-
Notifications
You must be signed in to change notification settings - Fork 5.1k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Indexing should recover from errors more gracefully #210
Comments
Log output of me running into this:
|
this is a great idea |
kahkeng
added a commit
to kahkeng/gpt_index
that referenced
this issue
Jan 12, 2023
kahkeng
added a commit
to kahkeng/gpt_index
that referenced
this issue
Jan 12, 2023
kahkeng
added a commit
to kahkeng/gpt_index
that referenced
this issue
Jan 12, 2023
I had to wrap my queries in exception code to catch these API outages earlier this week. Would nice if it's handled within the framework since the openai.errors aren't exposed to my client. |
should be handled with #215! |
viveksilimkhan1
pushed a commit
to viveksilimkhan1/llama_index
that referenced
this issue
Oct 30, 2023
viveksilimkhan1
pushed a commit
to viveksilimkhan1/llama_index
that referenced
this issue
Oct 30, 2023
* Fix regex -> re import. (run-llama#205) * Add 'gpu' marker. (run-llama#208) * Optional authentation verification at init time (run-llama#206) * Add verify_auth param. * Add _verify_auth() for Cohere and Anthropic. * Make auth check mandatory again. * Remove redundant PR. * Fix OpenLLaMA model names (run-llama#209) * Update PR template. (run-llama#207) * Update OpenLLaMA model names. * fix model name in documentation (run-llama#210) * Bump version to 0.4.1. (run-llama#211) --------- Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
I've been trying to generate a tree index, but I'm hitting OAI ratelimits. The problem is that this forces me to start the index from scratch again, which is time-consuming and expensive.
If a ratelimit gets hit, the index should retry, or at the very least save some sort of intermediate state so you can resume indexing later.
The text was updated successfully, but these errors were encountered: