Opportunity for you to write a blogpost about your approach :)

We did write one just yesterday that talks about rags and some techniques to improve their performance in production at https://llmstack.ai/blog/retrieval-augmented-generation

This is a neat post, thanks for sharing!

I tend to agree - i haven't seen the value in existing "retriever" components in langchain and others.

My favorite example is the asana loader[0] for llama-index. It's literally just the most basic wrapper around the Asana SDK to concatenate some strings.

[0] - https://github.com/emptycrown/llama-hub/blob/main/llama_hub/...

Yea that's langchain in a nutshell. Their postgres wrapper was the same last time I used it was pretty much

```

  def queryPostgres(client, string)
    return client.query(string)

```

For serious implementations, frameworks are not very helpful, even LangChain. All the components provide good SDKs/APIs, having a bunch of "integrations" doesn't add any real value.

If you know what you want to build, building from scratch is easier than you think. If you're tinkering on the weekend, then maybe the frameworks are helpful.

Yeah as soon as we write the word 'thread' or thinking about LLM API concurrency control across many user requests, all frameworks we tried are basically a wall instead of an accelerator. For a single user demo video on Twitter or a low-traffic streamlit POC to get a repo with lots of star gazers, they work quite well, and that's not far from what someone needs for an internal project with a small userbase. Just once this is supposed to be infra for production-grade software, the tools we have tried so far are still prioritizing features over being a foundation.