Enterprise adoption of LLMs has exploded yet building custom LLMs on your own knowledge base remains challenging. At http://
Abacus.AI, we have our own open-source Retrieval APIs based on our enterprise AI platform. But here’s what makes us unique: •Choose your own LLM
@abacusai
-
Enterprise LLMs: Abacus.AI’s Open-Source Retrieval APIs Solution
By
–
-
Free Webinar: ChatLLM, AI Agents, and RAG Applications Setup
By
–
Join us for a free 2-hour webinar. We will show you how to use ChatLLM & AI Agents. •Use any LLM including GPT 3.5, 4.0, Claude, PaLM, Llama-2 and Abacus Giraffe
•Set up and scale your own RAG applications
•Customize chunking, embedding, and retrieval strategies
•Automate -
Flexible LLM Integration: Open-Source and Closed Solutions for Enterprise
By
–
We at http://
Abacus.AI let you plug and play both closed and open-sourced LLMs. Open-source LLMs are cost-efficient, being just as performant for most enterprise AI use-cases. Choose the best LLM that works for your data set and use case; don’t use a single LLM provider! -
RAG vs Fine-tuning: When to Use Each Approach
By
–
When should you use RAG vs fine-tuning? When you have a custom knowledge base and want a ChatGPT-like interface then RAG makes sense. It has multiple components that can make it tricky to get right but it’s easier to implement than fine-tuning. When you want the model to adapt
-
Orca 2: Improving Core Reasoning in Small Language Models
By
–
If you are contributing to open-source AI, we recommend projects on improving core reasoning. A paper titled, “Orca 2: Teaching Small Language Models How to Reason” showcases some techniques to improve core reasoning. Their resulting Orca-2-13B model shows a 47.54% improvement
-
Local Open-Source LLMs: Future of Applied AI Systems
By
–
Local, small, open-source LLMs are going to be ubiquitous and useful in the coming months. Here’s why: Applied AI systems and most software systems have to make several small decisions based on inputs. You pick parameters and settings based on data type, size, and user inputs
-
Challenges of Deploying RAG Applications in Enterprise Environments
By
–
The most common use of LLMs in enterprise is building RAG (retrieval augmented generation) applications on a custom knowledge base, which are difficult to put in production. Some of the challenges are: •Parsing docs and PDFs (most open-source libraries struggle with this)
-
RAG with LLMs: Simple Concept, Complex Implementation
By
–
RAG with LLMS seems quite simple but is quite difficult to pull off. Creating a ChatGPT-like tool with a custom knowledge base requires multiple non-trivial components: you need a semantic understanding of the query and a full-scale search engine for the “retrieval.” We at
-
Large Collaborative AI Research Study Seeking 1000+ Collaborators
By
–
Do you want to participate in a large collaborative AI research study and paper? We’re looking for 1000+ collaborators! We’re kicking off this project early January but here is the plan: •Crowdsource 1 research idea; our research team will provide 5-6 ideas
•We’ll create an -
Build Scalable and Cost-Efficient AI Brain for Your Organization
By
–
Build An AI Brain For Your Organization! Do it in a scalable, reliable, and cost-efficient way. Use @abacusai