sandbox-notebookllamalm-nextjs/backend
Vadym Samoilenko 974a66288e Fix document processing: fallback to LLM when LlamaExtract returns data=None
LlamaExtract can return a non-None response object but with data=None for
certain PDFs, causing 'NoneType' object has no attribute 'get' on notebook_data.
Now falls back to LLM extraction instead of failing the task.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-05 10:46:36 +01:00
..
src Fix document processing: fallback to LLM when LlamaExtract returns data=None 2026-05-05 10:46:36 +01:00
.dockerignore Add Docker migration: Dockerfiles, compose config, and deployment scripts 2026-03-14 21:34:59 +00:00
.env .env 2025-11-17 19:48:56 +00:00
.env.example feat: integrate AI Cost Tracker for usage analytics 2026-04-27 16:12:01 +01:00
.gitignore adjusted document processing logic so only successful documents make it to the documents list 2025-10-20 13:01:18 -05:00
api.log WIP: Next.js migration - Core infrastructure complete (~25% feature parity) 2025-10-02 21:16:21 -04:00
conversation_6561c31d-65b6-4585-b2ab-5a1983595456.mp3 Fix document removal to clean up LlamaCloud index 2025-10-03 16:07:31 -04:00
Dockerfile Fix model IDs, hangs, deploy script, Docker healthchecks 2026-04-24 14:25:30 +01:00
migrate_add_sso.sql fixed some aesthetic things and added MSAL/PKCE login 2025-10-16 11:18:06 -05:00
pyproject.toml Fix podcast: bump llama-index-llms-openai 0.6.5→0.7.5, drop dead-code patches 2026-04-27 15:58:09 +01:00
uv.lock Fix podcast: bump llama-index-llms-openai 0.6.5→0.7.5, drop dead-code patches 2026-04-27 15:58:09 +01:00