Geração aumentada por recuperação (RAG, na sigla em inglês) multimodal usando a API Gemini na Agent Platform avaliações

Somesh S. · Revisado há 3 months

Vivek N. · Revisado há 3 months

Divya R. · Revisado há 3 months

Amritha V. · Revisado há 3 months

Rohith V. · Revisado há 3 months

Sarun K. · Revisado há 3 months

Anuram V. · Revisado há 3 months

Jenny Jolly M. · Revisado há 3 months

Pranav B. · Revisado há 3 months

Gowthaman N. · Revisado há 3 months

Anisetti R. · Revisado há 3 months

Sau Yee W. · Revisado há 3 months

Kazuto K. · Revisado há 3 months

BHANU TEJA KUMAR T. · Revisado há 3 months

Kazuto K. · Revisado há 3 months

MARCELO D. · Revisado há 3 months

Pedro L. · Revisado há 3 months

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. · Revisado há 3 months

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

Sogand A. · Revisado há 3 months

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

Fumiko K. · Revisado há 3 months

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. · Revisado há 3 months

Samruddhi S. D. · Revisado há 3 months

Very frequent resource is exhausted.

Nitin P. · Revisado há 3 months

Kazuto K. · Revisado há 3 months

Kazuto K. · Revisado há 3 months