Zep Vector Store Many of you guys have been using @zep_ai as memory node, finally you can now use Zep for vector store as well! Here's a Render yaml file that spins up both Zep + Flowise by @derekcheungsa https://
github.com/derekcheungsa/
flowise-zep-deploy/blob/master/render.yaml
…
INNOVATION
-

Zep Vector Store Now Available for Flowise Integration
By
–
-

Vector Store Document Loader Integration for Prompt Enhancement
By
–
VectorDB Document Loader Many of you have asked: how to use retrieved documents from vector store into the prompt? With this new integration, you can now do so! Even with the flexibility of specifying a minimum score for documents to be included.
-

ConversationalQAChain Templates LangChain Marketplace
By
–
Chat history variable Use previous chat history inside the prompt. You can now create your own ConversationalQAChain from scratch using LLMChain + PromptTemplate, and more customization! A template is readily available in the marketplace.
-
LoRA as Cost-Effective Solution for Multi-Customer LLM Deployment
By
–
I believe this would be easiest and most cost-effective because they won't have to store a new 175B parameter LLM for each customer then. With LoRA, you can use the same base LLM but only need to store the LoRA weights.
-
LLMate Launches Solution for Structured Data QA
By
–
QA over structured data is hard
— Harrison Chase (@hwchase17) 23 août 2023
Excited to so LLMate working with @manuelsoria_ and @fpingham to bring a solution to market
We've been chatting with them for a while – they've got some good ideas https://t.co/4ZLpFG4StDQA over structured data is hard Excited to so LLMate working with @manuelsoria_ and @fpingham to bring a solution to market We've been chatting with them for a while – they've got some good ideas
-
New Short Course on Fine-tuning Large Language Models
By
–
New short course on Fine-tuning LLMs! Many developers are moving beyond only prompting, to also fine-tuning LLMs – that is, taking a pre-trained model and training it further on your own data, which can deliver superior results inexpensively. In this course, @realSharonZhou, CEO… pic.twitter.com/kAocaAgX0k
— Andrew Ng (@AndrewYNg) 23 août 2023New short course on Fine-tuning LLMs! Many developers are moving beyond only prompting, to also fine-tuning LLMs – that is, taking a pre-trained model and training it further on your own data, which can deliver superior results inexpensively. In this course, @realSharonZhou
, CEO -
Data Layer and AI: Navigating the Trough of Disillusionment
By
–
The data layer is in that 2012 era of the iPhone moment. If we're talking about AI, we're probably at around 08-09 at best. So as we dive into the "trough of disillusionment" that Gartner loves to call it, it's important to remember we see these cycles a lot—and have a ways to go
-
Data Layer Revolution: Snowflake and Databricks Transform Enterprise Infrastructure
By
–
If there is an "iPhone moment" happening right now, it's in the data layer. Snowflake and Databricks basically came in and re-wrote the entire process of storing and accessing data for, well, everything, and spawned a whole universe of $1B+ companies around the two.
-
The Real iPhone Moment: Connected Apps and Cross-Platform Integration
By
–
A whole generation of apps built on top of connected APIs and accessible through the App Store built out the "real" iPhone moment. It wasn't until we were cross-posting Instagram photos and broadcasting Foursquare check-ins across networks that it started to "make sense."
-
JSON REST APIs and App Store: The Real iPhone Moment
By
–
Instead, the iPhone moment was really more of a rolling event triggered by two important events: the popularization of JSON-enabled REST APIs, and the launch of the App Store. And it was the former allowed apps to talk to each other for the first time.