Quivr's new web app is now in private beta! 🔥
To get access simply like and comment what will be the first question you will ask your Generative AI second brain
All of this is powered by @langchain, @supabase & @OpenAI
GenerativeAI as your second brain ?🧠
Dump all your knowledge into a vector store with any format ! Audio, URLs, text, code.
Query it with GPT4.
Created to replace my @obsdmd Vault using @streamlit , @langchain and @supabase.
🧵 for more details
Introducing LLM Colosseum ! 🔥
Evaluate LLMs quality by having them fight in realtime in Street Fighter III !
Who is the best ? @OpenAI or @MistralAI ?
Let them fight ! Open source code and ranking 👇
My current OSS go-to stack:
- @supabase for db, auth, storage, realtime
- @langchain for building my rag pipelines
- @posthog for analytics
- @FastAPI for the backend
- @nextjs for the frontend
- @resend for the emails
- @LiteLLM for LLMs compatibility
- @ollama &
Your Second @quivr_brain just got bigger and smarter! 🧠🤯
You can now:
- upload up to 200mb of files
- use GPT4
- unlimited chat with your brain
On one condition - use your own @OpenAI API key.
Powered by @supabase & @langchain
Here is how 👀
Spice up your AI game with Genoss GPT! 🌈🐂
Imagine swapping @OpenAI with any LLM, all in a single line.
- Switch to LLama V2 from @Meta? Done
- Experiment with GPT4ALL from @nomic_ai? Easy
- Custom model on @huggingface? Absolutely
Made w/ @langchain & @huggingface
🧵👇
Want to talk PRIVATELY to your files? 🧠
You can now use @quivr_brain to talk to any Audio, URLs, text, code files privately
We just integrated GPT4All from @nomic_ai 🔥
Your Second brain is now compatible with 4 different models thanks to @langchain 🤯
🧵🔗
Don't use @langchain, it is just a wrapper that adds complexity...
Is a lie! And here is why ?
Two days ago I removed my custom code on @quivr_brain to embed files and used @langchain. Guess what ? It made embedding 50/100 times faster and reduce my cloud cost by 2.
You
15 seconds to chat with a 200-page long document ?! 🔥
If you don’t trust me, trust the video of @quivr_brain 😏
Powered by @langchain & @supabase (PGVector).
It even works with @Ollama_ai! So fully private!
Code: github.com/stangirard/qui…
It used to take weeks to build a product.
Now you can build great product in less than 3 hours.
Here are the tools I used to create @Quivr_app in 3 hours which got 6k ⭐️ in 2 weeks on @github
