Introducing #AgentGPT, an attempt at #AutoGPT directly in the browser 🤖
Give your own AI agent a goal and watch as it thinks, comes up with an execution plan and takes actions. Try for free now at https://t.co/F8Nz4LGC0e
Fun release (🦜🔗v0.0.135) today with:
❄️MANY Deep Lake new features
📳RWKV-4 Model support
⏰Timeout for AgentExecutor
🟥Redis-backed entity memory
🛵Add Shared Google Drive support
📇Index support for SQL Chain
Another big end of week release! 🦜🔗0.0.114
Four big new features:
🐍 PydanticOutputParser - @jerwelborn
🦞SageMaker Endpoint LLM Integration - Piyush Jain
🧑🏫Blackboard Document Loader - @thehappydinoa
🍽️latex TextSplitter - @janldeboer
🧵
🦜🔗v0.0.99 released with:
ChatGPT API improvements!
🎏Streaming support
⏩Async Support
🧮Token Tracking (Zak King)
New big feature:
🔎Summarization Checker Chain - @tim_asp
Big improvements:
🤾 @qdrant_engine wrapper - @LukawskiKacper
🧵
A new developer product released by Foundry. This looks interesting...larger context...dedicated capacity and better means to fine-tune their latest models
OpenAI has privately announced a new developer product called Foundry, which enables customers to run OpenAI model inference at scale w/ dedicated capacity.
It also reveals that DV (Davinci; likely GPT-4) will have up to 32k max context length in the public version. 🔥
1. Hey there young Spielbergs!
Curious about how AI can be used for film making?
It's still early days, but between text-to-image, text-to-audio and AI-driven animation, building blocks are starting to appear.
Today's thread provides an overview.
🧵👇