Introducing the #MLflow #AI Gateway! Now in preview, this highly-scalable gateway that enables organizations to manage their LLMs and make them available for experimentation + production use cases. Learn more! https://
bit.ly/3KeIiG9
SOFTWARE
-

MLflow AI Gateway enables scalable LLM management preview
By
–
-
QA Bot Streaming with FastAPI and LangChain
By
–
This is a great example code snippet for creating a QA bot that streams via FastAPI The LangChain Expression Language makes this much simpler than before (more accurately, the standard streaming interface that all LCEL object have makes this simpler)
-
Airbyte scheduling with LangChain-powered transformations
By
–
Bringing robust scheduling and orchestration to unstructured data ingestion with @AirbyteHQ Transformations powered by LangChain
-
Open Source Models API Integration with Fine-tuning Capabilities
By
–
Really excited for this integration – not only do they support the top OSS models behind a stable & reliable API, but they're also making it easy to finetune (and then host) your own
-

Llama2-7B Now Runs on Replit with Boosted Machines
By
–
It's now easier than ever to start and stay on Replit no matter how big your code or filesystem gets – even if it’s a whole LLM.
— Replit ⠕ (@Replit) 8 août 2023
We put it to the test. Check out Llama2-7B running on Replit.
Try it yourself and add a boosted machine to the Repl for the best performance. pic.twitter.com/O6EZ1Au3oMIt's now easier than ever to start and stay on Replit no matter how big your code or filesystem gets – even if it’s a whole LLM. We put it to the test. Check out Llama2-7B running on Replit. Try it yourself and add a boosted machine to the Repl for the best performance.
-

Replit Expandable Storage Enables Large Generative AI Projects
By
–
Generative AI projects often ingest PDFs, images, and other files.
— Replit ⠕ (@Replit) 8 août 2023
Now you can upload your files on Replit with Expandable Storage without thinking twice.
Check out this demo where we fork a 2+ GiB chatbot from @LessonHacker and Boost it. pic.twitter.com/x2Vblq2c8MGenerative AI projects often ingest PDFs, images, and other files. Now you can upload your files on Replit with Expandable Storage without thinking twice. Check out this demo where we fork a 2+ GiB chatbot from @LessonHacker and Boost it.
-

Replit Expands Cloud Storage Capacity to 1 TiB
By
–
Expandable Storage on Replit is here. Starting today, Replit account storage can expand up to 1 TiB. Expand your project ideas and check out these big Repls you can now run on Replit
-

Royal Greenland Optimizes Supply Chain Through Digital Transformation
By
–
I chatted with @hassinggaard of @Royal_Greenland to explore how they optimized their #SupplyChain through digitization. Listen in on @SAP
’s #BetterTogetherStories #podcast: http://
bit.ly/SAPBetterToget
her
… #DigitalTransformation #sustainability -
User behavior analytics: choosing the right platform
By
–
Figure out where people are getting stuck, what keeps them coming back, what they like to use and what they don’t like to use. We tried out tons of products on the market. I remember Flurry, Google Analytics, Adobe, Kissmetrics, and others. And none of them were able to…
-
Modern Documentation Tool Leverages Notes as Market Entry Point
By
–
software using our tool, you can now click a button and get this modern docs/wiki product, without any work. It proved to be a great wedge into the market, because notes is the simplest unit of work, and it got people in the door and using the product. And then once people…