Alex Yang
Alex Yang
Hi, you can implement a class base on https://github.com/run-llama/LlamaIndexTS/blob/2e3a287a27b9cca764db5eac536fcf47362db7cc/packages/core/src/llm/base.ts#L15
You can follow this PR #305
> I have implemented partial support for bedrock. Will try to open up a PR soonish.. You can open PR and let me give some feedback!
Sorry but I cannot reproduce this bug ```shell ~/Code/practical-star git:[master] npm run generate > [email protected] generate > tsx app/generate.ts Using 'openai' model provider CHUNK_SIZE 512 CHUNK_OVERLAP 20 EMBEDDING_DIM 1024 Generating...
will check this, I think there are some bugs in node parser
I think we shouldn't modify the sentence splitter since there is no grammar for a CSV result. So I think it's better to split the CSV to different documents
See https://github.com/run-llama/LlamaIndexTS/pull/1065
Thanks for the feedback. This might be a bug, I'm working on to support getting all context during the Iterator
outdated, closing
There is some progress on this thread. For the recent PRs, I was moving some modules into @llamaindex/core with no extra dependency, so It will be easy to extend.