Aurelio AI
@AurelioAI_
Followers
42
Following
7
Media
0
Statuses
13
🚀 Boost Your Retrieval-Augmented Generation (RAG) Performance with Custom Embedding Models!. Check out the full tutorial and unlock new possibilities for your RAG applications! 💡 by @juanpml_ . #AI #RAG #AurelioAI.
aurelio.ai
Fine-Tune Embedding models using Sentence Transformers 3 for better RAG performance.
0
0
0
RT @budududuroiu: We've released local LLM and encoder support for @AurelioAI_ 's Semantic Router and I wanted to show y'all how I use it….
0
1
0
Semantic router v0.0.28 is here! Includes several fixes, new aggregation methods for route layers, and top_k support for HybridRouteLayer.
github.com
What's New Addition of different aggregation methods (sum, mean, max) and improvements to HybridRouteLayer thanks to @andreped! Much maintenance, fixes, and optimization. What's Changed ch...
0
0
1
RT @pelaseyed: Don't sleep on Semantic Router by @jamescalam and the whole @AurelioAI_ team. It has some profound use cases if you are bu….
0
4
0
Full release notes here:. Thanks to all contributors! mckeown12 hananell digriffiths @budududuroiu @issey1455 @sijak5 @jamescalam.
github.com
As part of the latest updates to the Semantic Router, we've made significant strides in enhancing its capabilities and compatibility: Full Local Support: We've added support for Local LLM...
0
0
2
and great news for those of you stuck in the stone age! Our latest release adds backward compatibility with Python 3.9, and we're gearing up for full compatibility with Python 3.12 soon. Stay tuned!.
1
0
1
There's more! We've integrated @huggingface, TFIDF, and Azure OpenAI encoders — this massively expands the scope of OSS and API-based embedding models available.
2
1
1
Exciting news from Semantic Router v0.0.16!. We now have full local support with LlamaCpp for dynamic routes. Initial tests show Mistral 7B w/ grammars outperforming GPT-3.5 in route decision making. #llamacpp #AritificialIntelligence #GenAI.
1
2
7
RT @jamescalam: Built a new Python lib to make chatbots steerable, make agentic RAG (and tool use) superfast, and provide safety guardrail….
github.com
Superfast AI decision making and intelligent processing of multi-modal data. - aurelio-labs/semantic-router
0
56
0
RT @martinkallstrom: 👋 Hey folks! If you're working with AI and looking for ways to speed up decision-making in your LLMs, take a look at @….
0
5
0
LangChain Streaming!. > More user-friendly AI.> No waiting for responses, near-instant "typing" of LLM generations.> Integrates with FastAPI.
Deep dive on @LangChainAI streaming — going from 101 essentials to FastAPI agent streaming in ~25 min 🚀
0
0
1
RT @jamescalam: No need to wait for slow LLM calls to make decisions on what agent actions to take — save time and money w/ similarity sear….
pinecone.io
Retrieval Augmented Generation (RAG) is the go-to method for adding external knowledge to Large Language Models (LLMs). RAG with agents can be slow, but we can make it much faster using NVIDIA NeMo...
0
3
0