Agent Platform の Gemini API を使用したマルチモーダル検索拡張生成（RAG） のレビュー

Shahane Somesh · 3ヶ月前にレビュー済み

Naskar Vivek · 3ヶ月前にレビュー済み

Rajsreekalarajendran Divya · 3ヶ月前にレビュー済み

Vikraman Amritha · 3ヶ月前にレビュー済み

Vijayan Rohith · 3ヶ月前にレビュー済み

Kenoth Sarun · 3ヶ月前にレビュー済み

Vaisakh Anuram · 3ヶ月前にレビュー済み

Mannil Jenny Jolly · 3ヶ月前にレビュー済み

Bhagwat Pranav · 3ヶ月前にレビュー済み

N Gowthaman · 3ヶ月前にレビュー済み

Ramya Anisetti · 3ヶ月前にレビュー済み

Wong Sau Yee · 3ヶ月前にレビュー済み

Kido Kazuto · 3ヶ月前にレビュー済み

TANNEERU BHANU TEJA KUMAR · 3ヶ月前にレビュー済み

Kido Kazuto · 3ヶ月前にレビュー済み

DA SILVEIRA AMORA MARCELO · 3ヶ月前にレビュー済み

Luiz Wilke Buttenbender Pedro · 3ヶ月前にレビュー済み

fail Vertex AI!!!! Task 4. Build metadata of documents containing text and images ResourceExhausted: 429 Resource exhausted. Please try again later. Please refer to https://cloud.google.com/vertex-ai/generative-ai/docs/error-code-429 for more details.

Cortes Teodoro · 3ヶ月前にレビュー済み

it was impossible to run the lab within an hour, keep getting 429 error!!!!!

Aghazadeh Sogand · 3ヶ月前にレビュー済み

We are constantly receiving 429 errors. At this point, it is impossible to tell whether any progress is being made at all.

Kurokawa Fumiko · 3ヶ月前にレビュー済み

The lab could not be completed due to repeated 429 quota/rate limit errors during the core metadata extraction step using Gemini multimodal processing. The issue occurred specifically in the `get_document_metadata()` pipeline while processing PDF pages and generating image descriptions/embeddings. Even after: * reducing the number of pages, * enabling `add_sleep_after_page=True`, * increasing sleep intervals significantly, * simplifying prompts, * and retrying multiple times, the process still failed repeatedly with 429 errors. Because `text_metadata_df` and `image_metadata_df` could not be generated successfully, the following RAG retrieval and similarity search steps could not be completed. This appears to be an infrastructure/shared quota issue rather than a user-side implementation problem. Since this metadata extraction step is the core part of the lab, the lab became effectively impossible to complete within the allocated session time and credits.

Jung Jiwoon · 3ヶ月前にレビュー済み

Devarde Samruddhi S. · 3ヶ月前にレビュー済み

Very frequent resource is exhausted.

Panwar Nitin · 3ヶ月前にレビュー済み

Kido Kazuto · 3ヶ月前にレビュー済み

Kido Kazuto · 3ヶ月前にレビュー済み