata_keys=[], excluded_llm_metadata_keys=[], relationships={}, text='NO_CONTENT_HERE', mimetype='text/plain', start_char_idx=None, end_char_idx=None, text_template='{metadata_str}\n\n{content}', metadata_template='{key}: {value}', metadata_seperator='\n'), Document(id_='c717118b-fad2-4dd3-b4fb-bc23838ca91d', embedding=None, metadata={}, excluded_embed_metadata_keys=[], excluded_llm_metadata_keys=[], relationships={}, text='NO_CONTENT_HERE', mimetype='text/plain', start_char_idx=None, end_char_idx=None, text_template='{metadata_str}\n\n{content}', metadata_template='{key}: {value}', metadata_seperator='\n'), Document(id_='a44fce52-c9af-4cb9-8bec-e156467b684a', embedding=None, metadata={}, excluded_embed_metadata_keys=[], excluded_llm_metadata_keys=[], relationships={}, text='NO_CONTENT_HERE', mimetype='text/plain', start_char_idx=None, end_char_idx=None, text_template='{metadata_str}\n\n{content}', metadata_template='{key}: {value}', metadata_seperator='\n'), Document(id_='d3296420-f2af-4b88-a2e3-51fbb3447c5d', embedding=None, metadata={}, excluded_embed_metadata_keys=[], excluded_llm_metadata_keys=[], relationships={}, text='NO_CONTENT_HERE', mimetype='text/plain', start_char_idx=None, end_char_idx=None, text_template='{metadata_str}\n\n{content}', metadata_template='{key}: {value}', metadata_seperator='\n'), Document(id_='4cb174c0-7d9a-4452-91c0-685b6fec3eac', embedding=None, metadata={}, excluded_embed_metadata_keys=[], excluded_llm_metadata_keys=[], relationships={}, text='NO_CONTENT_HERE', mimetype='text/plain', start_char_idx=None, end_char_idx=None, text_template='{metadata_str}\n\n{content}', metadata_template='{key}: {value}', metadata_seperator='\n'), Document(id_='6d58c8df-af55-4a97-ab20-ee36bfc8ba61', embedding=None, metadata={}, excluded_embed_metadata_keys=[], excluded_llm_metadata_keys=[], relationships={}, text='NO_CONTENT_HERE', mimetype='text/plain', start_char_idx=None, end_char_idx=None, text_template='{metadata_str}\n\n{content}', metadata_template='{key}: {value}', metadata_seperator='\n'), Document(id_='34e55283-4049-469c-8801-c3345a40c76b', embedding=None, metadata={}, excluded_embed_metadata_keys=[], excluded_llm_metadata_keys=[], relationships={}, text='NO_CONTENT_HERE', mimetype='text/plain', start_char_idx=None, end_char_idx=None, text_template='{metadata_str}\n\n{content}', metadata_template='{key}: {value}', metadata_seperator='\n'), Document(id_='49a0f8f9-f76e-4016-b574-cbedd4abbd95', embedding=None, metadata={}, excluded_embed_metadata_keys=[], excluded_llm_metadata_keys=[], relationships={}, text='NO_CONTENT_HERE', mimetype='text/plain', start_char_idx=None, end_char_idx=None, text_template='{metadata_str}\n\n{content}', metadata_template='{key}: {value}', metadata_seperator='\n'), Document(id_='f021e308-c701-415c-a734-0ac5db293181', embedding=None, metadata={}, excluded_embed_metadata_keys=[], excluded_llm_metadata_keys=[], relationships={}, text='NO_CONTENT_HERE', mimetype='text/plain', start_char_idx=None, end_char_idx=None, text_template='{metadata_str}\n\n{content}', metadata_template='{key}: {value}', metadata_seperator='\n'), Document(id_='bcf52338-3461-444c-86d8-9dc55ebe0900', embedding=None, metadata={}, excluded_embed_metadata_keys=[], excluded_llm_metadata_keys=[], relationships={}, text='NO_CONTENT_HERE', mimetype='text/plain', start_char_idx=None, end_char_idx=None, text_template='{metadata_str}\n\n{content}', metadata_template='{key}: {value}', metadata_seperator='\n'), Document(id_='f62ec862-190a-417e-ad6c-db8ca3109093', embedding=None, metadata={}, excluded_embed_metadata_keys=[], excluded_llm_metadata_keys=[], relationships={}, text='NO_CONTENT_HERE', mimetype='text/plain', start_char_idx=None, end_char_idx=None, text_template='{metadata_str}\n\n{content}', metadata_template='{key}: {value}', metadata_seperator='\n'), Document(id_='99d11a72-1e42-4148-89d8-d453c0d334df', embedding=None, metadata={}, excluded_embed_metadata_keys=[], excluded_llm_metadata_keys=[], relationships={}, text='NO_CONTENT_HERE', mimetype='text/plain', start_char_idx=None, end_char_idx=None, text_template='{metadata_str}\n\n{content}', metadata_template='{key}: {value}', metadata_seperator='\n'), Document(id_='4064790f-91d7-487c-8025-11c53a830308', embedding=None, metadata={}, excluded_embed_metadata_keys=[], excluded_llm_metadata_keys=[], relationships={}, text='NO_CONTENT_HERE', mimetype='text/plain', start_char_idx=None, end_char_idx=None, text_template='{metadata_str}\n\n{content}', metadata_template='{key}: {value}', metadata_seperator='\n'), Document(id_='ef3c3ba1-1556-46a9-bbd9-810906472f91', embedding=None, metadata={}, excluded_embed_metadata_keys=[], excluded_llm_metadata_keys=[], relationships={}, text='NO_CONTENT_HERE', mimetype='text/plain', start_char_idx=None, end_char_idx=None, text_template='{metadata_str}\n\n{content}', metadata_template='{key}: {value}', metadata_seperator='\n'), Document(id_='eda1dc8d-70e9-457d-836f-c528ea962576', embedding=None, metadata={}, excluded_embed_metadata_keys=[], excluded_llm_metadata_keys=[], relationships={}, text='NO_CONTENT_HERE', mimetype='text/plain', start_char_idx=None, end_char_idx=None, text_template='{metadata_str}\n\n{content}', metadata_template='{key}: {value}', metadata_seperator='\n') ``` Documents full of "NO_CONTENT_HERE". **Client:** Please remove untested options: - Notebook
yindo added the bug label 2026-02-16 00:17:31 -05:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
LlamaCloud
LlamaExtract
LlamaParse
bug
client
complex layout
documentation
duplicate
enhancement
figure
font
header footer
help wanted
ocr
parser
pdf_debug
pdf_debug
pull-request
Mirrored from GitHub Pull Request
 python-lib
question
server_issue
server_issue
ui
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: run-llama/llama_cloud_services#333
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?