Sublime

Python library for building Telegram clients and bots https://t.co/mNYpI4ibgi

Portkey's AI Gateway is the interface between your app and hosted LLMs. It streamlines API requests to OpenAI, Anthropic, Mistral, LLama2, Anyscale, Google Gemini and more with a unified API.

✅ Blazing fast (9.9x faster) with a tiny footprint (~45kb installed)

✅ Load balance across multiple models, providers, and keys

✅ Fallbacks make sure your app... See more

Introducing: Browser Use API (hosted) 🤖 Are you waiting for OpenAI Operator API? We shipped it faster. Now you can run web agents with simple api call. Everyone who has paid the monthly subscription of 30USD got 30USD in credits for the user in API. The price for now is 0.05USD per step that... See more

I believe I created this back in 2023. I thought I needed to update parts of it, but I didn’t find anything that needed changing, did I? 🌤️ The most important change to Lambda (not a limitation per se) was that the cold start/init duration is now charged, unlike before. 💸 https://t.co/QDRCiYpxbc

To get the best performance out of Llama 3 (@AIatMeta), you need to apply special tokens! Our day 0 @llama_index cookbook lets you build RAG with Llama 3 with in-built support for special tokens, like end-of-turn and begin-of-text. The capabilities are impressive. The 8B and 70B models... See more

AI SDK 4.1.2 Stable tool call streaming The streamText toolCallStreaming option is now stable: https://t.co/5xlkE7IS3Y

⚡️ Database Tip You can call lambda functions from @awscloud PostgreSQL sql queries. They can be called asynchronous e.g. from triggers or synchronous to get some data from the lambda function. It was never easier extending your database, the possibilities are endless 🤯 https://t.co/CCIhjYmZHQ