LangChain Release Notes Week of 2/5 LangSmith: better monitoring, cost visibility, regression testing, and feedback rubrics for annotation queues A deep dive into OpenGPTs Cookbooks for better RAGs & a new YouTube series around RAG: RAG from Scratch!
LLMS
-
Cohere releases Go SDK with Fern for better documentation
By
–
We’re excited to work with @buildwithfern to produce an always-up-to-date, well-documented Go SDK. Stay tuned for more language support in the coming weeks. https://
github.com/cohere-ai/cohe
re-go
…. -
Fine-tuning Code Llama 70B for Specific Coding Tasks
By
–
#CodeLlama-70B is the latest and greatest in open-source #codegen models. But, what if you want to #finetune it for a specific coding task? To help you get started, here's a step-by-step #tutorial w/ sample data and #code. Happy fine-tuning!
-
Building AI Agents Over Structured and Unstructured Data with LLMOps
By
–
Building AI agents over structured and unstructured data involves several components – like connecting your data sources, using your chosen LLM, and creating the agent that will automate many processes. LLMOps platforms like us at Abacus AI can accomplish this in a couple of
-
Multimodal Context and Ultra Model Usage in Conversations
By
–
If a prompt/response in the convo contains images does it use the old model for all subsequent prompts (since context is implicitly multimodal) or is each prompt considered in isolation? Is there any way to check if you’re actually using Ultra?
-
Gemini Ultra launches with AI agents and new tools
By
–
Top stories in AI today: -Bard officially becomes Gemini as Ultra arrives
-OpenAI developing AI agents to automate work
-Customize your Chrome theme with AI
-Huawei: AI needs physical body for AGI
-6 new AI tools & 4 new AI jobs Read more: http://
therundown.ai/p/gemini-ultra
-is-here
… -
Gemini’s conversational awareness issue when image generation fails
By
–
One soft difference I’m seeing is Gemini feels less conversationally aware, e.g.: I ask Gemini to make some images. After a few, it suddenly decides it can’t. I ask, “Why not?” It gives me a long-winded, polite version of “Huh? Why not *what*?”:
-
Gemini Advanced vs. GPT-4: Early impressions suggest similar capabilities
By
–
Trying out Gemini Advanced — will post some examples soon but first impression is it’s very close to GPT-4 in ability. Hard to find simple tasks that it’s obvious one can do and the other can’t.
-
Multiple Agents Framework Advances Machine Learning Capabilities
By
–
More Agents Is All You Need Li et al.: https://
arxiv.org/abs/2402.05120 #ArtificialIntelligence #DeepLearning #MachineLearning