Retrieval-Augmented Generation (RAG) Multimodal menggunakan Gemini API di Agent Platform Ulasan

Somesh S. · Diulas 3 bulan lalu

Vivek N. · Diulas 3 bulan lalu

Divya R. · Diulas 3 bulan lalu

Amritha V. · Diulas 3 bulan lalu

Rohith V. · Diulas 3 bulan lalu

Sarun K. · Diulas 3 bulan lalu

Anuram V. · Diulas 3 bulan lalu

Jenny Jolly M. · Diulas 3 bulan lalu

Pranav B. · Diulas 3 bulan lalu

Gowthaman N. · Diulas 3 bulan lalu

Anisetti R. · Diulas 3 bulan lalu

Sau Yee W. · Diulas 3 bulan lalu

Kazuto K. · Diulas 3 bulan lalu

BHANU TEJA KUMAR T. · Diulas 3 bulan lalu

Kazuto K. · Diulas 3 bulan lalu

MARCELO D. · Diulas 3 bulan lalu

Pedro L. · Diulas 3 bulan lalu

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.

Teodoro C. · Diulas 3 bulan lalu

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

Sogand A. · Diulas 3 bulan lalu

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

Fumiko K. · Diulas 3 bulan lalu

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.

Jiwoon J. · Diulas 3 bulan lalu

Samruddhi S. D. · Diulas 3 bulan lalu

Very frequent resource is exhausted.

Nitin P. · Diulas 3 bulan lalu

Kazuto K. · Diulas 3 bulan lalu

Kazuto K. · Diulas 3 bulan lalu