Oğuzhan Olguncu
Oğuzhan Olguncu
This PR - Replaces biome with eslint for stricter linting. - Adds prettier.js - Adds bun for test and runtime - Unidici for header and body types - Husky for...
### Checked other resources - [X] I added a very descriptive title to this issue. - [X] I searched the LangChain.js documentation with the integrated search. - [X] I used...
## What does this PR do? Fixes # (issue) *If there is not an issue for this, please create one first. This is used to tracking purposes and also helps...
This PR, from the Upstash DX team, aims to greatly simplify the `pdftochat` code. It proposes making the codebase easier by using Upstash's Vector store for embedding conversion. The Upstash...
Most of the implemented vector stores are missing from the documentation page: https://ts.llamaindex.ai/modules/vector_stores/qdrant. I'm not sure if this is intentional. Additionally, in the code, vector stores are treated as `Storage`,...
There are a few LLM observability tools we can integrate, but we need to check their feasibility first. For now, we can start with: - [x] LangSmith - [ ]...
Currently, our examples folder contains only basic use cases. It would be great if we could include some advanced usage and edge cases as well. PRs are welcome.
Currently, the RAG SDK only supports hosted models. If we could enable the use of local models, similar to web-llm, that would be great. The only issue is that while...
We need an optional way to remove messages when they are successfully received. By default it should be set to false.