A while ago, I had requested help with using LLMs to manage all my teaching notes. I have since installed Ollama and been playing with it to get a feel for the setup.
I was also suggested the use of RAG (Retrieval Augmented Generation ) and CA (cognitive architecture). However, I am unclear on good self hosted options for these two tasks. Could you please suggest a few?
For example, I tried ragflow.io and installed it on my system, but it seems I need to setup an account with a username and password to use it. It remains unclear if I can use the system offline like the base ollama model, and that information won’t be sent from my computer system.
I personally use exui for a lot of my LLM work, but that’s because I’m an uber minimalist.
And on your setup, I would host the best model you can on kobold.cpp or the built-in llama.cpp server (just not Ollama) and use Open Web UI as your front end. You can also use llama.cpp to host an embeddings model for RAG, if you wish.
…But generally, I prefer to not mess with RAG retrieval and just slap the context I want into the LLM myself, and for this, the performance of your machine is kind of critical (depending on just how much “context” you want it to cover). I know this is !selfhosted, but once you get your setup dialed in, you may consider making calls to an API like Groq, Cerebras or whatever, or even renting a Runpod GPU instance if that’s in your time/money budget.
I’m new to this and I was wondering why you don’t recommend ollama? This is the first one I managed to run and it seemed decent but if there are better alternatives I’m interested
Edit: it seems the two others don’t have an API. What would you recommend if you need an API?
ollama is OK because its easy and automated, but you can get higher performance, better vram efficiency, and better samplers from either kobold.cpp or tabbyAPI, with the catch being that more manual configuration is required. But this is good, as it “forces” you to pick and test an optimal config for your system.
I’d recommend kobold.cpp for very short context (like 6K or less) or if you need to partially offload the model to CPU because your GPU is relatively low VRAM. Use a good IQ quantization (like IQ4_M, for instance).
Otherwise use TabbyAPI with an exl2 quantization, as it’s generally faster (but GPU only) and much better at long context through its great k/v cache quantization.
They all have OpenAI APIs, though kobold.cpp also has its own web ui.
You are not logged in. However you can subscribe from another Fediverse account, for example Lemmy or Mastodon. To do this, paste the following into the search field of your instance: !selfhosted@lemmy.world
A place to share alternatives to popular online services that can be self-hosted without giving up privacy or locking you into a service you don’t control.
Rules:
Be civil: we’re here to support and learn from one another. Insults won’t be tolerated. Flame wars are frowned upon.
No spam posting.
Posts have to be centered around self-hosting. There are other communities for discussing hardware or home computing. If it’s not obvious why your post topic revolves around selfhosting, please include details to make it clear.
Don’t duplicate the full text of your blog or github here. Just post the link for folks to click.
Submission headline should match the article title (don’t cherry-pick information from the title to fit your agenda).
@Maroon@lemmy.world The biggest question I have for you is what graphics card, but generally speaking this is… less than ideal.
To answer your question, Open Web UI is the new hotness: https://github.com/open-webui/open-webui
I personally use exui for a lot of my LLM work, but that’s because I’m an uber minimalist.
And on your setup, I would host the best model you can on kobold.cpp or the built-in llama.cpp server (just not Ollama) and use Open Web UI as your front end. You can also use llama.cpp to host an embeddings model for RAG, if you wish.
This is a general ranking of the “best” models for document answering and summarization: https://huggingface.co/spaces/vectara/Hallucination-evaluation-leaderboard
…But generally, I prefer to not mess with RAG retrieval and just slap the context I want into the LLM myself, and for this, the performance of your machine is kind of critical (depending on just how much “context” you want it to cover). I know this is !selfhosted, but once you get your setup dialed in, you may consider making calls to an API like Groq, Cerebras or whatever, or even renting a Runpod GPU instance if that’s in your time/money budget.
I’m new to this and I was wondering why you don’t recommend ollama? This is the first one I managed to run and it seemed decent but if there are better alternatives I’m interested
Edit: it seems the two others don’t have an API. What would you recommend if you need an API?
Pretty much everything has an API :P
ollama is OK because its easy and automated, but you can get higher performance, better vram efficiency, and better samplers from either kobold.cpp or tabbyAPI, with the catch being that more manual configuration is required. But this is good, as it “forces” you to pick and test an optimal config for your system.
I’d recommend kobold.cpp for very short context (like 6K or less) or if you need to partially offload the model to CPU because your GPU is relatively low VRAM. Use a good IQ quantization (like IQ4_M, for instance).
Otherwise use TabbyAPI with an exl2 quantization, as it’s generally faster (but GPU only) and much better at long context through its great k/v cache quantization.
They all have OpenAI APIs, though kobold.cpp also has its own web ui.