Awesome, thanks man! Works like a charm. I learned two things: 1. haystack -> never came across that before -> NICE!!! 2. using open source llms to extract structured data the Pydantic-way. Again: NICE!!! Thanks!
Awesome stuff man! Your videos have been really helpful in helping me build my own local RAG applications! :) Have you also explored deploying a RAG implementation in a hosted environment? Perhaps also with Haystack or Graphlit or something along those lines? Anyway, thanks for the great content!
![JSON Output with Notus Local LLM [LlamaIndex, Ollama, Weaviate]](http://i.ytimg.com/vi/6EXgark9GpA/mqdefault.jpg)
![JSON Output with Notus Local LLM [LlamaIndex, Ollama, Weaviate]](/img/tr.png)
Awesome, thanks man! Works like a charm. I learned two things:
1. haystack -> never came across that before -> NICE!!!
2. using open source llms to extract structured data the Pydantic-way. Again: NICE!!!
Thanks!
Thanks for your feedback :)
Awesome stuff man! Your videos have been really helpful in helping me build my own local RAG applications! :)
Have you also explored deploying a RAG implementation in a hosted environment? Perhaps also with Haystack or Graphlit or something along those lines?
Anyway, thanks for the great content!
Hey, thanks a lot. Sparrow API runs on top of FastAPI, so technically, it can be deployed anywhere :)
Haystack vs Langchain - which one is better? What are the pros and cons?
I would say - both are good, it depends. Always need to test for your use case.