Emerson Gomes comments

Results 25 comments of


                                            Emerson Gomes

RecursionError: maximum recursion depth exceeded while calling a Python object

Try setting or increasing `SYSTEM_RECURSION_LIMIT` envvar

Update mistral-medium prices and context sizes

@regismesquita It's probably better to add a new entry for the new model matching the API naming from mistral: `mistral-medium-2505` and `mistral-medium-latest` to avoid removing information from the past model....

Update mistral-medium prices and context sizes

128k is for input tokens - not output tokens.

No ETA for indexing, too slow, can't parallel index

Note that recently a new feature was introduced that allows you to increase the number of indexing workers for parallel connector processing via the env var `NUM_INDEXING_WORKER`. It will not...

Enable Support for LiteLLM Customer feature

Bumping

Indexing Failure: Timeout while requesting OpenAI embeddings

Fixed by #2460

Improve PDF text extraction

We've been also looking forward to use cloud-based services such as https://azure.microsoft.com/en-us/products/ai-services/ai-document-intelligence or https://aws.amazon.com/textract/

Web connector refactoring

Closing as deprecated

[Feature]: Context Caching for Vertex AI

AWS has started a preview for the prompt caching for Claude: https://pages.awscloud.com/promptcaching-Preview.html Hope Vertex comes up next

[Feature]: Context Caching for Vertex AI

Vertex support is now live: https://cloud.google.com/vertex-ai/generative-ai/docs/partner-models/claude-prompt-caching#use_prompt_caching