Tired of OpenAI assistants API? I will deploy your first RAG pipeline
Recently, engaging with developers during my time at YCW24 revealed a valuable insight: the demand for the advanced Retrieval Augmented Generation (RAG) solutions I envisioned is overshadowed by the need for simpler, more intuitive tooling.
I'm grateful that YC's culture pushes hard to identify real "hair on fire" problems through direct user feedback. Motivated by this, I'm working to create a developer-centric platform that simplifies end-to-end deployment.
I'm happy to offer hands on support for interested devs - whether that be in the form of deploying your first RAG solution or helping you migrate off of an existing solution onto a more scaleable platform.
If better tooling interests you, or if you are are just interested in chatting RAG then let's connect.
7 comments
[ 3.3 ms ] story [ 23.8 ms ] threadhttps://open.substack.com/pub/paprai/p/supercharge-your-gpts...
It's really easy to setup and you get personalization for your users.
Right now I've focused on the following more general integrations:
VectorDBs - These include established providers like qdrant / pgvector / weaviate / pinecone / chroma. I’m also happy to try out lantern.dev if anyone is interested since their offering appears quite good.
Embeddings - I will embed your data with Jina-V2-base as part of onboarding. Alternatively, happy to use OpenAI if you supply keys (or I could take a crack at figuring out Cohere’s API).
LLMs - I can integrate with Anthropic / OpenAI / Hugging / Mistral / SciPhi and I am open to exploring any other providers that are relevant.
I've been very involved in that space the past few months,
Shoot me an email, see profile,
Best!