Opiniones sobre Aplica la generación mejorada por recuperación (RAG) multimodal con la API de Gemini en Agent Platform

Somesh S. · Se revisó hace 3 meses

Vivek N. · Se revisó hace 3 meses

Divya R. · Se revisó hace 3 meses

Amritha V. · Se revisó hace 3 meses

Rohith V. · Se revisó hace 3 meses

Sarun K. · Se revisó hace 3 meses

Anuram V. · Se revisó hace 3 meses

Jenny Jolly M. · Se revisó hace 3 meses

Pranav B. · Se revisó hace 3 meses

Gowthaman N. · Se revisó hace 3 meses

Anisetti R. · Se revisó hace 3 meses

Sau Yee W. · Se revisó hace 3 meses

Kazuto K. · Se revisó hace 3 meses

BHANU TEJA KUMAR T. · Se revisó hace 3 meses

Kazuto K. · Se revisó hace 3 meses

MARCELO D. · Se revisó hace 3 meses

Pedro L. · Se revisó hace 3 meses

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. · Se revisó hace 3 meses

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

Sogand A. · Se revisó hace 3 meses

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

Fumiko K. · Se revisó hace 3 meses

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. · Se revisó hace 3 meses

Samruddhi S. D. · Se revisó hace 3 meses

Very frequent resource is exhausted.

Nitin P. · Se revisó hace 3 meses

Kazuto K. · Se revisó hace 3 meses

Kazuto K. · Se revisó hace 3 meses